Dr. Yusuf Perwej - Academia.edu (original) (raw)
Papers by Dr. Yusuf Perwej
International Journal of Scientific Research in Science and Technology
In general, the characteristics of false news are difficult to distinguish from those of legitima... more In general, the characteristics of false news are difficult to distinguish from those of legitimate news. Even if it is wrong, people can make money by spreading false information. A long time ago, there were fake news stories, including the one about "Bat-men on the moon" in 1835. A mechanism for fact-checking statements must be put in place, particularly those that garner thousands of views and likes before being refuted and proven false by reputable sources. Many machine learning algorithms have been used to precisely categorize and identify fake news. In this experiment, an ML classifier was employed to distinguish between fake and real news. In this study, we present a Tropical Convolutional Neural Networks (TCNNs) model-based false news identification system. Convolutional neural networks (CNNs), Gradient Boost, long short-term memory (LSTMs), Random Forest, Decision Tree (DT), Ada Boost, and attention mechanisms are just a few of the cutting-edge techniques that are...
International Journal of Scientific Research in Science, Engineering and Technology
The social media has significantly changed how we communicate and exchange information throughout... more The social media has significantly changed how we communicate and exchange information throughout time. Along with it comes the issue of fake news' quick spread, which may have detrimental effects on both people and society. Fake news has been surfacing often and in enormous quantities online for a variety of political and economic goals. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up readers' emotions. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up the feelings of readers. As an outcome, it is now extremely difficult to analyses bogus news so that the creators may verify it through data processing channels without misleading the public. It is necessary to implement a system for fact-checking claims, especially those that receive thousands of views and likes before being disputed and disproved by rel...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Currently, almost everyone spends more time on online social media platforms engaging with and ex... more Currently, almost everyone spends more time on online social media platforms engaging with and exchanging information with people from all over the world, from children to adults. Our lives are greatly influenced by social media sites like Twitter, Facebook, Instagram, and LinkedIn. The social network is evolving into a well-liked platform for connecting with individuals across the globe. Social media platforms exist as a result of the enormous connectivity and information sharing that the internet has made possible. Social media's rising popularity has had both beneficial and detrimental consequences on society. However, it also has to deal with the issue of bogus profiles. False profiles are often constructed by humans, bots, or cyborgs and are used for phishing, propagating rumors, data breaches, and identity theft. Thus, we are emphasizing in this post the significance of setting up a system that can identify false profiles on social media networks. To illustrate the suggest...
International Journal of Scientific Research in Science, Engineering and Technology
Breast cancer is becoming the leading cause of mortality among women. One of the most prevalent d... more Breast cancer is becoming the leading cause of mortality among women. One of the most prevalent diseases in women, breast cancer is brought on by a variety of clinical, lifestyle, social, and economic variables. Predictive approaches based on machine learning offer methods for diagnosing breast cancer sooner. It may be found using a variety of analytical methods, including Breast MRI, X-ray, thermography, mammograms, ultrasound, etc. The most prevalent technique for performance evaluation uses accuracy measures, and the Convolutional Neural Network (CNN) is the most accurate and widely used model for breast cancer diagnosis. The Wisconsin Breast Cancer Datasets (WBCD) were used to evaluate the suggested method. Out of a total of 569 samples, 273 samples were chosen for this experiment as the test data, while the other samples were utilized for training and validation. The review's findings showed that the Convolutional Neural Network (CNN) is the most effective and widely used m...
International Journal of Innovative Research in Computer Science & Technology
The greatest method to anticipate the future is to look at what has happened in the past. We shal... more The greatest method to anticipate the future is to look at what has happened in the past. We shall present important election behavioral predictions in this paper. This study article will focus on the data offered by Present agewise voting statistics, voter demographics, votes cast, and spatial correlation among surrounding states in order to validate that a place's exit poll data. The major goals of our paper are to first encourage voting among different age groups based on projected circumstances, and then to understand the influence of a state's neighbours. Conclusively studying the entire voting scenario of previous years, which will aid in the forecast of citizens' voting behavior in the approaching years, as well as recognizing the root cause of the weaker portions and improving upon the flaws for a better future. Our main goal is to use some current voting data from a region to train and determine the major voting population in the various states of the United Sta...
