{"title":"High-Accuracy Joint Position Estimation and Posture Detection System for Driving","authors":"Takahiro Yamada, H. Irie, S. Sakai","doi":"10.1145/3004010.3004035","DOIUrl":"https://doi.org/10.1145/3004010.3004035","url":null,"abstract":"In this paper, we present a novel Advanced Driver Assistance System (ADAS) that monitors driving posture. To achieve accuracy and robustness of the system, we propose a high-accuracy method for estimating the joint positions of drivers and an algorithm for detecting abnormal driving posture. The key ideas for improving the accuracy of joint position estimation are that we train a Random Forests classifier with driver image sets that we built and we introduce specific knowledges to recognize the body parts of the driver. To achieve robustness, we invented an abnormal posture detecting algorithm that accumulates information on the most recent postures. We integrated our technologies in an actual vehicle. We evaluated the accuracy and the coverage of the abnormal posture detection of our system by conducting driving tests on a test course. The results show that this system detects four abnormal driving postures, discriminates small changes in posture, and has robustness against vehicle vibrations, environment lighting, and differences in drivers' physiques.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130970772","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}
Keisuke Nakashima, Masahiro Yokoyama, Y. Taniyama, T. Yoshihisa, T. Hara
{"title":"S3 System: A System for Sharing Social Sensor Data and Analytical Programs","authors":"Keisuke Nakashima, Masahiro Yokoyama, Y. Taniyama, T. Yoshihisa, T. Hara","doi":"10.1145/3004010.3004037","DOIUrl":"https://doi.org/10.1145/3004010.3004037","url":null,"abstract":"Recently, various SNSs (social networking services) such as Twitter1, Facebook2, and so on, have gained wide use. These enable access to a wide rage of information related to the real world, through analysis of texts posted on such SNSs. For example, when many people tweet about an earthquake, we can typically infer that an earthquake has occurred in the real world. In this study, we consider the acquisition of such information as social sensor usage, and call the generated data social sensor data. We can exploit social sensor data for many applications, and easily reuse the data by sharing analytical programs to develop new types of social sensors. However, there currently exists no suitable system for sharing them. In this study, we designed and implemented a system to generate and share such social sensor data, called the S3 (S-cube, social sensor sharing) system; then compared the features of the S3 system with those of other data- and analytical program-sharing systems, and assessed the relative effectiveness of the S3 system in sharing social sensor data.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134006307","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}
{"title":"Person Detection Techniques for an IoT Based Emergency Evacuation Assistance System","authors":"Prasad Annadata, Wisam Eltarjaman, R. Thurimella","doi":"10.1145/3004010.3004019","DOIUrl":"https://doi.org/10.1145/3004010.3004019","url":null,"abstract":"Emergency evacuations during disasters minimize loss of lives and injuries. It is not surprising that emergency evacuation preparedness is mandatory for organizations in many jurisdictions. In the case of corporations, this requirement translates to considerable expenses, consisting of construction costs, equipment, recruitment, retention and training. In addition, required regular evacuation drills cause recurring expenses and loss of productivity. Any automation to assist in these drills and in actual evacuations can mean savings of costs, time and lives. Evacuation assistance systems rely on attendance systems that often fall short in accuracy, particularly in environments with lot of \"non-swipers\" (customers, visitors, etc.,). A critical question to answer in the case of an emergency is \"How many people are still in the building?\". This number is calculated by comparing the number of people gathered at assembly point to the last known number of people inside the building. An IoT based system can enhance the answer to that question by providing the number of people in the building, provide their last known locations in an automated fashion and even automate the reconciliation process. Our proposed system detects the people in the building automatically using multiple channels such as WiFi and motion detection. Such a system needs the ability to link specific identifiers to persons reliably. In this paper we present our statistics and heuristics based solutions for linking detected identifiers as belonging to an actual persons in a privacy preserving manner using IoT technologies.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114573019","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}
Kazuya Sato, Takashi Kamimoto, Ryoki Shinohara, H. Shigeno
{"title":"Cache Management with Extended Interest for Information-centric Networking","authors":"Kazuya Sato, Takashi Kamimoto, Ryoki Shinohara, H. Shigeno","doi":"10.1145/3004010.3004038","DOIUrl":"https://doi.org/10.1145/3004010.3004038","url":null,"abstract":"In Information-centric Networking (ICN), users can obtain contents from caches in ICN routers. However, how to use caches efficiently is one of challenges. One existing scheme to obtain caches uses a caching algorithm reducing cache overlaps among routers, and users can obtain caches by referring to records that routers have about caches. However, this scheme has two problems. First, routers which forward Interests towards a cache are limited. Second, this scheme depends on information from an ISP on forwarding Interests. In this paper, we propose Cache-aware routing scheme Referring Distance for contents managed by extended Interest for ICN (CaRD), which enables all routers to obtain the closest content without information from an ISP. In CaRD, routers record hop counts to a server and a cache as passing information of contents. Routers compare these hop counts, and then send request packets towards the closest contents. Moreover, caches move by request packets, so a hop count to a cache of record needs updating. For that, CaRD extends request packets. We add two new fields to request packets and change their operation. To confirm effectiveness of CaRD, we implement CaRD on a simulator, ndnSIM, and evaluate cache hit ratio, traffic and download time.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126476523","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}
Shinnosuke Nirasawa, Masaki Hara, A. Nakao, M. Oguchi, Shu Yamamoto, Saneyasu Yamaguchi
{"title":"Network Application Performance Improvement with Deeply Programmable Switch","authors":"Shinnosuke Nirasawa, Masaki Hara, A. Nakao, M. Oguchi, Shu Yamamoto, Saneyasu Yamaguchi","doi":"10.1145/3004010.3004030","DOIUrl":"https://doi.org/10.1145/3004010.3004030","url":null,"abstract":"Large scale applications in data centers are composed of computers connected with a network. Traditional network switches cannot be flexibly controlled. Then, application developer cannot optimize network elements' behavior for improving application performance. On the other hand, Deeply Programmable Network (DPN) switches can completely analyze packet payloads and be profoundly programmed. In this paper, we focus on processing a part of application functions in network elements for improving application performance based on Deep Packet Inspection (DPI), i.e. analyzing packet payload, using DPN switches. We assume some applications as targets and implement some of functions of applications in network switches. We then present the comparison of performances with and without out method, and show that our method can significantly increase application performance.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127192071","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}