F. A. P. Figueiredo, Wei Liu, Xianjun Jiao, I. Moerman
Spectrum scarcity has been driving cellular operators to utilize unlicensed spectrum in conjunction with licensed bands to deliver mobile data to its Long-Term Evolution (LTE) users, offloading the fully allocated LTE bands. However, the use of LTE in unlicensed spectrum creates numerous challenges as the fair coexistence with other technologies. A myriad of experimental works tackles the problems involved in the coexistence of different radio access technologies (RAT) in unlicensed spectrum, however, they do not cover all aspects of the problem and fail to provide the framework adopted in the experiments for reproducible research. Therefore, in this demo we present a highly configurable packetized-LTE PHY open-source framework for coexistence experiments. The framework allows the evaluation and comparison of different coexistence techniques.
{"title":"Packetized-LTE Physical Layer Framework for Coexistence Experiments","authors":"F. A. P. Figueiredo, Wei Liu, Xianjun Jiao, I. Moerman","doi":"10.1145/3131672.3136964","DOIUrl":"https://doi.org/10.1145/3131672.3136964","url":null,"abstract":"Spectrum scarcity has been driving cellular operators to utilize unlicensed spectrum in conjunction with licensed bands to deliver mobile data to its Long-Term Evolution (LTE) users, offloading the fully allocated LTE bands. However, the use of LTE in unlicensed spectrum creates numerous challenges as the fair coexistence with other technologies. A myriad of experimental works tackles the problems involved in the coexistence of different radio access technologies (RAT) in unlicensed spectrum, however, they do not cover all aspects of the problem and fail to provide the framework adopted in the experiments for reproducible research. Therefore, in this demo we present a highly configurable packetized-LTE PHY open-source framework for coexistence experiments. The framework allows the evaluation and comparison of different coexistence techniques.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134398426","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}
Aveek K. Das, P. Pathak, Josiah Jee, C. Chuah, P. Mohapatra
Estimation of building occupancy has emerged as an important research problem with applications ranging from building energy efficiency, control and automation, safety, communication network resource allocation, etc. In this research work, we propose the estimation of occupancy using non-intrusive information that is already available from existing sensing modes, namely, number of WiFi devices, electrical energy demand and water consumption rate. Using data collected from 76 buildings in a university campus, we study the feasibility of multi-modal fusion between the three data sources for estimating fine-grained occupancy. In order to make the estimation model scalable, we propose three different clustering schemes to identify similarity in building characteristics and training per-cluster occupancy estimation models. The presented multi-modal fusion estimation framework achieves a mean absolute percentage error of 13.22% and we find that leveraging all three modalities provide an improvement of 48% in accuracy as compared to WiFi-only occupancy estimation. Our evaluation also shows that clustering buildings greatly increases the scalability of the proposed approach through significant reduction in training overhead, while providing an accuracy comparable to exhaustive, per-building estimation models.
{"title":"Non-Intrusive Multi-Modal Estimation of Building Occupancy","authors":"Aveek K. Das, P. Pathak, Josiah Jee, C. Chuah, P. Mohapatra","doi":"10.1145/3131672.3131680","DOIUrl":"https://doi.org/10.1145/3131672.3131680","url":null,"abstract":"Estimation of building occupancy has emerged as an important research problem with applications ranging from building energy efficiency, control and automation, safety, communication network resource allocation, etc. In this research work, we propose the estimation of occupancy using non-intrusive information that is already available from existing sensing modes, namely, number of WiFi devices, electrical energy demand and water consumption rate. Using data collected from 76 buildings in a university campus, we study the feasibility of multi-modal fusion between the three data sources for estimating fine-grained occupancy. In order to make the estimation model scalable, we propose three different clustering schemes to identify similarity in building characteristics and training per-cluster occupancy estimation models. The presented multi-modal fusion estimation framework achieves a mean absolute percentage error of 13.22% and we find that leveraging all three modalities provide an improvement of 48% in accuracy as compared to WiFi-only occupancy estimation. Our evaluation also shows that clustering buildings greatly increases the scalability of the proposed approach through significant reduction in training overhead, while providing an accuracy comparable to exhaustive, per-building estimation models.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133487232","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}
Many existing indoor localization systems have achieved applaudable performance through comprehensive modeling of its envisioned working scenario. However their real life deployment are often prohibited by high deployment overhead and performance degradation in dynamic environments. This paper presents SmartLight, a 3D digital indoor localization system based on LED lighting infrastructures. It adopts a novel design philosophy of shifting all the complexity into modifying a single LED lamp and maintaining minimum complexity on the receiver to reduce the hassle on system deployment/calibration. With a single modified LED lamp, the system is capable of localizing a large number of light sensors in a room. The underlying technique is to exploit the light splitting properties of convex lens to create an one-to-one mapping between a location and the set of orthogonal digital light signals receivable at that location. Advanced designs are also introduced to further improve the system accuracy and scalability beyond the hardware capability. In evaluating the design, we build an experimental prototype with a 60hz projector, achieving average localization around 10cm and 90 percentile error of 50cm.
