Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827598
W. Y. Alghamdi, Hui Wu, Jingjing Fei, S. Kanhere
WSN (Wireless Sensor Network) has a wide range of applications. As a result, security problems become increasingly important. We investigate the problem of minimising the failure rate of packet delivery in the presence of the modification attacks and the selective forwarding attacks in a static WSN with one base station without using expensive encryption/decryption algorithms. We propose a novel heuristic approach to this problem. Our approach is based on randomised multipath routing. When a sensor node needs to send a packet to the base station, it creates three copies and sends these three copies to the base station via three paths. Among the three paths, two of them are selected at random based on a spanning tree with the base station as the root. The base station accepts a packet only if it receives at least two identical copies. We have simulated our approach. The simulation results show that our approach achieves a very low failure rate of packet delivery in the presence of a relatively high percentage of malicious sensor nodes.
{"title":"Randomised multipath routing for secure data collection","authors":"W. Y. Alghamdi, Hui Wu, Jingjing Fei, S. Kanhere","doi":"10.1109/ISSNIP.2014.6827598","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827598","url":null,"abstract":"WSN (Wireless Sensor Network) has a wide range of applications. As a result, security problems become increasingly important. We investigate the problem of minimising the failure rate of packet delivery in the presence of the modification attacks and the selective forwarding attacks in a static WSN with one base station without using expensive encryption/decryption algorithms. We propose a novel heuristic approach to this problem. Our approach is based on randomised multipath routing. When a sensor node needs to send a packet to the base station, it creates three copies and sends these three copies to the base station via three paths. Among the three paths, two of them are selected at random based on a spanning tree with the base station as the root. The base station accepts a packet only if it receives at least two identical copies. We have simulated our approach. The simulation results show that our approach achieves a very low failure rate of packet delivery in the presence of a relatively high percentage of malicious sensor nodes.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125950740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827636
Ming Shang, Jingqiang Lin, Xiaokun Zhang, Changwei Xu
More and more intelligent functions are proposed, designed and implemented in meters to make the power supply be smart. However, these complex functions also bring risks to the smart meters, and they become susceptible to vulnerabilities and attacks. We present the rat-group attack in this paper, which exploits the vulnerabilities of smart meters in the cyber world, but spreads in the physical world due to the direct economic benefits. To the best of our knowledge, no systematic work has been conducted on this attack. Game theory is then applied to analyze this attack, and two game models are proposed and compared under different assumptions. The analysis results suggest that the power company shall follow an open defense policy: disclosing the defense parameters to all users (i.e., the potential attackers), results in less loss in the attack.
{"title":"A game-theory analysis of the rat-group attack in smart grids","authors":"Ming Shang, Jingqiang Lin, Xiaokun Zhang, Changwei Xu","doi":"10.1109/ISSNIP.2014.6827636","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827636","url":null,"abstract":"More and more intelligent functions are proposed, designed and implemented in meters to make the power supply be smart. However, these complex functions also bring risks to the smart meters, and they become susceptible to vulnerabilities and attacks. We present the rat-group attack in this paper, which exploits the vulnerabilities of smart meters in the cyber world, but spreads in the physical world due to the direct economic benefits. To the best of our knowledge, no systematic work has been conducted on this attack. Game theory is then applied to analyze this attack, and two game models are proposed and compared under different assumptions. The analysis results suggest that the power company shall follow an open defense policy: disclosing the defense parameters to all users (i.e., the potential attackers), results in less loss in the attack.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127639631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827633
W. Ang, Piotr Kropelmcki, Andrew Benson Randies, A. Gu, K. Leong, C. S. Tan
This paper describes the operation principle and design of a CMOS compatible and high temperature capable AIN-based piezoelectric resonant uncooled infrared detector. The A1N piezoelectric resonator is designed to operate at hundreds megahertz frequencies in Lamb wave mode or contour extensional. The design parameters include IDT electrode fingers and A1N piezoelectric film dimension. The performance of different structure designs of the A1N resonator are compared in ANSYS and COMSOL simulation tool.
