Increasing hydrogen energy efficiency by heat integration between fuel cell, hydride tank and electrolyzer
- Authors: Ghayur, Adeel , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 2019 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2019
- Full Text: false
- Reviewed:
- Description: Chemical processes offer untapped potential to increase overall system efficiencies by synergizing renewable hydrogen storage with dispatchable renewable energy facilities. In this study an Energy Storage Facility model is developed and simulation conducted to examine this potential. The model incorporates a Solid Oxide Fuel Cell (SOFC) integrated with a Magnesium Hydride (MgH2) Tank and an alkaline electrolyzer linked to the power grid. Surplus grid power is converted to hydrogen and stored as magnesium hydride. This storage process generates waste heat which is used to partially offset the water heating requirement of the electrolyzer. Simulation results demonstrate 20% reduction in parasitic heat energy consumption using this waste heat. Stored hydrogen provides power on demand via the SOFC. Waste heat from SOFC fulfils the desorption heat demand of the MgH2 Tank. Simulation results reveal waste heat from the SOFC is just enough to preheat oxygen and hydrogen and desorb hydrogen from the MgH2 tank. These results are encouraging, warranting further investigation into metal hydride storage to help Australia's transition towards renewable energy resources. © 2019 IEEE.
Pre-trained language models with limited data for intent classification
- Authors: Kasthuriarachchy, Buddhika , Chetty, Madhu , Karmakar, Gour , Walls, Darren
- Date: 2020
- Type: Text , Conference proceedings , Conference paper
- Relation: 2020 International Joint Conference on Neural Networks, IJCNN 2020
- Full Text: false
- Reviewed:
- Description: Intent analysis is capturing the attention of both the industry and academia due to its commercial and noncommercial significance. The rapid growth of unstructured data of micro-blogging platforms, such as Twitter and Facebook, are amongst the important sources for intent analysis. However, the social media data are often noisy and diverse, thus making the task very challenging. Further, the intent analysis frequently suffers from lack of sufficient data because the labeled datasets are often manually annotated. Recently, BERT (Bidirectional Encoder Representation from Transformers), a state-of-the-art language representation model, has attracted attention for accurate language modelling. In this paper, we investigate the application of BERT for its suitability for intent analysis. We study the fine-tuning of the BERT model through inductive transfer learning and investigate methods to overcome the challenges due to limited data availability by proposing a novel semantic data augmentation approach. This technique generates synthetic sentences while preserving the label-compatibility using the semantic meaning of the sentences, to improve the intent classification accuracy. Thus, based on the considerations for finetuning and data augmentation, a systematic and novel step-bystep methodology is presented for applying the linguistic model BERT for intent classification with limited data available. Our results show that the pre-trained language can be effectively used with noisy social media data to achieve state-of-the-art accuracy in intent analysis under low labeled-data regime. Moreover, our results also confirm that the proposed text augmentation technique is effective in eliminating noisy synthetic sentences, thereby achieving further performance improvements. © 2020 IEEE.
Multi-agent based autonomous control of microgrid
- Authors: Shawon, Mohammad Hasanuzzaman , Ghosh, Arimdam , Muyeen, S. , Baptista, Murilo , Islam, Syed
- Date: 2020
- Type: Text , Conference proceedings
- Relation: 2nd International Conference on Smart Power and Internet Energy Systems, SPIES 2020, 15-18 Sept. 2020, Bangkok, Thailand p. 333-338
- Full Text: false
- Reviewed:
- Description: Microgrid (MG), a revolutionary concept in the energy infrastructure, plays an important role for the establishment of a resilient grid infrastructure. Since its emergence, it has evolved around a number of cutting edge technologies for its smooth operation and control. Among them multi-agent system (MAS) provides an intelligent and decentralized platform for the control of microgrid. This paper highlights the application of a MAS in an AC microgrid, including a detailed structure of microgrid, the communication interface between microgrid and multi-agent platform. A detailed small scale microgrid model has been simulated in MATLAB/SIMULINK environment, whereas the agent platform has been implemented in JADE (Java Agent Development Framework) platform. The MAS autonomously detects main grid outage and facilitates seamless transition from grid-connected mode to islanding mode; thus ensures overall smooth operation of the power network. Simulation results are presented to verify the effectiveness of the MAS based control system. © 2020 IEEE.
