Acoustic alarms have been credited with saving thousands of lives from fires, gas leakage and electric leakage each year. By broadcasting sound with different tones, loudness and timbres, acoustic alarms keep people aware of surroundings, inform them of serendipitous events, and notify them critical information. However, maintaining the safety awareness through the acoustic alarm is difficult for people who are deaf or less sensitive to acoustic signals. They are too often among the last to access important information even when they are in dangers, especially when they stay alone. By leveraging the microphone on commodity smartphones, universal sound awareness applications are becoming possible. Deep learning models have large leaps in accuracy and robustness[1].
{"title":"Poster: MobiEar-Building an Environment-independent Acoustic Sensing Platform for the Deaf using Deep Learning","authors":"Sicong Liu, Junzhao Du","doi":"10.1145/2938559.2948831","DOIUrl":"https://doi.org/10.1145/2938559.2948831","url":null,"abstract":"Acoustic alarms have been credited with saving thousands of lives from fires, gas leakage and electric leakage each year. By broadcasting sound with different tones, loudness and timbres, acoustic alarms keep people aware of surroundings, inform them of serendipitous events, and notify them critical information. However, maintaining the safety awareness through the acoustic alarm is difficult for people who are deaf or less sensitive to acoustic signals. They are too often among the last to access important information even when they are in dangers, especially when they stay alone. By leveraging the microphone on commodity smartphones, universal sound awareness applications are becoming possible. Deep learning models have large leaps in accuracy and robustness[1].","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121503720","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}
N. Mirza, Shareen Mahmud, Prosonna Hossain Nabila, Nova Ahmed
Protibaadi, which addresses the issue of women's safety in public places, is a system consisting of a portable device which remotely activates a mobile application. The existing safety apps draw attention and it is risky to bring out cell phones in front of the harasser to seek help. Protibaadi allows the users to carry a hidden device inside a pouch which can either be worn or clipped to the user's bag.
{"title":"Poster: Protibaadi: An Extended Solution to Deal with Sexual Harassment","authors":"N. Mirza, Shareen Mahmud, Prosonna Hossain Nabila, Nova Ahmed","doi":"10.1145/2938559.2948796","DOIUrl":"https://doi.org/10.1145/2938559.2948796","url":null,"abstract":"Protibaadi, which addresses the issue of women's safety in public places, is a system consisting of a portable device which remotely activates a mobile application. The existing safety apps draw attention and it is risky to bring out cell phones in front of the harasser to seek help. Protibaadi allows the users to carry a hidden device inside a pouch which can either be worn or clipped to the user's bag.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125064637","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}
It is essential to select/assign appropriate background mu- sic (BGM) for each scene/cut when we edit a video or a slideshow of photos. However, it is a laborious task. Aim- ing to realise automatic BGM selection/assignment, we pro- pose a method to automatically assign emotion tag to various BGM. To realise this method, we need a model for classify- ing BGM. To build our model, we use a set of movie scene BGMs that a group of 14 users tagged with five (5) differ- ent sentiments: Love, Surprise, Joy, Sadness, and Fear. Af- ter confirming their agreements, we extracted the features of each audio file of our dataset. Using the machine-learning tool WEKA and the random forest algorithm, we built a model. Through a cross validation process, we evaluated our model and obtained an accuracy of 94% in prediction of the emotion in the BGM, demonstrating the effectiveness of the proposed approach.
{"title":"Poster: Sentiment Analysis of BGM Toward Automatic BGM Selection Based on Emotion","authors":"N. A. Konan, H. Suwa, Yutaka Arakawa, K. Yasumoto","doi":"10.1145/2938559.2948770","DOIUrl":"https://doi.org/10.1145/2938559.2948770","url":null,"abstract":"It is essential to select/assign appropriate background mu- sic (BGM) for each scene/cut when we edit a video or a slideshow of photos. However, it is a laborious task. Aim- ing to realise automatic BGM selection/assignment, we pro- pose a method to automatically assign emotion tag to various BGM. To realise this method, we need a model for classify- ing BGM. To build our model, we use a set of movie scene BGMs that a group of 14 users tagged with five (5) differ- ent sentiments: Love, Surprise, Joy, Sadness, and Fear. Af- ter confirming their agreements, we extracted the features of each audio file of our dataset. Using the machine-learning tool WEKA and the random forest algorithm, we built a model. Through a cross validation process, we evaluated our model and obtained an accuracy of 94% in prediction of the emotion in the BGM, demonstrating the effectiveness of the proposed approach.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122188969","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}
1. INSTRUCTION In contrast to existing techniques that offload complex computations to the cloud server which has infinite resources, the proposed technique offloads to the smart phone which has finite resources. Thus, we have to consider that a smartphone can perform the complex computation instead of a smart watch based on the smartphone’s state such as energy consumption, process delay and side-effect of other processes. For this reason, in the proposed technique, both the smart watch and smartphone have a component for offloading decision in contrast with other existing technique [1]. We also propose two algorithms, which are applied to offloading decision component of each devices for accurate decision.
