A brief guide to multi-objective reinforcement learning and planning JAAMAS track
- Hayes, Conor, Bargiacchi, Eugenio, Källström, Johan, Macfarlane, Matthew, Reymond, Mathieu, Verstraeten, Timothy, Zintgraf, Luisa, Dazeley, Richard, Heintz, Frederik, Howley, Enda, Irissappane, Aathirai, Mannion, Patrick, Nowé, Ann, Ramos, Gabriel, Restelli, Marcello, Vamplew, Peter, Roijers, Diederik
- Authors: Hayes, Conor , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederik , Howley, Enda , Irissappane, Aathirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023, London, 29 May to 2 June 2023, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS Vol. 2023-May, p. 1988-1990
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple - often conflicting - objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results. This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper [4], serves as a guide for the application of explicitly multi-objective methods to difficult problems. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
- Authors: Hayes, Conor , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederik , Howley, Enda , Irissappane, Aathirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023, London, 29 May to 2 June 2023, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS Vol. 2023-May, p. 1988-1990
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple - often conflicting - objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results. This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper [4], serves as a guide for the application of explicitly multi-objective methods to difficult problems. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Missing health data pattern matching technique for continuous remote patient monitoring
- Arora, Teena, Balasubramanian, Venki, Stranieri, Andrew
- Authors: Arora, Teena , Balasubramanian, Venki , Stranieri, Andrew
- Date: 2023
- Type: Text , Conference paper
- Relation: 20th International Conference on Smart Living and Public Health, ICOST 2023, Wonju, Korea, 7-8 July 2023, Digital Health Transformation, Smart Ageing, and Managing Disability, 20th International Conference, ICOST 2023, Wonju, South Korea, July 7–8, 2023, Proceedings Vol. 14237 LNCS, p. 130-143
- Full Text:
- Reviewed:
- Description: Remote patient monitoring (RPM) has been gaining popularity recently. However, health data acquisition is a significant challenge associated with patient monitoring. In continuous RPM, health data acquisition may miss health data during transmission. Missing data compromises the quality and reliability of patient risk assessment. Several studies suggested techniques for analyzing missing data; however, many are unsuitable for RPM. These techniques neglect the variability of missing data and provide biased results with imputation. Therefore, a holistic approach must consider the correlation and variability of the various vitals and avoid biased imputation. This paper proposes a coherent computation pattern-matching technique to identify and predict missing data patterns. The performance of the proposed approach is evaluated using data collected from a field trial. Results show that the technique can effectively identify and predict missing patterns. © 2023, The Author(s).
- Authors: Arora, Teena , Balasubramanian, Venki , Stranieri, Andrew
- Date: 2023
- Type: Text , Conference paper
- Relation: 20th International Conference on Smart Living and Public Health, ICOST 2023, Wonju, Korea, 7-8 July 2023, Digital Health Transformation, Smart Ageing, and Managing Disability, 20th International Conference, ICOST 2023, Wonju, South Korea, July 7–8, 2023, Proceedings Vol. 14237 LNCS, p. 130-143
- Full Text:
- Reviewed:
- Description: Remote patient monitoring (RPM) has been gaining popularity recently. However, health data acquisition is a significant challenge associated with patient monitoring. In continuous RPM, health data acquisition may miss health data during transmission. Missing data compromises the quality and reliability of patient risk assessment. Several studies suggested techniques for analyzing missing data; however, many are unsuitable for RPM. These techniques neglect the variability of missing data and provide biased results with imputation. Therefore, a holistic approach must consider the correlation and variability of the various vitals and avoid biased imputation. This paper proposes a coherent computation pattern-matching technique to identify and predict missing data patterns. The performance of the proposed approach is evaluated using data collected from a field trial. Results show that the technique can effectively identify and predict missing patterns. © 2023, The Author(s).
Real-time distributed trajectory planning for mobile robots
- Nguyen, Binh, Nghiem, Truong, Nguyen, Linh, Nguyen, Anh, Nguyen, Thang
- Authors: Nguyen, Binh , Nghiem, Truong , Nguyen, Linh , Nguyen, Anh , Nguyen, Thang
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd IFAC World Congress Vol. 56, p. 2152-2157
- Full Text:
- Reviewed:
- Description: Efficiently planning trajectories for nonholonomic mobile robots in formation tracking is a fundamental yet challenging problem. Nonholonomic constraints, complexity in collision avoidance, and limited computing resources prevent the robots from being practically deployed in realistic applications. This paper addresses these difficulties by modeling each mobile platform as a nonholonomic motion and formulating trajectory planning as an optimization problem using model predictive control (MPC). That is, the optimization problem is subject to both nonholonomic motions and collision avoidance. To reduce computing costs in real time, the nonholonomic constraints are convexified by finding the closest nominal points to the nonholonomic motion, which are then incorporated into a convex optimization problem. Additionally, the predicted values from the previous MPC step are utilized to form linear avoidance conditions for the next step, preventing collisions among robots. The formulated optimization problem is solved by the alternating direction method of multiplier (ADMM) in a distributed manner, which makes the proposed trajectory planning method scalable. More importantly, the convergence of the proposed planning algorithm is theoretically proved while its effectiveness is validated in a synthetic environment. Copyright © 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)