{"title":"Simulation and design of AIN piezoelectric resonator for infrared sensing application utilizing lamb wave mode","authors":"W. Ang, Piotr Kropelmcki, Andrew Benson Randies, A. Gu, K. Leong, C. S. Tan","doi":"10.1109/ISSNIP.2014.6827633","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827633","url":null,"abstract":"This paper describes the operation principle and design of a CMOS compatible and high temperature capable AIN-based piezoelectric resonant uncooled infrared detector. The A1N piezoelectric resonator is designed to operate at hundreds megahertz frequencies in Lamb wave mode or contour extensional. The design parameters include IDT electrode fingers and A1N piezoelectric film dimension. The performance of different structure designs of the A1N resonator are compared in ANSYS and COMSOL simulation tool.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122641475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827604
Nimsiri Abhayasinghe, I. Murray
Human gait analysis is a major topic in pedestrian navigation and geriatric care. Identifying gait phases is important in using human gait for pedestrian navigation and tracking. Most of existing gait phase identification techniques use multiple sensor modules attached to each section of the lower body. This paper discusses the feasibility of recognizing gait phases using a single inertial measurement unit (IMU) placed in a trouser pocket of the subject. The movement of the thigh is computed by fusing accelerometer and the gyroscopic data gathered from the of the IMU. Experimental results indicated that most of the major gait phases such as Initial Contact, Load Response, Mid Stance, Terminal Stance, Pre-Swing and Swing, can be identified by the movement of one thigh tracked by an IMU. It was also noted that the movement of the offside leg can also be estimated from the fused IMU data. This paper presents a method to recognize all major phases of human stride cycle during walking from movement of one thigh.
{"title":"Human gait phase recognition based on thigh movement computed using IMUs","authors":"Nimsiri Abhayasinghe, I. Murray","doi":"10.1109/ISSNIP.2014.6827604","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827604","url":null,"abstract":"Human gait analysis is a major topic in pedestrian navigation and geriatric care. Identifying gait phases is important in using human gait for pedestrian navigation and tracking. Most of existing gait phase identification techniques use multiple sensor modules attached to each section of the lower body. This paper discusses the feasibility of recognizing gait phases using a single inertial measurement unit (IMU) placed in a trouser pocket of the subject. The movement of the thigh is computed by fusing accelerometer and the gyroscopic data gathered from the of the IMU. Experimental results indicated that most of the major gait phases such as Initial Contact, Load Response, Mid Stance, Terminal Stance, Pre-Swing and Swing, can be identified by the movement of one thigh tracked by an IMU. It was also noted that the movement of the offside leg can also be estimated from the fused IMU data. This paper presents a method to recognize all major phases of human stride cycle during walking from movement of one thigh.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126320951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827620
Songsong Zhang, Tao Wang, Chengkuo Lee, Liang Lou, W. Tsang, D. Kwong
A NEMS piezoresistive pressure sensor with annular grooves on the circular diaphragm is presented here. Silicon Nanowires (SiNWs) are embedded as sensing elements at the edge of the diaphragm. This new diaphragm structure improves the device sensitivity by 2.5 times under a low pressure range of 0~120 mmHg with respect to our previously reported flat diaphragm pressure sensor. With the advantage of superior piezoresistive effect of SiNWs, this sensitivity improvement is even remarkable in contrast to other recently reported piezoresistive pressure sensing devices. Additionally, by leveraging the miniaturized sensing diaphragm (radius of 100 μm), the sensor can be potentially used as implantable device for low pressure sensing applications.
