Pub Date : 2014-04-21DOI: 10.1109/ISSNIP.2014.6827690
K. Subramanian, R. Venkatesh Babu, Savitha Ramasamy
Facial emotions are the most expressive way to display emotions. Many algorithms have been proposed which employ a particular set of people (usually a database) to both train and test their model. This paper focuses on the challenging task of database independent emotion recognition, which is a generalized case of subject-independent emotion recognition. The emotion recognition system employed in this work is a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS). McFIS has two components, a neuro-fuzzy inference system, which is the cognitive component and a self-regulatory learning mechanism, which is the meta-cognitive component. The meta-cognitive component, monitors the knowledge in the neuro-fuzzy inference system and decides on what-to-learn, when-to-learn and how-to-learn the training samples, efficiently. For each sample, the McFIS decides whether to delete the sample without being learnt, use it to add/ prune or update the network parameter or reserve it for future use. This helps the network avoid over-training and as a result improve its generalization performance over untrained databases. In this study, we extract pixel based emotion features from well-known (Japanese Female Facial Expression) JAFFE and (Taiwanese Female Expression Image) TFEID database. Two sets of experiment are conducted. First, we study the individual performance of both databases on McFIS based on 5-fold cross validation study. Next, in order to study the generalization performance, McFIS trained on JAFFE database is tested on TFEID and vice-versa. The performance The performance comparison in both experiments against SVM classifier gives promising results.
{"title":"Database independent human emotion recognition with Meta-Cognitive Neuro-Fuzzy Inference System","authors":"K. Subramanian, R. Venkatesh Babu, Savitha Ramasamy","doi":"10.1109/ISSNIP.2014.6827690","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827690","url":null,"abstract":"Facial emotions are the most expressive way to display emotions. Many algorithms have been proposed which employ a particular set of people (usually a database) to both train and test their model. This paper focuses on the challenging task of database independent emotion recognition, which is a generalized case of subject-independent emotion recognition. The emotion recognition system employed in this work is a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS). McFIS has two components, a neuro-fuzzy inference system, which is the cognitive component and a self-regulatory learning mechanism, which is the meta-cognitive component. The meta-cognitive component, monitors the knowledge in the neuro-fuzzy inference system and decides on what-to-learn, when-to-learn and how-to-learn the training samples, efficiently. For each sample, the McFIS decides whether to delete the sample without being learnt, use it to add/ prune or update the network parameter or reserve it for future use. This helps the network avoid over-training and as a result improve its generalization performance over untrained databases. In this study, we extract pixel based emotion features from well-known (Japanese Female Facial Expression) JAFFE and (Taiwanese Female Expression Image) TFEID database. Two sets of experiment are conducted. First, we study the individual performance of both databases on McFIS based on 5-fold cross validation study. Next, in order to study the generalization performance, McFIS trained on JAFFE database is tested on TFEID and vice-versa. The performance The performance comparison in both experiments against SVM classifier gives promising results.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123134233","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.2014.6827691
V. Ramachandran, Andrea Sanchez Ramirez, B. V. D. Zwaag, N. Meratnia, P. Havinga
In recent years, the use of wireless sensor networks for vibration monitoring is emphasized, because of its capability to continuously monitor at hard-to-reach locations of complex machines. Low power consumption is one of the main requirements for the sensor nodes in continuous and long-term vibration monitoring. However, the power consumption of state-of-the-art wireless sensor nodes is significantly increased by wireless radio in continuously transmitting the raw vibration data to the base station. One of the ways to reduce the power consumption is to reduce the duty-cycle of wireless transmission. Accurately processing the vibration data on the sensor node and transmitting only the critical information, such as natural frequency, defective frequency and amplitude of the vibration, will not only reduce the amount of data transmitted but also the duty cycle of the wireless communication. It eventually leads to reduction of total power consumed by the sensor nodes. In this paper the capability of a sensor node to accurately process the real-time vibration data is analyzed and the corresponding power consumption is measured. In particular, impact-based analysis of real-time vibration data is performed by breaking complex signal-processing tasks into manageable segments on the sensor nodes to minimize algorithmic complexity while still meeting real-time deadlines of the algorithm. As a result, it is found that the accuracy of the on-node signal processing is comparable with conventional off-node monitoring methods, whilst reducing total power consumption.