- Authors: Nguyen, Binh , Nghiem, Truong , Nguyen, Linh , Nguyen, Anh , Nguyen, Thang
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd IFAC World Congress Vol. 56, p. 2152-2157
- Full Text:
- Reviewed:
- Description: Efficiently planning trajectories for nonholonomic mobile robots in formation tracking is a fundamental yet challenging problem. Nonholonomic constraints, complexity in collision avoidance, and limited computing resources prevent the robots from being practically deployed in realistic applications. This paper addresses these difficulties by modeling each mobile platform as a nonholonomic motion and formulating trajectory planning as an optimization problem using model predictive control (MPC). That is, the optimization problem is subject to both nonholonomic motions and collision avoidance. To reduce computing costs in real time, the nonholonomic constraints are convexified by finding the closest nominal points to the nonholonomic motion, which are then incorporated into a convex optimization problem. Additionally, the predicted values from the previous MPC step are utilized to form linear avoidance conditions for the next step, preventing collisions among robots. The formulated optimization problem is solved by the alternating direction method of multiplier (ADMM) in a distributed manner, which makes the proposed trajectory planning method scalable. More importantly, the convergence of the proposed planning algorithm is theoretically proved while its effectiveness is validated in a synthetic environment. Copyright © 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)
A systematic literature review on the evaluation of business simulation games using PRISMA
- Faisal, Nadia, Chadhar, Mehmood, Goriss-Hunter, Anitra, Stranieri, Andrew
- Authors: Faisal, Nadia , Chadhar, Mehmood , Goriss-Hunter, Anitra , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 33rd Australasian Conference on Information Systems: The Changing Face of IS, ACIS 2022, Melbourne, 4-7 December 2022, ACIS 2022 - Australasian Conference on Information Systems, Proceedings
- Full Text:
- Reviewed:
- Description: In recent years, organisational software process education has seen a considerable uptick in interest in adopting business simulation games (BSGs) as a novel learning resource. However, the lack of reliable and valid instruments to evaluate simulation learning outcomes inhibits the adoption and progress of simulation in Information System education. To fill this need, we performed a systematic review of 33 empirical studies using the PRISMA declaration approach to identify the different evaluation methods used to analyse BSG learning outcomes. We created a concept matrix using a didactic framework that categorised these assessment methodologies into three game stages (pre-game, in-game and post-game). We established a comprehensive evaluation strategy using this concept matrix, which teachers and researchers may use to choose the best appropriate evaluation method to analyse a wide range of learning outcomes of business simulation games. Copyright © 2022 Faisal, Chadhar, Goriss-Hunter & Stranieri.
- Authors: Faisal, Nadia , Chadhar, Mehmood , Goriss-Hunter, Anitra , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 33rd Australasian Conference on Information Systems: The Changing Face of IS, ACIS 2022, Melbourne, 4-7 December 2022, ACIS 2022 - Australasian Conference on Information Systems, Proceedings
- Full Text:
- Reviewed:
- Description: In recent years, organisational software process education has seen a considerable uptick in interest in adopting business simulation games (BSGs) as a novel learning resource. However, the lack of reliable and valid instruments to evaluate simulation learning outcomes inhibits the adoption and progress of simulation in Information System education. To fill this need, we performed a systematic review of 33 empirical studies using the PRISMA declaration approach to identify the different evaluation methods used to analyse BSG learning outcomes. We created a concept matrix using a didactic framework that categorised these assessment methodologies into three game stages (pre-game, in-game and post-game). We established a comprehensive evaluation strategy using this concept matrix, which teachers and researchers may use to choose the best appropriate evaluation method to analyse a wide range of learning outcomes of business simulation games. Copyright © 2022 Faisal, Chadhar, Goriss-Hunter & Stranieri.
An ensemble of machine learning and clinician set thresholds for vital signs alarms
- Mai, Shenhan, Balasubramanian, Venki, Arora, Teena
- Authors: Mai, Shenhan , Balasubramanian, Venki , Arora, Teena
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 232-234
- Full Text:
- Reviewed:
- Description: High false alarm rates is a common issue in patient vital sign monitoring systems and may result in alarm fatigue for medical workers and even cause alarm-related patient deaths. In this study, the research toward the use of ensemble learning that combines a feed forward back propagation neural network, a random forest and manually set threshold based alarms is used. A method for estimating the false alarm rate using the machine learning, to help clinicians set thresholds is also proposed. Experimental results to date on a small dataset are promising. © 2022 ACM.
- Authors: Mai, Shenhan , Balasubramanian, Venki , Arora, Teena
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 232-234
- Full Text:
- Reviewed:
- Description: High false alarm rates is a common issue in patient vital sign monitoring systems and may result in alarm fatigue for medical workers and even cause alarm-related patient deaths. In this study, the research toward the use of ensemble learning that combines a feed forward back propagation neural network, a random forest and manually set threshold based alarms is used. A method for estimating the false alarm rate using the machine learning, to help clinicians set thresholds is also proposed. Experimental results to date on a small dataset are promising. © 2022 ACM.