HAL (Le Centre pour la Communication Scientifique Directe), Jan 22, 2022
International Journal of Scientific Research in Science, Engineering and Technology
It has long been difficult to create a safe electronic voting system that provides the transparen... more It has long been difficult to create a safe electronic voting system that provides the transparency and flexibility provided by electronic systems, while maintaining the fairness and privacy of present voting methods. Voting, especially during elections, is a technique where participants do not trust one another since the system might be attacked not just by an outsider but also by participants themselves (voters and organizers). The traditional methods of voting systems find it challenging to maintain the characteristics of an ideal voting system since there is a chance of tampering with results and disturbing the process itself. As a result, the effectiveness of the voting system is increased by translating the characteristics of an ideal voting system into digital space. It greatly lowers the expense of the elections and the work of the inspectors. In this essay, we'll use the open-source Blockchain technology to suggest a new electronic voting system's architecture. New ...
HAL (Le Centre pour la Communication Scientifique Directe), Mar 12, 2021
International Journal of Scientific Research in Science, Engineering and Technology
A computer vision system's basic goal is to detect moving things. For many applications, the ... more A computer vision system's basic goal is to detect moving things. For many applications, the performance of these systems is insufficient. One of the key reasons is that dealing with numerous restrictions such as environmental fluctuations makes the moving object detection process harder. Motion detection is a well-known computer technology associated with computer vision and image processing that focuses on detecting objects or instances of a specific class in digital photos and videos (for example, humans, flowers, and animals). Face detection, character recognition, and vehicle calculation are just a few of the well-studied applications of object motion detection. Object detection has a wide range of applications, including retrieval and surveillance. Object counting is a step after object detection that gets more exact and robust with the help of OpenCV. For object detection and counting, OpenCV includes a number of useful techniques. Object counting has a variety of applica...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
In many places today, the world's overcrowding causes crowded conditions. Analysis of crowd a... more In many places today, the world's overcrowding causes crowded conditions. Analysis of crowd activity is a developing field of study. It is common knowledge that mob activity can forecast what might happen during an event. Crowd management could be very effective if situations like riots, mass lynchings, traffic jams, accidents, stampedes, etc. could be predicted beforehand. In this paper, we propose a new multicolumn convolutional neural network (MCNN) based technique for predicting mob behavior. The features of the incoming image are first analyzed and extracted. The approximated number of the gathering is then established, and image cropping is completed. For each area of the image, low level characteristics are retrieved. The objects in the picture are then created as density images. Using our method, the gathered characteristics and their object density maps are then linearly mapped. At last, we forecast and quantify the population using the MCNN algorithm. For the ShanghaiT...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Reinforcement learning is an area of Machine Learning. The three primary types of machine learnin... more Reinforcement learning is an area of Machine Learning. The three primary types of machine learning are supervised learning, unsupervised learning, and reinforcement learning (RL). Pre-training a model on a labeled dataset is known as supervised learning. The model is trained on unlabeled data in unsupervised learning, on the other hand. Instead of being driven by labels, RL is motivated by assessing feedback. By interacting with the environment and choosing the best course of action in each circumstance in order to maximize the reward, the agent learns the best way to solve sequential decision-making issues. The RL agent chooses how to carry out tasks on its own. Furthermore, since there are no training data, the agent learns by gaining experience. In order to make subsequent judgments, RL aids agents in efficiently interacting with their surroundings. In this essay, the state-of-the-art RL is thoroughly reviewed in the literature. Applications for reinforcement learning (RL) may be...
