BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Calcutta BEGIN:STANDARD DTSTART:19451014T230000 TZOFFSETFROM:+0630 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210226T091411Z UID:D049D7F0-B28B-4543-8B5A-FAA6DC24D6F6 DTSTART;TZID=Asia/Calcutta:20210217T110000 DTEND;TZID=Asia/Calcutta:20210217T114500 DESCRIPTION:About:\nThe IEEE Computational Intelligence Society Chapter - I EEE Gujarat Section brings in Symposium series to foster exchange of ideas and experience. It provides a discussion forum for advancement of their r esearch and gain feedback on research work in the domain of computational intelligence. This is an initiative by IEEE CIS chapter - IEEE Gujarat sec tion to build community for intellectual exchange and support the budding researchers.\n\nIntended Participants: Anyone interested in Computational Intelligence Domain\n\nDetails of the next Symposium talk\n\nSpeaker: Mr J ayesh Munjani\, PhD Scholar\, Uka Tarsadia University\, Bardoli\, India\n\ nSupervisor: Dr Maulin Joshi\, Professor & Head\, Electronics and Communic ation Engineering department\, Sarvajanik College of Engineering &Technolo gy\, Surat\n\nTopic: A non-conventional lightweight Auto Regressive Neural Network for accurate and energy efficient target tracking in Wireless Sen sor Network\n\nAbstract:\nThe design of an energy-efficient tracking frame work is a well-investigated issue and a prominent sensor network applicati on. The current research state shows a clear scope for developing algorith ms that can work\, accompanying both energy efficiency and accuracy. The p rediction-based algorithms can save network energy by carefully selecting suitable nodes for continuous target tracking. However\, the conventional prediction algorithms are confined to fixed motion models and generally fa il in accelerated target movements. The neural networks can learn any non- linearity between input and output as they are model-free estimators. To d esign a lightweight neural network-based prediction algorithm for resource -constrained tiny sensor nodes is a challenging task. This research aims t o develop a simpler\, energy-efficient\, and accurate network-based tracki ng scheme for linear and non-linear target movements. The proposed techniq ue uses an autoregressive model to learn the temporal correlation between successive samples of a target trajectory. The simulation results are comp ared with the traditional Kalman filter (KF)\, Interacting Multiple models (IMM)\, Current Statistical model (CSM)\, Long Short Term Memory (LSTM)\, Decision Tree (DT)\, and Random Forest (RF) based tracking approach. It s hows that the proposed algorithm can save up to 70% of network energy with improved prediction accuracy.\n\nRegistration: Interested may please regi ster at https://forms.gle/6jHs8cy53cvrpu8Q8 and we will mail you the meeti ng details.\n\nSpeaker(s): Mr. Jayesh Munjani\, \n\nVirtual: https://event s.vtools.ieee.org/m/261509 LOCATION:Virtual: https://events.vtools.ieee.org/m/261509 ORGANIZER:pratik@iiitvadodara.ac.in SEQUENCE:1 SUMMARY:Virtual Research Symposium Series by IEEE CIS Chapter - IEEE Gujara t Section URL;VALUE=URI:https://events.vtools.ieee.org/m/261509 X-ALT-DESC:Description: <br /><div><strong>About:</strong></div>\n<div>The IEEE Computational Intelligence Society Chapter - IEEE Gujarat Section bri ngs in Symposium series to foster exchange of ideas and experience. It pro vides a discussion&nbsp\;forum for advancement of their research and gain feedback on research work in the domain of computational intelligence. Thi s is an initiative by IEEE CIS chapter - IEEE Gujarat section to build com munity for intellectual exchange and support the budding researchers.</div >\n<div>&nbsp\;</div>\n<div><strong>Intended Participants:&nbsp\;</strong> Anyone interested in Computational Intelligence Domain</div>\n<div>&nbsp\; </div>\n<div>\n<div><strong>Details of the next Symposium talk</strong></d iv>\n<div><strong>&nbsp\;</strong></div>\n<div><strong>Speaker:&nbsp\;</st rong>Mr Jayesh Munjani\, PhD Scholar\, Uka Tarsadia University\, Bardoli\, India</div>\n<div>&nbsp\;</div>\n<div><strong>Supervisor:&nbsp\;</strong> Dr Maulin Joshi\,&nbsp\;<span style="color: #000000\;">Professor&nbsp\; &a mp\; Head\,&nbsp\;</span>Electronics and Communication Engineering departm ent\,&nbsp\;Sarvajanik College of Engineering &amp\;Technology\, Surat</di v>\n<div>&nbsp\;</div>\n<div>\n<div><strong>Topic:&nbsp\;</strong>A non-co nventional lightweight Auto Regressive Neural Network for accurate and ene rgy efficient target tracking in Wireless Sensor Network</div>\n<div>&nbsp \;</div>\n<div>\n<div><strong>Abstract:</strong></div>\n<div>The design of an energy-efficient tracking framework is a well-investigated issue and a prominent sensor network application. The current research state shows a clear scope for developing algorithms that can work\, accompanying both en ergy efficiency and accuracy. The prediction-based algorithms can save net work energy by carefully selecting suitable nodes for continuous target tr acking. However\, the conventional prediction algorithms are confined to f ixed motion models and generally fail in accelerated target movements. The neural networks can learn any non-linearity between input and output as t hey are model-free estimators. To design a lightweight neural network-base d prediction algorithm for resource-constrained tiny sensor nodes is a cha llenging task. This research aims to develop a simpler\, energy-efficient\ , and accurate network-based tracking scheme for linear and non-linear tar get movements. The proposed technique uses an autoregressive model to lear n the temporal correlation between successive samples of a target trajecto ry. The simulation results are compared with the traditional Kalman filter (KF)\, Interacting Multiple models (IMM)\, Current Statistical model (CSM )\, Long Short Term Memory (LSTM)\, Decision Tree (DT)\, and Random Forest (RF) based tracking approach. It shows that the proposed algorithm can sa ve up to 70% of network energy with improved prediction accuracy.</div>\n< /div>\n</div>\n</div>\n<div>&nbsp\;</div>\n<div>Registration: Interested m ay please register at&nbsp\;<a href="https://forms.gle/6jHs8cy53cvrpu8Q8" target="_blank" rel="noopener" data-saferedirecturl="https://www.google.co m/url?q=https://forms.gle/6jHs8cy53cvrpu8Q8&amp\;source=gmail&amp\;ust=161 3217124470000&amp\;usg=AFQjCNEXi6A79s3T1NoBqTxiQn-rr9dmqA">https://forms.g le/<wbr />6jHs8cy53cvrpu8Q8</a>&nbsp\;and we will mail you the meeting det ails.</div> END:VEVENT END:VCALENDAR