Elevating engineering education via improved pedagogically based course structures
- Authors: Warren, Sara , Barton, Andrew
- Date: 2021
- Type: Text , Conference paper
- Relation: 9th Research in Engineering Education Symposium and 32nd Australasian Association for Engineering Education Conference: Engineering Education Research Capability Development, REES AAEE 2021, Perth, Australia, 5-8 December 2021, 9th Research in Engineering Education Symposium and 32nd Australasian Association for Engineering Education Conference, REES AAEE 2021: Engineering Education Research Capability Development Vol. 2, p. 1068-1076
- Full Text: false
- Reviewed:
- Description: CONTEXT In late 2018, the authors commenced a project in their School to improve the quality of student experience and enhance staff teaching within the Moodle LMS. This was motivated by the authors' interest in better meeting organisational strategic goals, related learning and teaching plans, and creating an improved pedagogical platform for their School. At the time, the University had also gone through an academic restructure, meaning that significant re-branding and realignment of disciplines had taken place. This project was timely in addressing these multi-dimensional obligations. PURPOSE The overall purpose of this high-level project was to provide course consistency in core structures and improve the educational experience for all students in the school. This consistency was to come primarily through the restructuring and alignment of the user experience, presentation, and provision of resources available to students in each course of study. An additional purpose was to provide a reduction in staff workload through the economic restructuring of resources thereby reducing time in searching for information, and the provision of additional content provided in the template, meant that minimum standards for learning and teaching online were being met at a greater extent. It was anticipated that improved levels of student engagement would also result by virtue of the improved user experience and the ability to individualise the course for each student. APPROACH To commence the project, an internal review of all course Moodle (learning management system, or LMS) shells was conducted and benchmarked against set University standards, known colloquially as Blended, Online and Digital Learning and Teaching (BOLD L&T) practices document. Courses were analysed and thematically grouped to identify where the largest gains could be made in the rollout of this work and greatest benefits realised to student and staff experience. Course priorities were moderated against University requirements and a final template was designed based on a constructivist pedagogy. Early versions of the templates were road tested by academic staff to seek feedback and to implement further template refinements. Rollout of the template commenced in 2019 and continued through 2020. ACTUAL OUTCOMES Outcomes include a consistent format that is more easily navigated by staff and students, reducing the time spent searching for information. The format has also reduced the data load on the University and student bandwidth systems by reducing the size of the up and download of each course page. The project implementation had negligible impact on academic staff workloads and occurred with minimal disruption to academic staff time. Students and staff have demonstrated their engagement and indicated their enjoyment and preference for the new interface. SUMMARY This paper presents a new LMS course template to address several student, staff and strategic requirements. Its core elements and rationale are presented, together with some preliminary statistics on its implementation and use. Some early success stories are used to provide further context. Copyright © Sara Warren, and Andrew Barton, 2021.
Eulerian granular CFD modelling of hydrodynamics of a free-falling particle curtain with particle size distribution
- Authors: Patel, Vishalkumar , Patel, Ankit , Kumar, Apurv
- Date: 2021
- Type: Text , Conference paper
- Relation: 5th-6th Thermal and Fluids Engineering Conference, TFEC 2021, Virtual online, 26-28 May 2021, Proceedings of the Thermal and Fluids Engineering Summer Conference Vol. 2021-May, p. 1241-1250
- Full Text: false
- Reviewed:
- Description: A solid particle receiver is a principal element in concentrated solar power technology in which falling ceramic particles in a cavity are exposed to extremely concentrated solar irradiation. Such particle receiver holds great promise in achieving high thermal efficiencies due to the possibility of reaching temperatures as high as 1000° C. To accurately model the hydrodynamics and the radiation heat transfer, it is imperative to simulate particle-gas interactions more realistically. All the particle receiver modelling till date has used only monodisperse size assumption to simplify the simulation. However, the radiation interaction with the particle curtain is greatly dependent on the size-dependent radiation properties. In the present work, we aim to model the two-dimensional mass and momentum equations using an Eulerian-Eulerian multiphase granular model with a particle size distribution in the falling particles. Gaussian distribution is assumed as a representative size distribution spread around a mean particle size of magnitudes generally used in particle receivers (~100-500 µm). The distribution is then split into n size bands and the Eulerian granular flow is modelled for n secondary phases (up to 3 in this study) with a corresponding concentration to simulate the particle size distribution. Finally, a parametric study is carried out to understand the effect of different particle sizes and their concentration on the volume fraction distribution and particle velocities inside the receiver. © 2021 Begell House Inc.. All rights reserved.
