Pub Date : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043264
Azamat Serek, A. Issabek, A. Bogdanchikov
Currently there are a large amount of studies conducted on the field of sentiment analysis worldwide. Due to continuous drastic increase of amount of data, all natural language processing systems require special approach oriented to it. Implementing and evaluating such mechanism was a strong incentive to conduct this research. In this paper, sentiment analysis was implemented on Kazakh language via Spark on the basis of data set taken from Kazakh books. The data was initially unbalanced. There was achieved training F1 measure over 90 %.
{"title":"Distributed sentiment analysis of an agglutinative language via Spark by applying machine learning methods","authors":"Azamat Serek, A. Issabek, A. Bogdanchikov","doi":"10.1109/ICECCO48375.2019.9043264","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043264","url":null,"abstract":"Currently there are a large amount of studies conducted on the field of sentiment analysis worldwide. Due to continuous drastic increase of amount of data, all natural language processing systems require special approach oriented to it. Implementing and evaluating such mechanism was a strong incentive to conduct this research. In this paper, sentiment analysis was implemented on Kazakh language via Spark on the basis of data set taken from Kazakh books. The data was initially unbalanced. There was achieved training F1 measure over 90 %.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130147344","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043277
H. Umar, R. Prasad, M. Fonkam
Electricity or power has become an essential service which is instrumental to many social, economic and technological developments worldwide. However, power utilities competing in emerging markets are confronted with challenges of shortfall in revenue due to collection losses known as Non-Technical losses (NTLs). Assessing and plummeting NTL to increase revenue, and reliability of the distribution of power remains a top priority for the utilities and regulators. The amount of data generated by power utilities offers exceptional opportunities owing to Machine Learning (ML) techniques to better understand the payment and consumption patterns of consumers. Consumers on the same profile can be segmented into clusters of similar behaviour through Customer segmentation. This paper applies k-means and DBSCAN clustering algorithms to segment customers by a measure of their bill payments, consumption and tariff plans then grouped into clusters. The clusters encountered, shows different categories of consumers in relation to their obligation profiles and tariff plans. K-means gives a better visualization in terms of cluster assignment. Dense clusters and outliers were viewed in DBSCAN.
{"title":"Assessing Severity of Non-technical Losses in Power using Clustering Algorithms","authors":"H. Umar, R. Prasad, M. Fonkam","doi":"10.1109/ICECCO48375.2019.9043277","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043277","url":null,"abstract":"Electricity or power has become an essential service which is instrumental to many social, economic and technological developments worldwide. However, power utilities competing in emerging markets are confronted with challenges of shortfall in revenue due to collection losses known as Non-Technical losses (NTLs). Assessing and plummeting NTL to increase revenue, and reliability of the distribution of power remains a top priority for the utilities and regulators. The amount of data generated by power utilities offers exceptional opportunities owing to Machine Learning (ML) techniques to better understand the payment and consumption patterns of consumers. Consumers on the same profile can be segmented into clusters of similar behaviour through Customer segmentation. This paper applies k-means and DBSCAN clustering algorithms to segment customers by a measure of their bill payments, consumption and tariff plans then grouped into clusters. The clusters encountered, shows different categories of consumers in relation to their obligation profiles and tariff plans. K-means gives a better visualization in terms of cluster assignment. Dense clusters and outliers were viewed in DBSCAN.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880522","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043274
Vera Ilenikhena, J. Abolarinwa, M. David
Power optimization in Device to Device networks has been studied using different approaches in literature which include allocation of resources (bandwidth and power) as well as Interference mitigation. However, in this paper, we propose a first exact modelling of several network parameters and their interaction in order to minimize the energy consumption in a Device to Device and Spectrum Sharing network. An optimization algorithm to also satisfy users with adequate quality of service while minimizing the Transmit power and achieving overall system Energy Efficiency is being proposed. With the proposed algorithm in this work, power level requirement for communication would be minimized without compromising the quality of service, therefore making the entire system energy efficient which is a metric for green communication.