Blockchain based smart auction mechanism for distributed peer-to-peer energy trading
- Islam, Md Ezazul, Chetty, Madhu, Lim, Suryani, Chadhar, Mehmood, Islam, Syed
- Authors: Islam, Md Ezazul , Chetty, Madhu , Lim, Suryani , Chadhar, Mehmood , Islam, Syed
- Date: 2022
- Type: Text , Conference paper
- Relation: 55th Annual Hawaii International Conference on System Sciences, HICSS 2022, Virtual, online, 3-7 January 2022, Proceedings of the Annual Hawaii International Conference on System Sciences Vol. 2022-January, p. 6013-6022
- Full Text:
- Reviewed:
- Description: Blockchain based framework provides data immutability in a distributed network. In this paper, we investigate the application of blockchain for peer-to-peer (P2P) energy trading. Traditional energy trading systems use simple passing mechanisms and basic pricing methods, thus adversely affect the efficiency and buyers' social welfare. We propose a blockchain based energy trading mechanism that uses smart passing of unspent auction reservations to (a) minimise the time taken to settle an auction (convergence time), (b) maximise the number of auction settlement; and (c) incorporate second-price auction pricing to maximise buyers' social welfare in a distributed double auction environment. The entire mechanism is implemented within Hyperledger Fabric, an open-source blockchain framework, to manage the data and provide smart contracts. Experiments show that our approach minimises the convergence time, maximises the number of auction settlement, and increases the social welfare of buyers compared to existing methods. © 2022 IEEE Computer Society. All rights reserved.
- Authors: Islam, Md Ezazul , Chetty, Madhu , Lim, Suryani , Chadhar, Mehmood , Islam, Syed
- Date: 2022
- Type: Text , Conference paper
- Relation: 55th Annual Hawaii International Conference on System Sciences, HICSS 2022, Virtual, online, 3-7 January 2022, Proceedings of the Annual Hawaii International Conference on System Sciences Vol. 2022-January, p. 6013-6022
- Full Text:
- Reviewed:
- Description: Blockchain based framework provides data immutability in a distributed network. In this paper, we investigate the application of blockchain for peer-to-peer (P2P) energy trading. Traditional energy trading systems use simple passing mechanisms and basic pricing methods, thus adversely affect the efficiency and buyers' social welfare. We propose a blockchain based energy trading mechanism that uses smart passing of unspent auction reservations to (a) minimise the time taken to settle an auction (convergence time), (b) maximise the number of auction settlement; and (c) incorporate second-price auction pricing to maximise buyers' social welfare in a distributed double auction environment. The entire mechanism is implemented within Hyperledger Fabric, an open-source blockchain framework, to manage the data and provide smart contracts. Experiments show that our approach minimises the convergence time, maximises the number of auction settlement, and increases the social welfare of buyers compared to existing methods. © 2022 IEEE Computer Society. All rights reserved.
Community capacity to envisage a post-mine future: rehabilitation options for Latrobe Valley brown coal mines
- Reeves, Jessica, Baumgartl, Thomas, Morgan, D., Reimers, Vaughan, Green, Michael
- Authors: Reeves, Jessica , Baumgartl, Thomas , Morgan, D. , Reimers, Vaughan , Green, Michael
- Date: 2022
- Type: Text , Conference paper
- Relation: 15th International Conference on Mine Closure, Mine Closure 2022, Brisbane, Australia, 4-6 October 2022, Proceedings of the International Conference on Mine Closure Vol. 1, p. 173-185
- Full Text:
- Reviewed:
- Description: Since closure of the Hazelwood Power Station in 2017, and the associated Morwell open cut mine, the community of the Latrobe Valley have largely come to terms with the coming end of an industry that for almost a century defined their region. However, the capacity for the community to envisage what comes next has been limited. This is in part due to uncertainty of the viability of options for rehabilitation, future ownership and responsibility for the sites, and a challenging policy framework. It is also related to systemic social issues, such as mistrust of both government and energy companies, as well as over-consultation fatigue. We draw here on findings from a recent study, commissioned by AGL Loy Yang, on the community perspectives on the final void forms and future land and water uses of the three Latrobe Valley open cut brown coal mines - and surrounding lands. The data were obtained through a series of focus groups with key stakeholders, including community organisations, environmental groups, government authorities, business groups, primary producers and Traditional Owners; and a web-based survey, completed by over 560 participants. From this we found a common theme concerning a desire to have the land returned to the community and to leave a positive legacy for the sites. Options that were visually attractive and enabled either recreation and/or tourism were preferred to future industrial uses; environmental benefit was also a strong priority. Authentic community consultation necessitates that the community be empowered to make an informed contribution to the discussion, and that they are made aware of how their input will be utilised. The community of the Latrobe Valley are invested in having a positive outcome for their region, which future generations can benefit from. To achieve this, the community must be actively engaged in the process. © 2022 Australian Centre for Geomechanics, Perth.
- Authors: Reeves, Jessica , Baumgartl, Thomas , Morgan, D. , Reimers, Vaughan , Green, Michael
- Date: 2022
- Type: Text , Conference paper
- Relation: 15th International Conference on Mine Closure, Mine Closure 2022, Brisbane, Australia, 4-6 October 2022, Proceedings of the International Conference on Mine Closure Vol. 1, p. 173-185
- Full Text:
- Reviewed:
- Description: Since closure of the Hazelwood Power Station in 2017, and the associated Morwell open cut mine, the community of the Latrobe Valley have largely come to terms with the coming end of an industry that for almost a century defined their region. However, the capacity for the community to envisage what comes next has been limited. This is in part due to uncertainty of the viability of options for rehabilitation, future ownership and responsibility for the sites, and a challenging policy framework. It is also related to systemic social issues, such as mistrust of both government and energy companies, as well as over-consultation fatigue. We draw here on findings from a recent study, commissioned by AGL Loy Yang, on the community perspectives on the final void forms and future land and water uses of the three Latrobe Valley open cut brown coal mines - and surrounding lands. The data were obtained through a series of focus groups with key stakeholders, including community organisations, environmental groups, government authorities, business groups, primary producers and Traditional Owners; and a web-based survey, completed by over 560 participants. From this we found a common theme concerning a desire to have the land returned to the community and to leave a positive legacy for the sites. Options that were visually attractive and enabled either recreation and/or tourism were preferred to future industrial uses; environmental benefit was also a strong priority. Authentic community consultation necessitates that the community be empowered to make an informed contribution to the discussion, and that they are made aware of how their input will be utilised. The community of the Latrobe Valley are invested in having a positive outcome for their region, which future generations can benefit from. To achieve this, the community must be actively engaged in the process. © 2022 Australian Centre for Geomechanics, Perth.