{"title":"Poster: A Novel Computation Offloading Technique for Reducing Energy Consumption of Smart Watch","authors":"Jaejun Ko, Jongwon Lee, Young-June Choi","doi":"10.1145/2938559.2948825","DOIUrl":"https://doi.org/10.1145/2938559.2948825","url":null,"abstract":"1. INSTRUCTION In contrast to existing techniques that offload complex computations to the cloud server which has infinite resources, the proposed technique offloads to the smart phone which has finite resources. Thus, we have to consider that a smartphone can perform the complex computation instead of a smart watch based on the smartphone’s state such as energy consumption, process delay and side-effect of other processes. For this reason, in the proposed technique, both the smart watch and smartphone have a component for offloading decision in contrast with other existing technique [1]. We also propose two algorithms, which are applied to offloading decision component of each devices for accurate decision.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"334 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120892277","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}
Akpa Akpro Elder Hippocrate, Yutaka Arakawa, K. Yasumoto
Statistics from the World Health Organization (WHO) show that overweight and obesity are the fifth leading risk of global death, with at least 2.8 millions adults dying each year [1]. In order to get a healthy weight, the daily food intake must be not only measured but also recorded and analyzed to provide to patients and healthy people suggestions about how to behave during their mealtimes. Recently, various studies and projects related to diet have been released. For example, Klesges et al. developed a computing game that encourages children and young people to enjoy learning good and bad nutrition balance, and explain how to make healthier meal choices [2]. However, few studies have been done on recommending healthy eating patterns based on users behaviors. To the best of our knowledge, there are no system that suggest future foods intake based on one’s previously consumed foods. Our work intends to address this gap, by extending our current food weight measurement system [3].
{"title":"Poster: Calorie-Aware Food Recommendation System","authors":"Akpa Akpro Elder Hippocrate, Yutaka Arakawa, K. Yasumoto","doi":"10.1145/2938559.2948783","DOIUrl":"https://doi.org/10.1145/2938559.2948783","url":null,"abstract":"Statistics from the World Health Organization (WHO) show that overweight and obesity are the fifth leading risk of global death, with at least 2.8 millions adults dying each year [1]. In order to get a healthy weight, the daily food intake must be not only measured but also recorded and analyzed to provide to patients and healthy people suggestions about how to behave during their mealtimes. Recently, various studies and projects related to diet have been released. For example, Klesges et al. developed a computing game that encourages children and young people to enjoy learning good and bad nutrition balance, and explain how to make healthier meal choices [2]. However, few studies have been done on recommending healthy eating patterns based on users behaviors. To the best of our knowledge, there are no system that suggest future foods intake based on one’s previously consumed foods. Our work intends to address this gap, by extending our current food weight measurement system [3].","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131179871","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}
Biyi Fang, N. Lane, Mi Zhang, Aidan Boran, F. Kawsar
The popularity of wearables continues to rise. However, their functions and applications are constrained by the types of sensors that are currently available. Inertial sensors can only track motions of body parts to which they are attached. Microphones and cameras are powerful but also capture privacy sensitive information. Physiological sensors are intrusive since firm skin contact is necessity. Recently, radio-based sensing has drawn significant attention as it provides a contactless and privacy-preserving approach to detect and monitor human activities. In this work, we demonstrate the search for a new sensing modality for the next generation of wearable devices by exploring the feasibility of radio-based human activity sensing and vital sign monitoring in the context of wearable setting. We envision radio-based sensing has the potential to fundamentally transform wearables as we currently know them. First, we have developed HeadScan, a first-of-its-kind wearable for radio-based sensing of a number of human activities that involve head and mouth movements include eating, drinking, coughing, and speaking. Experimental results highlight the enormous potential of our radio-based sensing approach and provide guidance to future explorations. Second, we have developed BodyScan, a wearable system for radio sensing of human whole body movement. Experimental results indicate that BodyScan is capable of capturing whole body activities with a lifetime of 15 hours.
{"title":"Poster: Towards Radio-based Sensing on Wearables","authors":"Biyi Fang, N. Lane, Mi Zhang, Aidan Boran, F. Kawsar","doi":"10.1145/2938559.2948802","DOIUrl":"https://doi.org/10.1145/2938559.2948802","url":null,"abstract":"The popularity of wearables continues to rise. However, their functions and applications are constrained by the types of sensors that are currently available. Inertial sensors can only track motions of body parts to which they are attached. Microphones and cameras are powerful but also capture privacy sensitive information. Physiological sensors are intrusive since firm skin contact is necessity. Recently, radio-based sensing has drawn significant attention as it provides a contactless and privacy-preserving approach to detect and monitor human activities. In this work, we demonstrate the search for a new sensing modality for the next generation of wearable devices by exploring the feasibility of radio-based human activity sensing and vital sign monitoring in the context of wearable setting. We envision radio-based sensing has the potential to fundamentally transform wearables as we currently know them. First, we have developed HeadScan, a first-of-its-kind wearable for radio-based sensing of a number of human activities that involve head and mouth movements include eating, drinking, coughing, and speaking. Experimental results highlight the enormous potential of our radio-based sensing approach and provide guidance to future explorations. Second, we have developed BodyScan, a wearable system for radio sensing of human whole body movement. Experimental results indicate that BodyScan is capable of capturing whole body activities with a lifetime of 15 hours.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134102259","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 this paper we have developed a system to analyse the road characteristics and identifying the chaotic portions of a route with properly identification of bus stoppages and characterizing their spatio-temporal features. Existing systems and algorithms cannot be merely replicated in this context because of the kind of heterogeneity and chaotic situation prevalent in the transport system.
