Pub Date : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689886
Mohammad Monirujjaman Khan, M. Hasan, M. Mahmud, Mahedi Hassan Pranto, Istiaqqe Azad, Shariar Mahmud Duke
Access to the modern health system is not prevalent in a developing country like Bangladesh. This paper aims to create an interface between pharmacists and pharmaceutical companies by building a common platform to address this limitation. We have developed an android mobile application where pharmacists can order medications from medicine companies. Pharmacists and medicine companies can register their business (Medicine Company) with this android application (app). Both users have to login to the system using their phone numbers and passwords. The system must verify whether the user is a pharmacist or a medicine company. If the pharmacist or the medicine company is already a member of this application, they access the application by logging in with their mobile number and password. They must complete the signup form as a first-time user of the application at first entry. To build an account, pharmacists and medicine companies can use their mobile numbers once. After completing the registration process, the medicine companies can add their medication to the database. The pharmacist can see several shops with different types of drugs in their windows. He or she can order medicine and make payments through the payment gateway system of the application. This android application (app) offers a faster way to order medication in remote areas. It adds a new era to the medicine business for pharmacists and medicine companies to help the needy people of our country, like Bangladesh.
{"title":"Towards the Development of a Common Platform for Pharmacists and Medicine Companies","authors":"Mohammad Monirujjaman Khan, M. Hasan, M. Mahmud, Mahedi Hassan Pranto, Istiaqqe Azad, Shariar Mahmud Duke","doi":"10.1109/ICCIT54785.2021.9689886","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689886","url":null,"abstract":"Access to the modern health system is not prevalent in a developing country like Bangladesh. This paper aims to create an interface between pharmacists and pharmaceutical companies by building a common platform to address this limitation. We have developed an android mobile application where pharmacists can order medications from medicine companies. Pharmacists and medicine companies can register their business (Medicine Company) with this android application (app). Both users have to login to the system using their phone numbers and passwords. The system must verify whether the user is a pharmacist or a medicine company. If the pharmacist or the medicine company is already a member of this application, they access the application by logging in with their mobile number and password. They must complete the signup form as a first-time user of the application at first entry. To build an account, pharmacists and medicine companies can use their mobile numbers once. After completing the registration process, the medicine companies can add their medication to the database. The pharmacist can see several shops with different types of drugs in their windows. He or she can order medicine and make payments through the payment gateway system of the application. This android application (app) offers a faster way to order medication in remote areas. It adds a new era to the medicine business for pharmacists and medicine companies to help the needy people of our country, like Bangladesh.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129452532","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689912
A. Z. Karim, Md. Sazal Miah, G. R. A. Jamal, Nusrat Jahan, Rafatul Alam Fahima, Muhammad Towhidur Rahman
Changes in illumination can substantially impact the apparent color of the skin, jeopardizing the effectiveness of any color-based segmentation method. Our solution to this problem is to use adaptive technology to generate skin color models in real-time. We employ a Viola-Jones feature-based face detector built-in MATLAB to sample faces inside a picture in a moderate-recall, high-precision configuration. We extract a set of pixels that are likely to be from skin areas from these samples. Then, filter them based on their relative luma values to remove non-skin face characteristics, producing a set of pixels. We train a unimodal Gaussian function to model the skin color in the provided image in the normalized rg color space using this representative set–a combination of the modeling strategy and color space that aids us in various ways. Subsequently, a developed function is employed for each pixel in the picture, allowing the likelihood that each pixel represents skin to be calculated. Application of a binary threshold to the computed probabilities may used to segment the skin. We discuss various current techniques in this work, detail the methodology behind our new proposed model. Moreover, provide the outcomes of its application to random photos of individuals with recognizable faces, which we found to be quite encouraging, and explores its possibilities for usage in real-time systems.