International Journal of Scientific Research in Science, Engineering and Technology
A recognition technique is essential in practically every industry in the current digital era. It... more A recognition technique is essential in practically every industry in the current digital era. It has several advantages and may be used for security, identification, and authentication. The relevance of access control systems based on biometrics has grown in recent years since they have the ability to address the majority of the shortcomings of existing security systems. Automated biometric systems for human identification take a measurement of the body's "signature," compare it to a database, and make an application-specific determination. These biometric methods for personal verification and identification are based on physiological or behavioral traits that are usually recognizable, despite changing over time, such as fingerprints, hand geometry, the face, voice, lip movement, gait, and iris patterns. The purpose of this study is to conduct a thorough literature review in order to pinpoint the most well-known recognition techniques, applications, and obstacles.
International Journal of Scientific Research in Science and Technology
One of the leading causes of mortality for women worldwide is breast cancer. The likelihood of br... more One of the leading causes of mortality for women worldwide is breast cancer. The likelihood of breast cancer-related mortality can be decreased by early identification and rapid treatment. Machine learning-based predictive technologies provide ways to detect breast cancer earlier. Several analytical techniques, such as breast MRI, X-ray, thermography, mammography, ultrasound, etc., may be used to find it. Accuracy metrics are the most extensively used approach for performance evaluation, and the Tropical Convolutional Neural Networks (TCNNs) model for breast cancer detection is the most precise and popular model. The proposed approach was examined using the Kaggle Breast Cancer Datasets (KBCD). The data set is partitioned into training and testing. We suggest a new class of CNNs called Tropical Convolutional Neural Networks (TCNNs), which are based on tropical convolutions and replace the multiplications and additions in traditional convolutional layers with additions and min/max op...
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), Apr 27, 2022
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Road conditions with holes are a common cause of accidents in a traffic environment. For motorcyc... more Road conditions with holes are a common cause of accidents in a traffic environment. For motorcycle riders, car drivers, and other vehicle drivers, this can be fatal. For driving comfort, transportation safety, and infrastructure integrity, road surface monitoring and maintenance are critical. As a result, by identifying pot holes on the highway, this article seeks to develop a road contour damage information system. In this work, we suggest an Android-based application for executing data collecting points for government entities such as the NHAI and municipalities, among others. To create the app, we trained a model to recognize whether or not an image has a pothole. If a pothole is detected, the image is saved on a server, where it can subsequently be retrieved by appropriate authorities for maintenance and analysis. Instead of using the classic paper pen method, government personnel can utilise this mobile app to collect data. We plan to limit the quantity of photographs a person...
International Journal of Scientific Research in Science and Technology, 2022
At the beginning and end of each session, attendance is an important aspect of the daily classroo... more At the beginning and end of each session, attendance is an important aspect of the daily classroom evaluation. When using traditional methods such as calling out roll calls or taking a student's signature, managing attendance can be a time-consuming task. The teacher normally checks it, although it's possible that a teacher will miss someone or some students' answers many times. Face recognition-based attendance system is a solution to the problem of recognizing faces for the purpose of collecting attendance by utilizing face recognition technology based on high-definition monitor video and other information technology. Instead of depending on time-consuming approaches, we present a real-time Face Recognition System for tracking student attendance in class in this work. The suggested method included identifying human faces from a webcam using the Viola-Jones technique, resizing the identified face to the desired size, and then processing the resized face using a basic Lo...
HAL (Le Centre pour la Communication Scientifique Directe), Jun 14, 2019
Emerging Trends in IoT and Computing Technologies
International Journal of Scientific Research and Management, 2021
In recent years, the Internet has become an integral element of people's everyday lifestyles ... more In recent years, the Internet has become an integral element of people's everyday lifestyles all across the world. Online criminality, on the other hand, has risen in tandem with the growth of Internet activity. Cyber security has advanced greatly in recent years in order to keep up with the rapid changes that occur in cyberspace. Cyber security refers to the methods that a country or organization can use to safeguard its products and information in cyberspace. Two decades ago, the term "cyber security" was barely recognized by the general public. Cyber security isn't just a problem that affects individuals but it also applies to an organization or a government. Everything has recently been digitized, with cybernetics employing a variety of technologies such as cloud computing, smart phones, and Internet of Things techniques, among others. Cyber-attacks are raising concerns about privacy, security, and financial compensation. Cyber security is a set of technologie...
