Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474131
Nitisha Shrivastava, P. Varshney
The role of non-integer calculus in the fields of signal processing, control and automation is gradually gaining high importance due to its additional degree of freedom. In this paper we focus on frequency band approximations of non-integer order differentiators and integrators in s-domain. The implementation of non-integer order proportional plus integral plus derivative (PID) controller to control a plant model is presented. This is done by first approximating the non-integer order terms to a finite value using different approximation techniques and then decomposing the finite model to obtain the circuit elements. The frequency response analysis of the approximated model is presented and it is shown that the number of circuit elements depends on the approximation technique. The time domain analysis of the closed loop system is presented by plotting the step response. The simulations have been performed using MATLAB and OrCAD Capture CIS simulator.
{"title":"Frequency band implementation of non-integer order functions","authors":"Nitisha Shrivastava, P. Varshney","doi":"10.1109/SPIN.2018.8474131","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474131","url":null,"abstract":"The role of non-integer calculus in the fields of signal processing, control and automation is gradually gaining high importance due to its additional degree of freedom. In this paper we focus on frequency band approximations of non-integer order differentiators and integrators in s-domain. The implementation of non-integer order proportional plus integral plus derivative (PID) controller to control a plant model is presented. This is done by first approximating the non-integer order terms to a finite value using different approximation techniques and then decomposing the finite model to obtain the circuit elements. The frequency response analysis of the approximated model is presented and it is shown that the number of circuit elements depends on the approximation technique. The time domain analysis of the closed loop system is presented by plotting the step response. The simulations have been performed using MATLAB and OrCAD Capture CIS simulator.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130297654","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474103
Pranjal Gupta, M. Srivastava
This research article proposes a new grounded frequency dependent negative conductance (FDNC) simulator. The presented simulator is designed by employing two voltage differencing trans-conductance amplifiers (VDTAs) along with two grounded capacitances. The presented FDNC simulator enjoys electronic controllability of realized negative conductance with no component matching constraints and exhibits excellent behavior under non-ideal conditions with low active/passive sensitivity indexes. The working of presented FDNC simulator has been verified by some voltage mode filter design examples. The performance of presented circuits has been verified by PSPICE simulations.
{"title":"New Frequency Dependent Negative Conductance Simulator employing VDTAs and Grounded Capacitances","authors":"Pranjal Gupta, M. Srivastava","doi":"10.1109/SPIN.2018.8474103","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474103","url":null,"abstract":"This research article proposes a new grounded frequency dependent negative conductance (FDNC) simulator. The presented simulator is designed by employing two voltage differencing trans-conductance amplifiers (VDTAs) along with two grounded capacitances. The presented FDNC simulator enjoys electronic controllability of realized negative conductance with no component matching constraints and exhibits excellent behavior under non-ideal conditions with low active/passive sensitivity indexes. The working of presented FDNC simulator has been verified by some voltage mode filter design examples. The performance of presented circuits has been verified by PSPICE simulations.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133956518","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474256
Nishank Singhal, Neetika Singhal, Srishti
This paper presents a novel technique of judging the performance of a candidate in a video interview. The candidate is judged as confident and attentive or unconfident and inattentive by taking the direction of face and eye into consideration. This corresponds to how many times is the candidate interacting actively, by making a firm eye contact with the interviewer. Image Processing techniques like Haar Cascade, Image filtering, Gamma Correction have been used for the detection of face and eye. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) have been used for training and testing the images into right classes.