{"title":"Application of Feature based Face Detection in Adaptive Skin Pixel Identification Using Signal Processing Techniques","authors":"A. Z. Karim, Md. Sazal Miah, G. R. A. Jamal, Nusrat Jahan, Rafatul Alam Fahima, Muhammad Towhidur Rahman","doi":"10.1109/ICCIT54785.2021.9689912","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689912","url":null,"abstract":"Changes in illumination can substantially impact the apparent color of the skin, jeopardizing the effectiveness of any color-based segmentation method. Our solution to this problem is to use adaptive technology to generate skin color models in real-time. We employ a Viola-Jones feature-based face detector built-in MATLAB to sample faces inside a picture in a moderate-recall, high-precision configuration. We extract a set of pixels that are likely to be from skin areas from these samples. Then, filter them based on their relative luma values to remove non-skin face characteristics, producing a set of pixels. We train a unimodal Gaussian function to model the skin color in the provided image in the normalized rg color space using this representative set–a combination of the modeling strategy and color space that aids us in various ways. Subsequently, a developed function is employed for each pixel in the picture, allowing the likelihood that each pixel represents skin to be calculated. Application of a binary threshold to the computed probabilities may used to segment the skin. We discuss various current techniques in this work, detail the methodology behind our new proposed model. Moreover, provide the outcomes of its application to random photos of individuals with recognizable faces, which we found to be quite encouraging, and explores its possibilities for usage in real-time systems.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114729962","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689913
Md. Ibne Joha, Md. Shafiul Islam
In this modern era, internet connectivity is widespread and easily affordable. Therefore, it has become an essential part of everyday life. The Internet of Things (IoT) is a network where devices, appliances, and other items along with the sensors and software are connected to the network via the internet. This paper presents a user-friendly and straightforward approach for controlling and monitoring home appliances using the IoT-based smart multi-plug. This smart multi-plug can be accessed, monitored, and controlled through a smartphone using Wi-Fi via the smartphone Blynk framework. For this, it does not require any extra coding, irrespective of the internet connection used, making this multi-plug convenient and user-friendly. Moreover, it protects the appliances and the plugs from being damaged against overload, over-temperature. Furthermore, it offers voice command control through Google Assistant and timer setup for each plug, saving electricity, human energy, and effort.
{"title":"IoT-Based Smart Home Automation Using NodeMCU: A Smart Multi-Plug with Overload and Over Temperature Protection","authors":"Md. Ibne Joha, Md. Shafiul Islam","doi":"10.1109/ICCIT54785.2021.9689913","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689913","url":null,"abstract":"In this modern era, internet connectivity is widespread and easily affordable. Therefore, it has become an essential part of everyday life. The Internet of Things (IoT) is a network where devices, appliances, and other items along with the sensors and software are connected to the network via the internet. This paper presents a user-friendly and straightforward approach for controlling and monitoring home appliances using the IoT-based smart multi-plug. This smart multi-plug can be accessed, monitored, and controlled through a smartphone using Wi-Fi via the smartphone Blynk framework. For this, it does not require any extra coding, irrespective of the internet connection used, making this multi-plug convenient and user-friendly. Moreover, it protects the appliances and the plugs from being damaged against overload, over-temperature. Furthermore, it offers voice command control through Google Assistant and timer setup for each plug, saving electricity, human energy, and effort.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128195501","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689780
Zabir Mohammad, Israt Jahan, Md. Mohsin Kabir, M. A. Ali, M. F. Mridha
Handwritten Signature is considered one of the most effective behavioral biometrics. It plays an important role in identifying and verifying persons for banking access control, criminal investigation, legal support, etc. Since the handwritten signature is used in such a high prominence, its misuse can be dangerous. Deep learning-based verification approaches are becoming extremely popular to reduce the risk of signatures misuse. Signature verification depends on pairwise constraints to verify if the person is genuine that he/she claims to be or forged. This paper proposes an Autoembedded system that uses Deep Neural Network (DNN) with the pairwise loss for signature verification. The model either generates embedding vectors closer to zero if the input pair is in the same class or generates a value greater or equal to $alpha$ (a hyperparameter) that indicates a different class. The proposed approach uses a Siamese network that computes the pairwise distance in feature learning phase. The performance has been evaluated based on CEDAR dataset in a writer-independent (WI) context, and the experimental result shows clear distance between the genuine and forged signatures and verifies genuine ones.