Deep learning model to empower student engagement in online synchronous learning environment
- Godly, Cinthia, Balasubramanian, Venki, Stranieri, Andrew, Saikrishna, Vidya, Mohammed, Rehena, Chackappan, Godly
- Authors: Godly, Cinthia , Balasubramanian, Venki , Stranieri, Andrew , Saikrishna, Vidya , Mohammed, Rehena , Chackappan, Godly
- Date: 2022
- Type: Text , Conference paper
- Relation: 19th IEEE India Council International Conference, INDICON 2022, Kochi India, 24-26 November 2022, INDICON 2022 - 2022 IEEE 19th India Council International Conference
- Full Text:
- Reviewed:
- Description: Following the start of the pandemic, online synchronous learning has grown significantly. The higher education sector is searching for new creative ways to provide the information online because of the switch from face-to-face to online synchronous course delivery. Students are also becoming accustomed to studying online, and research has shown that synchronous online learning has a variety of effects on student engagement. For instance, according to statistics from the National Survey of Student Engagement, students are less likely to participate in collaborative learning, studentfaculty interactions, and conversations when learning online if they use quantitative reasoning during face-to-face instruction. Additionally, studies suggest that because they depend on their devices to take online classes, students feel more alienated from their lecturers. This has been linked to a drop in contacts with peers and teachers as a result. By using a cutting-edge deep learning model to predict learner engagement behaviour in a synchronous teaching environment, our research intends to improve online engagement. The model with a clever trigger will encourage the disengaged pupils to communicate with the teachers online. Smart triggers will be built around factors that have been found, focusing on disengaged students to engage them in real-time with automatic, personalized feedback. © 2022 IEEE.
- Authors: Godly, Cinthia , Balasubramanian, Venki , Stranieri, Andrew , Saikrishna, Vidya , Mohammed, Rehena , Chackappan, Godly
- Date: 2022
- Type: Text , Conference paper
- Relation: 19th IEEE India Council International Conference, INDICON 2022, Kochi India, 24-26 November 2022, INDICON 2022 - 2022 IEEE 19th India Council International Conference
- Full Text:
- Reviewed:
- Description: Following the start of the pandemic, online synchronous learning has grown significantly. The higher education sector is searching for new creative ways to provide the information online because of the switch from face-to-face to online synchronous course delivery. Students are also becoming accustomed to studying online, and research has shown that synchronous online learning has a variety of effects on student engagement. For instance, according to statistics from the National Survey of Student Engagement, students are less likely to participate in collaborative learning, studentfaculty interactions, and conversations when learning online if they use quantitative reasoning during face-to-face instruction. Additionally, studies suggest that because they depend on their devices to take online classes, students feel more alienated from their lecturers. This has been linked to a drop in contacts with peers and teachers as a result. By using a cutting-edge deep learning model to predict learner engagement behaviour in a synchronous teaching environment, our research intends to improve online engagement. The model with a clever trigger will encourage the disengaged pupils to communicate with the teachers online. Smart triggers will be built around factors that have been found, focusing on disengaged students to engage them in real-time with automatic, personalized feedback. © 2022 IEEE.
Designs and applications of the rotary limaçon compressors and expanders - a review
- Belfiore, Christopher, Lu, Kui, Phung, Truong, Sultan, Ibrahim
- Authors: Belfiore, Christopher , Lu, Kui , Phung, Truong , Sultan, Ibrahim
- Date: 2022
- Type: Text , Conference paper
- Relation: 3rd International Conference on Energy and Power, ICEP 2021, Chiang Mai, Thailand, 18-20 November 2021, AIP Conference Proceedings Vol. 2681
- Full Text:
- Reviewed:
- Description: Limaçon machines are positive displacement fluid processing machines that belong to the rotary machine family. The limaçon machines can be utilized as expanders to extract work from the working fluid or as compressors to provide energy to the working fluid. The main components of the limaçon machine that are directly involved in fluid processing are the housing and rotor, the construction of which are of either limaçon of Pascal curves or circular curves. One distinct feature of the limaçon machine is the limaçon motion of the rotor; the rotor rotates about and slides along a pole, o, inside a housing during the machine operation. Of important note is the motion of the machine rotor inside the housing always follows the limaçon motion irrespective of their profiles. In this paper, different designs and embodiments of the limaçon machine and their advantages and disadvantages have beed discussed, and the research has been carried out on specific applications, i.e., expander and compressor including the work done on fluid induction, sealing and leakages, porting, and inlet and outlet valve control of such machines. © 2022 American Institute of Physics Inc.. All rights reserved.