{"title":"SmartLight: Light-weight 3D Indoor Localization Using a Single LED Lamp","authors":"Song Liu, T. He","doi":"10.1145/3131672.3131677","DOIUrl":"https://doi.org/10.1145/3131672.3131677","url":null,"abstract":"Many existing indoor localization systems have achieved applaudable performance through comprehensive modeling of its envisioned working scenario. However their real life deployment are often prohibited by high deployment overhead and performance degradation in dynamic environments. This paper presents SmartLight, a 3D digital indoor localization system based on LED lighting infrastructures. It adopts a novel design philosophy of shifting all the complexity into modifying a single LED lamp and maintaining minimum complexity on the receiver to reduce the hassle on system deployment/calibration. With a single modified LED lamp, the system is capable of localizing a large number of light sensors in a room. The underlying technique is to exploit the light splitting properties of convex lens to create an one-to-one mapping between a location and the set of orthogonal digital light signals receivable at that location. Advanced designs are also introduced to further improve the system accuracy and scalability beyond the hardware capability. In evaluating the design, we build an experimental prototype with a 60hz projector, achieving average localization around 10cm and 90 percentile error of 50cm.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114150678","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 demo, we propose I-Navi, an Indoor Navigation system which leverages the gradient WiFi signal. To be more adaptive to time-variant RSSI and enrich information dimension, I-Navi exploits a three-step backward gradient binary method. Meanwhile, we adopt a lightweight online dynamic time warping (DTW) algorithm to achieve real-time navigation. We fully implemented I-Navi on smartphones and conducted extensive experiments in a five-story campus building and a newly opened two-floor shopping mall with a 90% accuracy of 2m and 3.2m achieved at two places.
{"title":"Indoor Navigation Leveraging Gradient WiFi Signals","authors":"Zhuoying Shi, Zhenyong Zhang, Yuanchao Shu, Peng Cheng, Jiming Chen","doi":"10.1145/3131672.3136993","DOIUrl":"https://doi.org/10.1145/3131672.3136993","url":null,"abstract":"In this demo, we propose I-Navi, an Indoor Navigation system which leverages the gradient WiFi signal. To be more adaptive to time-variant RSSI and enrich information dimension, I-Navi exploits a three-step backward gradient binary method. Meanwhile, we adopt a lightweight online dynamic time warping (DTW) algorithm to achieve real-time navigation. We fully implemented I-Navi on smartphones and conducted extensive experiments in a five-story campus building and a newly opened two-floor shopping mall with a 90% accuracy of 2m and 3.2m achieved at two places.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117169906","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}
C. Pérez-Penichet, Claro Noda, Ambuj Varshney, T. Voigt
The sensing capabilities of most sensor networks are fixed at the time of deployment. Adding new sensing capabilities to such networks is a costly and cumbersome process. We present Passive Sensor Tags, battery-free sensing devices that could be used to extend the sensing capabilities of an existing network. Sensor tags feature our new 802.15.4 receiver design which is suitable for micro-power operation, making battery-free tags possible. Because our tags can both transmit and receive 802.15.4 frames there is no need for any modification to the deployed hardware. We present preliminary measurements of transmission and reception range.
{"title":"Augmenting WSNs with Interoperable 802.15.4 Sensor Tags","authors":"C. Pérez-Penichet, Claro Noda, Ambuj Varshney, T. Voigt","doi":"10.1145/3131672.3136999","DOIUrl":"https://doi.org/10.1145/3131672.3136999","url":null,"abstract":"The sensing capabilities of most sensor networks are fixed at the time of deployment. Adding new sensing capabilities to such networks is a costly and cumbersome process. We present Passive Sensor Tags, battery-free sensing devices that could be used to extend the sensing capabilities of an existing network. Sensor tags feature our new 802.15.4 receiver design which is suitable for micro-power operation, making battery-free tags possible. Because our tags can both transmit and receive 802.15.4 frames there is no need for any modification to the deployed hardware. We present preliminary measurements of transmission and reception range.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124905894","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}
Xinyu Liu, Xinlei Chen, Xiangxiang Xu, Enhan Mai, H. Noh, Pei Zhang, Lin Zhang
In this paper, given the scenario of a mobile sensing system for air pollution monitoring, we aim at the cause and influence of delay effect on measurement and present a filter-based solution to calibrate the sensing data. We also validate the idea and solution by a real-data experiment. It indicates that the solution decreases deviation on spatial measurement and can be applied in mobile sensing systems to improve the sensing data quality.