{"title":"Energy-efficient on-node signal processing for vibration monitoring","authors":"V. Ramachandran, Andrea Sanchez Ramirez, B. V. D. Zwaag, N. Meratnia, P. Havinga","doi":"10.1109/ISSNIP.2014.6827691","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827691","url":null,"abstract":"In recent years, the use of wireless sensor networks for vibration monitoring is emphasized, because of its capability to continuously monitor at hard-to-reach locations of complex machines. Low power consumption is one of the main requirements for the sensor nodes in continuous and long-term vibration monitoring. However, the power consumption of state-of-the-art wireless sensor nodes is significantly increased by wireless radio in continuously transmitting the raw vibration data to the base station. One of the ways to reduce the power consumption is to reduce the duty-cycle of wireless transmission. Accurately processing the vibration data on the sensor node and transmitting only the critical information, such as natural frequency, defective frequency and amplitude of the vibration, will not only reduce the amount of data transmitted but also the duty cycle of the wireless communication. It eventually leads to reduction of total power consumed by the sensor nodes. In this paper the capability of a sensor node to accurately process the real-time vibration data is analyzed and the corresponding power consumption is measured. In particular, impact-based analysis of real-time vibration data is performed by breaking complex signal-processing tasks into manageable segments on the sensor nodes to minimize algorithmic complexity while still meeting real-time deadlines of the algorithm. As a result, it is found that the accuracy of the on-node signal processing is comparable with conventional off-node monitoring methods, whilst reducing total power consumption.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"39 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126602936","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.2014.6827627
S. K. Datta, C. Bonnet, N. Nikaein
This paper presents a novel application that allows mobile clients to interact with M2M devices and endpoints in real time. The application "Connect and Control Things" (CCT) is designed to discover things, receive data from the sensors, control the actuators and generate alarms in real time. The novel capabilities of CCT are: (i) dynamic discovery of device and endpoint, (ii) real time interaction with sensors and actuators associated to M2M devices, (iii) benefit from Sensor Markup Language (SenML) representation, (iv) supporting extension of SenML capabilities for actuators and (v) learning actuators' resources and control them. The architectural design, prototypes implementation, flow of network operations and a real-life test scenario are illustrated. The prototype Android application registers higher CPU usage and power consumption due to intense network operations and parsing sensor metadata repeatedly. We have proposed several optimization techniques to reduce the CPU load, network data usage and overall power consumption. Two use cases of the application have been discussed. Finally the paper summarizes the contributions and concludes with the future research directions.
{"title":"CCT: Connect and Control Things: A novel mobile application to manage M2M devices and endpoints","authors":"S. K. Datta, C. Bonnet, N. Nikaein","doi":"10.1109/ISSNIP.2014.6827627","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827627","url":null,"abstract":"This paper presents a novel application that allows mobile clients to interact with M2M devices and endpoints in real time. The application \"Connect and Control Things\" (CCT) is designed to discover things, receive data from the sensors, control the actuators and generate alarms in real time. The novel capabilities of CCT are: (i) dynamic discovery of device and endpoint, (ii) real time interaction with sensors and actuators associated to M2M devices, (iii) benefit from Sensor Markup Language (SenML) representation, (iv) supporting extension of SenML capabilities for actuators and (v) learning actuators' resources and control them. The architectural design, prototypes implementation, flow of network operations and a real-life test scenario are illustrated. The prototype Android application registers higher CPU usage and power consumption due to intense network operations and parsing sensor metadata repeatedly. We have proposed several optimization techniques to reduce the CPU load, network data usage and overall power consumption. Two use cases of the application have been discussed. Finally the paper summarizes the contributions and concludes with the future research directions.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121193606","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.2014.6827611
S. Xie, K. Low, E. Gunawan
A wireless network control system (WNCS) is a control system whose network is closed over a wireless channel. The control performance can be degraded due to the imperfection of the wireless network. This paper studies the co-design of Media Access Control (MAC) layer parameters and sampling period of a model-based network control system (MB-NCS). In particular, a stability condition of MB-NCS in terms of packet loss, packet delay and sampling period is established. An adaptive tuning algorithm is proposed to find the optimum parameter set, which can guarantee the stability of control system and minimize the energy consumption. The results show that the co-design approach outperforms traditional network control system in terms of energy reduction and is robust against time-varying network traffic.