{"title":"Minimizing Battery Consumption in Mobile Device To Device and Spectrum Sharing Network: An Approach","authors":"Vera Ilenikhena, J. Abolarinwa, M. David","doi":"10.1109/ICECCO48375.2019.9043274","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043274","url":null,"abstract":"Power optimization in Device to Device networks has been studied using different approaches in literature which include allocation of resources (bandwidth and power) as well as Interference mitigation. However, in this paper, we propose a first exact modelling of several network parameters and their interaction in order to minimize the energy consumption in a Device to Device and Spectrum Sharing network. An optimization algorithm to also satisfy users with adequate quality of service while minimizing the Transmit power and achieving overall system Energy Efficiency is being proposed. With the proposed algorithm in this work, power level requirement for communication would be minimized without compromising the quality of service, therefore making the entire system energy efficient which is a metric for green communication.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133266838","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043249
Salma I. Babani, C. C. Ogbaga, D. Okolo, G. Mangse
Sesamum indicum is an oil-rich plant that is moderately drought tolerant. The leaves and seeds are used for the preparation of local soups in Nigeria. There is a need to understand the traits possessed by this plant in order to improve its production in a developing country like Nigeria. In this study, the bioactive compounds and Rubisco content of the leaf and seed were investigated using standard techniques of aqueous, ethanol and DNA extractions. The leaf and seed differed in the bioactive compounds with saponins, glycosides, alkaloids, and tannins present in both samples. However, steroids and quinones were absent in both samples. The study also revealed a great variation in the Rubisco and DNA contents of the leaf and seed. Rubisco content was higher in the leaf relative to the seeds whilst DNA was lower in the leaf relative to the seeds. Overall, the study provided new insights into the bioactive compounds present in the leaf and seeds. It also showed that under normal growth conditions, there is a higher Rubisco gene in the leaf of this moderate drought tolerant plant relative to the seeds. The implications of these variations are discussed in relation to nutrition and carbon storage.
{"title":"Bioactive Compound and Rubisco Analyses of Leaf and Seed Extracts of Sesamum indicum","authors":"Salma I. Babani, C. C. Ogbaga, D. Okolo, G. Mangse","doi":"10.1109/ICECCO48375.2019.9043249","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043249","url":null,"abstract":"Sesamum indicum is an oil-rich plant that is moderately drought tolerant. The leaves and seeds are used for the preparation of local soups in Nigeria. There is a need to understand the traits possessed by this plant in order to improve its production in a developing country like Nigeria. In this study, the bioactive compounds and Rubisco content of the leaf and seed were investigated using standard techniques of aqueous, ethanol and DNA extractions. The leaf and seed differed in the bioactive compounds with saponins, glycosides, alkaloids, and tannins present in both samples. However, steroids and quinones were absent in both samples. The study also revealed a great variation in the Rubisco and DNA contents of the leaf and seed. Rubisco content was higher in the leaf relative to the seeds whilst DNA was lower in the leaf relative to the seeds. Overall, the study provided new insights into the bioactive compounds present in the leaf and seeds. It also showed that under normal growth conditions, there is a higher Rubisco gene in the leaf of this moderate drought tolerant plant relative to the seeds. The implications of these variations are discussed in relation to nutrition and carbon storage.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127462626","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043222
Asim Balarabe Yazid, J. Chijioke, Moussa Boukar Mahamat, Hamisu Ismail Ahmad, V. Anye, M. Zakariya
Pipeline vandalism has been a problem to Nigeria for many decades, Nigeria suffered loss of oil revenue as a result of lingering menace of oil pipeline and oil theft. Aside the loss of money from oil theft and leak, cost of pipeline repairs and damage to the environment and ecosystem are other devastating negative consequences posed by pipeline breaks, whether naturally occurring or caused by man. Many of the techniques proposed by researchers are infeasible and very costly. In this research, we propose a moderately cheap, environmental-friendly, and simple method of monitoring pipeline. Pipelines are independently coated using socket switching and proximity sensors. Attempts to open the enclosure or break the pipeline will first trigger the proximity sensors, which in their normal state have a HIGH signal. By triggering the alarm when there is no obstruction detected, the proximity sensors used operate in reverse. Independently, if the pipeline breaks inside an open-circuit is created which triggers the annunciator. Through the proximity sensor, this technique will be able to detect an attack before occurrence based on the notion that to access the pipeline the protective layer must first be removed. Ultimately, the real-time location of ongoing vandalism will be tracked and transmitted. The system has shown promising result in attempt to combat pipeline vandalism and oil theft.