{"title":"Delay Effect in Mobile Sensing System for Urban Air Pollution Monitoring","authors":"Xinyu Liu, Xinlei Chen, Xiangxiang Xu, Enhan Mai, H. Noh, Pei Zhang, Lin Zhang","doi":"10.1145/3131672.3136997","DOIUrl":"https://doi.org/10.1145/3131672.3136997","url":null,"abstract":"In this paper, given the scenario of a mobile sensing system for air pollution monitoring, we aim at the cause and influence of delay effect on measurement and present a filter-based solution to calibrate the sensing data. We also validate the idea and solution by a real-data experiment. It indicates that the solution decreases deviation on spatial measurement and can be applied in mobile sensing systems to improve the sensing data quality.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122218662","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}
Inkjet 3D printing is a disruptive manufacturing technology in emerging metal- and bio-printing applications. The nozzle of the printer deposits tiny liquid droplets, which are subsequently solidified on a target location. Due to the elegant concept of micro-droplet deposition, inkjet 3D printing is capable of achieving a sub-millimeter scale manufacturing resolution. However, the droplet deposition process is dynamic and uncertain which imposes a significant challenge on quality assurance of inkjet 3D printing in terms of product reproducibility and process repeatability. To this end, we present Luban as a certification tool to examine the printing quality in the inkjet printing process. Luban is a new low-cost and in-situ droplet micro-sensing system that can precisely detect, analyze and localize a droplet. Specifically, we present a novel tiny object sensing method by exploiting the computational light beam field and its sensitive interference effect. The realization of Luban is associated with two technical thrusts. First, we study integral sensing, i.e., a new scheme towards computational light beam field sensing, to efficiently extract droplet location information. This sensing scheme offers a new in-situ droplet sensing modality, which can promote the information acquisition efficiency and reduce the sensing cost compared to prior approaches. Second, we characterize interference effect of the computational light beam field and develop an efficient integration-domain droplet location estimation algorithm. We design and implement Luban in a real inkjet 3D printing system with commercially off-the-shelf devices, which costs less than a hundred dollars. Experimental results in both simulation and real-world evaluation show that Luban can reach the certification precision of a sub-millimeter scale with a 99% detection accuracy of defect droplets; furthermore, the enabled in-situ certification throughput is as high as over 700 droplets per second. Therefore, the performance of our Luban system can meet the quality assurance requirements (e.g., cost-effective, in-situ, high-accuracy and high-throughput) in general industrial applications.
{"title":"LuBan: Low-Cost and In-Situ Droplet Micro-Sensing for Inkjet 3D Printing Quality Assurance","authors":"Aosen Wang, Tianjiao Wang, Chi Zhou, Wenyao Xu","doi":"10.1145/3131672.3131686","DOIUrl":"https://doi.org/10.1145/3131672.3131686","url":null,"abstract":"Inkjet 3D printing is a disruptive manufacturing technology in emerging metal- and bio-printing applications. The nozzle of the printer deposits tiny liquid droplets, which are subsequently solidified on a target location. Due to the elegant concept of micro-droplet deposition, inkjet 3D printing is capable of achieving a sub-millimeter scale manufacturing resolution. However, the droplet deposition process is dynamic and uncertain which imposes a significant challenge on quality assurance of inkjet 3D printing in terms of product reproducibility and process repeatability. To this end, we present Luban as a certification tool to examine the printing quality in the inkjet printing process. Luban is a new low-cost and in-situ droplet micro-sensing system that can precisely detect, analyze and localize a droplet. Specifically, we present a novel tiny object sensing method by exploiting the computational light beam field and its sensitive interference effect. The realization of Luban is associated with two technical thrusts. First, we study integral sensing, i.e., a new scheme towards computational light beam field sensing, to efficiently extract droplet location information. This sensing scheme offers a new in-situ droplet sensing modality, which can promote the information acquisition efficiency and reduce the sensing cost compared to prior approaches. Second, we characterize interference effect of the computational light beam field and develop an efficient integration-domain droplet location estimation algorithm. We design and implement Luban in a real inkjet 3D printing system with commercially off-the-shelf devices, which costs less than a hundred dollars. Experimental results in both simulation and real-world evaluation show that Luban can reach the certification precision of a sub-millimeter scale with a 99% detection accuracy of defect droplets; furthermore, the enabled in-situ certification throughput is as high as over 700 droplets per second. Therefore, the performance of our Luban system can meet the quality assurance requirements (e.g., cost-effective, in-situ, high-accuracy and high-throughput) in general industrial applications.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123522412","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}
Wenchao Jiang, Zhijun Li, Zhimeng Yin, Ruofeng Liu, Ling Liu, T. He
Cross-Technology Communication is an emerging research direction providing a promising solution to the wireless coexistence problem in the ISM bands. However, the state-of-the-art CTC designs have intrinsic limitations in the throughput due to their use of coarse-grained packet-level information. In contrast, we propose to exploit the fine-grained signal modulation information via a technique called PHY-layer emulation to boost CTC throughput. We can embed a legitimate packet of a target technology, e.g., ZigBee, within the payload of a source technology, e.g., WiFi or Bluetooth Low Energy (BLE). At the mean time, we require no modification at the hardware or firmware at either sender or receiver. We can achieve 8,000x throughput from WiFi to ZigBee and 10,000x throughput from BLE to ZigBee compared to the state of the art. We also have a demo showcasing how our designs can be implemented on off-the-shelf smartphones for smart light bulbs control.
