Pub Date : 2019-12-01DOI: 10.1109/ICECCO48375.2019.9043252
Muktar MT. Othman, Steve A. Adeshina, Moussa Mahamat Boukar
This study aim is to design a road anomaly transmission Algorithms using Ant Colony optimization (ACO) based Technique in a Vehicle-to-Vehicle (V2V) and Vehicle to Infrastructure (V2I) Communication. The developed VACO also uses the features of VANET to find out the optimal path by considering a minimum number of nodes and cost parameters, which provides information related to accidents, speed of neighbouring vehicle and weather to help users in making informed decisions. Vehicle routing protocol based on ACO (VACO) also ensures to mitigate issues by combining the reactive and proactive approach and considers the parameters affecting the Quality of Service (QoS) such as latency, bandwidth, and delivery ratio in evaluating the Algorithms.
{"title":"Development Of Road Anomaly Data Transmission Using Ant Colony Optimization Algorithm in a Vehicle-To-Vehicle Communication","authors":"Muktar MT. Othman, Steve A. Adeshina, Moussa Mahamat Boukar","doi":"10.1109/ICECCO48375.2019.9043252","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043252","url":null,"abstract":"This study aim is to design a road anomaly transmission Algorithms using Ant Colony optimization (ACO) based Technique in a Vehicle-to-Vehicle (V2V) and Vehicle to Infrastructure (V2I) Communication. The developed VACO also uses the features of VANET to find out the optimal path by considering a minimum number of nodes and cost parameters, which provides information related to accidents, speed of neighbouring vehicle and weather to help users in making informed decisions. Vehicle routing protocol based on ACO (VACO) also ensures to mitigate issues by combining the reactive and proactive approach and considers the parameters affecting the Quality of Service (QoS) such as latency, bandwidth, and delivery ratio in evaluating the Algorithms.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"11 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":"133171488","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/ICECCO48375.2019.9043248
Yusuf Muhammad Tukur, Yusuf Sahabi Ali
A lot of fascinating capabilities are being presented by the Internet of Things (IoT) since its inception, which has made and still makes it gather so much interest. As a result, it is being deployed in many domains and particularly in modern computation and intelligent processing demand in businesses and government organizations. Nevertheless, the IoT system has become susceptible to different physical and cyberattacks due to its widespread applications, including the insider threat which can be significantly damaging and harmful. In this work, we demonstrate the effects insider attack could have on an IoT system. We built a working IoT system prototype to measure and send environmental temperature data to an IoT platform over The Things Network gateway using LoRaWAN. We set up our experiments both indoors and outdoors and conducted successful insider attacks on the IoT system without tampering with the system components. The results show that insider threats have significant and overreaching effect on IoT system, which justifies the need to focus research on protecting the system from attacks by insiders at the perception layer, which are often successful, affect the integrity of entire system data and can be highly destructive.
{"title":"Demonstrating the Effect of Insider Attacks on Perception Layer of Internet of Things (IoT) Systems","authors":"Yusuf Muhammad Tukur, Yusuf Sahabi Ali","doi":"10.1109/ICECCO48375.2019.9043248","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043248","url":null,"abstract":"A lot of fascinating capabilities are being presented by the Internet of Things (IoT) since its inception, which has made and still makes it gather so much interest. As a result, it is being deployed in many domains and particularly in modern computation and intelligent processing demand in businesses and government organizations. Nevertheless, the IoT system has become susceptible to different physical and cyberattacks due to its widespread applications, including the insider threat which can be significantly damaging and harmful. In this work, we demonstrate the effects insider attack could have on an IoT system. We built a working IoT system prototype to measure and send environmental temperature data to an IoT platform over The Things Network gateway using LoRaWAN. We set up our experiments both indoors and outdoors and conducted successful insider attacks on the IoT system without tampering with the system components. The results show that insider threats have significant and overreaching effect on IoT system, which justifies the need to focus research on protecting the system from attacks by insiders at the perception layer, which are often successful, affect the integrity of entire system data and can be highly destructive.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"44 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":"124586183","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/ICECCO48375.2019.9043258
Ochilbek Rakhmanov
Classification of hand drawn sketches (images) reached a classification accuracy of % 77 with the latest state-of-the-art method, called Sketch-a-Net, in 2017. Most of the developed methods use image feature extractor techniques like HOG, BOVW, or CNN. In this paper, we tested the classification accuracy of hand drawn sketches with SVM and ANN, without using image feature extraction algorithms and compared the results with the findings of a number of important state-of-art researches. Our findings show that existing methods are reasonable to accept, even though the results of our experiments also produced some valuable results. We propose that our findings can serve as kind of `minimal milestone’ on future prediction experiments.