Factors affecting the organizational adoption of blockchain technology : an Australian perspective
- Authors: Malik, Saleem , Chadhar, Mehmood , Chetty, Madhu
- Date: 2021
- Type: Text , Conference paper
- Relation: 54th Annual Hawaii International Conference on System Sciences, HICSS 2021 Vol. 2020-January, p. 5597-5606
- Full Text:
- Reviewed:
- Description: Blockchain Technology (BCT) is a novel innovation that has the potential to transform industries, for instance, supply chain, energy, finance, and healthcare. However, despite the potential and the wide range of benefits reported, organizational adoption of BCT is low in several countries including Australia. Some studies investigated the adoption of BCT in different countries, however, there is a lack of research that examines the organizational adoption of BCT in Australia. This study fills this gap by exploring the factors, which influence BCT adoption among Australian organizations. To achieve this, we used an interpretative qualitative research approach based on the Technology, Organization, and Environment (TOE) framework and the Institutional Theory. The findings show that organizational adoption of BCT in Australia is influenced by perceived novelty, complexity, cost, and disintermediation feature of BCT; top management knowledge and support; government support, customer pressure, trading partner readiness, and consensus among trading partners. © 2021 IEEE Computer Society. All rights reserved.
Heterogeneous graph learning for explainable recommendation over academic networks
- Authors: Chen, Xiangtai , Tang, Tao , Ren, Jing , Lee, Ivan , Chen, Honglong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, 14-17 December 2021, ACM International Conference Proceeding Series p. 29-36
- Full Text:
- Reviewed:
- Description: With the explosive growth of new graduates with research degrees every year, unprecedented challenges arise for early-career researchers to find a job at a suitable institution. This study aims to understand the behavior of academic job transition and hence recommend suitable institutions for PhD graduates. Specifically, we design a deep learning model to predict the career move of early-career researchers and provide suggestions. The design is built on top of scholarly/academic networks, which contains abundant information about scientific collaboration among scholars and institutions. We construct a heterogeneous scholarly network to facilitate the exploring of the behavior of career moves and the recommendation of institutions for scholars. We devise an unsupervised learning model called HAI (Heterogeneous graph Attention InfoMax) which aggregates attention mechanism and mutual information for institution recommendation. Moreover, we propose scholar attention and meta-path attention to discover the hidden relationships between several meta-paths. With these mechanisms, HAI provides ordered recommendations with explainability. We evaluate HAI upon a real-world dataset against baseline methods. Experimental results verify the effectiveness and efficiency of our approach. © 2021 ACM.
Higher-order structure based anomaly detection on attributed networks
- Authors: Yuan, Xu , Zhou, Na , Yu, Shuo , Huang, Huafei , Chen, Zhikui , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 2691-2700
- Full Text:
- Reviewed:
- Description: Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods. © 2021 IEEE.