- Authors: Belfiore, Christopher , Lu, Kui , Phung, Truong , Sultan, Ibrahim
- Date: 2022
- Type: Text , Conference paper
- Relation: 3rd International Conference on Energy and Power, ICEP 2021, Chiang Mai, Thailand, 18-20 November 2021, AIP Conference Proceedings Vol. 2681
- Full Text:
- Reviewed:
- Description: Limaçon machines are positive displacement fluid processing machines that belong to the rotary machine family. The limaçon machines can be utilized as expanders to extract work from the working fluid or as compressors to provide energy to the working fluid. The main components of the limaçon machine that are directly involved in fluid processing are the housing and rotor, the construction of which are of either limaçon of Pascal curves or circular curves. One distinct feature of the limaçon machine is the limaçon motion of the rotor; the rotor rotates about and slides along a pole, o, inside a housing during the machine operation. Of important note is the motion of the machine rotor inside the housing always follows the limaçon motion irrespective of their profiles. In this paper, different designs and embodiments of the limaçon machine and their advantages and disadvantages have beed discussed, and the research has been carried out on specific applications, i.e., expander and compressor including the work done on fluid induction, sealing and leakages, porting, and inlet and outlet valve control of such machines. © 2022 American Institute of Physics Inc.. All rights reserved.
Enhancing Sustainable Development on Land: Using birds of prey to disperse flocks of native birds that threaten resource use and human activities
- Wallis, Robert, Coles, Graeme
- Authors: Wallis, Robert , Coles, Graeme
- Date: 2022
- Type: Text , Conference paper
- Relation: 28th International Sustainable Development Research Society Conference: Sustainable Development and Courage: Culture, Art and Human rights, Stockholm, 15-17 June 2022, PROCEEDINGS of the 28th Annual Conference, International Sustainable Development Research Society Conference p. 307-319
- Full Text:
- Reviewed:
- Authors: Wallis, Robert , Coles, Graeme
- Date: 2022
- Type: Text , Conference paper
- Relation: 28th International Sustainable Development Research Society Conference: Sustainable Development and Courage: Culture, Art and Human rights, Stockholm, 15-17 June 2022, PROCEEDINGS of the 28th Annual Conference, International Sustainable Development Research Society Conference p. 307-319
- Full Text:
- Reviewed:
Evaluating human-like explanations for robot actions in reinforcement learning scenarios
- Cruz, Francisco, Young, Charlotte, Dazeley, Richard, Vamplew, Peter
- Authors: Cruz, Francisco , Young, Charlotte , Dazeley, Richard , Vamplew, Peter
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, 23-27 October 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vol. 2022-October, p. 894-901
- Full Text:
- Reviewed:
- Description: Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations. © 2022 IEEE.
- Authors: Cruz, Francisco , Young, Charlotte , Dazeley, Richard , Vamplew, Peter
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, 23-27 October 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vol. 2022-October, p. 894-901
- Full Text:
- Reviewed:
- Description: Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations. © 2022 IEEE.
Geometric design of the limaçon rotary compressor using bayesian optimization
- Lu, Kui, Sultan, Ibrahim, Phung, Truong
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2022
- Type: Text , Conference paper
- Relation: 3rd International Conference on Energy and Power, ICEP 2021, Chiang Mai, Thailand, 18-20 November 2021, AIP Conference Proceedings 2681 Vol. 2681
- Full Text:
- Reviewed:
- Description: In the design of positive displacement compressors, the mathematical relationship between design parameters and design objectives is usually impractical and costly to be extracted, making the optimization process becomes a 'black-box' problem. In the available literature, the Bayesian optimization method, compared to other optimization techniques, has been proven as an accurate and efficient method to solve the 'black-box' problem. However, the application of such a method in the design of the rotary compressor has not been discussed in published papers. Hence, the current study is intended to employ Bayesian optimization to geometric design a class of positive displacement compressors, which is known as the limaçon compressor. In this paper, the geometric characteristics of the limaçon compressor are presented, and a function, which incorporates volumetric and geometric aspects, is employed to evaluate the optimization process and to reveal the optimum design scenario as per design requirements. A case study is offered to prove the validity of the presented approach. © 2022 American Institute of Physics Inc.. All rights reserved.
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2022
- Type: Text , Conference paper
- Relation: 3rd International Conference on Energy and Power, ICEP 2021, Chiang Mai, Thailand, 18-20 November 2021, AIP Conference Proceedings 2681 Vol. 2681
- Full Text:
- Reviewed:
- Description: In the design of positive displacement compressors, the mathematical relationship between design parameters and design objectives is usually impractical and costly to be extracted, making the optimization process becomes a 'black-box' problem. In the available literature, the Bayesian optimization method, compared to other optimization techniques, has been proven as an accurate and efficient method to solve the 'black-box' problem. However, the application of such a method in the design of the rotary compressor has not been discussed in published papers. Hence, the current study is intended to employ Bayesian optimization to geometric design a class of positive displacement compressors, which is known as the limaçon compressor. In this paper, the geometric characteristics of the limaçon compressor are presented, and a function, which incorporates volumetric and geometric aspects, is employed to evaluate the optimization process and to reveal the optimum design scenario as per design requirements. A case study is offered to prove the validity of the presented approach. © 2022 American Institute of Physics Inc.. All rights reserved.