Le Centre pour la Communication Scientifique Directe - HAL - memSIC, Mar 12, 2021
International Journal of Scientific Research in Science and Technology
In general, the characteristics of false news are difficult to distinguish from those of legitima... more In general, the characteristics of false news are difficult to distinguish from those of legitimate news. Even if it is wrong, people can make money by spreading false information. A long time ago, there were fake news stories, including the one about "Bat-men on the moon" in 1835. A mechanism for fact-checking statements must be put in place, particularly those that garner thousands of views and likes before being refuted and proven false by reputable sources. Many machine learning algorithms have been used to precisely categorize and identify fake news. In this experiment, an ML classifier was employed to distinguish between fake and real news. In this study, we present a Tropical Convolutional Neural Networks (TCNNs) model-based false news identification system. Convolutional neural networks (CNNs), Gradient Boost, long short-term memory (LSTMs), Random Forest, Decision Tree (DT), Ada Boost, and attention mechanisms are just a few of the cutting-edge techniques that are...
International Journal of Scientific Research in Science, Engineering and Technology
The social media has significantly changed how we communicate and exchange information throughout... more The social media has significantly changed how we communicate and exchange information throughout time. Along with it comes the issue of fake news' quick spread, which may have detrimental effects on both people and society. Fake news has been surfacing often and in enormous quantities online for a variety of political and economic goals. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up readers' emotions. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up the feelings of readers. As an outcome, it is now extremely difficult to analyses bogus news so that the creators may verify it through data processing channels without misleading the public. It is necessary to implement a system for fact-checking claims, especially those that receive thousands of views and likes before being disputed and disproved by rel...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Currently, almost everyone spends more time on online social media platforms engaging with and ex... more Currently, almost everyone spends more time on online social media platforms engaging with and exchanging information with people from all over the world, from children to adults. Our lives are greatly influenced by social media sites like Twitter, Facebook, Instagram, and LinkedIn. The social network is evolving into a well-liked platform for connecting with individuals across the globe. Social media platforms exist as a result of the enormous connectivity and information sharing that the internet has made possible. Social media's rising popularity has had both beneficial and detrimental consequences on society. However, it also has to deal with the issue of bogus profiles. False profiles are often constructed by humans, bots, or cyborgs and are used for phishing, propagating rumors, data breaches, and identity theft. Thus, we are emphasizing in this post the significance of setting up a system that can identify false profiles on social media networks. To illustrate the suggest...
International Journal of Scientific Research in Science, Engineering and Technology
Breast cancer is becoming the leading cause of mortality among women. One of the most prevalent d... more Breast cancer is becoming the leading cause of mortality among women. One of the most prevalent diseases in women, breast cancer is brought on by a variety of clinical, lifestyle, social, and economic variables. Predictive approaches based on machine learning offer methods for diagnosing breast cancer sooner. It may be found using a variety of analytical methods, including Breast MRI, X-ray, thermography, mammograms, ultrasound, etc. The most prevalent technique for performance evaluation uses accuracy measures, and the Convolutional Neural Network (CNN) is the most accurate and widely used model for breast cancer diagnosis. The Wisconsin Breast Cancer Datasets (WBCD) were used to evaluate the suggested method. Out of a total of 569 samples, 273 samples were chosen for this experiment as the test data, while the other samples were utilized for training and validation. The review's findings showed that the Convolutional Neural Network (CNN) is the most effective and widely used m...
International Journal of Innovative Research in Computer Science & Technology
The greatest method to anticipate the future is to look at what has happened in the past. We shal... more The greatest method to anticipate the future is to look at what has happened in the past. We shall present important election behavioral predictions in this paper. This study article will focus on the data offered by Present agewise voting statistics, voter demographics, votes cast, and spatial correlation among surrounding states in order to validate that a place's exit poll data. The major goals of our paper are to first encourage voting among different age groups based on projected circumstances, and then to understand the influence of a state's neighbours. Conclusively studying the entire voting scenario of previous years, which will aid in the forecast of citizens' voting behavior in the approaching years, as well as recognizing the root cause of the weaker portions and improving upon the flaws for a better future. Our main goal is to use some current voting data from a region to train and determine the major voting population in the various states of the United Sta...
