The Diabetes Mellitus prediction system projected in this paper employs the Enhanced K-Strange Points Clustering Algorithm (EKSPCA) and the Naïve Bayes Classifier for clustering and classification respectively. The Enhanced K-Strange Points Clustering Algorithm is employed for its benefits over other clustering algorithms in that it takes lesser time compared to the previously used clustering algorithms, with higher accuracy rate. The outcomes proved that the Diabetes Mellitus prediction system projected in this paper produced better results than the existing systems with respect to execution speed.
{"title":"Diabetes Mellitus Prediction Based on Enhanced K Strange Points Clustering and Classification","authors":"Terence Johnson, Anup Narvekar, Jude Vaz, A. Haldankar, Shivani Hubli, Omkar Naik","doi":"10.1109/wispnet54241.2022.9767143","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767143","url":null,"abstract":"The Diabetes Mellitus prediction system projected in this paper employs the Enhanced K-Strange Points Clustering Algorithm (EKSPCA) and the Naïve Bayes Classifier for clustering and classification respectively. The Enhanced K-Strange Points Clustering Algorithm is employed for its benefits over other clustering algorithms in that it takes lesser time compared to the previously used clustering algorithms, with higher accuracy rate. The outcomes proved that the Diabetes Mellitus prediction system projected in this paper produced better results than the existing systems with respect to execution speed.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"89 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114091525","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767151
Fariha Siddiqua, Samiur Rahman M., Mahmuda Tamanna Dolon, Tahsin Ferdous Ara Nayna, M. Rashid, Md. Abdur Razzak
Temperature and humidity monitoring is crucial when it comes to the prolonged storage of perishable foods and crops in cold storage, as the use of correct temperature while controlling the moisture levels is a must not only for the safety of those products but also to ensure the quality. With the help of Internet of Things (IoT), the monitoring as well as the controlling of the Temperature and humidity of a system can be done automatically from anywhere in the world. This paper presents an IoT-based low-cost automatic cold storage monitoring and controlling system. The proposed system includes a sensor for measuring both temperature and humidity, a microcontroller, a DC-DC step down converter-based power supply module, a cooling fan to lower the temperature and an app to monitor and control the temperature of the cold storage system. The hardware prototype of the system has been tested for consecutive three months for ensuring the accuracy.
{"title":"IoT-Based Low-Cost Cold Storage Atmosphere Monitoring and Controlling System","authors":"Fariha Siddiqua, Samiur Rahman M., Mahmuda Tamanna Dolon, Tahsin Ferdous Ara Nayna, M. Rashid, Md. Abdur Razzak","doi":"10.1109/wispnet54241.2022.9767151","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767151","url":null,"abstract":"Temperature and humidity monitoring is crucial when it comes to the prolonged storage of perishable foods and crops in cold storage, as the use of correct temperature while controlling the moisture levels is a must not only for the safety of those products but also to ensure the quality. With the help of Internet of Things (IoT), the monitoring as well as the controlling of the Temperature and humidity of a system can be done automatically from anywhere in the world. This paper presents an IoT-based low-cost automatic cold storage monitoring and controlling system. The proposed system includes a sensor for measuring both temperature and humidity, a microcontroller, a DC-DC step down converter-based power supply module, a cooling fan to lower the temperature and an app to monitor and control the temperature of the cold storage system. The hardware prototype of the system has been tested for consecutive three months for ensuring the accuracy.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124134904","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767179
Gopika Rejith, L. P., Tom Toby, S. B., Sethuraman N. Rao
Disasters cause disruptions to human life, damage public properties, and hinder the economic growth of the country. Building collapse is one of the most common disasters and causes severe loss to humans. Advanced innovative technologies such as the Internet of Things (IoT), image detection and machine learning algorithms are employed to minimize post-disaster risk factors and support rescue management. In this paper, we summarise the state of the art in rescue management and the role of advanced technologies in rescue assistance. We also propose a machine learning algorithm for first responders to safely evacuate people trapped under debris from collapsed buildings. This paper summarises the identified machine learning algorithms for this application and compares their performances with the data that we generated from the simulation setup at our laboratory.