{"title":"An adaptive tuning algorithm for IEEE 802.15.4-based network control system","authors":"S. Xie, K. Low, E. Gunawan","doi":"10.1109/ISSNIP.2014.6827611","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827611","url":null,"abstract":"A wireless network control system (WNCS) is a control system whose network is closed over a wireless channel. The control performance can be degraded due to the imperfection of the wireless network. This paper studies the co-design of Media Access Control (MAC) layer parameters and sampling period of a model-based network control system (MB-NCS). In particular, a stability condition of MB-NCS in terms of packet loss, packet delay and sampling period is established. An adaptive tuning algorithm is proposed to find the optimum parameter set, which can guarantee the stability of control system and minimize the energy consumption. The results show that the co-design approach outperforms traditional network control system in terms of energy reduction and is robust against time-varying network traffic.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121653351","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.2014.6827616
Z. Ahmed, G. Strouse
For the past century, industrial temperature measurements have relied on resistance measurement of a thin metal wire or filament whose resistance varies with temperature. Though resistance thermometers can routinely measure industrial temperatures with uncertainties of 10 mK, they are sensitive to mechanical shock which causes the sensor resistance to drift over time requiring frequent off-line, expensive, and time consuming calibrations. These fundamental limitations of resistance thermometry have produced considerable interest in developing photonic temperature sensors to leverage advances in frequency metrology and to achieve greater mechanical and environmental stability. We are developing a suite of photonic devices that leverage advances in microwave and C-band light sources to fabricate cost-effective photonic temperature sensors. Our preliminary results indicate that using photonic devices such as the ring resonator we can measure short term temperature fluctuations of 80 μK at room temperature. Photonic sensor technology provides a low cost, lightweight, portable and electromagnetic interference (EMI) resistant solution which can be deployed in a wide variety of settings ranging from controlled laboratory conditions, a noisy factory floor, advanced manufacturing, to the variable environment of a residential setting.
{"title":"Transitioning from resistance devices to photonic devices for temperature measurements","authors":"Z. Ahmed, G. Strouse","doi":"10.1109/ISSNIP.2014.6827616","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827616","url":null,"abstract":"For the past century, industrial temperature measurements have relied on resistance measurement of a thin metal wire or filament whose resistance varies with temperature. Though resistance thermometers can routinely measure industrial temperatures with uncertainties of 10 mK, they are sensitive to mechanical shock which causes the sensor resistance to drift over time requiring frequent off-line, expensive, and time consuming calibrations. These fundamental limitations of resistance thermometry have produced considerable interest in developing photonic temperature sensors to leverage advances in frequency metrology and to achieve greater mechanical and environmental stability. We are developing a suite of photonic devices that leverage advances in microwave and C-band light sources to fabricate cost-effective photonic temperature sensors. Our preliminary results indicate that using photonic devices such as the ring resonator we can measure short term temperature fluctuations of 80 μK at room temperature. Photonic sensor technology provides a low cost, lightweight, portable and electromagnetic interference (EMI) resistant solution which can be deployed in a wide variety of settings ranging from controlled laboratory conditions, a noisy factory floor, advanced manufacturing, to the variable environment of a residential setting.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124978800","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.2014.6827639
A. Narayanan, Lihui Chen, C. K. Chan
Applications that run on mobile operating systems such as Android use in-app advertisement libraries for monetization. Recent research reveals that many ad libraries, including popular ones pose threats to user privacy. Some aggressive ad libraries involve in active privacy leaks with the intention of providing targeted ads. Few intrusive ad libraries are classified as adware by commercial mobile anti-virus apps. Despite such issues, semantic detection of ad libraries from Android apps remains an unsolved problem. To this end, we have proposed and developed the AdDetect framework to perform automatic semantic detection of in-app ad libraries using semantic analysis and machine learning. A module decoupling technique based on hierarchical clustering is used to identify and recover the primary and non-primary modules of apps. Each of these modules is then represented as vectors using semantic features. A SVM classifier trained with these feature vectors is used to detect ad libraries. We have conducted an experimental study on 300 apps spread across 15 categories obtained from the official market to verify the effectiveness of AdDetect. The simulation results are promising. AdDetect achieves 95.34% accurate detection of ad libraries with very less false positives. Further analysis reveals that the proposed detection mechanism is robust against common obfuscation techniques. Detailed analysis on the detection results and semantic characteristics of different families of ad libraries is also presented.