Electric vehicle participated electricity market model considering flexible ramping product provisions
- Authors: Zhang, Xian , Hu, Jiefeng , Wang, Huaizhi , Wang, Guibin , Chan, Ka , Qiu, Jing
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Industry Applications Vol. 56, no. 5 (2020), p. 5868-5879
- Full Text: false
- Reviewed:
- Description: This article studies electric vehicle (EV) potential to participate in the energy market and provide flexible ramping products (FRPs). EV traffic flows are predicted by the deep belief network, and the availability of flexible EVs is estimated based on the predicted EV traffic flows. Then, a novel market mechanism in distribution system is proposed to encourage the dispatchable EV demand to react to economic signals and provide ramping services. The designed market model is based on locational marginal pricing of energy and marginal pricing of FRPs. System ramping capacity constraints and EV operation constraints are incorporated in the proposed model to achieve the balance between the system social cost minimization and the EV traveling convenience. Moreover, typical uncertainties are considered by the scenario-based approach. Finally, simulations are conducted to verify the effectiveness of the established model and demonstrate the contributions of EVs to the system reliability and flexibility. © 1972-2012 IEEE.
- Description: ITIAC: Funding details: JCYJ20170817100412438, 2019-AAAE-1307, JCYJ20190808141019317
Automatic building footprint extraction and regularisation from LIDAR point cloud data
- Authors: Awrangjeb, Mohammad , Lu, Guojun
- Date: 2014
- Type: Text , Conference proceedings
- Full Text: false
- Description: This paper presents a segmentation of LIDAR point cloud data for automatic extraction of building footprint. Using the ground height information from a DEM (Digital Elevation Model), the non-ground points (mainly buildings and trees) are separated from the ground points. Points on walls are removed from the set of non-ground points. The remaining non-ground points are then divided into clusters based on height and local neighbourhood. Planar roof segments are extracted from each cluster of points following a region-growing technique. Planes are initialised using coplanar points as seed points and then grown using plane compatibility tests. Once all the planar segments are extracted, a rule-based procedure is applied to remove tree planes which are small in size and randomly oriented. The neighbouring planes are then merged to obtain individual building boundaries, which are regularised based on a new feature-based technique. Corners and line-segments are extracted from each boundary and adjusted using the assumption that each short building side is parallel or perpendicular to one or more neighbouring long building sides. Experimental results on five Australian data sets show that the proposed method offers higher correctness rate in building footprint extraction than a state-of-the-art method.
A novel multi-modal image registration method based on corners
- Authors: Lv, Guohua , Teng, Shyh , Lu, Guojun
- Date: 2015
- Type: Text , Conference proceedings
- Relation: 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014, Wollongong, New South Wales, 25th-27th November 2014
- Full Text: false
- Description: This paper presents a novel method for registering multi-modal images, based on corners. The proposed method is motivated by the fact that large content differences are likely to occur in multi-modal images. Unlike traditional multi-modal image registration methods that utilize intensities or gradients for feature representation, we propose to use curvatures of corners. Moreover, a novel local descriptor called Distribution of Edge Pixels Along Contour (DEPAC) is proposed to represent the neighborhood of corners. Curvature and DEPAC similarities are combined in our method to improve the registration accuracy. Using a set of benchmark multi-modal images and multi-modal microscopic images, we demonstrate that our proposed method outperforms an existing state-of-the-art image registration method.
Efficient coding of depth map by exploiting temporal correlation
- Authors: Shahriyar, Shampa , Murshed, Manzur , Ali, Mortuza , Paul, Manoranjan
- Date: 2014
- Type: Text , Conference proceedings
- Relation: 2014 International Conference on Digital Image Computing : Techniques and Applications (DICTA); Wollongong, Australia; 25th-27th November 2014
- Relation: http://purl.org/au-research/grants/arc/DP130103670
- Full Text: false
- Description: With the growing demands for 3D and multi-view video content, efficient depth data coding becomes a vital issue in image and video coding area. In this paper, we propose a simple depth coding scheme using multiple prediction modes exploiting temporal correlation of depth map. Current depth coding techniques mostly depend on intra-coding mode that cannot get the advantage of temporal redundancy in the depth maps and higher spatial redundancy in inter-predicted depth residuals. Depth maps are characterized by smooth regions with sharp edges that play an important role in the view synthesis process. As depth maps are more sensitive to coding errors, use of transformation or approximation of edges by explicit edge modelling has impact on view synthesis quality. Moreover, lossy compression of depth map brings additional geometrical distortion to synthetic view. In this paper, we have demonstrated that encoding inter-coded depth block residuals with quantization at pixel domain is more efficient than the intra-coding techniques relying on explicit edge preservation. On standard 3D video sequences, the proposed depth coding has achieved superior image quality of synthesized views against the new 3D-HEVC standard for depth map bit-rate 0.25 bpp or higher.