{"title":"Testing strength of the state-of-art image classification methods for hand drawn sketches","authors":"Ochilbek Rakhmanov","doi":"10.1109/ICECCO48375.2019.9043258","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043258","url":null,"abstract":"Classification of hand drawn sketches (images) reached a classification accuracy of % 77 with the latest state-of-the-art method, called Sketch-a-Net, in 2017. Most of the developed methods use image feature extractor techniques like HOG, BOVW, or CNN. In this paper, we tested the classification accuracy of hand drawn sketches with SVM and ANN, without using image feature extraction algorithms and compared the results with the findings of a number of important state-of-art researches. Our findings show that existing methods are reasonable to accept, even though the results of our experiments also produced some valuable results. We propose that our findings can serve as kind of `minimal milestone’ on future prediction experiments.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"24 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":"115961765","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/ICECCO48375.2019.9043182
Nazerke Sultanova, Gulshat Kessikbayeva, Y. Amangeldi
Natural Language models are a crucial tool in computational linguistics. They are specially difficult to build in agglutinative languages, which require attention since the words are formed by attaching sequences of different morphemes, where each morpheme can change the meaning of the word. For the mentioned type of language fixed and limited vocabulary itself can pose restrictions. The character-based solution may help to overcome the problem. However, it triggers the disambiguation of a word according to the context. The present work aims to build a character-based language model for the Kazakh Language, with the use of Deep Neural Networks, namely a Long Short-Term Memory model. The Language Model in the present research is generative and aims to produce all possible correct words within the context given. A word can be treated as a morpheme generated by characters where any possible word type could be generated. In order to understand the language model correctly, it is necessary to use data which was initially written in Kazakh and not translated from other sources. Therefore, the model will be trained using books written in Kazakh.
{"title":"Kazakh Language Open Vocabulary Language Model with Deep Neural Networks","authors":"Nazerke Sultanova, Gulshat Kessikbayeva, Y. Amangeldi","doi":"10.1109/ICECCO48375.2019.9043182","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043182","url":null,"abstract":"Natural Language models are a crucial tool in computational linguistics. They are specially difficult to build in agglutinative languages, which require attention since the words are formed by attaching sequences of different morphemes, where each morpheme can change the meaning of the word. For the mentioned type of language fixed and limited vocabulary itself can pose restrictions. The character-based solution may help to overcome the problem. However, it triggers the disambiguation of a word according to the context. The present work aims to build a character-based language model for the Kazakh Language, with the use of Deep Neural Networks, namely a Long Short-Term Memory model. The Language Model in the present research is generative and aims to produce all possible correct words within the context given. A word can be treated as a morpheme generated by characters where any possible word type could be generated. In order to understand the language model correctly, it is necessary to use data which was initially written in Kazakh and not translated from other sources. Therefore, the model will be trained using books written in Kazakh.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"15 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":"116029340","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/ICECCO48375.2019.9043275
A. Muhammad, I. H. Shanono
An important factor used in determining the crashworthiness of an automobile vehicle during impact is its strength. In designing, a car structure should have the property of protecting or reducing the level of damage done to the driver and the car body, by absorbing the impacted load and reducing the stress values. The frontal side of a car is more liable to high energy impact and deformation during a crash. This paper provides the simulation and analysis of a car frontal crash impact on different barriers using explicit dynamics in ANSYS workbench. A car body of Aluminum materials moving with an initial velocity of 35m/s is used to analyse the developed stress and deformation on impact into a steel material wall, static and a moving car having the same speed and body structure. The developed stress and deformation due to the crash for all the three scenario were plotted and analysed. The collision impact and deformation between two moving cars was found to be higher, followed by a static vehicle, and the least is with the static wall.