{"title":"AdDetect: Automated detection of Android ad libraries using semantic analysis","authors":"A. Narayanan, Lihui Chen, C. K. Chan","doi":"10.1109/ISSNIP.2014.6827639","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827639","url":null,"abstract":"Applications that run on mobile operating systems such as Android use in-app advertisement libraries for monetization. Recent research reveals that many ad libraries, including popular ones pose threats to user privacy. Some aggressive ad libraries involve in active privacy leaks with the intention of providing targeted ads. Few intrusive ad libraries are classified as adware by commercial mobile anti-virus apps. Despite such issues, semantic detection of ad libraries from Android apps remains an unsolved problem. To this end, we have proposed and developed the AdDetect framework to perform automatic semantic detection of in-app ad libraries using semantic analysis and machine learning. A module decoupling technique based on hierarchical clustering is used to identify and recover the primary and non-primary modules of apps. Each of these modules is then represented as vectors using semantic features. A SVM classifier trained with these feature vectors is used to detect ad libraries. We have conducted an experimental study on 300 apps spread across 15 categories obtained from the official market to verify the effectiveness of AdDetect. The simulation results are promising. AdDetect achieves 95.34% accurate detection of ad libraries with very less false positives. Further analysis reveals that the proposed detection mechanism is robust against common obfuscation techniques. Detailed analysis on the detection results and semantic characteristics of different families of ad libraries is also presented.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825401","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.2014.6827703
Hai-Jun Rong, Rong-Jing Bao, Guangshe Zhao
In this paper, a Model Reference Adaptive Neural Control (MRANC) that uses both off-line and online learning strategies and Single Hidden Layer Feedforward Networks (SLFNs) is proposed for a class of nonlinear systems. In the proposed scheme, one SLFN is used as the identifier to identify the unknown nonlinear system and then the other SLFN is used as the controller to construct the control law based on the information of the identified model. The neural-network parameters of the NNI and NNC are adapted off-line. The off-line trained neural controller ensures the stability and provides the necessary tracking performance. If there is a change in the system dynamics or characteristics, the trained neural identifier and controller are also adapted online for providing the appropriate control input to maintain the system's satisfactory tracking performance. Different from the existing technology where the Back-Propagation (BP) is employed to train the two SLFNs, the identifier is trained using a fast neural algorithm developed recently, namely Extreme Learning Machine (ELM) while the controller is trained using the Dynamic BP method. Simulation results show that the proposed approach has faster learning speed and higher tracking performance than the existing method.
{"title":"Model Reference Adaptive Neural Control for nonlinear systems based on Back-Propagation and Extreme Learning Machine","authors":"Hai-Jun Rong, Rong-Jing Bao, Guangshe Zhao","doi":"10.1109/ISSNIP.2014.6827703","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827703","url":null,"abstract":"In this paper, a Model Reference Adaptive Neural Control (MRANC) that uses both off-line and online learning strategies and Single Hidden Layer Feedforward Networks (SLFNs) is proposed for a class of nonlinear systems. In the proposed scheme, one SLFN is used as the identifier to identify the unknown nonlinear system and then the other SLFN is used as the controller to construct the control law based on the information of the identified model. The neural-network parameters of the NNI and NNC are adapted off-line. The off-line trained neural controller ensures the stability and provides the necessary tracking performance. If there is a change in the system dynamics or characteristics, the trained neural identifier and controller are also adapted online for providing the appropriate control input to maintain the system's satisfactory tracking performance. Different from the existing technology where the Back-Propagation (BP) is employed to train the two SLFNs, the identifier is trained using a fast neural algorithm developed recently, namely Extreme Learning Machine (ELM) while the controller is trained using the Dynamic BP method. Simulation results show that the proposed approach has faster learning speed and higher tracking performance than the existing method.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133882667","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.2014.6827698
T. Takeshita, Takuma Iwasaki, Kota Harisaki, R. Sawada, H. Ando, Y. Arinaga, E. Higurashi
We propose a promising biaxial shearing force measurement device with an integrated micro displacement sensor (chip size of 3 mm by 3 mm and 0.7 mm in thickness) housed in an external trapezoidal metallic frame. The displacement sensor is used to measure the tilt angles of a mirror on the ceiling of the frame caused by the shearing force applied to the upper surface of the frame. A linear signal response to applied biaxial shearing force was obtained. The range and sensitivity of the sensor depend on the material and shape of the frame and thereby allow the sensor great versatility with numerous possible applications.