{"title":"An Offline Writer-independent Signature Verification System using AutoEmbedder","authors":"Zabir Mohammad, Israt Jahan, Md. Mohsin Kabir, M. A. Ali, M. F. Mridha","doi":"10.1109/ICCIT54785.2021.9689780","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689780","url":null,"abstract":"Handwritten Signature is considered one of the most effective behavioral biometrics. It plays an important role in identifying and verifying persons for banking access control, criminal investigation, legal support, etc. Since the handwritten signature is used in such a high prominence, its misuse can be dangerous. Deep learning-based verification approaches are becoming extremely popular to reduce the risk of signatures misuse. Signature verification depends on pairwise constraints to verify if the person is genuine that he/she claims to be or forged. This paper proposes an Autoembedded system that uses Deep Neural Network (DNN) with the pairwise loss for signature verification. The model either generates embedding vectors closer to zero if the input pair is in the same class or generates a value greater or equal to $alpha$ (a hyperparameter) that indicates a different class. The proposed approach uses a Siamese network that computes the pairwise distance in feature learning phase. The performance has been evaluated based on CEDAR dataset in a writer-independent (WI) context, and the experimental result shows clear distance between the genuine and forged signatures and verifies genuine ones.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283626","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689856
Mohiuddin Ahmed, M. Islam
Breast cancer is considered the second most common reason for death among women. The gold standard for detecting breast cancer is the visual interpretation of histopathological images, but it is a complicated process that takes years of experience and a lot of skills of the pathologists. Sometimes, the limitations of the visual interpretation and the lack of experience result in the failure of diagnosing breast cancer. So, the computer-aided diagnosis (CAD) system can be taken into consideration as a helping tool to reduce the error of diagnosis of breast cancer. In this paper, a novel approach based on convolutional neural networks is introduced to classify breast cancer from the histopathological images of the breast tissues. In the clinical process of breast cancer diagnosis, pathologists examine the histopathological images of the breast tissue at different magnification levels. In this research, a single convolutional neural networks model is used to take the input of the same image with four different magnification levels parallelly. Our proposed approach outperformed existing state-of-the-art approaches by a substantial margin.
{"title":"A Multiple-Input Based Convolutional Neural Network in Breast Cancer Classification from Histopathological Images","authors":"Mohiuddin Ahmed, M. Islam","doi":"10.1109/ICCIT54785.2021.9689856","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689856","url":null,"abstract":"Breast cancer is considered the second most common reason for death among women. The gold standard for detecting breast cancer is the visual interpretation of histopathological images, but it is a complicated process that takes years of experience and a lot of skills of the pathologists. Sometimes, the limitations of the visual interpretation and the lack of experience result in the failure of diagnosing breast cancer. So, the computer-aided diagnosis (CAD) system can be taken into consideration as a helping tool to reduce the error of diagnosis of breast cancer. In this paper, a novel approach based on convolutional neural networks is introduced to classify breast cancer from the histopathological images of the breast tissues. In the clinical process of breast cancer diagnosis, pathologists examine the histopathological images of the breast tissue at different magnification levels. In this research, a single convolutional neural networks model is used to take the input of the same image with four different magnification levels parallelly. Our proposed approach outperformed existing state-of-the-art approaches by a substantial margin.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131057891","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689868
Kazi Rumman Reswan Turjo, Partho Anthony D'Costa, Surjo Bhowmick, A. Galib, Sami Raian, Mst. Shapna Akter, Nova Ahmed, M. Mahdy
Physical abuse and sexual harassment are serious issues all over the world. In Bangladesh, India, and other south Asian countries, crimes of these natures have risen to a substantial number during the past decade. We have designed an Arduino-based simple safety-vest device by using E-Textiles as pressure sensing fabric and incorporated a mobile application for women. This paper explains the details of the proposed smart device, which is cost-effective and re-usable as an undergarment, and the smartphone application with which the device is incorporated. The aim of this idea is to provide a device as a sense of protection for women at an affordable range. This smart vest has been designed by conducting various real-life experiments to make the device efficient and accurate. It has been designed with the target of commercial use. The device has also been beta-tested to get some insights from the people who will be using this cost-effective device as a sense of protection. It has eventually helped to make the vest more reliable and user-friendly for future commercialization.
{"title":"Design of Low-Cost Smart Safety Vest for the Prevention of Physical Abuse and Sexual Harassment","authors":"Kazi Rumman Reswan Turjo, Partho Anthony D'Costa, Surjo Bhowmick, A. Galib, Sami Raian, Mst. Shapna Akter, Nova Ahmed, M. Mahdy","doi":"10.1109/ICCIT54785.2021.9689868","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689868","url":null,"abstract":"Physical abuse and sexual harassment are serious issues all over the world. In Bangladesh, India, and other south Asian countries, crimes of these natures have risen to a substantial number during the past decade. We have designed an Arduino-based simple safety-vest device by using E-Textiles as pressure sensing fabric and incorporated a mobile application for women. This paper explains the details of the proposed smart device, which is cost-effective and re-usable as an undergarment, and the smartphone application with which the device is incorporated. The aim of this idea is to provide a device as a sense of protection for women at an affordable range. This smart vest has been designed by conducting various real-life experiments to make the device efficient and accurate. It has been designed with the target of commercial use. The device has also been beta-tested to get some insights from the people who will be using this cost-effective device as a sense of protection. It has eventually helped to make the vest more reliable and user-friendly for future commercialization.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114812937","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689805
M. B. Mohammed, Lubaba Salsabil, Mahir Shahriar, Sabrina Sultana Tanaaz, Ahmed Fahmin
Autism Spectrum Disorder (ASD) is a developmental disability that is likely to be perceived at a young age, persisting throughout a lifetime. The goal of this study is to detect ASD more efficiently with the use of Machine Learning methods. In our paper, we worked with the AQ-10 Adult dataset. Multiple steps have been taken to perform the data preprocessing. We have used different data synthesization techniques and a few feature selection techniques and eventually implemented them with other classifiers. Although throughout our analysis, we can see that the usage of Neural Network has some significant effect due to a smaller data set, the best-performance was provided by the combination of classifiers and feature selection methods to develop the prediction model. After evaluation, We deduced that a model with Principal Component Analysis (PCA) feature selection method using the AdaBoost classifier gave the best results.
