This paper studies the joint assignment of time slots and frequency channels in tree-based wireless sensor networks for data collection applications. Our proposed approach is based on dynamic programming and is resilient to link errors. Extensive simulations are conducted and the results show the superior performance of our approach over peer methods. In addition, our evaluation reveals the impacts of implementation-specific factors, such as link reliability, deployment area, and transmission power, making our results valuable for real-world deployments.
{"title":"Optimal Time and Channel Assignment for Data Collection in Wireless Sensor Networks","authors":"Yanhong Yang, Huan Yang, Liang Cheng, Xiaotong Zhang","doi":"10.1109/MASS.2015.90","DOIUrl":"https://doi.org/10.1109/MASS.2015.90","url":null,"abstract":"This paper studies the joint assignment of time slots and frequency channels in tree-based wireless sensor networks for data collection applications. Our proposed approach is based on dynamic programming and is resilient to link errors. Extensive simulations are conducted and the results show the superior performance of our approach over peer methods. In addition, our evaluation reveals the impacts of implementation-specific factors, such as link reliability, deployment area, and transmission power, making our results valuable for real-world deployments.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127138570","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}
Jiaqing Luo, Shijie Zhou, Hongrong Cheng, Yongjian Liao, Kai Bu
Recently, there has been growing interest in indoor localization, because numerous applications depend on the rapid and accurate position estimation of tagged objects. While RFID-based indoor localization is attractive, the need for a large-scale and high-density deployment of readers and reference tags is costly. Being the range-free localization, our schemes depend solely on mobile readers without reference tags or other devices, and it avoids the need of distance estimation according to RSSI or phase difference. We propose two novel algorithms, continuous scanning and category-based scheduling, for locating single and multiple tagged objects, respectively. Our primary experimental results show that the system can achieve high time efficiency and localization accuracy.
{"title":"A Range-Free Localization of Passive RFID Tags Using Mobile Readers","authors":"Jiaqing Luo, Shijie Zhou, Hongrong Cheng, Yongjian Liao, Kai Bu","doi":"10.1109/MASS.2015.34","DOIUrl":"https://doi.org/10.1109/MASS.2015.34","url":null,"abstract":"Recently, there has been growing interest in indoor localization, because numerous applications depend on the rapid and accurate position estimation of tagged objects. While RFID-based indoor localization is attractive, the need for a large-scale and high-density deployment of readers and reference tags is costly. Being the range-free localization, our schemes depend solely on mobile readers without reference tags or other devices, and it avoids the need of distance estimation according to RSSI or phase difference. We propose two novel algorithms, continuous scanning and category-based scheduling, for locating single and multiple tagged objects, respectively. Our primary experimental results show that the system can achieve high time efficiency and localization accuracy.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128570741","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}
S. Rafiqi, C. Wangwiwattana, E. Fernandez, S. Nair, Eric C. Larson
Cognitive load refers to the amount of informationa person can process or hold in working memory. Historically, the psychology community has estimated this quantity objectively by monitoring the involuntary dilations and constrictions of the pupil using medical grade equipment known as pupillometers. At the same time, researchers in the HCI and Ubi Comp communities have hypothesized how cognitive load sensing might be integrated into context aware computing systems, but limitations of sensing cognitive load ubiquitously and reliably prevent the mass integration of such a technology. Our system, Pupil Ware-M, seeks to begin bridging this sensing gap. We build upon a recent platform, Pupil Ware, which measures a user's sub-millimeter pupil dilation from an unmodified camera. We update the Pupil Ware sensing system with a calibration protocol that brings pupillary responses of a diverse range of people and lighting conditions onto a single 0.0-1.0 scale called Cog Point. Furthermore, we update and optimize the algorithms employed to run in real time from a smartphone. We validate the calibration process using eight users in a controlled experiment where cognitive load is simple to determine from its situational context. Discussion of future work and remaining challenges is then described.