Human-machine collaborative video coding through cuboidal partitioning
- Authors: Ahmmed, Ashek , Paul, Manoranjan , Murshed, Manzur , Taubman, David
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Image Processing, ICIP 2021, Anchorage, USA 19-22 September 2021, Proceedings - International Conference on Image Processing, ICIP Vol. 2021-September, p. 2074-2078
- Full Text:
- Reviewed:
- Description: Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human perception, while feature coding aims for machine vision tasks. Recently, attempts are being made to bridge the gap between these two domains. In this work, we propose a video coding framework by leveraging on to the commonality that exists between human vision and machine vision applications using cuboids. This is because cuboids, estimated rectangular regions over a video frame, are computationally efficient, has a compact representation and object centric. Such properties are already shown to add value to traditional video coding systems. Herein cuboidal feature descriptors are extracted from the current frame and then employed for accomplishing a machine vision task in the form of object detection. Experimental results show that a trained classifier yields superior average precision when equipped with cuboidal features oriented representation of the current test frame. Additionally, this representation costs 7% less in bit rate if the captured frames are need be communicated to a receiver. © 2021 IEEE.
Impact of Active Current Ramping of Large-Scale PV Plant on the Dynamic Voltage Stability
- Authors: Alshareef, Abdulrhman , Shah, Rakibuzzaman , Mithulananthan, Nadarajah
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE PES Innovative Smart Grid Technologies - Asia, ISGT Asia 2021, Brisbane, 5-8 December 2021
- Full Text: false
- Reviewed:
- Description: This paper investigates the impact of active current ramping rate (rrpwr) of Large-Scale photovoltaic (LSPV) plants on the short-term dynamic voltage stability. Thus, the rrpwr is adapted according to the fault distance from the LSPV plant Point of Integration (POI). The investigation shows that when a fault occurs closer to POI, lower rrpwr helps to achieve better voltage recovery. Lower rrpwr means slower active power recovery following active power curtailment activated by a grid fault. Therefore, lower rrpwr will not compromise the reactive power injection as needed. Based on the minimal improvement in the voltage recovery at POI, it can be concluded that the adaptive rrpwr is not an influential factor to improve the short-term dynamic voltage stability. © 2021 IEEE
Improving the behaviours of expansive soils using recycled tyres
- Authors: Taheri, Abbas , Soltani, Amin , Dastoor, N.
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st NZGS Symposium, Dunedin, New Zealand, 24-26 March 2021, Proceedings of the 21st NZGS Symposium
- Full Text: false
- Reviewed:
In your face : sentiment analysis of metaphor with facial expressive features
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
Infiltration rates of recycled tyre-based permeable asphalt pavements and future maintenance
- Authors: Raeesi, Ramin , King, Russell , Soltani, Amin , Distani, Mahdi
- Date: 2021
- Type: Text , Conference paper
- Relation: Stormwater2021; Melbourne; 17-19 June 2021
- Full Text: false
- Reviewed:
- Description: More than a quarter of Australian urban areas are covered by impermeable surfaces. This shift from "naturally-permeable" to "impervious" surfaces results in an increase in the surface runoff during rainfalls, which contributes to an increase in flash flooding. Permeable pavements are among potential solutions to reduce the amount of surface runoff and the risk of flash floods; however, the main barriers in their uptake is their perceived lack of capacity to perform under traffic loads, rate of infiltration, and perceived reduction in permeability over time caused by clogging. This study reports on the hydro-mechanical performance of a large-scale permeable pavement trial site, constructed by the combination of tyre-and rock-derived aggregates, bonded together using a polyurethane-based binder, located at a car park in the City of Mitcham, South Australia. An area of approximately 400 m 2 , consisting of 24 parking bays, was paved using a variety of waste tyre-based blends. A series of in-situ double-ring infiltration tests were carried out over a nine-month period to study the evolution of clogging over time. A practical maintenance program, involving the use of a conventional street sweeper vehicle, was also developed and successfully implemented to cope with the potential adverse effects of pavement clogging. The infiltration rates, even nine months after construction, were consistently greater than the 0.4 cm/s-requirement commonly suggested for porous asphalt systems. The mechanical sweeper using one sweeping pass was found to be an effective solution for permeability recovery. Furthermore, the intense spot-sweeping approach, which involved five sweeping passes over highly-clogged locations, led to a further increase in the permeability; however, the magnitude of improvement was relatively small compared with the single-sweeping technique