A recurrent neural network for solving bilevel linear programming problem
- Authors: He, Xing , Li, Chuandong , Huang, Tingwen , Li, Chaojie , Huang, Junjian
- Date: 2014
- Type: Text , Journal article
- Relation: IEEE Transactions on Neural Networks and Learning Systems Vol. 25, no. 4 (April 2014 2014), p. 824-830
- Full Text: false
- Reviewed:
- Description: In this brief, based on the method of penalty functions, a recurrent neural network (NN) modeled by means of a differential inclusion is proposed for solving the bilevel linear programming problem (BLPP). Compared with the existing NNs for BLPP, the model has the least number of state variables and simple structure. Using nonsmooth analysis, the theory of differential inclusions, and Lyapunov-like method, the equilibrium point sequence of the proposed NNs can approximately converge to an optimal solution of BLPP under certain conditions. Finally, the numerical simulations of a supply chain distribution model have shown excellent performance of the proposed recurrent NNs.
Informatics to support patient choice between diverse medical systems C3 - 2014 IEEE 16th International Conference on e-Health Networking, Applications and Services, Healthcom 2014
- Authors: Golden, Isaac , Stranieri, Andrew , Sahama, Tony , Pilapitiya, Senaka , Siribaddana, Sisira , Vaughan, Stephen
- Date: 2014
- Type: Text , Conference proceedings
- Full Text: false
- Description: Culturally, philosophically and religiously diverse medical systems including Western medicine, Traditional Chinese Medicine, Ayurvedic Medicine and Homeopathic Medicine, once situated in places and times relatively unconnected from each other, currently co-exist to a point where patients must choose which system to consult. These decisions require comparative analyses, yet the divergence in key underpinning assumptions is so great that comparisons cannot easily be made. However, diverse medical systems can be meaningfully juxtaposed for the purpose of making practical decisions if relevant information is presented appropriately. Information regarding privacy provisions inherent in the typical practice of each medical system is an important element in this juxtaposition. In this paper the information needs of patients making decisions regarding the selection of a medical system, are examined.
An adaptive approach to opportunistic data forwarding in underwater acoustic sensor networks
- Authors: Nowsheen, Nusrat , Karmakar, Gour , Kamruzzaman, Joarder
- Date: 2014
- Type: Text , Conference proceedings
- Full Text:
- Description: Reliable data transfer for underwater acoustic sensor networks (UASNs) is a major research challenge in applications such as pollution monitoring, oceanic data collection, and surveillance due to the long propagation delay and high error rate of the acoustic channel. To address this issue, an opportunistic data forwarding protocol was proposed which achieves high packet delivery success ratio with less routing overhead and energy consumption by selecting the next hop forwarder among a set of candidates based on its link reliability and data transfer reach ability. However, the protocol relies on fixed data hold time approach, i.e., Each node holds data packets for a fixed amount of time before a forwarder discovery process is initiated. Depending on the value of the fixed hold time and deployment contextual scenario, this may incur large end-to-end delay. Moreover, lack of consideration of network condition in hold time limits its performance. In this paper, we propose an adaptive technique to improve its performance. The adaptive approach calculates data hold time at each node dynamically considering a number of 'node and network' metrics including current buffer occupancy, delay experienced by stored data packets, arrival and service rate, neighbors' data transmissions and reach ability. Simulation results show that compared with fixed hold time approach, our adaptive technique reduces end-to-end delay significantly, achieves considerably higher data delivery and less energy consumption per successful packet delivery.