{"title":"Comparing CNN and RNN for Prediction of Judgement in Video Interview Based on Facial Gestures","authors":"Nishank Singhal, Neetika Singhal, Srishti","doi":"10.1109/SPIN.2018.8474256","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474256","url":null,"abstract":"This paper presents a novel technique of judging the performance of a candidate in a video interview. The candidate is judged as confident and attentive or unconfident and inattentive by taking the direction of face and eye into consideration. This corresponds to how many times is the candidate interacting actively, by making a firm eye contact with the interviewer. Image Processing techniques like Haar Cascade, Image filtering, Gamma Correction have been used for the detection of face and eye. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) have been used for training and testing the images into right classes.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132889669","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474134
Chirag Arorak, S. Pattnaik, R. N. Baral
This paper presents a shorted-pin, dual-band, metamaterial-loaded microstrip patch antenna array. Under the unloaded conditions, the traditional patch antenna array resonates at 5.8 GHz with gain of 9.8 dBi and bandwidth of 540 MHz. However, when each patch of this traditional array is loaded with split ring resonator (SRR) and a metallic via hole is made on the patch, the same antenna array also produces an additional resonant frequency in 2.45 GHz Wi-Fi band with bandwidth and gain of 290 MHz and 5.6 dBi, respectively, while the initial resonant frequency (i.e. 5.8 GHz) gets shifted to 5 GHz Wi-Fi band, providing the gain and bandwidth of 11.4 dBi and 510 MHz, respectively. The prototype of this proposed antenna array has been fabricated.
{"title":"Metamaterial Inspired Dual Band Patch Antenna Array","authors":"Chirag Arorak, S. Pattnaik, R. N. Baral","doi":"10.1109/SPIN.2018.8474134","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474134","url":null,"abstract":"This paper presents a shorted-pin, dual-band, metamaterial-loaded microstrip patch antenna array. Under the unloaded conditions, the traditional patch antenna array resonates at 5.8 GHz with gain of 9.8 dBi and bandwidth of 540 MHz. However, when each patch of this traditional array is loaded with split ring resonator (SRR) and a metallic via hole is made on the patch, the same antenna array also produces an additional resonant frequency in 2.45 GHz Wi-Fi band with bandwidth and gain of 290 MHz and 5.6 dBi, respectively, while the initial resonant frequency (i.e. 5.8 GHz) gets shifted to 5 GHz Wi-Fi band, providing the gain and bandwidth of 11.4 dBi and 510 MHz, respectively. The prototype of this proposed antenna array has been fabricated.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134137840","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474067
Manishkumar Purohit, Arvind R. Yadav
In India, it is observed that the number of people losing their lives in road accidents especially on highways is more than the death resulting due to naxalite, terrorism activity or epidemic. Government is investing plenty of money to educate people regarding road safety and curb death due to accidents, but people used to avoid it and entering themselves into danger zone. Several lives could be saved if the person(s) make use of helmet and wear seat belts while driving vehicles. Further, it is next to impossible for traffic police to catch each rider violating traffic rules, thus there is a need of the system to identify people disobeying road safety guideline which involves use of helmet and seat belt. The idea is to impose appropriate fine on such people to force them follow the road safety guidelines. Bike-riders without helmet and driving four wheeler without wearing seatbelt should be caught. Authors have performed four feature extraction techniques namely Scale-Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Template Matching and Oriented FAST and Rotated BRIEF(ORB) to detect objects like vehicles, helmets, number plates, seatbelts for traffic data sets on Raspberry Pi 2 (B) using OpenCV3.0 and Python 3.4.2. These feature extraction techniques have been evaluated on collected dataset and simulation results performed on raspberry pi on valid dataset. The observation suggests that SIFT algorithm can be used to get higher accuracy compared to SURF and ORB for rule violators at toll system on highways or traffic cross road in city.