Graph augmentation learning
- Yu, Shuo, Huang, Huafei, Dao, Minh, Xia, Feng
- Authors: Yu, Shuo , Huang, Huafei , Dao, Minh , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 31st ACM Web Conference, WWW 2022, Virtual, online, 25 April 2022, WWW 2022 - Companion Proceedings of the Web Conference 2022 p. 1063-1072
- Full Text:
- Reviewed:
- Description: Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow forecasting. However, the underlying reasons for the effectiveness of these GAL methods are still unclear. As a consequence, how to choose optimal graph augmentation strategy for a certain application scenario is still in black box. There is a lack of systematic, comprehensive, and experimentally validated guideline of GAL for scholars. Therefore, in this survey, we in-depth review GAL techniques from macro (graph), meso (subgraph), and micro (node/edge) levels. We further detailedly illustrate how GAL enhance the data quality and the model performance. The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios. To better show the outperformance of GAL, we experimentally validate the effectiveness and adaptability of different GAL strategies in different downstream tasks. Finally, we share our insights on several open issues of GAL, including heterogeneity, spatio-temporal dynamics, scalability, and generalization. © 2022 ACM.
- Authors: Yu, Shuo , Huang, Huafei , Dao, Minh , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 31st ACM Web Conference, WWW 2022, Virtual, online, 25 April 2022, WWW 2022 - Companion Proceedings of the Web Conference 2022 p. 1063-1072
- Full Text:
- Reviewed:
- Description: Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow forecasting. However, the underlying reasons for the effectiveness of these GAL methods are still unclear. As a consequence, how to choose optimal graph augmentation strategy for a certain application scenario is still in black box. There is a lack of systematic, comprehensive, and experimentally validated guideline of GAL for scholars. Therefore, in this survey, we in-depth review GAL techniques from macro (graph), meso (subgraph), and micro (node/edge) levels. We further detailedly illustrate how GAL enhance the data quality and the model performance. The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios. To better show the outperformance of GAL, we experimentally validate the effectiveness and adaptability of different GAL strategies in different downstream tasks. Finally, we share our insights on several open issues of GAL, including heterogeneity, spatio-temporal dynamics, scalability, and generalization. © 2022 ACM.
Instructors’ perceptions of the development of work-readiness through simulations
- Faisal, Nadia, Chadhar, Mehmood, Goriss-Hunter, Anitra, Stranieri, Andrew
- Authors: Faisal, Nadia , Chadhar, Mehmood , Goriss-Hunter, Anitra , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 33rd Australasian Conference on Information Systems: The Changing Face of IS, ACIS 2022, Melbourne, 4-7 December 2022, ACIS 2022 - Australasian Conference on Information Systems, Proceedings
- Full Text:
- Reviewed:
- Description: The global ERP software market is expected to reach $117.09 billion by 2030 (Biel, July 12, 2022). To boost graduate work-readiness, Australian institutions are adopting new pedagogical strategies by familiarising Information systems (IS) students with this highly sought-after software. One of these techniques is simulation games that provide students with a risk-free, real-world simulation of popular software to develop soft and hard skills needed by the IS industry. This exploratory study employed the Grounded Theory approach to evaluate instructors' perceptions of the influence of simulation games on the work-readiness of information systems students. We conducted semi-structured interviews with (Enterprise Resource Planning Simulation) ERPsim game laboratory instructors. The authors utilised Work Readiness Integrated Competency Model to map the three learning outcomes from the interviews’ analysis: abilities, knowledge, and attitudes. The mapping demonstrated that simulation games could support the development of specific skills and attitudes needed by the information systems sector. Copyright © 2022 Faisal, Chadhar, Goriss-Hunter & Stranieri.
- Authors: Faisal, Nadia , Chadhar, Mehmood , Goriss-Hunter, Anitra , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 33rd Australasian Conference on Information Systems: The Changing Face of IS, ACIS 2022, Melbourne, 4-7 December 2022, ACIS 2022 - Australasian Conference on Information Systems, Proceedings
- Full Text:
- Reviewed:
- Description: The global ERP software market is expected to reach $117.09 billion by 2030 (Biel, July 12, 2022). To boost graduate work-readiness, Australian institutions are adopting new pedagogical strategies by familiarising Information systems (IS) students with this highly sought-after software. One of these techniques is simulation games that provide students with a risk-free, real-world simulation of popular software to develop soft and hard skills needed by the IS industry. This exploratory study employed the Grounded Theory approach to evaluate instructors' perceptions of the influence of simulation games on the work-readiness of information systems students. We conducted semi-structured interviews with (Enterprise Resource Planning Simulation) ERPsim game laboratory instructors. The authors utilised Work Readiness Integrated Competency Model to map the three learning outcomes from the interviews’ analysis: abilities, knowledge, and attitudes. The mapping demonstrated that simulation games could support the development of specific skills and attitudes needed by the information systems sector. Copyright © 2022 Faisal, Chadhar, Goriss-Hunter & Stranieri.
Revisiting social media in health care : a Bakhtinian carnival perspective
- Ukoha, Chukwuma, Stranieri, Andrew
- Authors: Ukoha, Chukwuma , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 254-256
- Full Text:
- Reviewed:
- Description: Understanding the value of social media in health care has been a conundrum. Much of the literature in this area focuses on the use of social media for promotion, with very few studies seeking to elucidate how social media yields value in health care settings. This article draws on concepts from 18th century linguist Mikhail Bahktin to explain that social media acts like a Carnival in suspension of behavioral norms, and the provision of a forum for the proliferation of diverse dialogues. As a Carnival, social media plays an important role in encouraging dialogues that would not be appropriate within other spaces in the health care system. As such, social media is playing a pivotal role in changing norms toward shared care and patient empowerment. © 2022 ACM.