{"title":"Identification of Autism Spectrum Disorder through Feature Selection-based Machine Learning","authors":"M. B. Mohammed, Lubaba Salsabil, Mahir Shahriar, Sabrina Sultana Tanaaz, Ahmed Fahmin","doi":"10.1109/ICCIT54785.2021.9689805","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689805","url":null,"abstract":"Autism Spectrum Disorder (ASD) is a developmental disability that is likely to be perceived at a young age, persisting throughout a lifetime. The goal of this study is to detect ASD more efficiently with the use of Machine Learning methods. In our paper, we worked with the AQ-10 Adult dataset. Multiple steps have been taken to perform the data preprocessing. We have used different data synthesization techniques and a few feature selection techniques and eventually implemented them with other classifiers. Although throughout our analysis, we can see that the usage of Neural Network has some significant effect due to a smaller data set, the best-performance was provided by the combination of classifiers and feature selection methods to develop the prediction model. After evaluation, We deduced that a model with Principal Component Analysis (PCA) feature selection method using the AdaBoost classifier gave the best results.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127135223","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689806
Subrata Kumar Das, Mohammad Zahidur Rahman
Healthcare data management has improved in the last decade with increasing data volume due to the advancement of information technologies. While the digital patient data are accessed through a bad network from a remote place, data could be altered. Any modification of transferring data over the networks may create security issues like data integrity and authentication. The solution to these security problems is significant because they may cause sensitive data loss can hamper medical diagnoses. Watermarking is an effective method to provide such data security, which has attracted the researcher’s attention with a cheaper computational cost. Different watermarking techniques had applied to secure medical data, especially for images, in the healthcare system. Watermarking text data is a task that ensures authenticity and integrity on text patient data. It has become difficult for the lack of proper techniques. This paper proposes a new watermarking approach for real-time text patient data to provide their authentication and integrity. Both robust and fragile watermarks are used to detect reliable source information and any data alternation. Experiment results show that our proposed algorithm can identify the source information correctly and provide expected accuracy against possible attacks. The proposed technique could help to serve authentic data to the recipient from the geographically trustworthy distant source without any data manipulation.
{"title":"A New Watermarking Approach for Ensuring Patient Data Authentication over a Low-quality Communication Environment","authors":"Subrata Kumar Das, Mohammad Zahidur Rahman","doi":"10.1109/ICCIT54785.2021.9689806","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689806","url":null,"abstract":"Healthcare data management has improved in the last decade with increasing data volume due to the advancement of information technologies. While the digital patient data are accessed through a bad network from a remote place, data could be altered. Any modification of transferring data over the networks may create security issues like data integrity and authentication. The solution to these security problems is significant because they may cause sensitive data loss can hamper medical diagnoses. Watermarking is an effective method to provide such data security, which has attracted the researcher’s attention with a cheaper computational cost. Different watermarking techniques had applied to secure medical data, especially for images, in the healthcare system. Watermarking text data is a task that ensures authenticity and integrity on text patient data. It has become difficult for the lack of proper techniques. This paper proposes a new watermarking approach for real-time text patient data to provide their authentication and integrity. Both robust and fragile watermarks are used to detect reliable source information and any data alternation. Experiment results show that our proposed algorithm can identify the source information correctly and provide expected accuracy against possible attacks. The proposed technique could help to serve authentic data to the recipient from the geographically trustworthy distant source without any data manipulation.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126858136","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689777
Habiba Sultana, A. Kamal
In the field of image steganography, edge detection based implantation methods play vital rules in providing stronger security of hided data. In this arena, researcher applies a suitable edge detection method to detect edge pixels in an image. Those detected pixels then conceive secret message bits. A very recent trend is to employ multiple edge detection methods to increase edge pixels in an image and thus to enhance the embedding capacity. The uses of multiple edge detectors additionally boost up the data security. Like as the demand for embedding capacity, many applications need to have the modified image, i.e., stego image, with good quality. Indeed, when the message payload is low, it will not be a better idea to finds more local pixels for embedding that small payload. Rather, the image quality will look better, visually and statistically, if we could choose a part but sufficient pixels to implant bits. In this article, we propose an algorithm that uses multiple edge detection algorithms to find edge pixels separately and then selects pixels which are common to all edges. This way, the proposed method decreases the number of embeddable pixels and thus, increases the image quality. The experimental results provide promising output.