Inspection of open-pit mine drainage characteristics with a horizontal borehole camera
- Authors: Perdigao, Cristhiana , Dyson, Ashley , Yaghoubi, Mohammadjavad , Baumgartl, Thomas
- Date: 2021
- Type: Text , Conference paper
- Relation: 14th Baltic Sea Region Geotechnical Conference, BSGC 2020 Vol. 727
- Full Text:
- Reviewed:
- Description: Horizontal bores and drains are crucial infrastructures for maintaining the stability of large open-pit mines. Induced deformations as the result of mining activities and the infiltration of water from large surface catchments during heavy rain events can cause the build-up of pore water pressures in brown coal batters. This can potentially lead to catastrophic slope failures. Horizontal boreholes and drains are commonly installed at shallow inclines and typically range in length from 150 to 400 metres. Due to complexities in surveying lengthy horizontal bores, the long-term internal properties of these structures are poorly understood. In this research, a specialised horizontal borehole camera was developed to observe a range of factors influencing borehole performance including the identification of fractured or jointed material, borehole geometry and features, and locationally dependent water outflow and drainage paths. Investigations were undertaken at an operational brown coal mine in the Latrobe Valley, located in Victoria, Australia. Features observed on the profile of horizontal bores are discussed, with an emphasis on providing in-situ material characterisation and for the purposes of maintaining stable mine batters. © Published under licence by IOP Publishing Ltd.
Integrating line weber local descriptor and deep feature for tire indentation mark image classification
- Authors: Liu, Ying , Che, Xin , Dong, Haitao , Li, Daxiang , Teng, Shyh , Lu, Guojun
- Date: 2021
- Type: Text , Conference paper
- Relation: 4th International Conference on Artificial Intelligence and Pattern Recognition, 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021,Virtual, Online,17-19 September 2021, 2021, ACM International Conference Proceeding Series p. 56-61
- Full Text: false
- Reviewed:
- Description: Tire indentation mark matching is an essential tool used for the investigation of criminal cases and traffic incidents. As such images are unique and uncommon, there is a lack of dedicated databases and relevant research on this topic. This paper presents a feature extraction algorithm effective for tire indentation mark image description. The main contributions include: (1) Line feature Weber local descriptor (LWLD) is proposed, which uses the Gabor orientations instead of the original gradient orientation. This feature can describe texture information of tire indentation mark image more efficiently. (2) An attention model is constructed to produce attention feature map of tire indentation mark image. This attention feature map is then fused with LWLD resulting in a feature with more powerful representation capability. Experimental results prove that the combined use of LWLD and attention model greatly enhances the performance of tire indentation mark image matching tasks. © 2021 ACM.
Integrating Real-Time Analytics and Situational Awareness into Business Process Management
- Authors: Zhao, Xiaohui
- Date: 2021
- Type: Text , Conference paper
- Relation: 17th IEEE International Conference on e-Business Engineering, ICEBE 2021, Guangzhou, China, 12-14 November 2021, Proceedings - 2021 IEEE International Conference on e-Business Engineering, ICEBE 2021 p. 21-26
- Full Text:
- Reviewed:
- Description: The integration of real-Time business intelligence into business process navigation is expected to boost business process management to a highly intelligent and flexible level. This advance comes with many appealing features, such as operational business intelligence, adaptive process evolution, situational awareness, etc. With such capabilities, businesses can effectively improve their customer relationships, increase revenue and maximise operational efficiency. Despite the strong demand from industry, little work has been done in attempting this integration. With the aim of filling this gap, this paper discusses the requirements for realising data-driven, context-Aware business process management with real-Time intelligence. A system architecture is proposed to illustrate this integration, and a real-Time recommendation approach is also introduced to best adapt a business process to perceived changes. © 2021 IEEE.