- Authors: Ukoha, Chukwuma , Stranieri, Andrew
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 254-256
- Full Text:
- Reviewed:
- Description: Understanding the value of social media in health care has been a conundrum. Much of the literature in this area focuses on the use of social media for promotion, with very few studies seeking to elucidate how social media yields value in health care settings. This article draws on concepts from 18th century linguist Mikhail Bahktin to explain that social media acts like a Carnival in suspension of behavioral norms, and the provision of a forum for the proliferation of diverse dialogues. As a Carnival, social media plays an important role in encouraging dialogues that would not be appropriate within other spaces in the health care system. As such, social media is playing a pivotal role in changing norms toward shared care and patient empowerment. © 2022 ACM.
Theoretical study and empirical investigation of sentence analogies
- Afantenos, Stergos, Lim, Suryani, Prade, Henri, Richard, Gilles
- Authors: Afantenos, Stergos , Lim, Suryani , Prade, Henri , Richard, Gilles
- Date: 2022
- Type: Text , Conference paper
- Relation: 1st Workshop on the Interactions between Analogical Reasoning and Machine Learning at 31st International Joint Conference on Artificial Intelligence - 25th European Conference on Artificial Intelligence, IARML@IJCAI-ECAI 2022, Vienna, Austria, 23 July 2022, CEUR Workshop Proceedings Vol. 3174, p. 15-28
- Full Text:
- Reviewed:
- Description: Analogies between 4 sentences, “a is to b as c is to d”, are usually defined between two pairs of sentences (a, b) and (c, d) by constraining a relation R holding between the sentences of the first pair, to hold for the second pair. From a theoretical perspective, three postulates define an analogy - one of which is the “central permutation” postulate which allows the permutation of central elements b and c. This postulate is no longer appropriate in sentence analogies since the existence of R offers no guarantee in general for the existence of some relation S such that S also holds for the pairs (a, c) and (b, d). In this paper, the “central permutation” postulate is replaced by a weaker “internal reversal” postulate to provide an appropriate definition of sentence analogies. To empirically validate the aforementioned postulate, we build a LSTM as well as baseline Random Forest models capable of learning analogies based on quadruplets. We use the Penn Discourse Treebank (PDTB), the Stanford Natural Language Inference (SNLI) and the Microsoft Research Paraphrase (MSRP) corpora. Our experiments show that our models trained on samples of analogies between (a, b) and (c, d), recognize analogies between (b, a) and (d, c) when the underlying relation is symmetrical, validating thus the formal model of sentence analogies using “internal reversal” postulate. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
- Authors: Afantenos, Stergos , Lim, Suryani , Prade, Henri , Richard, Gilles
- Date: 2022
- Type: Text , Conference paper
- Relation: 1st Workshop on the Interactions between Analogical Reasoning and Machine Learning at 31st International Joint Conference on Artificial Intelligence - 25th European Conference on Artificial Intelligence, IARML@IJCAI-ECAI 2022, Vienna, Austria, 23 July 2022, CEUR Workshop Proceedings Vol. 3174, p. 15-28
- Full Text:
- Reviewed:
- Description: Analogies between 4 sentences, “a is to b as c is to d”, are usually defined between two pairs of sentences (a, b) and (c, d) by constraining a relation R holding between the sentences of the first pair, to hold for the second pair. From a theoretical perspective, three postulates define an analogy - one of which is the “central permutation” postulate which allows the permutation of central elements b and c. This postulate is no longer appropriate in sentence analogies since the existence of R offers no guarantee in general for the existence of some relation S such that S also holds for the pairs (a, c) and (b, d). In this paper, the “central permutation” postulate is replaced by a weaker “internal reversal” postulate to provide an appropriate definition of sentence analogies. To empirically validate the aforementioned postulate, we build a LSTM as well as baseline Random Forest models capable of learning analogies based on quadruplets. We use the Penn Discourse Treebank (PDTB), the Stanford Natural Language Inference (SNLI) and the Microsoft Research Paraphrase (MSRP) corpora. Our experiments show that our models trained on samples of analogies between (a, b) and (c, d), recognize analogies between (b, a) and (d, c) when the underlying relation is symmetrical, validating thus the formal model of sentence analogies using “internal reversal” postulate. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Third party data service providers can enhance patient-provider interactions : insights from a Delphi study
- Hashmi, Mustafa, McInnes, Angelique, Stranieri, Andrew, Sahama, Tony
- Authors: Hashmi, Mustafa , McInnes, Angelique , Stranieri, Andrew , Sahama, Tony
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 224-228
- Full Text:
- Reviewed:
- Description: Data sharing between financial services organisations has led to a proliferation of third party data service providers that are not parties to transactions but facilitate interactions between them by analysing, manipulating or storing data related to transactions. This has led to widespread legal, technological and sociocultural changes in that sector broadly described as Open-Banking initiatives. Third party service providers have not emerged in the healthcare sector in the same way. This study reports preliminary results of a Delphi study comprising healthcare and financial experts to explore the extent to which third party providers in healthcare is beneficial and feasible. Ensuring the quality of data service provided by third parties was seen to be a critical success factor. A causal loop model was used to describe the inter-dependent factors underpinning this factor. Further investigations to augment the model with Consumer Data Rights and validate empirically are underway. © 2022 ACM.