{"title":"Image Steganography System based on Hybrid Edge Detector","authors":"Habiba Sultana, A. Kamal","doi":"10.1109/ICCIT54785.2021.9689777","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689777","url":null,"abstract":"In the field of image steganography, edge detection based implantation methods play vital rules in providing stronger security of hided data. In this arena, researcher applies a suitable edge detection method to detect edge pixels in an image. Those detected pixels then conceive secret message bits. A very recent trend is to employ multiple edge detection methods to increase edge pixels in an image and thus to enhance the embedding capacity. The uses of multiple edge detectors additionally boost up the data security. Like as the demand for embedding capacity, many applications need to have the modified image, i.e., stego image, with good quality. Indeed, when the message payload is low, it will not be a better idea to finds more local pixels for embedding that small payload. Rather, the image quality will look better, visually and statistically, if we could choose a part but sufficient pixels to implant bits. In this article, we propose an algorithm that uses multiple edge detection algorithms to find edge pixels separately and then selects pixels which are common to all edges. This way, the proposed method decreases the number of embeddable pixels and thus, increases the image quality. The experimental results provide promising output.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123283772","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689881
A. Siddika, Aifa Faruque, Abdul Kadar Muhammad Masum
Continual advancement in technology has led an initiative to the competitive environment among the institutes relating to the technological domain. The telecommunication industry is no exception in such cases. There exists immense competition among the telecom service providers for maximization of profit and expansion of market interest by attracting new clients. However, the retention of existing customers is easier and cheaper than acquiring new ones. As the customers are more concerned about the quality of services provided by the institutions it becomes challenging for companies to maintain client satisfaction. The CRM as well as analysts need to recognize the potential churners and the cause of their migration. This paper suggests a framework that employs machine learning and deep learning techniques for determining churn customers as well as distinguishes notable factors that typically govern the customer towards churn. Firstly, the classification between churn and non-churn customers is conducted utilizing both machine learning and deep learning algorithms where Random Forest achieved supremacy over others and followed by the deep learning models CNN and MLP. Besides the work deduced the significant factors affecting the churning procedure by applying Attribute Selection Techniques. The experimentation results unveil the prediction models that recognize the potential churners with optimal accuracy and the important factors that show impact over the churning of the customer. The findings acquired from this research are hoped to be lucrative for the companies in the present world for taking an effective decision and acting accurately in terms of customer retention.
{"title":"Comparative Analysis of Churn Predictive Models and Factor Identification in Telecom Industry","authors":"A. Siddika, Aifa Faruque, Abdul Kadar Muhammad Masum","doi":"10.1109/ICCIT54785.2021.9689881","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689881","url":null,"abstract":"Continual advancement in technology has led an initiative to the competitive environment among the institutes relating to the technological domain. The telecommunication industry is no exception in such cases. There exists immense competition among the telecom service providers for maximization of profit and expansion of market interest by attracting new clients. However, the retention of existing customers is easier and cheaper than acquiring new ones. As the customers are more concerned about the quality of services provided by the institutions it becomes challenging for companies to maintain client satisfaction. The CRM as well as analysts need to recognize the potential churners and the cause of their migration. This paper suggests a framework that employs machine learning and deep learning techniques for determining churn customers as well as distinguishes notable factors that typically govern the customer towards churn. Firstly, the classification between churn and non-churn customers is conducted utilizing both machine learning and deep learning algorithms where Random Forest achieved supremacy over others and followed by the deep learning models CNN and MLP. Besides the work deduced the significant factors affecting the churning procedure by applying Attribute Selection Techniques. The experimentation results unveil the prediction models that recognize the potential churners with optimal accuracy and the important factors that show impact over the churning of the customer. The findings acquired from this research are hoped to be lucrative for the companies in the present world for taking an effective decision and acting accurately in terms of customer retention.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121133445","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：