PhD forum '14最新文献

{"title":"Extended abstract: efficient image processing for continuous mobile vision","authors":"R. Likamwa","doi":"10.1145/2611166.2611171","DOIUrl":"https://doi.org/10.1145/2611166.2611171","url":null,"abstract":"Vision algorithms have enabled our camera-equipped devices to perform powerful tasks, including barcode scanning, object detection, text recognition, and face identification. Unfortunately, current systems require significant energy to capture, process, and analyze an image through the image sensor (imager), image signal processor (ISP), and application processor, limiting the longevity of such applications to short-term, on-demand use. We propose the investigation of an image processing paradigm that uses vision task information to optimize the energy cost of the image capture pipeline.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123460550","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":"Energy-awareness in large-scale internet of things networks","authors":"Vilen Looga","doi":"10.1145/2611166.2611169","DOIUrl":"https://doi.org/10.1145/2611166.2611169","url":null,"abstract":"The goal of my thesis is to research ways to improve energy efficiency in IoT networks, which contain various devices including sensor nodes and smartphones. In my research, I will use a bottom-up approach by starting with modeling of traffic impact on energy consumption in single wireless nodes to large-scale IoT networks. The result of my work will be energy and interference models for WSNs and energy management middleware for IoT networks. As of now, I have published work in traffic scheduling and currently working on a large-scale 802.15.4/CoAP network emulation experiment and interference modeling.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130772216","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":"Smartphone application delay optimizations","authors":"David T. Nguyen","doi":"10.1145/2611166.2611168","DOIUrl":"https://doi.org/10.1145/2611166.2611168","url":null,"abstract":"Despite the rapid hardware upgrades, current smartphones suffer various unpredictable delays during operation, e.g., when launching an app, leading to poor user experience. In this work, we investigate the behavior of reads and writes in smartphones. We conduct the first large-scale measurement study on the I/O delay of Android using the data collected from our Android app running on 1009 devices within 130 days. Among other factors, we observe that reads experience up to 626% slowdown when blocked by concurrent writes for certain workloads. We use this obtained knowledge to design a pilot solution called SmartIO that reduces application delays by prioritizing reads over writes. SmartIO is implemented on the Android platform and evaluated extensively on several groups of popular applications. The results show that our system reduces launch delays by up to 37.8%, and run-time delays by up to 29.6%.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442497","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":"Towards efficient data collection in WSNs","authors":"Imane Horiya Brahmi","doi":"10.1145/2611166.2611172","DOIUrl":"https://doi.org/10.1145/2611166.2611172","url":null,"abstract":"Wireless Sensor Networks (WSNs) are nowadays used in many diverse applications such as road traffic monitoring, emergency medical care, battlefield surveillance and agriculture etc. In such applications, it is fundamental to gather the data accumulated by each sensor and forward it to the sink for processing. Transmitting this data from the sensor field to the sink is reliant on efficient data collection mechanisms. Various collection processes address the following fundamental questions: how fast can we transmit the data carrying emergency events? What data actually needs to be transmitted? How do we ensure the accuracy of the transmitted data? In my PhD, I investigate these questions by exploring and evaluating different techniques for efficient data collection in terms of time delay, energy consumption, and accuracy of the reported data. This paper presents an overview of our proposed solutions to reduce emergency messages transmission delay in WSNs based Road Traffic Monitoring, as well as our current and future works.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134460584","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":"Agentless cloud-wide monitoring of virtual disk state","authors":"Wolfgang Richter","doi":"10.1145/2611166.2611174","DOIUrl":"https://doi.org/10.1145/2611166.2611174","url":null,"abstract":"Abstract : This dissertation proposes a fundamentally different way of monitoring persistent storage. It introduces a monitoring platform based on the modern reality of software defined storage which enables the decoupling of policy from mechanism. The proposed platform is both agentlessmeaning it operates external to and independent of the entities it monitorsand scalablemeaning it is designed to address many systems at once with a mixture of operating systems and applications. Concretely, this dissertation focuses on virtualized clouds, but the proposed monitoring platform generalizes to any form of persistent storage. The core mechanism this dissertation introduces is called Distributed Streaming Virtual Machine Introspection (DS-VMI), and it leverages two properties of modern clouds: virtualized servers managed by hypervisors enabling efficient introspection, and file-level duplication of data within cloud instances. We explore a new class of agentless monitoring applications via three interfaces with two different consistency models: cloud-inotify (strong consistency), /cloud (eventual consistency), and /cloud-history (strong consistency). cloud inotify is a publish-subscribe interface to cloud-wide file-level updates and it supports event-based monitoring applications. /cloud is designed to support batch-based and legacy monitoring applications by providing a file system interface to cloud-wide file-level state. /cloud-history is designed to support efficient search and management of historic virtual disk state. It leverages new fast-to-access archival storage systems, and achieves tractable indexing of file-level history via whole-file deduplication using a novel application of an incremental hashing construction.