在印度，人们注意到，在道路事故中丧生的人数，特别是在高速公路上丧生的人数，超过了纳萨尔派、恐怖主义活动或流行病造成的死亡人数。政府投入了大量的资金来教育人们关于道路安全，减少交通事故造成的死亡，但人们过去常常回避它，让自己进入危险地带。如果人们在驾驶车辆时使用头盔并系好安全带，可能会挽救一些生命。此外，交通警察几乎不可能抓住每个违反交通规则的骑手，因此需要系统来识别不遵守道路安全准则的人，包括使用头盔和安全带。这个想法是对这些人处以适当的罚款，迫使他们遵守道路安全准则。不戴头盔骑自行车和不系安全带驾驶四轮车者应被抓。作者使用OpenCV3.0和Python 3.4.2在Raspberry Pi 2 (B)上执行了四种特征提取技术，即尺度不变特征变换(SIFT)、加速鲁棒特征(SURF)、模板匹配和定向FAST和旋转BRIEF(ORB)，以检测交通数据集的车辆、头盔、车牌、安全带等物体。这些特征提取技术已经在收集的数据集上进行了评估，并在有效数据集上在树莓派上进行了模拟结果。结果表明，在高速公路或城市十字路口的收费系统中，与SURF和ORB相比，SIFT算法对违规者的识别精度更高。
{"title":"Comparison of feature extraction techniques to recognize traffic rule violations using low processing embedded system","authors":"Manishkumar Purohit, Arvind R. Yadav","doi":"10.1109/SPIN.2018.8474067","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474067","url":null,"abstract":"In India, it is observed that the number of people losing their lives in road accidents especially on highways is more than the death resulting due to naxalite, terrorism activity or epidemic. Government is investing plenty of money to educate people regarding road safety and curb death due to accidents, but people used to avoid it and entering themselves into danger zone. Several lives could be saved if the person(s) make use of helmet and wear seat belts while driving vehicles. Further, it is next to impossible for traffic police to catch each rider violating traffic rules, thus there is a need of the system to identify people disobeying road safety guideline which involves use of helmet and seat belt. The idea is to impose appropriate fine on such people to force them follow the road safety guidelines. Bike-riders without helmet and driving four wheeler without wearing seatbelt should be caught. Authors have performed four feature extraction techniques namely Scale-Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Template Matching and Oriented FAST and Rotated BRIEF(ORB) to detect objects like vehicles, helmets, number plates, seatbelts for traffic data sets on Raspberry Pi 2 (B) using OpenCV3.0 and Python 3.4.2. These feature extraction techniques have been evaluated on collected dataset and simulation results performed on raspberry pi on valid dataset. The observation suggests that SIFT algorithm can be used to get higher accuracy compared to SURF and ORB for rule violators at toll system on highways or traffic cross road in city.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132033757","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474281
Ashutosh Kumar Singh, R. Pamula
Delay Tolerant Networks (DTNs) are special class of networks which can work in the challenged environment where conventional networks fail to work. The main reason for the failure of conventional or traditional network is absence of end-to-end path. If end-to-end path does not exist traditional network can not work, but in modern day to day life computer network and internet is an essential part of our life. Thus, DTNs is the most probable solution for challenged area where traditional networks can not provide services. In real life everyone carries smart phones and handheld devices, these devices can play important role in relaying data for DTNs i.e, social DTNs. Socially aware (DTNs) are human-driven DTNs in which nodes act similar to human behavior. They can act selfishly to save their resources and deny to relay packets. For the solution of this problem we have proposed IRS, incentive based routing strategy. In this approach intermediate nodes can participate and earn incentives for sacrificing their selfishness.