HAL (Le Centre pour la Communication Scientifique Directe), Jan 22, 2022
International Journal of Scientific Research in Science, Engineering and Technology
It has long been difficult to create a safe electronic voting system that provides the transparen... more It has long been difficult to create a safe electronic voting system that provides the transparency and flexibility provided by electronic systems, while maintaining the fairness and privacy of present voting methods. Voting, especially during elections, is a technique where participants do not trust one another since the system might be attacked not just by an outsider but also by participants themselves (voters and organizers). The traditional methods of voting systems find it challenging to maintain the characteristics of an ideal voting system since there is a chance of tampering with results and disturbing the process itself. As a result, the effectiveness of the voting system is increased by translating the characteristics of an ideal voting system into digital space. It greatly lowers the expense of the elections and the work of the inspectors. In this essay, we'll use the open-source Blockchain technology to suggest a new electronic voting system's architecture. New ...
HAL (Le Centre pour la Communication Scientifique Directe), Mar 12, 2021
International Journal of Scientific Research in Science, Engineering and Technology
A computer vision system's basic goal is to detect moving things. For many applications, the ... more A computer vision system's basic goal is to detect moving things. For many applications, the performance of these systems is insufficient. One of the key reasons is that dealing with numerous restrictions such as environmental fluctuations makes the moving object detection process harder. Motion detection is a well-known computer technology associated with computer vision and image processing that focuses on detecting objects or instances of a specific class in digital photos and videos (for example, humans, flowers, and animals). Face detection, character recognition, and vehicle calculation are just a few of the well-studied applications of object motion detection. Object detection has a wide range of applications, including retrieval and surveillance. Object counting is a step after object detection that gets more exact and robust with the help of OpenCV. For object detection and counting, OpenCV includes a number of useful techniques. Object counting has a variety of applica...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
In many places today, the world's overcrowding causes crowded conditions. Analysis of crowd a... more In many places today, the world's overcrowding causes crowded conditions. Analysis of crowd activity is a developing field of study. It is common knowledge that mob activity can forecast what might happen during an event. Crowd management could be very effective if situations like riots, mass lynchings, traffic jams, accidents, stampedes, etc. could be predicted beforehand. In this paper, we propose a new multicolumn convolutional neural network (MCNN) based technique for predicting mob behavior. The features of the incoming image are first analyzed and extracted. The approximated number of the gathering is then established, and image cropping is completed. For each area of the image, low level characteristics are retrieved. The objects in the picture are then created as density images. Using our method, the gathered characteristics and their object density maps are then linearly mapped. At last, we forecast and quantify the population using the MCNN algorithm. For the ShanghaiT...
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Reinforcement learning is an area of Machine Learning. The three primary types of machine learnin... more Reinforcement learning is an area of Machine Learning. The three primary types of machine learning are supervised learning, unsupervised learning, and reinforcement learning (RL). Pre-training a model on a labeled dataset is known as supervised learning. The model is trained on unlabeled data in unsupervised learning, on the other hand. Instead of being driven by labels, RL is motivated by assessing feedback. By interacting with the environment and choosing the best course of action in each circumstance in order to maximize the reward, the agent learns the best way to solve sequential decision-making issues. The RL agent chooses how to carry out tasks on its own. Furthermore, since there are no training data, the agent learns by gaining experience. In order to make subsequent judgments, RL aids agents in efficiently interacting with their surroundings. In this essay, the state-of-the-art RL is thoroughly reviewed in the literature. Applications for reinforcement learning (RL) may be...
International Journal of Scientific Research in Science, Engineering and Technology
A recognition technique is essential in practically every industry in the current digital era. It... more A recognition technique is essential in practically every industry in the current digital era. It has several advantages and may be used for security, identification, and authentication. The relevance of access control systems based on biometrics has grown in recent years since they have the ability to address the majority of the shortcomings of existing security systems. Automated biometric systems for human identification take a measurement of the body's "signature," compare it to a database, and make an application-specific determination. These biometric methods for personal verification and identification are based on physiological or behavioral traits that are usually recognizable, despite changing over time, such as fingerprints, hand geometry, the face, voice, lip movement, gait, and iris patterns. The purpose of this study is to conduct a thorough literature review in order to pinpoint the most well-known recognition techniques, applications, and obstacles.