{"title":"Real-time Pipeline Vandalism Detection Using Open-Circuit Technique","authors":"Asim Balarabe Yazid, J. Chijioke, Moussa Boukar Mahamat, Hamisu Ismail Ahmad, V. Anye, M. Zakariya","doi":"10.1109/ICECCO48375.2019.9043222","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043222","url":null,"abstract":"Pipeline vandalism has been a problem to Nigeria for many decades, Nigeria suffered loss of oil revenue as a result of lingering menace of oil pipeline and oil theft. Aside the loss of money from oil theft and leak, cost of pipeline repairs and damage to the environment and ecosystem are other devastating negative consequences posed by pipeline breaks, whether naturally occurring or caused by man. Many of the techniques proposed by researchers are infeasible and very costly. In this research, we propose a moderately cheap, environmental-friendly, and simple method of monitoring pipeline. Pipelines are independently coated using socket switching and proximity sensors. Attempts to open the enclosure or break the pipeline will first trigger the proximity sensors, which in their normal state have a HIGH signal. By triggering the alarm when there is no obstruction detected, the proximity sensors used operate in reverse. Independently, if the pipeline breaks inside an open-circuit is created which triggers the annunciator. Through the proximity sensor, this technique will be able to detect an attack before occurrence based on the notion that to access the pipeline the protective layer must first be removed. Ultimately, the real-time location of ongoing vandalism will be tracked and transmitted. The system has shown promising result in attempt to combat pipeline vandalism and oil theft.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130294088","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043188
Aisha Yahaya, Yusuf Aleshinloye Abass, Steve A. Adeshina
Agriculture is a major part of our lives as human beings. A lot of research has been carried out in order to be able to develop a monitored and controlled greenhouse system/environment that will help in solving the main problems relating to agriculture which is to enable the increase in the crops being cultivated all year round in the comfort of a small space like the home, and also to reduce human interaction in a small scale greenhouse environment. So accordingly, an automated greenhouse monitoring and control system was proposed for the sole purpose stated above. The methodology used in building the greenhouse monitoring and control system is a wired connection. The system was built using a number of connection wires, sensors, LCD, a cooling system, a power bank, LEDs, LDRs, Arduino board among a few other components. The result obtained was a fully functioning system that was set to monitor the greenhouse environment.
{"title":"Greenhouse Monitoring and Control System with an Arduino System","authors":"Aisha Yahaya, Yusuf Aleshinloye Abass, Steve A. Adeshina","doi":"10.1109/ICECCO48375.2019.9043188","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043188","url":null,"abstract":"Agriculture is a major part of our lives as human beings. A lot of research has been carried out in order to be able to develop a monitored and controlled greenhouse system/environment that will help in solving the main problems relating to agriculture which is to enable the increase in the crops being cultivated all year round in the comfort of a small space like the home, and also to reduce human interaction in a small scale greenhouse environment. So accordingly, an automated greenhouse monitoring and control system was proposed for the sole purpose stated above. The methodology used in building the greenhouse monitoring and control system is a wired connection. The system was built using a number of connection wires, sensors, LCD, a cooling system, a power bank, LEDs, LDRs, Arduino board among a few other components. The result obtained was a fully functioning system that was set to monitor the greenhouse environment.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"7 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114108804","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043205
Aliyu Abubakar, H. Ugail, A. M. Bukar, Ali Ahmad Aminu, Ahmad Musa
Burn is one of the most leading devastating injuries affecting people worldwide with high impact rate in low-and middle-income countries subjecting hundreds of thousands to loss of lives and physical deformities. Both affected individuals and health institutions are faced with challenges such as inadequate experience/well trained workforce and high diagnostics cost. The demand of having efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100% identification accuracy was recorded using ImageNet model and SVM.