The importance of mandatory data breach notification to identity crime
- Authors: Holm, Eric , Mackenzie, Geraldine
- Date: 2014
- Type: Text , Conference proceedings
- Full Text:
- Description: The relationship between data breaches and identity crime has been scarcely explored in current literature. However, there is an important relationship between the misuse of personal identification information and identity crime as the former is in many respects the catalyst for the latter. Data breaches are one of the ways in which this personal identification information is obtained by identity criminals, and thereby any response to data breaches is likely to impact the incidence of identity crime. Initiatives around data breach notification have become increasingly prevalent and are now seen in many State legislatures in the United States and overseas. The Australian Government is currently in the process of introducing mandatory data breach notification laws. This paper explores the introduction of mandatory data breach notification in Australia, and lessons learned from the experience in the US, particularly noting the link between data breaches and identity crime. The paper proposes that through the introduction of such laws, identity crimes are likely to be reduced.
Monitoring oxy-coal flame stability
- Authors: Valliappan, Palaniappan , Wilcox, Steven , Spliethoff, Hartmut , Diego Garcia, Ruth
- Date: 2018
- Type: Text , Conference proceedings
- Relation: 27th IEEE International Symposium on Industrial Electronics, ISIE 2018; Cairns, Australia; 13th-15th June 2018 Vol. 2018-June, p. 847-853
- Full Text: false
- Reviewed:
- Description: This paper presents a novel approach to monitoring the stability of oxy-coal flames. Oxy-coal combustion has the potential to generate high concentrations of carbon dioxide in the exhaust gas stream. This could increase the efficiency of the removal of carbon dioxide emissions from a coal fired utility boiler. In order to convert an existing boiler high levels of flue gas need to be recycled to reduce the combustion zone temperatures, but this can lead to combustion instability. This paper presents an approach using three broadband photodiodes to monitor the infra-red, visible and ultra-violet emissions from an individual flame and then, by using the Wigner-Ville transform, detect unstable flames.
- Description: IEEE International Symposium on Industrial Electronics
Battery impedance measurement using sinusoidal ripple current emulator
- Authors: Hossain, Kamal , Islam, Syed , Park, Sung-Yeul
- Date: 2017
- Type: Text , Conference proceedings , Conference paper
- Relation: 9th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2017; Cincinnati, United States; 1st-5th October 2017 Vol. 2017, p. 2754-2759
- Full Text: false
- Reviewed:
- Description: This paper presents a sinusoidal ripple current (SRC) emulator which superimposes an ac ripple current frequency into a dc charging current in order to produce a sinusoidal ripple current without a ripple current controller. It can be used for several purposes:1) to analyze the impact of ac ripple current magnitude and frequency on the battery internal characteristics; 2) to determine the parameters related to thermal rise and lithium plating; 3) to obtain more updated parameter information for improved utilization of a battery; 4) to determine the optimal ripple current frequency at the minimum impedance point by sweeping the ripple current frequency; 5) to utilize the obtained impedance data for estimating the battery circuit parameters and SOC level. The internal characteristics of batteries are complex and dynamic; therefore, it is beneficial to use the SRC emulator to validate SRC performance in a battery stack before integrating a SRC algorithm into a battery charger. This paper describes the development procedure of a SRC emulator to produce the electrochemical impedance spectroscopy (EIS) measurement for measuring the battery internal impedance. In order to validate the performance of the SRC emulator, a 12.8 V, 40 Ah Li-ion battery was charged at C/8 rate in CC mode with ± 1 App ac ripple current perturbation with an impedance from 20 Hz to 2 kHz.
Improved kernel descriptors for effective and efficient image classification
- Authors: Karmakar, Priyabrata , Teng, Shyh , Zhang, Dengsheng , Liu, Ying , Lu, Guojun
- Date: 2017
- Type: Text , Conference proceedings
- Relation: 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA); Sydney, Australia; 29th November-1st December 2017 p. 195-202
- Full Text: false
- Reviewed:
- Description: Kernel descriptors have been proven to outperform existing histogram based local descriptors as such descriptors are extracted from the match kernels which measure similarities between image patches using different pixel attributes (gradient, colour or LBP pattern). The extraction of kernel descriptors does not require coarse quantization of pixel attributes. Instead, each pixel equally participates in matching between two image patches. In this paper, by leveraging the kernel properties, we propose a unique approach which simultaneously increases the effectiveness and efficiency of the existing kernel descriptors. Specifically, this is done by improving the similarity measure between two different patches in terms of any pixel attribute. The proposed kernel descriptors are more discriminant, take less time to be extracted and have much lower dimensions. Our experiments on Scene Categories and Caltech 101 databases show that our proposed approach outperforms the existing kernel descriptors.