{"title":"Cross-Technology Communication via PHY-Layer Emulation","authors":"Wenchao Jiang, Zhijun Li, Zhimeng Yin, Ruofeng Liu, Ling Liu, T. He","doi":"10.1145/3131672.3136972","DOIUrl":"https://doi.org/10.1145/3131672.3136972","url":null,"abstract":"Cross-Technology Communication is an emerging research direction providing a promising solution to the wireless coexistence problem in the ISM bands. However, the state-of-the-art CTC designs have intrinsic limitations in the throughput due to their use of coarse-grained packet-level information. In contrast, we propose to exploit the fine-grained signal modulation information via a technique called PHY-layer emulation to boost CTC throughput. We can embed a legitimate packet of a target technology, e.g., ZigBee, within the payload of a source technology, e.g., WiFi or Bluetooth Low Energy (BLE). At the mean time, we require no modification at the hardware or firmware at either sender or receiver. We can achieve 8,000x throughput from WiFi to ZigBee and 10,000x throughput from BLE to ZigBee compared to the state of the art. We also have a demo showcasing how our designs can be implemented on off-the-shelf smartphones for smart light bulbs control.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127762887","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}
M. Bezunartea, Benjamin Sartori, In Frances, J. Tiberghien, An Braeken, K. Steenhaut
Several recent sensor platforms combine long-range and more classical short-range radio technologies. In this poster we propose some modifications to the RPL routing protocol such that it automatically selects the most suitable radio link when more than one is available. The solution has been implemented in the ContikiOS and tested on the Zolertia Re-mote platform.
{"title":"Enabling dual-band operation with the RPL routing protocol","authors":"M. Bezunartea, Benjamin Sartori, In Frances, J. Tiberghien, An Braeken, K. Steenhaut","doi":"10.1145/3131672.3136978","DOIUrl":"https://doi.org/10.1145/3131672.3136978","url":null,"abstract":"Several recent sensor platforms combine long-range and more classical short-range radio technologies. In this poster we propose some modifications to the RPL routing protocol such that it automatically selects the most suitable radio link when more than one is available. The solution has been implemented in the ContikiOS and tested on the Zolertia Re-mote platform.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125715840","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}
Weixi Gu, Zimu Zhou, Yuxun Zhou, M. He, Han Zou, Lin Zhang
Predicting blood glucose dynamics is vital for people to take preventive measures in time against health risks. Previous efforts adopt handcrafted features and design prediction models for each person, which result in low accuracy due to ineffective feature representation and the limited training data. This work proposes MT-LSTM, a multi-time-series deep LSTM model for accurate and efficient blood glucose concentration prediction. MT-LSTM automatically learns feature representations and temporal dependencies of blood glucose dynamics by jointly sharing data among multiple users and utilizes an individual learning layer for personalized prediction. Evaluations on 112 users demonstrate that MT-LSTM significant outperform conventional predictive regression models.
{"title":"Predicting Blood Glucose Dynamics with Multi-time-series Deep Learning","authors":"Weixi Gu, Zimu Zhou, Yuxun Zhou, M. He, Han Zou, Lin Zhang","doi":"10.1145/3131672.3136965","DOIUrl":"https://doi.org/10.1145/3131672.3136965","url":null,"abstract":"Predicting blood glucose dynamics is vital for people to take preventive measures in time against health risks. Previous efforts adopt handcrafted features and design prediction models for each person, which result in low accuracy due to ineffective feature representation and the limited training data. This work proposes MT-LSTM, a multi-time-series deep LSTM model for accurate and efficient blood glucose concentration prediction. MT-LSTM automatically learns feature representations and temporal dependencies of blood glucose dynamics by jointly sharing data among multiple users and utilizes an individual learning layer for personalized prediction. Evaluations on 112 users demonstrate that MT-LSTM significant outperform conventional predictive regression models.","PeriodicalId":424262,"journal":{"name":"Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123309383","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：