Pub Date : 2020-10-13DOI: 10.5121/csit.2020.101910
Pamely Zantou, Ange Mikaël Mousse, B. Atohoun
Visually impaired people need help to travel safely. To make this possible, many travel aids have been designed. Among them, the cane which is considered as a symbol of visual deficiency in the whole world. In this work, we build an electronic white cane using sensors' technology. This intelligent cane detects obstacles within 2m on the ground or in height, and sends vocal instructions via a Bluetooth headset. We have also built a mobile application to track in real time the visually impaired and a WEB application to control the access to the mobile one. We use ultrasound, IR sensors and a raspberry pi to process data. We use Python as programming language for electronic devices. The mobile application is Android. Though, the WEB application is a REST API developed using Python and Java Script.
{"title":"An Intelligent based System for Blind People Monitoring in a Smart Home","authors":"Pamely Zantou, Ange Mikaël Mousse, B. Atohoun","doi":"10.5121/csit.2020.101910","DOIUrl":"https://doi.org/10.5121/csit.2020.101910","url":null,"abstract":"Visually impaired people need help to travel safely. To make this possible, many travel aids have been designed. Among them, the cane which is considered as a symbol of visual deficiency in the whole world. In this work, we build an electronic white cane using sensors' technology. This intelligent cane detects obstacles within 2m on the ground or in height, and sends vocal instructions via a Bluetooth headset. We have also built a mobile application to track in real time the visually impaired and a WEB application to control the access to the mobile one. We use ultrasound, IR sensors and a raspberry pi to process data. We use Python as programming language for electronic devices. The mobile application is Android. Though, the WEB application is a REST API developed using Python and Java Script.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43646992","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 : 2020-09-26DOI: 10.5121/CSIT.2020.101105
S. Ghose, Suhrid Datta
The pandemic of COVID-19 has been rapidly spreading across the globe since it first surfaced in the Wuhan province of China. Several governments are forced to have nationwide lockdowns due to the progressive increase in a daily number of cases. The hospitals and other medical facilities are facing difficulties to cope with the overwhelming number of patients they can provide support due to the shortage in the number of required medical professionals and resources for meeting this demand. While the vaccine to cure this disease is still on the way, early diagnosis of patients and putting them in quarantine has become a cumbersome task too. In this study, we propose to build an artificial intelligence-based system for classifying patients as COVID-19 positive or negative within a few seconds by using their chest CT Scans. We use a transfer learning approach to build our classifier model using a dataset obtained from openly available sources. This work is meant to assist medical professionals in saving hours of their time for the diagnosis of the Coronavirus using chest radiographs and not intended to be the sole way of diagnosis.
{"title":"Covid CT Net: A Transfer Learning Approach for Identifying Corona Virus from CT Scans","authors":"S. Ghose, Suhrid Datta","doi":"10.5121/CSIT.2020.101105","DOIUrl":"https://doi.org/10.5121/CSIT.2020.101105","url":null,"abstract":"The pandemic of COVID-19 has been rapidly spreading across the globe since it first surfaced in the Wuhan province of China. Several governments are forced to have nationwide lockdowns due to the progressive increase in a daily number of cases. The hospitals and other medical facilities are facing difficulties to cope with the overwhelming number of patients they can provide support due to the shortage in the number of required medical professionals and resources for meeting this demand. While the vaccine to cure this disease is still on the way, early diagnosis of patients and putting them in quarantine has become a cumbersome task too. In this study, we propose to build an artificial intelligence-based system for classifying patients as COVID-19 positive or negative within a few seconds by using their chest CT Scans. We use a transfer learning approach to build our classifier model using a dataset obtained from openly available sources. This work is meant to assist medical professionals in saving hours of their time for the diagnosis of the Coronavirus using chest radiographs and not intended to be the sole way of diagnosis.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44267924","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 : 2020-09-26DOI: 10.5121/CSIT.2020.101116
Motoki Seguchi, F. Harada, H. Shimakawa
{"title":"Non-Negative Matrix Factorization of Story Watching Time of Tourists for Best Sightseeing Spot and Preference","authors":"Motoki Seguchi, F. Harada, H. Shimakawa","doi":"10.5121/CSIT.2020.101116","DOIUrl":"https://doi.org/10.5121/CSIT.2020.101116","url":null,"abstract":"","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42269441","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 : 2020-07-11DOI: 10.5121/csit.2020.100910
Bolanle F. Oladejo, Oladejo Olajide Ademola
Plant disease detection and classification have undergone successful researches using Convolutional Neural Network (CNN); however, due to the intrinsic inability of max pooling layer in CNN, it fails to capture the pose, view and orientation of images. It also requires large training data and fails to learn the spatial relationship of the features in an object. Thus, Capsule Network (CapsNet) is a novel deep learning model proposed to overcome the shortcomings of CNN. We developed an optimized Capsule Network model for classification problem using banana leaf diseases as a case study. The two dataset classes include Bacterial Wilt and Black Sigatoka, with healthy leaves. The developed model adequately classified the banana bacterial wilt, black sigatoka and healthy leaves with a test accuracy of 95%. Its outperformed three variants of CNN architectures implemented (a trained CNN model from scratch, LeNet5 and ResNet50) with respect to rotation invariance.