{"title":"Work-in-Progress, PupilWare-M: Cognitive Load Estimation Using Unmodified Smartphone Cameras","authors":"S. Rafiqi, C. Wangwiwattana, E. Fernandez, S. Nair, Eric C. Larson","doi":"10.1109/MASS.2015.31","DOIUrl":"https://doi.org/10.1109/MASS.2015.31","url":null,"abstract":"Cognitive load refers to the amount of informationa person can process or hold in working memory. Historically, the psychology community has estimated this quantity objectively by monitoring the involuntary dilations and constrictions of the pupil using medical grade equipment known as pupillometers. At the same time, researchers in the HCI and Ubi Comp communities have hypothesized how cognitive load sensing might be integrated into context aware computing systems, but limitations of sensing cognitive load ubiquitously and reliably prevent the mass integration of such a technology. Our system, Pupil Ware-M, seeks to begin bridging this sensing gap. We build upon a recent platform, Pupil Ware, which measures a user's sub-millimeter pupil dilation from an unmodified camera. We update the Pupil Ware sensing system with a calibration protocol that brings pupillary responses of a diverse range of people and lighting conditions onto a single 0.0-1.0 scale called Cog Point. Furthermore, we update and optimize the algorithms employed to run in real time from a smartphone. We validate the calibration process using eight users in a controlled experiment where cognitive load is simple to determine from its situational context. Discussion of future work and remaining challenges is then described.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122817141","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}
Modeling large-scale fading effects in Vehicle-to-Vehicle communications (V2V) in the 5.9GHz Dedicated Short Range Communication band has received broad coverage in the literature over the last 15 years. The majority of V2V channel measurement campaigns have focused on describing the expected path loss of the V2V channel through empirical models. The path loss is a channel metric which describes how fast the received signal strength decays with distance. It is well known that the path loss exponent and reference path loss (y-intercept) varies for different environments, but it is not well understood how the channel changes in a given environment relative to lane separation or vehicle orientation. This paper presents an improved path loss model for line-of-sight (LOS) V2V communications at distances less than 100m. The path loss model removes the Gaussian random variable component, typically used to model shadowing in classic power law path loss model, and instead makes the y-intercept and path loss exponent Gaussian random variables. Derived from extensive empirical measurement campaigns in which vehicle orientation, approach direction, and lane separation are considered, the new channel model is compared to experimental data in which the vehicles move at different speeds. The improved path loss model performs a better fit to experimental data than existing path loss models, including two-ray ground reflection, dual-slope piecewise linear, and classic power law.
{"title":"Improved 5.9GHz V2V Short Range Path Loss Model","authors":"Billy Kihei, J. Copeland, Yusun Chang","doi":"10.1109/MASS.2015.84","DOIUrl":"https://doi.org/10.1109/MASS.2015.84","url":null,"abstract":"Modeling large-scale fading effects in Vehicle-to-Vehicle communications (V2V) in the 5.9GHz Dedicated Short Range Communication band has received broad coverage in the literature over the last 15 years. The majority of V2V channel measurement campaigns have focused on describing the expected path loss of the V2V channel through empirical models. The path loss is a channel metric which describes how fast the received signal strength decays with distance. It is well known that the path loss exponent and reference path loss (y-intercept) varies for different environments, but it is not well understood how the channel changes in a given environment relative to lane separation or vehicle orientation. This paper presents an improved path loss model for line-of-sight (LOS) V2V communications at distances less than 100m. The path loss model removes the Gaussian random variable component, typically used to model shadowing in classic power law path loss model, and instead makes the y-intercept and path loss exponent Gaussian random variables. Derived from extensive empirical measurement campaigns in which vehicle orientation, approach direction, and lane separation are considered, the new channel model is compared to experimental data in which the vehicles move at different speeds. The improved path loss model performs a better fit to experimental data than existing path loss models, including two-ray ground reflection, dual-slope piecewise linear, and classic power law.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121646735","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}
With the rapid increasing of smart mobile devices and the advances of sensing technologies, mobile crowd sensing (MCS) becomes a new popular sensing paradigm, which enables a variety of large-scale sensing applications. One of the key challenges of large-scale mobile crowd sensing systems is how to effectively select appropriate participants from a huge user pool to perform various sensing tasks while satisfying certain constraints. This becomes more complex when the sensing tasks are dynamic (coming in real time) and heterogeneous (having different temporal and spacial requirements). In this paper, we consider such a dynamic participant recruitment problem with heterogeneous sensing tasks which aims to minimize the sensing cost while maintaining certain level of probabilistic coverage. Both offline and online algorithms are proposed to solve the challenging problem. Extensive simulations over a real-life mobile dataset confirm the efficiency of the proposed algorithms.