{"title":"Two axial shearing force measurement device with a built-in integrated micro displacement sensor","authors":"T. Takeshita, Takuma Iwasaki, Kota Harisaki, R. Sawada, H. Ando, Y. Arinaga, E. Higurashi","doi":"10.1109/ISSNIP.2014.6827698","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827698","url":null,"abstract":"We propose a promising biaxial shearing force measurement device with an integrated micro displacement sensor (chip size of 3 mm by 3 mm and 0.7 mm in thickness) housed in an external trapezoidal metallic frame. The displacement sensor is used to measure the tilt angles of a mirror on the ceiling of the frame caused by the shearing force applied to the upper surface of the frame. A linear signal response to applied biaxial shearing force was obtained. The range and sensitivity of the sensor depend on the material and shape of the frame and thereby allow the sensor great versatility with numerous possible applications.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116671727","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.2014.6827668
Ladji Adiaviakoye, P. Plainchault, Marc Bolircene, J. Auberlet
In everyday life, we can see amazing choreographies of movements of crowds of pedestrians. Pedestrians run into and avoid each other but do not seem to consciously cooperate. In this paper, we track a crowd of pedestrians in a large covered and cluttered area to understand their social behavior. Additionally, we try to analyze the characteristics of crowds of pedestrians such as traffic density, velocity, and trajectory. We introduce a stable feature extraction method based on accumulated distribution of successive laser frames. To isolate pedestrians, we propose a non-parametric method exploiting the Parzen windowing technique. We apply the new method of Rao-Blackwellized Monte Carlo data association to track a highly variable number of pedestrians. The algorithm is quantitatively evaluated through a social behavior experiment taking place in the lobby of a school. During this experiment, nearly 300 students are tracked.
{"title":"Tracking of multiple people in crowds using laser range scanners","authors":"Ladji Adiaviakoye, P. Plainchault, Marc Bolircene, J. Auberlet","doi":"10.1109/ISSNIP.2014.6827668","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827668","url":null,"abstract":"In everyday life, we can see amazing choreographies of movements of crowds of pedestrians. Pedestrians run into and avoid each other but do not seem to consciously cooperate. In this paper, we track a crowd of pedestrians in a large covered and cluttered area to understand their social behavior. Additionally, we try to analyze the characteristics of crowds of pedestrians such as traffic density, velocity, and trajectory. We introduce a stable feature extraction method based on accumulated distribution of successive laser frames. To isolate pedestrians, we propose a non-parametric method exploiting the Parzen windowing technique. We apply the new method of Rao-Blackwellized Monte Carlo data association to track a highly variable number of pedestrians. The algorithm is quantitatively evaluated through a social behavior experiment taking place in the lobby of a school. During this experiment, nearly 300 students are tracked.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116951906","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.2014.6827614
D. Reinhardt, Daniel Rodriguez Pons-Sorolla, M. Hollick, S. Kanhere
In typical participatory sensing applications, mobile devices record a variety of sensor readings (e.g., sound samples and accelerometer data), which are tagged with spatiotemporal information and uploaded to an application server. The collection of detailed location data reveal insights about the users' whereabouts and daily routines, therefore seriously compromising their privacy. Users can mutually preserve their privacy by opportunistically exchanging sensor readings during physical meetings, thus breaking the link between the collected data and their permanent identities. The success of this procedure depends on the collaboration of all participating users. Our paper proposes a scheme called TrustMeter to assess the individual user contribution to this privacy protection mechanism. Based on peer-based ratings, our system attributes trust levels to each user allowing to readily identify and quarantine malicious users. We investigate the TrustMeters performance under different attacks by means of extensive simulations, and show that it succeeds in quarantining malicious users in most analyzed scenarios.
{"title":"TrustMeter: A trust assessment scheme for collaborative privacy mechanisms in participatory sensing applications","authors":"D. Reinhardt, Daniel Rodriguez Pons-Sorolla, M. Hollick, S. Kanhere","doi":"10.1109/ISSNIP.2014.6827614","DOIUrl":"https://doi.org/10.1109/ISSNIP.2014.6827614","url":null,"abstract":"In typical participatory sensing applications, mobile devices record a variety of sensor readings (e.g., sound samples and accelerometer data), which are tagged with spatiotemporal information and uploaded to an application server. The collection of detailed location data reveal insights about the users' whereabouts and daily routines, therefore seriously compromising their privacy. Users can mutually preserve their privacy by opportunistically exchanging sensor readings during physical meetings, thus breaking the link between the collected data and their permanent identities. The success of this procedure depends on the collaboration of all participating users. Our paper proposes a scheme called TrustMeter to assess the individual user contribution to this privacy protection mechanism. Based on peer-based ratings, our system attributes trust levels to each user allowing to readily identify and quarantine malicious users. We investigate the TrustMeters performance under different attacks by means of extensive simulations, and show that it succeeds in quarantining malicious users in most analyzed scenarios.","PeriodicalId":269784,"journal":{"name":"2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115248609","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：