{"title":"Transfer Learning Based Histopathologic Image Classification for Burns Recognition","authors":"Aliyu Abubakar, H. Ugail, A. M. Bukar, Ali Ahmad Aminu, Ahmad Musa","doi":"10.1109/ICECCO48375.2019.9043205","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043205","url":null,"abstract":"Burn is one of the most leading devastating injuries affecting people worldwide with high impact rate in low-and middle-income countries subjecting hundreds of thousands to loss of lives and physical deformities. Both affected individuals and health institutions are faced with challenges such as inadequate experience/well trained workforce and high diagnostics cost. The demand of having efficient, cost-effective and user-friendly technique to aid in addressing the problem is on the rise. Deep neural networks have recently attracted the attention of many researchers and achieved impressive results in many applications. Therefore, this paper proposed the use of off-the-shelf Convolutional Neural Network features from two ImageNet pre-trained models (GoogleNet and ResNet152), VGG-Face. The features are used to train Support Vector Machine (SVM) and Decision Tree (DT). 100% identification accuracy was recorded using ImageNet model and SVM.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"71 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114383460","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043294
E. Michael, J. Agajo, O. Osanaiye, A. M. Oyinbo
Water is essential for life. However, waste is a major problem in the world. Although, several research work have proposed the use of IoT as a solution to curb waste and achieve effective billing. However, in developing countries like Nigeria, the application of such technology is challenging since power or energy supply is often times erratic in nature. Taking Tunga Minna, Niger state Nigeria as a case study, it is observed that the rate of power outage is high. This will however, result to large loss of water consumption data that is supposed to be uploaded to the cloud via IoT platform. To reduce the level of outage, this study presents the design of a green IoT based water monitoring system for metropolitan area. The purpose of the design is to ensure minimum probability of outage. The scope of the design is limited to the hardware design. At the end, it is expected that a design with low probability of outage is achieved.
{"title":"Design Of A Green Iot Based Water Monitoring System For Metropolitan City.","authors":"E. Michael, J. Agajo, O. Osanaiye, A. M. Oyinbo","doi":"10.1109/ICECCO48375.2019.9043294","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043294","url":null,"abstract":"Water is essential for life. However, waste is a major problem in the world. Although, several research work have proposed the use of IoT as a solution to curb waste and achieve effective billing. However, in developing countries like Nigeria, the application of such technology is challenging since power or energy supply is often times erratic in nature. Taking Tunga Minna, Niger state Nigeria as a case study, it is observed that the rate of power outage is high. This will however, result to large loss of water consumption data that is supposed to be uploaded to the cloud via IoT platform. To reduce the level of outage, this study presents the design of a green IoT based water monitoring system for metropolitan area. The purpose of the design is to ensure minimum probability of outage. The scope of the design is limited to the hardware design. At the end, it is expected that a design with low probability of outage is achieved.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124391702","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043210
U. Mbanaso, V. Kulugh, J. Makinde
This paper presents the characterisation of critical infrastructures in Nigeria as an initial step towards development of a framework for the uniform designation of an infrastructure as a Critical National Information Infrastructure (CNII) in Nigeria. Notably, there is no globally acceptable criteria for the designation of an infrastructure as Critical National Infrastructure (CNI) or CNII. However, there is a consensus that CNIs are vital for a modern society, and drives economic growths and national prosperity. Although there are similarities in such infrastructures worldwide, every nation determines the value to attach to each CNI depending on its developmental goal, priorities and the level of dependency on such infrastructure. In Nigeria, there is no publicly available information on the categorisation of infrastructures as CNI or CNII. The mythological approach adopted was document scan, analysis and synthesis of publicly available information on CNI and CNII of some selected countries, followed by a comparative analysis. Five countries were selected from each of the six continents based on population size and adoption of Information and Communications Technology (ICT). The findings revealed that about 90% of the countries studied categorised energy, transportation, water, communications and health as sectors of CNI. Conceptually, based on the outcome, CNIs in Nigeria were characterised into twelve critical sectors. This initial study forms the first step towards development of a framework for the correct designation of an infrastructure as a CNII in Nigeria as opposed to arbitrary designation.