{"title":"Dynamic Participant Recruitment of Mobile Crowd Sensing for Heterogeneous Sensing Tasks","authors":"Hanshang Li, Ting Li, Yu Wang","doi":"10.1109/MASS.2015.46","DOIUrl":"https://doi.org/10.1109/MASS.2015.46","url":null,"abstract":"With the rapid increasing of smart mobile devices and the advances of sensing technologies, mobile crowd sensing (MCS) becomes a new popular sensing paradigm, which enables a variety of large-scale sensing applications. One of the key challenges of large-scale mobile crowd sensing systems is how to effectively select appropriate participants from a huge user pool to perform various sensing tasks while satisfying certain constraints. This becomes more complex when the sensing tasks are dynamic (coming in real time) and heterogeneous (having different temporal and spacial requirements). In this paper, we consider such a dynamic participant recruitment problem with heterogeneous sensing tasks which aims to minimize the sensing cost while maintaining certain level of probabilistic coverage. Both offline and online algorithms are proposed to solve the challenging problem. Extensive simulations over a real-life mobile dataset confirm the efficiency of the proposed algorithms.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122559516","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}
Rasool Tavakoli, Majid Nabi, T. Basten, K. Goossens
Cross-technology interference on the license-free ISM bands has a major negative effect on the performance of Wireless Sensor Networks (WSNs). Channel hopping has been adopted in the Time-Slotted Channel Hopping (TSCH) mode of IEEE 802.15.4e to eliminate blocking of wireless links caused by external interference on some frequency channels. This paper proposes an Enhanced version of the TSCH protocol (ETSCH) which restricts the used channels for hopping to the channels that are measured to be of good quality. The quality of channels is extracted using a new Non-Intrusive Channel-quality Estimation (NICE) technique by performing energy detections in selected idle periods every timeslot. NICE enables ETSCH to follow dynamic interference well, while it does not reduce throughput of the network. It also does not change the protocol, and does not require non-standard hardware. ETSCH uses a small Enhanced Beacon hopping Sequence List (EBSL) to broadcast periodic Enhanced Beacons (EB) in the network to synchronize nodes at the start of timeslots. Experimental results show that ETSCH improves reliability of network communication, compared to basic TSCH and a more advanced mechanism ATSCH. It provides higher packet reception ratios and reduces the maximum length of burst packet losses.