{"title":"Machine Learning based Criticality Estimation Algorithm for Search & Rescue Operations in Collapsed Infrastructures","authors":"Gopika Rejith, L. P., Tom Toby, S. B., Sethuraman N. Rao","doi":"10.1109/wispnet54241.2022.9767179","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767179","url":null,"abstract":"Disasters cause disruptions to human life, damage public properties, and hinder the economic growth of the country. Building collapse is one of the most common disasters and causes severe loss to humans. Advanced innovative technologies such as the Internet of Things (IoT), image detection and machine learning algorithms are employed to minimize post-disaster risk factors and support rescue management. In this paper, we summarise the state of the art in rescue management and the role of advanced technologies in rescue assistance. We also propose a machine learning algorithm for first responders to safely evacuate people trapped under debris from collapsed buildings. This paper summarises the identified machine learning algorithms for this application and compares their performances with the data that we generated from the simulation setup at our laboratory.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127784100","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767186
M. Das, Tilendra Choudhary, Bhuyan M. K., S. N., Pallab Jyoti Dutta H.
In recent years, camera-based non-contact heart rate (HR) measurement technology has grown immensely. The system captures the reflection of light from the facial tissues and lead to the formation of a remote photoplethysmogram (rPPG) signal that can be used to measure physiological parameters for cardiac health assessment. Due to environmental interferences, extraction of a reliable rPPG signal is a challenging task and thus, requires a robust denoising algorithm. In this paper, a discrete wavelet transform (DWT)-based multiresolution method is used to remove the noises from the video frames caused due to illumination variation and motion artifacts. Subsequently, rPPG signal is extracted and HR is measured from two region of interests (ROIs), facial and forehead regions. The study evaluates the performance of the proposed method on each of the RGB color channels from both the ROIs. The performance results for the COHFACE dataset show that the proposed method works well for the estimation of HR values. Furthermore, they reveal that the forehead region on the green channel is more suitable for HR measurement.
{"title":"A Multiresolution Method for Non-Contact Heart Rate Estimation Using Facial Video Frames","authors":"M. Das, Tilendra Choudhary, Bhuyan M. K., S. N., Pallab Jyoti Dutta H.","doi":"10.1109/wispnet54241.2022.9767186","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767186","url":null,"abstract":"In recent years, camera-based non-contact heart rate (HR) measurement technology has grown immensely. The system captures the reflection of light from the facial tissues and lead to the formation of a remote photoplethysmogram (rPPG) signal that can be used to measure physiological parameters for cardiac health assessment. Due to environmental interferences, extraction of a reliable rPPG signal is a challenging task and thus, requires a robust denoising algorithm. In this paper, a discrete wavelet transform (DWT)-based multiresolution method is used to remove the noises from the video frames caused due to illumination variation and motion artifacts. Subsequently, rPPG signal is extracted and HR is measured from two region of interests (ROIs), facial and forehead regions. The study evaluates the performance of the proposed method on each of the RGB color channels from both the ROIs. The performance results for the COHFACE dataset show that the proposed method works well for the estimation of HR values. Furthermore, they reveal that the forehead region on the green channel is more suitable for HR measurement.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128650642","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767124
T. R. Chenthil, P. Jayarin
Underwater Wireless Sensor Networks (UWSN) have emerged as a promising technology for detecting physical attributes of water such as pressure, temperature, etc. However, the dynamic conditions of water depth, energy constraints, and delay are the main challenges in the design of energy-efficient routing protocols. Hence, there is a need for a forwarder set selection with depth coordination to reduce the energy constraints of UWSN. In this work, we presented an Energy-efficient Clustering Based Depth coordination routing protocol (E-CDBR) to minimize energy consumption with less delay for UWSN. Initially, the nodes are randomly deployed, and a surface sink is positioned at the top of the underwater network area. Then a clustering approach is used to determine the optimal number of clusters before CH selection in the cluster area. In the CH selection process, we employed two criteria to select the CH based on depth coordination and in-cluster position. Lastly, the selected CH transmits its data towards the surface sink when the cluster area is in the transmission range. Simulations are conducted to validate the performance in terms of selected parameters. Performance results show that the E-CDBR approach achieves lower energy consumption, higher network lifetime, and less delay than existing methods.