KIDNet : a knowledge-aware neural network model for academic performance prediction
- Authors: Tang, Tao , Hou, Jie , Guo, Teng , Bai, Xiaomei , Tian, Xue , Noori Hoshyar, Azadeh
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online14-17 December 2021, ACM International Conference Proceeding Series p. 37-44
- Full Text: false
- Reviewed:
- Description: Academic performance prediction and analysis in educational data mining is meaningful for instructors to know the student's ongoing learning status, and also provide appropriate help to students as early as possible if academic difficulties appear. In this paper, we first collect the basic information of students and courses as features. Then, we propose a novel knowledge extraction framework to obtain course knowledge features to reinforce feature groups. The comparative analyses of the knowledge similarity and average grades of the courses in all terms demonstrate a strong correlation between them. Furthermore, we build the Knowledge Interaction Discovery Network (KIDNet) model, based on factorization machine (FM) and deep neural network (DNN) algorithms. This model uses FM to model lower-order interactions of sparse features and employs DNN to model higher-order interactions of both dense and sparse features. The effectiveness of KIDNet has been validated by conducting experiments based on a real-world dataset. © 2021 ACM.
Language representations for generalization in reinforcement learning
- Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
- Date: 2021
- Type: Text , Conference paper
- Relation: 13th Asian Conference on Machine Learning, Virtual, 17-19 November 2021, Proceedings of The 13th Asian Conference on Machine Learning Vol. 157, p. 390-405
- Full Text:
- Reviewed:
- Description: The choice of state and action representation in Reinforcement Learning (RL) has a significant effect on agent performance for the training task. But its relationship with generalization to new tasks is under-explored. One approach to improving generalization investigated here is the use of language as a representation. We compare vector-states and discreteactions to language representations. We find the agents using language representations generalize better and could solve tasks with more entities, new entities, and more complexity than seen in the training task. We attribute this to the compositionality of language
Lateral cyclic performance of hybrid fabricated beam‐columns
- Authors: Javidan, Fatemeh
- Date: 2021
- Type: Text , Conference paper
- Relation: 9th European Conference on Steel and Composite Structures, Sheffield, UK, 1-3 September 2021, ce/papers Eurosteel 2021 Sheffield Vol. 4, p. 1657-1662
- Full Text: false
- Reviewed:
- Description: In this paper, a high‐capacity fabricated hollow section is proposed as a lightweight replacement for concrete‐filled composite members which are commonly used as beam‐columns in seismic zones. The lateral cyclic performance of the fabricated hollow beam‐column comprising of mild steel plates (grade 250) and high strength steel (HSS) tubes (grade 750) is investigated. A finite element model is developed and validated against available experimental data. To incorporate the cyclic hardening and softening of both steel materials, a combined plasticity model obtained from low‐cycle material tests is incorporated in the finite element model. A comprehensive sensitivity analysis is undertaken to propose an optimum slenderness design for the thin‐walled steel elements with ductile failure. While the high strength steel tube elements can significantly increase the axial and lateral capacity of the hybrid section, the cyclic failure mechanism is governed by mild steel plate elements, rather than a sudden failure in the high strength steel tubes.
Machine learning based biosignals mental stress detection
- Authors: Al-Jumaily, Adel , Matin, Nafisa , Hoshyar, Azadeh
- Date: 2021
- Type: Text , Conference paper
- Relation: 6th International Conference on Soft Computing in Data Science, SCDS 2021 Vol. 1489 CCIS, p. 28-41
- Full Text: false
- Reviewed:
- Description: Mental Stress can be defined as a normal physiological and biological reaction to an incident or a situation that makes a person feel challenged, troubled, or helpless. While dealing with stress, some changes occur in the biological function of a person, which results in a considerable change in some bio-signals such as, Electrocardiogram (ECG), Electromyography (EMG), Electrodermal Activity (EDA), respiratory rate. This paper aims to review the effect of mental stress on mental condition and health, the changes in biosignals as an indicator of the stress response and train a model to detect stressed states using the biosignals. This paper delivers a brief review of mental stress and biosignals correlation. It represents four Support Vector Machine (SVM) models trained with ECG and EMG features from an open access database based on task related stress. After performing comparative analysis on the four types of trained SVM models with chosen features, Gaussian Kernel SVM is selected as the best SVM model to detect mental stress which can predict the mental condition of a subject for a stressed and relaxed condition having an accuracy of 93.7%. These models can be investigated further with more biosignals and applied in practice, which will be beneficial for the physician. © 2021, Springer Nature Singapore Pte Ltd.