{"title":"IRS: Incentive Based Routing Strategy for Socially Aware Delay Tolerant Networks","authors":"Ashutosh Kumar Singh, R. Pamula","doi":"10.1109/SPIN.2018.8474281","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474281","url":null,"abstract":"Delay Tolerant Networks (DTNs) are special class of networks which can work in the challenged environment where conventional networks fail to work. The main reason for the failure of conventional or traditional network is absence of end-to-end path. If end-to-end path does not exist traditional network can not work, but in modern day to day life computer network and internet is an essential part of our life. Thus, DTNs is the most probable solution for challenged area where traditional networks can not provide services. In real life everyone carries smart phones and handheld devices, these devices can play important role in relaying data for DTNs i.e, social DTNs. Socially aware (DTNs) are human-driven DTNs in which nodes act similar to human behavior. They can act selfishly to save their resources and deny to relay packets. For the solution of this problem we have proposed IRS, incentive based routing strategy. In this approach intermediate nodes can participate and earn incentives for sacrificing their selfishness.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129476302","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474241
A. Singh, Malay Ranjan Tripathy
This paper presents design and simulation of an ultra wide band antenna for Customer Premise Equipment (CPE) in the TV White Space (TVWS) spectrum band operating between 420 MHz – 1040 MHz. Integrated, lightweight and wideband antennas have received much attention following the development of wireless communications. The M-shaped monopole is a lightweight, wideband antenna suitable for integration. The size of the antenna has been reduced by using a T-shaped ground plane. The wide bandwidth and reduced size of this antenna makes it desirable for use in TVWS CPE communication systems. The antenna elements are designed on low cost FR4 substrate with εr = 4.4 and tanδ = 0.02. The M-shaped monopole is fed by a 50 Ω microstrip line. Total volume of the antenna is 198.32 × 111.11 × 1.6 mm3. The antenna shows an impedance bandwidth for VSWR ≤ 2 in the frequency range of 420 MHz – 1040 MHz. The gain of this antenna is between 2.24 dB to 4.8 dB in the entire band of operation. The radiation pattern is omnidirectional in both E and H-planes. Radiation and total efficiency of the simulated M shaped monopole antenna achieved is approximately 99 %.
{"title":"M Shaped Ultra Wide Band Monopole Antenna for TVWS CPE","authors":"A. Singh, Malay Ranjan Tripathy","doi":"10.1109/SPIN.2018.8474241","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474241","url":null,"abstract":"This paper presents design and simulation of an ultra wide band antenna for Customer Premise Equipment (CPE) in the TV White Space (TVWS) spectrum band operating between 420 MHz – 1040 MHz. Integrated, lightweight and wideband antennas have received much attention following the development of wireless communications. The M-shaped monopole is a lightweight, wideband antenna suitable for integration. The size of the antenna has been reduced by using a T-shaped ground plane. The wide bandwidth and reduced size of this antenna makes it desirable for use in TVWS CPE communication systems. The antenna elements are designed on low cost FR4 substrate with εr = 4.4 and tanδ = 0.02. The M-shaped monopole is fed by a 50 Ω microstrip line. Total volume of the antenna is 198.32 × 111.11 × 1.6 mm3. The antenna shows an impedance bandwidth for VSWR ≤ 2 in the frequency range of 420 MHz – 1040 MHz. The gain of this antenna is between 2.24 dB to 4.8 dB in the entire band of operation. The radiation pattern is omnidirectional in both E and H-planes. Radiation and total efficiency of the simulated M shaped monopole antenna achieved is approximately 99 %.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130112976","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474064
N. Londhe, G. B. Kshirsagar, Hitesh Tekchandani
The existing ASR for Chhattisgarhi using conventional machine learning technique was implemented for speaker dependent speech recognition. However, the conventional machine learning based speech recognition is incapable to handle the spectral variations as well as the spectral correlation of acoustic signals. Therefore, to overcome the aforementioned limitations, authors have implemented the deep convolution neural network (DCNN) based ASR for Chhattisgarhi dialect. Unlike other deep learning models, DCNN can efficiently handle the spectral variations and spectral correlation of speech signal with the less computational burden. The experiment of isolated Chhattisgarhi word recognition was implemented on self-recorded dataset acquired from 150 subjects from various geographical parts of Chhattisgarh state. The implemented algorithm is promisingly achieving 99.49% of accuracy for isolated word recognition. The different performance paraments are presented to validate the performed experiment.