- Authors: Hashmi, Mustafa , McInnes, Angelique , Stranieri, Andrew , Sahama, Tony
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 224-228
- Full Text:
- Reviewed:
- Description: Data sharing between financial services organisations has led to a proliferation of third party data service providers that are not parties to transactions but facilitate interactions between them by analysing, manipulating or storing data related to transactions. This has led to widespread legal, technological and sociocultural changes in that sector broadly described as Open-Banking initiatives. Third party service providers have not emerged in the healthcare sector in the same way. This study reports preliminary results of a Delphi study comprising healthcare and financial experts to explore the extent to which third party providers in healthcare is beneficial and feasible. Ensuring the quality of data service provided by third parties was seen to be a critical success factor. A causal loop model was used to describe the inter-dependent factors underpinning this factor. Further investigations to augment the model with Consumer Data Rights and validate empirically are underway. © 2022 ACM.
Validation framework of bayesian networks in asset management decision-making
- Morey, Stephen, Chattopadhyay, Gopinath, Larkins, Jo-ann
- Authors: Morey, Stephen , Chattopadhyay, Gopinath , Larkins, Jo-ann
- Date: 2022
- Type: Text , Conference paper
- Relation: International Congress and Workshop on Industrial AI, IAI 2021, Virtual online, 6-7 October 2021, published in Lecture Notes in Mechanical Engineering p. 360-369
- Full Text:
- Reviewed:
- Description: Capital-intensive industries are under increasing pressure from capital constraints to extend the life of long-life assets and to defer asset renewals. Assets in most of those industries have complex life-cycle management challenges in aspects of design, manufacture, maintenance and service contracts, the usage environment, and changes in support personnel over the asset life. A significant challenge is the availability and quality of relevant data for informed decision-making in assuring reliability, availability and safety. There is a need for better-informed maintenance decisions and cost-effective interventions in managing the risk and assuring performance of those assets. Bayesian networks have been considered in asset management applications in recent years for addressing these challenges, by modelling of reliability, maintenance decisions, life extension and prognostics, across a wide range of technological domains of complex assets. However, models of long-life assets are challenging to validate, particularly due to issues with data scarcity and quality. A literature review on Bayesian networks in asset management in this paper shows that there is a need for further work in this area. This paper discusses the issues and challenges of validation of Bayesian network models in asset management and draws on findings from literature research to propose a preliminary validation framework for Bayesian network models in life-cycle management applications of capital-intensive long-life assets. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
- Authors: Morey, Stephen , Chattopadhyay, Gopinath , Larkins, Jo-ann
- Date: 2022
- Type: Text , Conference paper
- Relation: International Congress and Workshop on Industrial AI, IAI 2021, Virtual online, 6-7 October 2021, published in Lecture Notes in Mechanical Engineering p. 360-369
- Full Text:
- Reviewed:
- Description: Capital-intensive industries are under increasing pressure from capital constraints to extend the life of long-life assets and to defer asset renewals. Assets in most of those industries have complex life-cycle management challenges in aspects of design, manufacture, maintenance and service contracts, the usage environment, and changes in support personnel over the asset life. A significant challenge is the availability and quality of relevant data for informed decision-making in assuring reliability, availability and safety. There is a need for better-informed maintenance decisions and cost-effective interventions in managing the risk and assuring performance of those assets. Bayesian networks have been considered in asset management applications in recent years for addressing these challenges, by modelling of reliability, maintenance decisions, life extension and prognostics, across a wide range of technological domains of complex assets. However, models of long-life assets are challenging to validate, particularly due to issues with data scarcity and quality. A literature review on Bayesian networks in asset management in this paper shows that there is a need for further work in this area. This paper discusses the issues and challenges of validation of Bayesian network models in asset management and draws on findings from literature research to propose a preliminary validation framework for Bayesian network models in life-cycle management applications of capital-intensive long-life assets. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
A study on the use of machine learning methods to improve reciprocating compressor reliability via torque tailoring
- Lu, Kui, Sultan, Ibrahim, Phung, Truong
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021, Ballarat, Australia, 12-15 December 2021, 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021
- Full Text:
- Reviewed:
- Description: Reciprocating compressors have found popularity in applications where compressed air is required at high pressure levels with moderate flow rates. The mechanical drives used for these compressors are based on the traditional slider-crank linkage which, despite its simplicity, does not lend itself to optimization effort aimed at improving the compressor reliability and performance. The work presented in this paper adopts the notion that the mechanical reliability of the compressor drive is limited by the level and cyclical variability of the loads transmitted through its members and the effectiveness of its cooling system. In the paper, machine learning methods will be employed to craft an objective function suitable to use in a Bayesian optimization effort undertaken to produce a more reliable compressor drive. A numerical example is presented to prove the validity of the presented method and its suitability for use in real life compressor designs. © 2021 IEEE.
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021, Ballarat, Australia, 12-15 December 2021, 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021
- Full Text:
- Reviewed:
- Description: Reciprocating compressors have found popularity in applications where compressed air is required at high pressure levels with moderate flow rates. The mechanical drives used for these compressors are based on the traditional slider-crank linkage which, despite its simplicity, does not lend itself to optimization effort aimed at improving the compressor reliability and performance. The work presented in this paper adopts the notion that the mechanical reliability of the compressor drive is limited by the level and cyclical variability of the loads transmitted through its members and the effectiveness of its cooling system. In the paper, machine learning methods will be employed to craft an objective function suitable to use in a Bayesian optimization effort undertaken to produce a more reliable compressor drive. A numerical example is presented to prove the validity of the presented method and its suitability for use in real life compressor designs. © 2021 IEEE.
A3Graph : adversarial attributed autoencoder for graph representation learning
- Hou, Mingliang, Wang, Lei, Liu, Jiaying, Kong, Xiangjie, Xia, Feng
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.