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121516287","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":"Coexistence of LTE and WiFi heterogeneous networks via inter network coordination","authors":"S. Sagari","doi":"10.1145/2611166.2611167","DOIUrl":"https://doi.org/10.1145/2611166.2611167","url":null,"abstract":"Fast increases in mobile data demand and inherently limited RF spectrum motivate the use of dynamic spectrum sharing between different radio technologies such as WiFi and LTE, most notably in small cell (HetNet) scenarios. In our project, we propose an inter-network coordination architecture which facilitates dynamic spectrum management in the HetNets for interference mitigation and efficient spectrum utilization. We aim to model interference between LTE and WiFi networks through experimental evaluation using the ORBIT testbed and the USRP/GNU radio platform. We further propose to study the performance of cooperative algorithms between LTE and WiFi network involving logically centralized system level optimization for maximizing throughput subject to certain constraints.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126489225","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":"The internet of tags: energy-harvesting adaptive algorithms","authors":"R. Margolies","doi":"10.1145/2611166.2611170","DOIUrl":"https://doi.org/10.1145/2611166.2611170","url":null,"abstract":"In this thesis, we will focus on the design and performance evaluation of networking algorithms for energy-harvesting tags. We will build upon our recent work on developing Energy-Harvesting Active Networked Tags (EnHANTS) [3– 5]. In this capacity, we have taken a bottom-up approach and integrated ultra-low power Ultra-Wideband ImpulseRadio (UWB-IR) transceivers with energy harvesting circuitry. In this thesis, we will take a top-down approach and develop energy harvesting adaptive algorithms to support the Internet of Tags (IoTags). We believe that IoTags will be a key component of the Internet of Things (IoT). In the near future, objects equipped with heterogeneous devices such as sensors, actuators, and tags, will be able to interact with each other and cooperate to achieve common goals. The IoT has been gaining increased attention from academia and industry [1], with applications in healthcare, smart buildings, assisted living, manufacturing, supply chain management, and intelligent transportation. Small, flexible, and energetically self-reliant, IoTags will be attached to objects that are traditionally not networked, such as books, furniture, walls, doors, toys, produce, and clothing. In their capacity as active tags, IoTags will provide infrastructure for novel tracking applications. We have already taken steps toward developing IoTags in our ongoing EnHANTs project. Our goal is to build upon our ongoing research to design and evaluate energyharvesting adaptive algorithms to enable IoTag networks.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130884130","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":"Improving trust in personal sensing","authors":"Aarathi Prasad","doi":"10.1145/2611166.2611173","DOIUrl":"https://doi.org/10.1145/2611166.2611173","url":null,"abstract":"Personal sensing technologies allow subjects to collect and share their personal data with recipients to obtain some benefits. For example, mobile health and wellness (mHealth) devices and applications allow subjects to monitor their own health and lifestyle and share the health and wellness data with their family, friends and peers for emotional support, clinical providers for diagnosis and health coaches for medical advice. Subjects may earn monetary benefits by sharing data with insurance companies, or contribute to the greater good by sharing with researchers. In such scenarios, recipients might be concerned about the accuracy of the data collected, affecting their trust in the data. Malicious subjects and devices can provide fake data. Malfunctioning devices can produce inaccurate data. Careless subjects or delegates (in mHealth scenarios, delegates could be health workers and caretakers who might use devices to collect subject’s data for the recipient) might apply sensors incorrectly and collect inaccurate data. Data could also be collected from wrong subjects or devices deliberately or accidentally. Hence, recipients will need assurances about accuracy of the data and trustworthy behavior of the subjects and delegates who collected the data and the devices that were used in data collection. Recipients might also need metadata to better interpret the meaning of the data. On the other hand, subjects might be concerned about how recipients might use the shared data, affecting their trust in recipients. Subjects might be unsure of what data to share to receive benefits and share more than necessary (and disclose sensitive data unintentionally to unintended recipients). Subjects might be concerned about how their data might be used by the recipients and share less than necessary and not receive benefits from the recipients. Hence, subjects will need assurance about the disclosure of their information, and will want to be aware of how recipients will use their data and what benefits subjects will receive for sharing data with the recipients. The goal of this work is to improve the trust that subjects and recipients have in personal sensing technologies by ensuring that they have control over and can understand how information is collected, shared and used. The paper approaches the problem of improving trust by proposing techniques for increasing awareness and control. We focus on mHealth scenarios, but our solutions are applicable to other personal sensing technologies as well.","PeriodicalId":186121,"journal":{"name":"PhD forum '14","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128294782","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}