{"title":"Deep Convolution Neural Network Based Speech Recognition for Chhattisgarhi","authors":"N. Londhe, G. B. Kshirsagar, Hitesh Tekchandani","doi":"10.1109/SPIN.2018.8474064","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474064","url":null,"abstract":"The existing ASR for Chhattisgarhi using conventional machine learning technique was implemented for speaker dependent speech recognition. However, the conventional machine learning based speech recognition is incapable to handle the spectral variations as well as the spectral correlation of acoustic signals. Therefore, to overcome the aforementioned limitations, authors have implemented the deep convolution neural network (DCNN) based ASR for Chhattisgarhi dialect. Unlike other deep learning models, DCNN can efficiently handle the spectral variations and spectral correlation of speech signal with the less computational burden. The experiment of isolated Chhattisgarhi word recognition was implemented on self-recorded dataset acquired from 150 subjects from various geographical parts of Chhattisgarh state. The implemented algorithm is promisingly achieving 99.49% of accuracy for isolated word recognition. The different performance paraments are presented to validate the performed experiment.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114145700","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474286
R. Priyadarshi, Lucky Singh, Randheer, Anurag Singh
In this article, Hybrid Energy Efficient Distributed (HEED) algorithm for the network where nodes are non-uniformly distributed has been proposed. The foremost necessities of sensor network are to lengthen network lifetime as well as energy efficacy. Here, a novel HEED Protocol for clustered non-uniform for sensor network has been planned to extend network lifetime. The performance analysis of proposed HEED and different variant of existing HEED protocol is done in terms of dissipated energy, first node die with respect to cluster radius and number of alive nodes. Simulation outcomes reflect that planned HEED protocol achieves longer lifetime and also it is more energy efficient compared to the existing HEED protocol.
{"title":"A Novel HEED Protocol for Wireless Sensor Networks","authors":"R. Priyadarshi, Lucky Singh, Randheer, Anurag Singh","doi":"10.1109/SPIN.2018.8474286","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474286","url":null,"abstract":"In this article, Hybrid Energy Efficient Distributed (HEED) algorithm for the network where nodes are non-uniformly distributed has been proposed. The foremost necessities of sensor network are to lengthen network lifetime as well as energy efficacy. Here, a novel HEED Protocol for clustered non-uniform for sensor network has been planned to extend network lifetime. The performance analysis of proposed HEED and different variant of existing HEED protocol is done in terms of dissipated energy, first node die with respect to cluster radius and number of alive nodes. Simulation outcomes reflect that planned HEED protocol achieves longer lifetime and also it is more energy efficient compared to the existing HEED protocol.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114204076","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}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474181
Priyanka S. Sase, S. Bhandari
The proposed fall detection approach is aimed at building a support system for old age people living alone in their homes. In this work, a method is proposed based on depth videos. A Region of interest (ROI) is detected by subtracting background from extracted frames along with preprocessing such as filtration, binarization and connected component analysis. The threshold is calculated by contemplating ROI points. Comparing ROI in each frame with calculated threshold, fall is detected. To scrutinize fall detection approach, videos of fall and no-fall activities from UR fall dataset and SDU fall dataset are processed. The results show 100% accuracy for fall activities and 82.50% for no-fall activities with UR fall dataset. Also SDU fall dataset shows 100% accuracy for fall and 80% for no-fall.
{"title":"Human Fall Detection using Depth Videos","authors":"Priyanka S. Sase, S. Bhandari","doi":"10.1109/SPIN.2018.8474181","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474181","url":null,"abstract":"The proposed fall detection approach is aimed at building a support system for old age people living alone in their homes. In this work, a method is proposed based on depth videos. A Region of interest (ROI) is detected by subtracting background from extracted frames along with preprocessing such as filtration, binarization and connected component analysis. The threshold is calculated by contemplating ROI points. Comparing ROI in each frame with calculated threshold, fall is detected. To scrutinize fall detection approach, videos of fall and no-fall activities from UR fall dataset and SDU fall dataset are processed. The results show 100% accuracy for fall activities and 82.50% for no-fall activities with UR fall dataset. Also SDU fall dataset shows 100% accuracy for fall and 80% for no-fall.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114951800","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：