{"title":"Enhanced Time-Slotted Channel Hopping in WSNs Using Non-intrusive Channel-Quality Estimation","authors":"Rasool Tavakoli, Majid Nabi, T. Basten, K. Goossens","doi":"10.1109/MASS.2015.48","DOIUrl":"https://doi.org/10.1109/MASS.2015.48","url":null,"abstract":"Cross-technology interference on the license-free ISM bands has a major negative effect on the performance of Wireless Sensor Networks (WSNs). Channel hopping has been adopted in the Time-Slotted Channel Hopping (TSCH) mode of IEEE 802.15.4e to eliminate blocking of wireless links caused by external interference on some frequency channels. This paper proposes an Enhanced version of the TSCH protocol (ETSCH) which restricts the used channels for hopping to the channels that are measured to be of good quality. The quality of channels is extracted using a new Non-Intrusive Channel-quality Estimation (NICE) technique by performing energy detections in selected idle periods every timeslot. NICE enables ETSCH to follow dynamic interference well, while it does not reduce throughput of the network. It also does not change the protocol, and does not require non-standard hardware. ETSCH uses a small Enhanced Beacon hopping Sequence List (EBSL) to broadcast periodic Enhanced Beacons (EB) in the network to synchronize nodes at the start of timeslots. Experimental results show that ETSCH improves reliability of network communication, compared to basic TSCH and a more advanced mechanism ATSCH. It provides higher packet reception ratios and reduces the maximum length of burst packet losses.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123506551","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}
In the latest version of content-centric networking (CCN 1.0), a number of interests are issued when a large content is retrieved, and this could be a serious problem due to routers' heavy workload. In order to solve this problem, this paper proposes a novel strategy of "grouping" multiple interests with the common information and "packing" them to a special interest called the list interest. Our list interest is designed to cooperate with the manifest of CCN 1.0. This paper demonstrates that by using the common information in the list interest, the router can search its FIB/PIT/CS for the list interest-based request with dramatically smaller complexity than the case of the standard interest-based request. Furthermore, we also give a novel TCP-like congestion control method for list interests.
{"title":"List Interest: Packing Interests for Reduction of Router Workload in CCN 1.0","authors":"Jun Kurihara, K. Yokota, Kazuaki Ueda, A. Tagami","doi":"10.1109/MASS.2015.20","DOIUrl":"https://doi.org/10.1109/MASS.2015.20","url":null,"abstract":"In the latest version of content-centric networking (CCN 1.0), a number of interests are issued when a large content is retrieved, and this could be a serious problem due to routers' heavy workload. In order to solve this problem, this paper proposes a novel strategy of \"grouping\" multiple interests with the common information and \"packing\" them to a special interest called the list interest. Our list interest is designed to cooperate with the manifest of CCN 1.0. This paper demonstrates that by using the common information in the list interest, the router can search its FIB/PIT/CS for the list interest-based request with dramatically smaller complexity than the case of the standard interest-based request. Furthermore, we also give a novel TCP-like congestion control method for list interests.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512924","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}
Simulation is the most widely used tool for evaluating network protocols in multihop wireless networks, yet this has so far been limited due to a lack of models for creating a wide range of scenarios of mobile nodes moving about. For example, for evaluating multihop routing protocols, the frequently used Random Waypoint model can only effectively be used in scenarios with relatively high node density, as sparser configurations (e.g., The same nodes in a larger area) result in frequently or always partitioned networks, with no possible multihop path between many different pairs of nodes. In this extended abstract, we summarize the design and evaluation of the Random Controlled Sparse (RCS) mobility model, a new dynamic mobility model that can be controlled for a wide range of scenarios with varying levels of node sparsity or density while avoiding network partitions. Our goal is to be able to create mobile scenarios that expose previously unexplored areas of wireless protocol performance, particularly for multihop routing protocols. We evaluate the performance of the model in generating scenarios and demonstrate the sometimes surprising performance results that different degrees of node density have on example multihop wireless routing protocols.