Industry-led mechatronics degree development in regional Australia
- Authors: Ibrahim, Yousef , Kahandawa, Gayan , Choudhury, Tanveer , Mazid, Abdul Md
- Date: 2017
- Type: Text , Conference proceedings , Conference paper
- Relation: 2017 IEEE International Conference on Mechatronics, ICM 2017; Gippsland, Australia; 13th-15th February 2017 p. 419-424
- Full Text: false
- Reviewed:
- Description: This paper presents a technique that was used in the recent development of a new Mechatronics degree in Australia. This technique addressed the local industry needs and the available resources for a well-balanced Mechatronics degree program. The degree development was based on project-based learning and industry engagement. The development of the new Mechatronics degree was made possible via a State Government grant of AU$2.4 Million which was matched by industry contribution of AU$10 Million in cash and in-kind. Since industry was a major stake holder in this degree, a specific industry survey was conducted to check the desired graduates attributes, from industry point of view. The results of this survey is also included in this papers. In addition, the program also addressed the regional industry's challenge of retaining qualified engineers via a clear pathway program for students knowledge and skills development. This paper presents industry's anticipated outputs of the academic Mechatronics program. In addition the paper also discusses the mechanisms adopted for the development of this new degree. The developed fully integrated Mechatronics program was founded on the realisation that if a person undertook a mechanical degree followed by an electronics degree followed by a computer science degree, that person is, still, NOT a Mechatronics engineer. © 2017 IEEE.
- Description: Proceedings - 2017 IEEE International Conference on Mechatronics, ICM 2017
Comparative study on object tracking algorithms for mobile robot navigation in GPS-denied environment
- Authors: Hewawasam, Hasitha , Ibrahim, Yousef , Kahandawa, Gayan , Choudhury, Tanveer
- Date: 2019
- Type: Text , Conference proceedings
- Relation: 2019 IEEE International Conference on Industrial Technology, ICIT 2019; Melbourne, Australia; 13th-15th February 2019 Vol. 2019-February, p. 19-26
- Full Text: false
- Reviewed:
- Description: This paper presents a comparative study conducted on the performance of the commonly used object tracking and location prediction algorithms for mobile robot navigation in a dynamically cluttered and GPS-denied mining environment. The study was done to test the different algorithms for the same set criteria (such as accuracy and computational time) under the same conditions.The identified commonly used algorithms for object tracking and location prediction of moving objects used in this investigation are Kalman filter (KF), extended Kalman filter (EKF) and particle filter (PF). The study results of those algorithms are analyzed and discussed in this paper. A trade-off was apparent. However, in overall performance KF has shown its competitiveness.The result from the study has found that the KF based algorithm provides better performance in terms of accuracy in tracking dynamic objects under commonly used benchmarks. This finding can be used in development of an efficient robot navigation algorithm.
- Description: Proceedings of the IEEE International Conference on Industrial Technology
Novel tire inflating system using extreme learning machine algorithm for efficient tire identification
- Authors: Choudhury, Tanveer , Kahandawa, Gayan , Ibrahim, Yousef , Dzitac, Pavel , Mazid, Abdul Md , Man, Zhihong
- Date: 2017
- Type: Text , Conference proceedings , Conference paper
- Relation: 2017 IEEE International Conference on Mechatronics, ICM 2017; Gippsland, Victoria; 13th-15th February 2017 p. 404-409
- Full Text: false
- Reviewed:
- Description: Tire inflators are widely used all around the word and the efficient and accurate operation is essential. The main difficulty in improving the inflation cycle of a tire inflator is the identification of the tire connected for inflation. A robust single hidden layer feed forward neural network (SLFN) is, thus, used in this study to model and predict the correct tire size. The tire size is directly related to the tire inflation cycle. Once the tire size is identified, the inflation process can be optimized to improve performance, speed and accuracy of the inflation system. Properly inflated tire and tire condition is critical to vehicle safety, stability and controllability. The training times of traditional back propagation algorithms, mostly used to model such tire identification processes, are far slower than desired for implementation of an on-line control system. Use of slow gradient based learning methods and iterative tuning of all network parameters during the learning process are the two major causes for such slower learning speed. An extreme learning machine (ELM) algorithm, which randomly selects the input weights and biases and analytically determines the output weights, is used in this work to train the SLFNs. It is found that networks trained with ELM have relatively good generalization performance, much shorter training times and stable performance with regard to the changes in number of hidden layer neurons. The result represents robustness of the trained networks and enhance reliability of the mode. Together with short training time, the algorithm has valuable application in tire identification process. © 2017 IEEE.