MAM : a metaphor-based approach for mental illness detection
- Authors: Zhang, Dongyu , Shi, Nan , Peng, Ciyuan , Aziz, Abdul , Zhao, Wenhong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st International Conference on Computational Science, ICCS 2021 Vol. 12744 LNCS, p. 570-583
- Full Text:
- Reviewed:
- Description: Among the most disabling disorders, mental illness is one that affects millions of people across the world. Although a great deal of research has been done to prevent mental disorders, detecting mental illness in potential patients remains a considerable challenge. This paper proposes a novel metaphor-based approach (MAM) to determine whether a social media user has a mental disorder or not by classifying social media texts. We observe that the social media texts posted by people with mental illness often contain many implicit emotions that metaphors can express. Therefore, we extract these texts’ metaphor features as the primary indicator for the text classification task. Our approach firstly proposes a CNN-RNN (Convolution Neural Network - Recurrent Neural Network) framework to enable the representations of long texts. The metaphor features are then applied to the attention mechanism for achieving the metaphorical emotions-based mental illness detection. Subsequently, compared with other works, our approach achieves creative results in the detection of mental illnesses. The recall scores of MAM on depression, anorexia, and suicide detection are the highest, with 0.50, 0.70, and 0.65, respectively. Furthermore, MAM has the best F1 scores on depression and anorexia detection tasks, with 0.51 and 0.71. © 2021, Springer Nature Switzerland AG.
MATLAB/Simulink Modelling of Multi-junction PV Cell for Conversion Efficiency Improvement using Maximum Power Point Tracking Method
- Authors: Dave, Malvika , Das, Narottam , Islam, Syed
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE PES Innovative Smart Grid Technologies - Asia, ISGT Asia 2021, Brisbane, 5-8 December 2021
- Full Text: false
- Reviewed:
- Description: This research focuses the modelling of multi-junction solar cells (MJSCs) for conversion efficiency improvement considering maximum power point tracking (MPPT) utilizing MATLAB/Simulink software. The conversion efficiency of a single-junction photovoltaic (PV) cell is comparatively low than the MJSCs (GaInP/GaInAs/Ge). The cell conversion efficiency is improved by forming MJSCs, where two or more single junctions are stacked, and higher conversion efficiency is achieved using the MPPT method in MATLAB/Simulink environment to maximize the output power of PV panel. This research considered different parameters of MJSCs, such as lattice matching, bandgap matching, current matching to improve the conversion efficiency. The maximum performance of MJSCs also obtained through the I-V and P-V characteristics by varying different environmental factors, such as temperature and irradiance in MATLAB/Simulink environment. perturb and observe (P&O) MPPT algorithm which is the most suitable for PV applications. Finally, two different Pulse Width Modulation techniques are compared and analyzed with respect to Perturb and observe by applying Quasi Z source inverter (QZSI) within the MATLAB/Simulink environment to enhance the conversion efficiency of triple MJSC. © 2021 IEEE
Melanoma classification using efficientnets and ensemble of models with different input resolution
- Authors: Karki, Sagar , Kulkarni, Pradnya , Stranieri, Andrew
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 Australasian Computer Science Week Multiconference, ACSW 2021, Virtual, Online, 1-5 February 2021, ACM International Conference Proceeding Series
- Full Text:
- Reviewed:
- Description: Early and accurate detection of melanoma with data analytics can make treatment more effective. This paper proposes a method to classify melanoma cases using deep learning on dermoscopic images. The method demonstrates that heavy augmentation during training and testing produces promising results and warrants further research. The proposed method has been evaluated on the SIIM-ISIC Melanoma Classification 2020 dataset and the best ensemble model achieved 0.9411 area under the ROC curve on hold out test data. © 2021 ACM.