{"title":"Silicon Nanowires embedded pressure sensor with annularly grooved diaphragm for sensitivity improvement","authors":"Songsong Zhang, Tao Wang, Chengkuo Lee, Liang Lou, W. Tsang, D. Kwong","doi":"10.1109/ISSNIP.2014.6827620","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827620","url":null,"abstract":"A NEMS piezoresistive pressure sensor with annular grooves on the circular diaphragm is presented here. Silicon Nanowires (SiNWs) are embedded as sensing elements at the edge of the diaphragm. This new diaphragm structure improves the device sensitivity by 2.5 times under a low pressure range of 0~120 mmHg with respect to our previously reported flat diaphragm pressure sensor. With the advantage of superior piezoresistive effect of SiNWs, this sensitivity improvement is even remarkable in contrast to other recently reported piezoresistive pressure sensing devices. Additionally, by leveraging the miniaturized sensing diaphragm (radius of 100 μm), the sensor can be potentially used as implantable device for low pressure sensing applications.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125307037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827704
R. Mehta, Bharat Menon, D. Srinivasan, S. K. Panda, A. Rathore
The National Electricity Market of Singapore (NEMS) is designed to promote the efficient supply of competitively priced electricity. In Singapore, the Power Demand and Uniform Singapore Energy Price (USEP) vary in half hour periods. This paper presents a Multi-agent System (MAS) to effectively manage the energy sources of a microgrid depending on the power requirement and market price. The MAS is developed in Java Agent Development Environment (JADE) which interfaces with Matlab-Simulink to validate the control and management of microgrid in a simulated environment. The MAS determines the microgrid's mode of operation based on the fluctuations in the market price and power balance between generation and demand. In this paper, three scenarios have been formulated with the help of real-time data from Energy Market Authority (EMA) to demonstrate the actions taken by the proposed MAS.
{"title":"Market based multi-agent control of microgrid","authors":"R. Mehta, Bharat Menon, D. Srinivasan, S. K. Panda, A. Rathore","doi":"10.1109/ISSNIP.2014.6827704","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827704","url":null,"abstract":"The National Electricity Market of Singapore (NEMS) is designed to promote the efficient supply of competitively priced electricity. In Singapore, the Power Demand and Uniform Singapore Energy Price (USEP) vary in half hour periods. This paper presents a Multi-agent System (MAS) to effectively manage the energy sources of a microgrid depending on the power requirement and market price. The MAS is developed in Java Agent Development Environment (JADE) which interfaces with Matlab-Simulink to validate the control and management of microgrid in a simulated environment. The MAS determines the microgrid's mode of operation based on the fluctuations in the market price and power balance between generation and demand. In this paper, three scenarios have been formulated with the help of real-time data from Energy Market Authority (EMA) to demonstrate the actions taken by the proposed MAS.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131702484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827637
Richard Mietz, P. Abraham, K. Römer
The number of sensors pervading our everyday life, e.g., in smartphones, cars, and buildings, is constantly increasing. These sensors, which are typically embedded into resource constrained devices such as sensor nodes or smartphones, allow measuring the state of the entities they observe or are attached to. If this information is accessible via the Internet, they contribute to the Internet of Things (IoT), where real-world objects have virtual representations. The standardization process to have a complete and efficient communication protocol stack for these constrained devices is in full swing. The Constrained Application Protocol (CoAP) on the application layer allows retrieving data from devices (e.g., metadata) and its sensors (e.g., sensor measurements). This information can be used in a variety of new real-time real-world applications. However, sometimes it is sufficient and desirable not to communicate raw sensor readings but abstractions, i.e., high-level states of the observed entities. Furthermore, as resource constrained devices will be accessible by everyone on the Internet, mechanism to reduce energy consumption play a key role. This paper presents a new option for CoAP which contributes to these two requirements as it allows the creation of high-level states from raw sensor readings. We show that the option can reduce the number of messages when observing a sensor resource which can substantially decrease energy consumption and thus increase device lifetime.