{"title":"Protocol Evaluation in Multihop Wireless Networks with Controllable Node Sparsity or Density (Extended Abstract)","authors":"K. Amiri, David B. Johnson","doi":"10.1109/MASS.2015.85","DOIUrl":"https://doi.org/10.1109/MASS.2015.85","url":null,"abstract":"Simulation is the most widely used tool for evaluating network protocols in multihop wireless networks, yet this has so far been limited due to a lack of models for creating a wide range of scenarios of mobile nodes moving about. For example, for evaluating multihop routing protocols, the frequently used Random Waypoint model can only effectively be used in scenarios with relatively high node density, as sparser configurations (e.g., The same nodes in a larger area) result in frequently or always partitioned networks, with no possible multihop path between many different pairs of nodes. In this extended abstract, we summarize the design and evaluation of the Random Controlled Sparse (RCS) mobility model, a new dynamic mobility model that can be controlled for a wide range of scenarios with varying levels of node sparsity or density while avoiding network partitions. Our goal is to be able to create mobile scenarios that expose previously unexplored areas of wireless protocol performance, particularly for multihop routing protocols. We evaluate the performance of the model in generating scenarios and demonstrate the sometimes surprising performance results that different degrees of node density have on example multihop wireless routing protocols.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124505268","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}
Mobile crowd sourcing (MCS) has grown to be a powerful computation paradigm to harness human power to solve real-world problems. Many commercial MCS platforms have arisen, enabling various novel applications. As crowd workers can be unreliable, a critical issue of these platforms is quality control. Many task assignment approaches have been proposed to increase the quality of crowd sourced tasks by matching workers and tasks in a bipartite graph. However, they fail to apply to MCS platforms where tasks are bound with locations. This paper considers the quality-aware online task assignment problem with location-based tasks. The goal is to optimize tasks' overall quality by assigning appropriate sets of tasks to workers in an online manner. To solve this problem, we propose a probabilistic quality measurement model and a hitchhiking model to characterize workers' behavior. Then we design a polynomial-time online assignment algorithm and prove that the proposed algorithm approximates the offline optimal solution with a competitive ratio of 10/7. Through extensive simulations, we demonstrate the efficiency and effectiveness of our solution.
{"title":"Quality-Aware Online Task Assignment in Mobile Crowdsourcing","authors":"Xin Miao, Kebin Liu, Lei Chen, Yunhao Liu","doi":"10.1145/3397180","DOIUrl":"https://doi.org/10.1145/3397180","url":null,"abstract":"Mobile crowd sourcing (MCS) has grown to be a powerful computation paradigm to harness human power to solve real-world problems. Many commercial MCS platforms have arisen, enabling various novel applications. As crowd workers can be unreliable, a critical issue of these platforms is quality control. Many task assignment approaches have been proposed to increase the quality of crowd sourced tasks by matching workers and tasks in a bipartite graph. However, they fail to apply to MCS platforms where tasks are bound with locations. This paper considers the quality-aware online task assignment problem with location-based tasks. The goal is to optimize tasks' overall quality by assigning appropriate sets of tasks to workers in an online manner. To solve this problem, we propose a probabilistic quality measurement model and a hitchhiking model to characterize workers' behavior. Then we design a polynomial-time online assignment algorithm and prove that the proposed algorithm approximates the offline optimal solution with a competitive ratio of 10/7. Through extensive simulations, we demonstrate the efficiency and effectiveness of our solution.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129783817","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}
In recent years, enabling computer systems to recognize facial expressions and infer emotions from them in real time has become very important since such information can be used in emerging applications such as video games, educational software, computer-based tutoring for special need children for better human computer interactions. However, real time emotion recognition using video streams face challenges due to the varying illuminations. In this paper, we present a real time emotion recognition scheme using dense optical flow based approach and SVM classifier. Via extensive analysis using newly collected datasets of 370 videos, we demonstrate that our approach demonstrates high accuracy in recognizing 4 basic emotions: happy, angry, surprise and sad.
{"title":"Dense Optical Flow Based Emotion Recognition Classifier","authors":"Anthony Lowhur, M. Chuah","doi":"10.1109/MASS.2015.28","DOIUrl":"https://doi.org/10.1109/MASS.2015.28","url":null,"abstract":"In recent years, enabling computer systems to recognize facial expressions and infer emotions from them in real time has become very important since such information can be used in emerging applications such as video games, educational software, computer-based tutoring for special need children for better human computer interactions. However, real time emotion recognition using video streams face challenges due to the varying illuminations. In this paper, we present a real time emotion recognition scheme using dense optical flow based approach and SVM classifier. Via extensive analysis using newly collected datasets of 370 videos, we demonstrate that our approach demonstrates high accuracy in recognizing 4 basic emotions: happy, angry, surprise and sad.","PeriodicalId":436496,"journal":{"name":"2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123843146","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：