{"title":"Simulation of a Car crash using ANSYS","authors":"A. Muhammad, I. H. Shanono","doi":"10.1109/ICECCO48375.2019.9043275","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043275","url":null,"abstract":"An important factor used in determining the crashworthiness of an automobile vehicle during impact is its strength. In designing, a car structure should have the property of protecting or reducing the level of damage done to the driver and the car body, by absorbing the impacted load and reducing the stress values. The frontal side of a car is more liable to high energy impact and deformation during a crash. This paper provides the simulation and analysis of a car frontal crash impact on different barriers using explicit dynamics in ANSYS workbench. A car body of Aluminum materials moving with an initial velocity of 35m/s is used to analyse the developed stress and deformation on impact into a steel material wall, static and a moving car having the same speed and body structure. The developed stress and deformation due to the crash for all the three scenario were plotted and analysed. The collision impact and deformation between two moving cars was found to be higher, followed by a static vehicle, and the least is with the static wall.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"20 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":"115499127","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/ICECCO48375.2019.9043228
M. Umar, Aminu Mohammed, A. Roko, Ahmed Yusuf Tambuwal, Abdulhakeem Abdulazeez
Quality of Service (QoS) provisioning is a critical challenge in any wireless broadband (WiBB) network. LTE being a WiBB network technology aimed at providing adequate network resources for speedy transmission of applications with varying QoS requirements. It uses radio resource management (RRM) techniques such as call admission control (CAC) for resource utilization and to guarantee these QoS requirements. In this paper, a novel call admission control scheme is proposed to guarantee the QoS of calls and also increase the throughput of Real-time (RT) calls. The scheme allocates maximum bandwidth requirements to both RT and NRT calls at the point of admission. It then degrades all admitted NRT calls when a call arrives and there are insufficient resources to admit the requested call. Several simulation experiments were conducted with the aid of Vienna LTE system level simulator and the results reveal that the proposed scheme achieved superior performance in terms of throughput and blocking rate of RT traffic compared to the benchmark scheme
{"title":"QoS-Aware Call Admission Control (QA-CAC) Scheme for LTE Networks.","authors":"M. Umar, Aminu Mohammed, A. Roko, Ahmed Yusuf Tambuwal, Abdulhakeem Abdulazeez","doi":"10.1109/ICECCO48375.2019.9043228","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043228","url":null,"abstract":"Quality of Service (QoS) provisioning is a critical challenge in any wireless broadband (WiBB) network. LTE being a WiBB network technology aimed at providing adequate network resources for speedy transmission of applications with varying QoS requirements. It uses radio resource management (RRM) techniques such as call admission control (CAC) for resource utilization and to guarantee these QoS requirements. In this paper, a novel call admission control scheme is proposed to guarantee the QoS of calls and also increase the throughput of Real-time (RT) calls. The scheme allocates maximum bandwidth requirements to both RT and NRT calls at the point of admission. It then degrades all admitted NRT calls when a call arrives and there are insufficient resources to admit the requested call. Several simulation experiments were conducted with the aid of Vienna LTE system level simulator and the results reveal that the proposed scheme achieved superior performance in terms of throughput and blocking rate of RT traffic compared to the benchmark scheme","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"27 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":"115142567","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/ICECCO48375.2019.9043185
Isa Muslu, Moussa Mahamat Boukar
Many physical, engineering problems from some areas like fluid mechanics, heat transfer, rigid body dynamics and elasticity are modelled by Partial Differential Equations (PDEs). That’s why, PDEs course is the main course in the higher educations. The aim of this work is to develop an interactive digital course material for some kind of PDEs. A digital question bank is developed using Wildcard technology on the automated management system Moodle.
{"title":"Developing a Digital Interactive Course Material on Automated Management System (AMS) Moodle for Partial Differential Equations (PDEs) Course","authors":"Isa Muslu, Moussa Mahamat Boukar","doi":"10.1109/ICECCO48375.2019.9043185","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043185","url":null,"abstract":"Many physical, engineering problems from some areas like fluid mechanics, heat transfer, rigid body dynamics and elasticity are modelled by Partial Differential Equations (PDEs). That’s why, PDEs course is the main course in the higher educations. The aim of this work is to develop an interactive digital course material for some kind of PDEs. A digital question bank is developed using Wildcard technology on the automated management system Moodle.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"38 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":"115277879","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/ICECCO48375.2019.9043211
F. Shaibu, M. Uthman
The properties of radio wave propagation in feed line are studied, and the power level is examined to determine the effect of water in coaxial feed line during radio wave propagation. A 50-ohm, 3 1/8 inch coaxial feed line was connected between the BE20S solid-state transmitter of 0.5 kW step and antenna at 100m above the earth. Two cases were considered; the case of a matched feed line without water and a case of matched feed line with 25c1 of water in it. A spectrum analyzer was deployed to monitor the behavior of the wave propagation pattern during these two cases of transmission. Transmitter’s display board was used to monitor the forward and reflected power level. An increase in the forward power lead to gradual increase of reflected power during case I, compared to rapid increase in the reflected power during case II. This confirms the effect of water in feed line during radio wave propagation for VHF communication, as it rejects more of the forward power to the transmitter, which can lead to destruction of the transmitter if not shut off due to this effect.