{"title":"High-level states with CoAP: Giving meaning to raw sensor values to support IoT applications","authors":"Richard Mietz, P. Abraham, K. Römer","doi":"10.1109/ISSNIP.2014.6827637","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827637","url":null,"abstract":"The number of sensors pervading our everyday life, e.g., in smartphones, cars, and buildings, is constantly increasing. These sensors, which are typically embedded into resource constrained devices such as sensor nodes or smartphones, allow measuring the state of the entities they observe or are attached to. If this information is accessible via the Internet, they contribute to the Internet of Things (IoT), where real-world objects have virtual representations. The standardization process to have a complete and efficient communication protocol stack for these constrained devices is in full swing. The Constrained Application Protocol (CoAP) on the application layer allows retrieving data from devices (e.g., metadata) and its sensors (e.g., sensor measurements). This information can be used in a variety of new real-time real-world applications. However, sometimes it is sufficient and desirable not to communicate raw sensor readings but abstractions, i.e., high-level states of the observed entities. Furthermore, as resource constrained devices will be accessible by everyone on the Internet, mechanism to reduce energy consumption play a key role. This paper presents a new option for CoAP which contributes to these two requirements as it allows the creation of high-level states from raw sensor readings. We show that the option can reduce the number of messages when observing a sensor resource which can substantially decrease energy consumption and thus increase device lifetime.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827686
E. T. Yazdi, A. Willig, K. Pawlikowski
One of the main problems affecting reliable transmission in wireless body sensor networks based on IEEE 802.15.4 is interference caused by sharing the unlicensed 2.4 GHz ISM band with other technologies such as Wifi. One possible approach to deal with this problem is to allow a body sensor network to change its operating frequency and its transmit power in response to changes in the observed interference. In this paper we consider the effect of the variation of transmit power in the presence and absence of frequency adaptation.
{"title":"Coupling power and frequency adaptation for interference mitigation in IEEE 802.15.4-based mobile body sensor networks","authors":"E. T. Yazdi, A. Willig, K. Pawlikowski","doi":"10.1109/ISSNIP.2014.6827686","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827686","url":null,"abstract":"One of the main problems affecting reliable transmission in wireless body sensor networks based on IEEE 802.15.4 is interference caused by sharing the unlicensed 2.4 GHz ISM band with other technologies such as Wifi. One possible approach to deal with this problem is to allow a body sensor network to change its operating frequency and its transmit power in response to changes in the observed interference. In this paper we consider the effect of the variation of transmit power in the presence and absence of frequency adaptation.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132595887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827591
K. Toh
The use of a full multivariate polynomial model for predictor learning was deemed a daunting task due to its explosive number of expansion terms for high dimensional inputs and high order models. This paper investigates into the viability of using full multivariate polynomials for predictor learning. Particularly, we investigate into the frequently encountered under-determined system with an estimation formulation based on a ridge regression beyond the commonly known primal and dual forms. Extensive experiments are performed to observe the predictor learning properties on polynomial models beyond the frequently adopted second order.
{"title":"Pattern classification adopting multivariate polynomials","authors":"K. Toh","doi":"10.1109/ISSNIP.2014.6827591","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827591","url":null,"abstract":"The use of a full multivariate polynomial model for predictor learning was deemed a daunting task due to its explosive number of expansion terms for high dimensional inputs and high order models. This paper investigates into the viability of using full multivariate polynomials for predictor learning. Particularly, we investigate into the frequently encountered under-determined system with an estimation formulation based on a ridge regression beyond the commonly known primal and dual forms. Extensive experiments are performed to observe the predictor learning properties on polynomial models beyond the frequently adopted second order.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132875182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827664
Suraj Vantigodi, Venkatesh Babu Radhakrishnan
Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 3D angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).
动作识别在包括智能家居和个人辅助机器人在内的各种应用中发挥着重要作用。在本文中,我们提出了一种利用动作捕捉动作数据来识别人类动作的算法。动作捕捉数据提供了构成人体骨骼的关节的精确三维位置。为了对动作进行分类,我们在时间上对骨骼关节的运动进行建模。动作序列每一帧中的骨架表示为一个129维向量,其中每个分量是由每个关节在骨架上的固定点构成的一个三维角度。最后,将视频表示为从所有动作序列获得的码本上的直方图。与此同时,骨骼关节的时间方差被用作附加特征。使用元认知径向基函数网络(McRBFN)及其基于投影的学习(PBL)算法对动作进行分类。我们在广泛使用的Berkeley Multimodal Human Action Database (MHAD)上实现了超过97%的识别准确率。
{"title":"Action recognition from motion capture data using Meta-Cognitive RBF Network classifier","authors":"Suraj Vantigodi, Venkatesh Babu Radhakrishnan","doi":"10.1109/ISSNIP.2014.6827664","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827664","url":null,"abstract":"Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 3D angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114221434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}