{"title":"Automated Classification of Banana Leaf Diseases using an Optimized Capsule Network Model","authors":"Bolanle F. Oladejo, Oladejo Olajide Ademola","doi":"10.5121/csit.2020.100910","DOIUrl":"https://doi.org/10.5121/csit.2020.100910","url":null,"abstract":"Plant disease detection and classification have undergone successful researches using Convolutional Neural Network (CNN); however, due to the intrinsic inability of max pooling layer in CNN, it fails to capture the pose, view and orientation of images. It also requires large training data and fails to learn the spatial relationship of the features in an object. Thus, Capsule Network (CapsNet) is a novel deep learning model proposed to overcome the shortcomings of CNN. We developed an optimized Capsule Network model for classification problem using banana leaf diseases as a case study. The two dataset classes include Bacterial Wilt and Black Sigatoka, with healthy leaves. The developed model adequately classified the banana bacterial wilt, black sigatoka and healthy leaves with a test accuracy of 95%. Its outperformed three variants of CNN architectures implemented (a trained CNN model from scratch, LeNet5 and ResNet50) with respect to rotation invariance.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":"91 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80567947","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 : 2020-06-20DOI: 10.5121/csit.2020.100704
Bingzhang Hu, Y. Guan
{"title":"A Self-Attentional Auto Encoder based Intrusion Detection System","authors":"Bingzhang Hu, Y. Guan","doi":"10.5121/csit.2020.100704","DOIUrl":"https://doi.org/10.5121/csit.2020.100704","url":null,"abstract":"","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85323011","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 : 2020-06-20DOI: 10.5121/csit.2020.100701
Ouiem Bchir
This research aims to separate the hands from the background of colored images representing the Arabic Sign language alphabet gestures. This hand segmentation task is one of the main challenges of image based Sign language recognition systems due to the issue of skin tones variations and the complexity of the background. For this purpose, an efficient system that segment the hand object and separate it from the rest of the image based on deep learning is investigated. More specifically, the DeepLab v3+ network architecture that is a combination of spatial pyramid pooling module and encode-decoder structure will be trained to learn the visual characteristics of the hand and segment it with detailed boundaries. The effectiveness of the proposed solution is investigated on a large dataset of size 12000 with an accuracy of 98%, an IoU of 93% of and BF score of 87%.
{"title":"Hand Segmentation for Arabic Sign Language Alphabet Recognition","authors":"Ouiem Bchir","doi":"10.5121/csit.2020.100701","DOIUrl":"https://doi.org/10.5121/csit.2020.100701","url":null,"abstract":"This research aims to separate the hands from the background of colored images representing the Arabic Sign language alphabet gestures. This hand segmentation task is one of the main challenges of image based Sign language recognition systems due to the issue of skin tones variations and the complexity of the background. For this purpose, an efficient system that segment the hand object and separate it from the rest of the image based on deep learning is investigated. More specifically, the DeepLab v3+ network architecture that is a combination of spatial pyramid pooling module and encode-decoder structure will be trained to learn the visual characteristics of the hand and segment it with detailed boundaries. The effectiveness of the proposed solution is investigated on a large dataset of size 12000 with an accuracy of 98%, an IoU of 93% of and BF score of 87%.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83514918","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}
Today very important means of communication is the e-mail that allows people all over the world to communicate, share data, and perform business. Yet there is nothing worse than an inbox full of spam; i.e., information crafted to be delivered to a large number of recipients against their wishes. In this paper, we present a numerous anti-spam methods and solutions that have been proposed and deployed, but they are not effective because most mail servers rely on blacklists and rules engine leaving a big part on the user to identify the spam, while others rely on filters that might carry high false positive rate.