{"title":"Characterisation of Critical Infrastructure Organisation in Nigeria","authors":"U. Mbanaso, V. Kulugh, J. Makinde","doi":"10.1109/ICECCO48375.2019.9043210","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043210","url":null,"abstract":"This paper presents the characterisation of critical infrastructures in Nigeria as an initial step towards development of a framework for the uniform designation of an infrastructure as a Critical National Information Infrastructure (CNII) in Nigeria. Notably, there is no globally acceptable criteria for the designation of an infrastructure as Critical National Infrastructure (CNI) or CNII. However, there is a consensus that CNIs are vital for a modern society, and drives economic growths and national prosperity. Although there are similarities in such infrastructures worldwide, every nation determines the value to attach to each CNI depending on its developmental goal, priorities and the level of dependency on such infrastructure. In Nigeria, there is no publicly available information on the categorisation of infrastructures as CNI or CNII. The mythological approach adopted was document scan, analysis and synthesis of publicly available information on CNI and CNII of some selected countries, followed by a comparative analysis. Five countries were selected from each of the six continents based on population size and adoption of Information and Communications Technology (ICT). The findings revealed that about 90% of the countries studied categorised energy, transportation, water, communications and health as sectors of CNI. Conceptually, based on the outcome, CNIs in Nigeria were characterised into twelve critical sectors. This initial study forms the first step towards development of a framework for the correct designation of an infrastructure as a CNII in Nigeria as opposed to arbitrary designation.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115629109","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 : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043195
Omotayo Oshiga, Hussein U. Suleiman, Sadiq Thomas, P. Nzerem, Labaran Farouk, Steve A. Adeshina
We address the problem of crowd estimation in situations such as indoor events using anonymous and non-participatory CSI of WiFi Signals. Observing the great resemblance of Channel State Information (CSI, a finegrained information captured from the received Wi-Fi signal) to texture, we propose a brand-new framework based on statistical mechanics, and relying only on sets of machine learning techniques.In this paper, a framework for crowd count estimation is presented which utilizes Chebyshev filter and SVD to remove background noise in the CSI data, PCA to reduce the dimensionality of the CSI data and spectral descriptors for feature extraction. From the extracted feature, a set of classiffying algorithms are then utilised for training and testing the accuracy of our crowd estimation framework The aim of this framework to effectively and efficiently extract the channel information in WiFi signals across OFDM carriers reflected by the presence of human bodies. From the experiments conducted, we demonstrate the feasibility and efficacy of the proposed framework. Our result depict that our estimation becomes more–rather than less–accurate when the crowd count increases.
{"title":"Human Detection For Crowd Count Estimation Using CSI of WiFi Signals","authors":"Omotayo Oshiga, Hussein U. Suleiman, Sadiq Thomas, P. Nzerem, Labaran Farouk, Steve A. Adeshina","doi":"10.1109/ICECCO48375.2019.9043195","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043195","url":null,"abstract":"We address the problem of crowd estimation in situations such as indoor events using anonymous and non-participatory CSI of WiFi Signals. Observing the great resemblance of Channel State Information (CSI, a finegrained information captured from the received Wi-Fi signal) to texture, we propose a brand-new framework based on statistical mechanics, and relying only on sets of machine learning techniques.In this paper, a framework for crowd count estimation is presented which utilizes Chebyshev filter and SVD to remove background noise in the CSI data, PCA to reduce the dimensionality of the CSI data and spectral descriptors for feature extraction. From the extracted feature, a set of classiffying algorithms are then utilised for training and testing the accuracy of our crowd estimation framework The aim of this framework to effectively and efficiently extract the channel information in WiFi signals across OFDM carriers reflected by the presence of human bodies. From the experiments conducted, we demonstrate the feasibility and efficacy of the proposed framework. Our result depict that our estimation becomes more–rather than less–accurate when the crowd count increases.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125422191","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：