- Description: Proceedings - 2017 IEEE International Conference on Mechatronics, ICM 2017
Alleviating post-contingency congestion risk of wind integrated systems with dynamic line ratings
- Authors: Banerjee, Binayak , Jayaweera, Dilan , Islam, Syed
- Date: 2014
- Type: Text , Conference proceedings , Conference paper
- Relation: 24th Australasian Universities Power Engineering Conference, AUPEC 2014; Perth, Australia; 28th September-1st October 2014 p. 1-6
- Full Text: false
- Reviewed:
- Description: One of the factors hindering the large scale integration of wind power is the post contingency congestion of a network due to limited availability of network capacity and auxiliary constraints. Under such conditions, the network operators can potentially request a curtailment of wind farm output if the remedial strategies fail. The paper investigates this problem in detail and proposes a mathematical framework to capture the post contingency spare capacity of network assets that is required to limit the wind curtailment. The proposed approach incorporates stochastic variation in asset thermal rating; models network congestion, and quantifies the risk of congestion using an extended version of conic-quadratic programming based optimization. The uniqueness of the proposed mathematical model is that it converts conventional thermal constraints to dynamic constraints by using a discretized stochastic penalty function with quadratic approximation of constraint relaxation penalty. The results suggest that the wind utilization can be maximized if the networks are operated 30-50% less than the nominal rating of the assets.
Exploring the application of artificial neural network in rural streamflow prediction - A feasibility study
- Authors: Choudhury, Tanveer , Wei, Jackie , Barton, Andrew , Kandra, Harpreet , Aziz, Abdul
- Date: 2018
- Type: Text , Conference proceedings
- Relation: 27th IEEE International Symposium on Industrial Electronics, ISIE 2018; Cairns, Australia; 13th-15th June 2018 Vol. 2018-June, p. 753-758
- Full Text:
- Reviewed:
- Description: Streams and rivers play a critical role in the hydrologic cycle with their management being essential to maintaining a balance across social, economic and environmental outcomes. Accurate streamflow predictions can provide benefits in many different ways such as water allocation decision making, flood forecasting and environmental watering regimes. This is particularly important in regional areas of Australia where rivers can play a critical role in irrigated agriculture, recreation and social wellbeing, major floods and sustainable environments. There are several hydrological parameters that effect stream flows in rivers and a major challenge with any prediction methodology, is to understand these parameter interdependencies, correlations and their individual effects. A robust methodology is, thus, required for accurate prediction of streamflow under usually unique, waterway-specific conditions using available data. This research employs an approach based on Artificial Neural Network (ANN) to provide this robust methodology. Data from readily available sources has been selected to provide appropriate input and output parameters to train, validate and optimise the neural network. The optimisation steps of the methodology are discussed and the predicted outputs are compared and analysed with respect to the actual collected values. © 2018 IEEE.
- Description: IEEE International Symposium on Industrial Electronics
Multi-source cyber-attacks detection using machine learning
- Authors: Taheri, Sona , Gondal, Iqbal , Bagirov, Adil , Harkness, Greg , Brown, Simon , Chi, Chihung
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 2019 IEEE International Conference on Industrial Technology, ICIT 2019; Melbourne, Australia; 13th-15th February 2019 Vol. 2019-February, p. 1167-1172
- Full Text:
- Reviewed:
- Description: The Internet of Things (IoT) has significantly increased the number of devices connected to the Internet ranging from sensors to multi-source data information. As the IoT continues to evolve with new technologies number of threats and attacks against IoT devices are on the increase. Analyzing and detecting these attacks originating from different sources needs machine learning models. These models provide proactive solutions for detecting attacks and their sources. In this paper, we propose to apply a supervised machine learning classification technique to identify cyber-attacks from each source. More precisely, we apply the incremental piecewise linear classifier that constructs boundary between sources/classes incrementally starting with one hyperplane and adding more hyperplanes at each iteration. The algorithm terminates when no further significant improvement of the separation of sources/classes is possible. The construction and usage of piecewise linear boundaries allows us to avoid any possible overfitting. We apply the incremental piecewise linear classifier on the multi-source real world cyber security data set to identify cyber-attacks and their sources.
- Description: Proceedings of the IEEE International Conference on Industrial Technology