{"title":"Empirical Study of Water Impact on Forward Signal i Feed Line for VHF Communication","authors":"F. Shaibu, M. Uthman","doi":"10.1109/ICECCO48375.2019.9043211","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043211","url":null,"abstract":"The properties of radio wave propagation in feed line are studied, and the power level is examined to determine the effect of water in coaxial feed line during radio wave propagation. A 50-ohm, 3 1/8 inch coaxial feed line was connected between the BE20S solid-state transmitter of 0.5 kW step and antenna at 100m above the earth. Two cases were considered; the case of a matched feed line without water and a case of matched feed line with 25c1 of water in it. A spectrum analyzer was deployed to monitor the behavior of the wave propagation pattern during these two cases of transmission. Transmitter’s display board was used to monitor the forward and reflected power level. An increase in the forward power lead to gradual increase of reflected power during case I, compared to rapid increase in the reflected power during case II. This confirms the effect of water in feed line during radio wave propagation for VHF communication, as it rejects more of the forward power to the transmitter, which can lead to destruction of the transmitter if not shut off due to this effect.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"67 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":"114659720","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/ICECCO48375.2019.9043186
A. P. Adedigba, Steve A. Adeshinat, A. Aibinu
Breast Cancer is one of the most diagnosed cancer and the leading cause of death among women worldwide, second only to lung cancer. Mammographic screening has been the most successful screening technology capable of detecting up to 90% of all breast cancer even before a lump growth can be felt using breast exam. However, mammogram is a low intensity image and the heterogeneous nature of breast can make healthy breast tissue appears as cancerous, this is most common among women with dense breast (aged 40-44). Thus, the sensitivity for early detection of breast cancer from mammogram has been estimated to 85-90%. This result can be improved by Deep CNN, however, to achieve good generalization, it must be train with high voluminous dataset whereas, mammographic dataset exists in smaller volume. In this paper, we present a method of training deep CNN with few datasets to achieve high training result and good generalization. An augmentation technique that increase both size and variance of the dataset is presented herewith, the augmented dataset was used to train five state of the art models. Highest training and validation accuracy (99.01% and 99.99% respectively) were achieved with DensNet. Meanwhile, SqueezeNet, a deep CNN model with fewer parameter also shows promising result, which means soon this model can be deployed into microcontroller and FPGAs for clinical applications.
{"title":"Deep Learning-based Mammogram Classification using Small Dataset","authors":"A. P. Adedigba, Steve A. Adeshinat, A. Aibinu","doi":"10.1109/ICECCO48375.2019.9043186","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043186","url":null,"abstract":"Breast Cancer is one of the most diagnosed cancer and the leading cause of death among women worldwide, second only to lung cancer. Mammographic screening has been the most successful screening technology capable of detecting up to 90% of all breast cancer even before a lump growth can be felt using breast exam. However, mammogram is a low intensity image and the heterogeneous nature of breast can make healthy breast tissue appears as cancerous, this is most common among women with dense breast (aged 40-44). Thus, the sensitivity for early detection of breast cancer from mammogram has been estimated to 85-90%. This result can be improved by Deep CNN, however, to achieve good generalization, it must be train with high voluminous dataset whereas, mammographic dataset exists in smaller volume. In this paper, we present a method of training deep CNN with few datasets to achieve high training result and good generalization. An augmentation technique that increase both size and variance of the dataset is presented herewith, the augmented dataset was used to train five state of the art models. Highest training and validation accuracy (99.01% and 99.99% respectively) were achieved with DensNet. Meanwhile, SqueezeNet, a deep CNN model with fewer parameter also shows promising result, which means soon this model can be deployed into microcontroller and FPGAs for clinical applications.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"1 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":"127407713","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/ICECCO48375.2019.9043246
J. D. Akinyemi, O. Onifade
Facial age estimation has increasingly gained attention in the Computer Vision and Image Processing research community due to its numerous applications in several domains. Thus, research efforts are still on to improve facial age estimation accuracy. One of the ways to improve facial age estimation is to strengthen the associated preprocessing stages, two of which are face detection and face alignment. In this paper, a computational method of aligning the face prior to facial age estimation is proposed. Without any form of learning, the proposed face alignment method uses trigonometric and set operations to align a given facial image and to enhance the face detection process prior to age estimation. The impact of the proposed face alignment method on facial age estimation was evaluated via experiments on two publicly available facial ageing datasets FG-NET and Lifespan datasets.
{"title":"A Computational Face Alignment Method for Improved Facial Age Estimation","authors":"J. D. Akinyemi, O. Onifade","doi":"10.1109/ICECCO48375.2019.9043246","DOIUrl":"https://doi.org/10.1109/ICECCO48375.2019.9043246","url":null,"abstract":"Facial age estimation has increasingly gained attention in the Computer Vision and Image Processing research community due to its numerous applications in several domains. Thus, research efforts are still on to improve facial age estimation accuracy. One of the ways to improve facial age estimation is to strengthen the associated preprocessing stages, two of which are face detection and face alignment. In this paper, a computational method of aligning the face prior to facial age estimation is proposed. Without any form of learning, the proposed face alignment method uses trigonometric and set operations to align a given facial image and to enhance the face detection process prior to age estimation. The impact of the proposed face alignment method on facial age estimation was evaluated via experiments on two publicly available facial ageing datasets FG-NET and Lifespan datasets.","PeriodicalId":166322,"journal":{"name":"2019 15th International Conference on Electronics, Computer and Computation (ICECCO)","volume":"235 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":"124736096","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：