{"title":"Poster: Road Behavior and Stoppage Pattern Analysis from Public Bus Trajectories: A Perspective of Developing Region","authors":"Ratna Mandal, Sujoy Saha, S. Nandi","doi":"10.1145/2938559.2948835","DOIUrl":"https://doi.org/10.1145/2938559.2948835","url":null,"abstract":"In this paper we have developed a system to analyse the road characteristics and identifying the chaotic portions of a route with properly identification of bus stoppages and characterizing their spatio-temporal features. Existing systems and algorithms cannot be merely replicated in this context because of the kind of heterogeneity and chaotic situation prevalent in the transport system.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132927734","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}
Muhammad Faran Majeed, Syed Hassan Ahmed, Siraj Muhammad, M. Dailey
Recently, Named Data Networking (NDN) deployment has been investigated in VANETs (VNDN) [1]. In NDN, content is the first class citizen of the network. However, the pull-based communication model of VNDN proposals introduce suboptimal data forwarding delay, especially, when considering critical data that need to be forwarded promptly. For instance, any router (i.e., vehicle in our case) that receives a data packet first checks its Pending Interest Table (PIT). If there is no PIT entry for that content, the content is considered unsolicited and is dropped. Although this helps avoid unsolicited content and helps prevent networks from being overwhelmed, the behavior of VNDN is more consumer-centric than content-centric.
近年来，命名数据网络(Named Data Networking, NDN)在VANETs (VNDN)[1]中的部署进行了研究。在NDN中，内容是网络的第一等公民。然而，VNDN提案的基于拉的通信模型引入了次优的数据转发延迟，特别是在考虑需要及时转发的关键数据时。例如，接收到数据包的任何路由器(在本例中为车辆)首先检查其未决兴趣表(PIT)。如果该内容没有PIT条目，则认为该内容是未经请求的，并被删除。虽然这有助于避免未经请求的内容，并有助于防止网络不堪重负，但VNDN的行为更以消费者为中心，而不是以内容为中心。
{"title":"Poster: PDF: Push-based Data Forwarding in Vehicular NDN","authors":"Muhammad Faran Majeed, Syed Hassan Ahmed, Siraj Muhammad, M. Dailey","doi":"10.1145/2938559.2948818","DOIUrl":"https://doi.org/10.1145/2938559.2948818","url":null,"abstract":"Recently, Named Data Networking (NDN) deployment has been investigated in VANETs (VNDN) [1]. In NDN, content is the first class citizen of the network. However, the pull-based communication model of VNDN proposals introduce suboptimal data forwarding delay, especially, when considering critical data that need to be forwarded promptly. For instance, any router (i.e., vehicle in our case) that receives a data packet first checks its Pending Interest Table (PIT). If there is no PIT entry for that content, the content is considered unsolicited and is dropped. Although this helps avoid unsolicited content and helps prevent networks from being overwhelmed, the behavior of VNDN is more consumer-centric than content-centric.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115117937","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 times, derailments due to uprooting rails on a railway track has become a banal and noteworthy occurrence in Bangladesh due to different reasons such as political unrest, mass protest, etc. However, the railway tracks in Bangladesh are yet to deploy an automated system that can prevent the losses due to derailments through early detection of missing rails on a railway track. As a remedy to this situation, in this project, we propose to develop a WSN based automated system, which can sense the discontinuity of rail blocks and thus prevent from derailment of trains.
{"title":"Poster: RailCop: Detecting Missing Rail on Railway Using Wireless Sensor Networks","authors":"Tusher Chakraborty, T. Khan, A. Islam","doi":"10.1145/2938559.2948844","DOIUrl":"https://doi.org/10.1145/2938559.2948844","url":null,"abstract":"In recent times, derailments due to uprooting rails on a railway track has become a banal and noteworthy occurrence in Bangladesh due to different reasons such as political unrest, mass protest, etc. However, the railway tracks in Bangladesh are yet to deploy an automated system that can prevent the losses due to derailments through early detection of missing rails on a railway track. As a remedy to this situation, in this project, we propose to develop a WSN based automated system, which can sense the discontinuity of rail blocks and thus prevent from derailment of trains.","PeriodicalId":298684,"journal":{"name":"MobiSys '16 Companion","volume":"398 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133579190","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：