{"title":"A Survey On Image Spam Detection Techniques","authors":"S. Khawandi, Firas Abdallah, Anis Ismail","doi":"10.5121/CSIT.2019.90102","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90102","url":null,"abstract":"Today very important means of communication is the e-mail that allows people all over the world to communicate, share data, and perform business. Yet there is nothing worse than an inbox full of spam; i.e., information crafted to be delivered to a large number of recipients against their wishes. In this paper, we present a numerous anti-spam methods and solutions that have been proposed and deployed, but they are not effective because most mail servers rely on blacklists and rules engine leaving a big part on the user to identify the spam, while others rely on filters that might carry high false positive rate.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42467691","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}
CAPTCHA is almost a standard security technology, and has found widespread application in commercial websites. There are two types: labeling and image based CAPTCHAs. To date, almost all CAPTCHA designs are labeling based. Labeling based CAPTCHAs refer to those that make judgment based on whether the question “what is it?” has been correctly answered. Essentially in Artificial Intelligence (AI), this means judgment depends on whether the new label provided by the user side matches the label already known to the server. Labeling based CAPTCHA designs have some common weaknesses that can be taken advantage of attackers. First, the label set, i.e., the number of classes, is small and fixed. Due to deformation and noise in CAPTCHAs, the classes have to be further reduced to avoid confusion. Second, clean segmentation in current design, in particular character labeling based CAPTCHAs, is feasible. The state of the art of CAPTCHA design suggests that the robustness of character labeling schemes should rely on the difficulty of finding where the character is (segmentation), rather than which character it is (recognition). However, the shapes of alphabet letters and numbers have very limited geometry characteristics that can be used by humans to tell them yet are also easy to be indistinct. Image recognition CAPTCHAs faces many potential problems which have not been fully studied. It is difficult for a small site to acquire a large dictionary of images which an attacker does not have access to and without a means of automatically acquiring new labeled images, an image based challenge does not usually meet the definition of a CAPTCHA. They are either unusable or prone to attacks. In this paper, we present the different types of CAPTCHAs trying to defeat advanced computer programs or bots, discussing the limitations and drawbacks of each.
{"title":"A Survey On The Different Implemented Captchas","authors":"S. Khawandi, Firas Abdallah, Anis Ismail","doi":"10.5121/CSIT.2019.90101","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90101","url":null,"abstract":"CAPTCHA is almost a standard security technology, and has found widespread application in commercial websites. There are two types: labeling and image based CAPTCHAs. To date, almost all CAPTCHA designs are labeling based. Labeling based CAPTCHAs refer to those that make judgment based on whether the question “what is it?” has been correctly answered. Essentially in Artificial Intelligence (AI), this means judgment depends on whether the new label provided by the user side matches the label already known to the server. Labeling based CAPTCHA designs have some common weaknesses that can be taken advantage of attackers. First, the label set, i.e., the number of classes, is small and fixed. Due to deformation and noise in CAPTCHAs, the classes have to be further reduced to avoid confusion. Second, clean segmentation in current design, in particular character labeling based CAPTCHAs, is feasible. The state of the art of CAPTCHA design suggests that the robustness of character labeling schemes should rely on the difficulty of finding where the character is (segmentation), rather than which character it is (recognition). However, the shapes of alphabet letters and numbers have very limited geometry characteristics that can be used by humans to tell them yet are also easy to be indistinct. Image recognition CAPTCHAs faces many potential problems which have not been fully studied. It is difficult for a small site to acquire a large dictionary of images which an attacker does not have access to and without a means of automatically acquiring new labeled images, an image based challenge does not usually meet the definition of a CAPTCHA. They are either unusable or prone to attacks. In this paper, we present the different types of CAPTCHAs trying to defeat advanced computer programs or bots, discussing the limitations and drawbacks of each.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46175217","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}
A growing popularity of smart devices of various type, shape and form factor with multitude of applications from diverse categories and data are used to meet the demands of users in their digitally enriched living environment. The data sharing between these applications would be beneficial to the users when these heterogeneous devices are used together by them in their home network. The inter-application communication enables an application to discover, connect and share data with other applications across heterogeneous devices in a home network. This paper provides a prototype implementation of the inter-application communication in a home network along with a brief summary about its demand in near future.
{"title":"Inter-Application Communication: A Prototype Implementation","authors":"K. Arunachalam, G. Ganapathy","doi":"10.5121/csit.2019.90103","DOIUrl":"https://doi.org/10.5121/csit.2019.90103","url":null,"abstract":"A growing popularity of smart devices of various type, shape and form factor with multitude of applications from diverse categories and data are used to meet the demands of users in their digitally enriched living environment. The data sharing between these applications would be beneficial to the users when these heterogeneous devices are used together by them in their home network. The inter-application communication enables an application to discover, connect and share data with other applications across heterogeneous devices in a home network. This paper provides a prototype implementation of the inter-application communication in a home network along with a brief summary about its demand in near future.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44917096","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}
{"title":"Magnetic Anomalies Due To 2-D Cylindrical Structures - An Artificial Neural Network Based Inversion","authors":"Bhagwan Das Mamidala, S. Narasimman","doi":"10.5121/csit.2019.90105","DOIUrl":"https://doi.org/10.5121/csit.2019.90105","url":null,"abstract":"","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42933596","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：