International Journal of Scientific Research in Science and Technology
One of the leading causes of mortality for women worldwide is breast cancer. The likelihood of br... more One of the leading causes of mortality for women worldwide is breast cancer. The likelihood of breast cancer-related mortality can be decreased by early identification and rapid treatment. Machine learning-based predictive technologies provide ways to detect breast cancer earlier. Several analytical techniques, such as breast MRI, X-ray, thermography, mammography, ultrasound, etc., may be used to find it. Accuracy metrics are the most extensively used approach for performance evaluation, and the Tropical Convolutional Neural Networks (TCNNs) model for breast cancer detection is the most precise and popular model. The proposed approach was examined using the Kaggle Breast Cancer Datasets (KBCD). The data set is partitioned into training and testing. We suggest a new class of CNNs called Tropical Convolutional Neural Networks (TCNNs), which are based on tropical convolutions and replace the multiplications and additions in traditional convolutional layers with additions and min/max op...
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), Apr 27, 2022
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Road conditions with holes are a common cause of accidents in a traffic environment. For motorcyc... more Road conditions with holes are a common cause of accidents in a traffic environment. For motorcycle riders, car drivers, and other vehicle drivers, this can be fatal. For driving comfort, transportation safety, and infrastructure integrity, road surface monitoring and maintenance are critical. As a result, by identifying pot holes on the highway, this article seeks to develop a road contour damage information system. In this work, we suggest an Android-based application for executing data collecting points for government entities such as the NHAI and municipalities, among others. To create the app, we trained a model to recognize whether or not an image has a pothole. If a pothole is detected, the image is saved on a server, where it can subsequently be retrieved by appropriate authorities for maintenance and analysis. Instead of using the classic paper pen method, government personnel can utilise this mobile app to collect data. We plan to limit the quantity of photographs a person...
International Journal of Scientific Research in Science and Technology, 2022
At the beginning and end of each session, attendance is an important aspect of the daily classroo... more At the beginning and end of each session, attendance is an important aspect of the daily classroom evaluation. When using traditional methods such as calling out roll calls or taking a student's signature, managing attendance can be a time-consuming task. The teacher normally checks it, although it's possible that a teacher will miss someone or some students' answers many times. Face recognition-based attendance system is a solution to the problem of recognizing faces for the purpose of collecting attendance by utilizing face recognition technology based on high-definition monitor video and other information technology. Instead of depending on time-consuming approaches, we present a real-time Face Recognition System for tracking student attendance in class in this work. The suggested method included identifying human faces from a webcam using the Viola-Jones technique, resizing the identified face to the desired size, and then processing the resized face using a basic Lo...
HAL (Le Centre pour la Communication Scientifique Directe), Jun 14, 2019
Emerging Trends in IoT and Computing Technologies
International Journal of Scientific Research and Management, 2021
In recent years, the Internet has become an integral element of people's everyday lifestyles ... more In recent years, the Internet has become an integral element of people's everyday lifestyles all across the world. Online criminality, on the other hand, has risen in tandem with the growth of Internet activity. Cyber security has advanced greatly in recent years in order to keep up with the rapid changes that occur in cyberspace. Cyber security refers to the methods that a country or organization can use to safeguard its products and information in cyberspace. Two decades ago, the term "cyber security" was barely recognized by the general public. Cyber security isn't just a problem that affects individuals but it also applies to an organization or a government. Everything has recently been digitized, with cybernetics employing a variety of technologies such as cloud computing, smart phones, and Internet of Things techniques, among others. Cyber-attacks are raising concerns about privacy, security, and financial compensation. Cyber security is a set of technologie...
Le Centre pour la Communication Scientifique Directe - HAL - memSIC, Mar 12, 2021