{"title":"Energy Efficient Clustering Based Depth Coordination Routing Protocol For Underwater Wireless Sensor Networks","authors":"T. R. Chenthil, P. Jayarin","doi":"10.1109/wispnet54241.2022.9767124","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767124","url":null,"abstract":"Underwater Wireless Sensor Networks (UWSN) have emerged as a promising technology for detecting physical attributes of water such as pressure, temperature, etc. However, the dynamic conditions of water depth, energy constraints, and delay are the main challenges in the design of energy-efficient routing protocols. Hence, there is a need for a forwarder set selection with depth coordination to reduce the energy constraints of UWSN. In this work, we presented an Energy-efficient Clustering Based Depth coordination routing protocol (E-CDBR) to minimize energy consumption with less delay for UWSN. Initially, the nodes are randomly deployed, and a surface sink is positioned at the top of the underwater network area. Then a clustering approach is used to determine the optimal number of clusters before CH selection in the cluster area. In the CH selection process, we employed two criteria to select the CH based on depth coordination and in-cluster position. Lastly, the selected CH transmits its data towards the surface sink when the cluster area is in the transmission range. Simulations are conducted to validate the performance in terms of selected parameters. Performance results show that the E-CDBR approach achieves lower energy consumption, higher network lifetime, and less delay than existing methods.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116653172","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767111
Deepa Thangarasu, S. Palaniswamy, T. Rao, M. Kanagasabai, Sachin Kumar
This paper presents a dual-polarized reconfigurable MIMO antenna for IoT applications using pin diodes. The proposed antenna covers a wideband from 3.3 GHz to 6 GHz (5G band) and also switches between two resonating frequencies 2.4 GHz - Zigbee and 5.8 GHz - WLAN. However, the developed antenna achieves the gain and efficiency of about 4 dBi and 80 % respectively. The designed antenna also achieves ECC less than 0.08 and a diversity gain of around 9 dB. The antenna is modeled in Computer Simulation Tool (CST).
{"title":"An Integrated Frequency Tunable MIMO Antenna for IOT Applications","authors":"Deepa Thangarasu, S. Palaniswamy, T. Rao, M. Kanagasabai, Sachin Kumar","doi":"10.1109/wispnet54241.2022.9767111","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767111","url":null,"abstract":"This paper presents a dual-polarized reconfigurable MIMO antenna for IoT applications using pin diodes. The proposed antenna covers a wideband from 3.3 GHz to 6 GHz (5G band) and also switches between two resonating frequencies 2.4 GHz - Zigbee and 5.8 GHz - WLAN. However, the developed antenna achieves the gain and efficiency of about 4 dBi and 80 % respectively. The designed antenna also achieves ECC less than 0.08 and a diversity gain of around 9 dB. The antenna is modeled in Computer Simulation Tool (CST).","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127743839","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 : 2021-01-17DOI: 10.1109/wispnet54241.2022.9767158
R. Paropkari, Anurag Thantharate, C. Beard
5G cellular networks are being deployed all over the world and this architecture supports ultra-dense network (UDN) deployment. Small cells have a very important role in providing 5G connectivity to the end users. Exponential increases in devices, data and network demands make it mandatory for the service providers to manage handovers better, to cater to the services that a user desire. In contrast to any traditional handover improvement scheme, we develop a ‘Deep-Mobility’ model by implementing a deep learning neural network (DLNN) to manage network mobility, utilizing in-network deep learning and prediction. We use network key performance indicators (KPIs) to train our model to analyze network traffic and handover requirements. In this method, (i) RF signal conditions are continuously observed and tracked using deep learning neural networks such as the Recurrent neural network (RNN) or Long Short-Term Memory network (LSTM) and (ii) system level inputs are also considered in conjunction, to take a collective decision for a handover. We can study multiple parameters and interactions between system events along with the user mobility, which would then trigger a handoff in any given scenario. Here, we show the fundamental modeling approach and demonstrate usefulness of our model while investigating impacts and sensitivities of certain KPIs from the user equipment (UE) and network side.
{"title":"Deep-Mobility: A Deep Learning Approach for an Efficient and Reliable 5G Handover","authors":"R. Paropkari, Anurag Thantharate, C. Beard","doi":"10.1109/wispnet54241.2022.9767158","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767158","url":null,"abstract":"5G cellular networks are being deployed all over the world and this architecture supports ultra-dense network (UDN) deployment. Small cells have a very important role in providing 5G connectivity to the end users. Exponential increases in devices, data and network demands make it mandatory for the service providers to manage handovers better, to cater to the services that a user desire. In contrast to any traditional handover improvement scheme, we develop a ‘Deep-Mobility’ model by implementing a deep learning neural network (DLNN) to manage network mobility, utilizing in-network deep learning and prediction. We use network key performance indicators (KPIs) to train our model to analyze network traffic and handover requirements. In this method, (i) RF signal conditions are continuously observed and tracked using deep learning neural networks such as the Recurrent neural network (RNN) or Long Short-Term Memory network (LSTM) and (ii) system level inputs are also considered in conjunction, to take a collective decision for a handover. We can study multiple parameters and interactions between system events along with the user mobility, which would then trigger a handoff in any given scenario. Here, we show the fundamental modeling approach and demonstrate usefulness of our model while investigating impacts and sensitivities of certain KPIs from the user equipment (UE) and network side.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"90 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128936662","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：