Dr. SUJEET MORE | Trinity College of Engineering and Research (original) (raw)

Papers by Dr. SUJEET MORE

Industrial Engineering Journal, 2024

The hand gesture recognition project aims to develop a real-time system capable of detecting and ... more The hand gesture recognition project aims to develop a real-time system capable of detecting and recognizing hand gestures from a video stream captured by a webcam. The system utilizes the MediaPipe and OpenCV libraries for hand tracking and gesture recognition. The project involves capturing video frames from the webcam, preprocessing the frames, detecting hand landmarks using MediaPipe, and recognizing specific gestures based on the detected landmarks. Once a gesture is recognized, the system displays the corresponding text overlay on the video frame using OpenCV. The project is designed to provide a user-friendly interface for interpreting hand gestures, enabling applications such as gesture-based control systems, sign language translation, and interactive user interfaces. OpenCV is a widely used open-source computer vision and machine learning software library. It provides a wide range of functionalities for image and video processing, MediaPipe is an open-source framework for building multimodal (e.g., video, audio) applied ML pipelines. It provides ready-to-use ML solutions for various tasks.

Industrial Engineering Journal, 2024

Personalized e-learning systems powered by AI represent a transformative approach to education. T... more Personalized e-learning systems powered by AI represent a transformative approach to education. These systems aim to revolutionize traditional learning by tailoring the experience for individual students. By leveraging AI, data analytics, and natural language processing, these systems dynamically adjust learning paths, conduct assessments, and provide immediate feedback. This reshapes the educational paradigm. Personalized e-learning systems create interactive and collaborative learning environments. This promotes engagement between peers and sharing of knowledge. By encouraging natural language interactions and social learning, these systems enhance the effectiveness of instruction and deepen understanding. The research emphasizes the need to customize learning to cater to diverse student needs, considering their skills, speed, and learning styles. Through exploring intelligent tutoring systems, adaptive learning methodologies, and self-regulated learning principles, the paper elucidates the complexities of personalized education. These AI-powered e-learning systems hold the potential to revolutionize the way we learn and educate ourselves.

Industrial Engineering Journal, 2024

Brain tumors are a significant health concern globally, with early and accurate detection being c... more Brain tumors are a significant health concern globally, with early and accurate detection being critical for effective treatment and improved patient outcomes. This paper presents an innovative approach for brain tumor detection and classification using a two-level diagnosis system. The proposed system combines advanced medical imaging techniques with artificial intelligence algorithms to enhance the accuracy and efficiency of brain tumor diagnosis. Furthermore, the proposed system incorporates an expert system that integrates medical knowledge and decision-making rules. The expert system refines the diagnosis results by considering additional clinical parameters, patient history, and expert opinions, ensuring a comprehensive and accurate diagnosis. This research contributes significantly to the field of medical imaging and artificial intelligence, offering a robust and reliable solution for brain tumor detection and classification. The proposed system has the potential to revolutionize clinical practices, leading to early diagnosis, personalized treatment plans, and ultimately, improved outcomes for patients with brain tumors.

Industrial Engineering Journal, 2024

Brain tumors are a significant health concern globally, with early and accurate detection being c... more Brain tumors are a significant health concern globally, with early and accurate detection being critical for effective treatment and improved patient outcomes. This paper presents an innovative approach for brain tumor detection and classification using a two-level diagnosis system. The proposed system combines advanced medical imaging techniques with artificial intelligence algorithms to enhance the accuracy and efficiency of brain tumor diagnosis. Furthermore, the proposed system incorporates an expert system that integrates medical knowledge and decision-making rules. The expert system refines the diagnosis results by considering additional clinical parameters, patient history, and expert opinions, ensuring a comprehensive and accurate diagnosis. This research contributes significantly to the field of medical imaging and artificial intelligence, offering a robust and reliable solution for brain tumor detection and classification. The proposed system has the potential to revolutionize clinical practices, leading to early diagnosis, personalized treatment plans, and ultimately, improved outcomes for patients with brain tumors.

Industrial Engineering Journal, 2024

Our project discusses a proposed solution for tracking a person's emotions using a network of cam... more Our project discusses a proposed solution for tracking a person's emotions using a network of cameras and adjusting lighting, music, and ambiance accordingly to improve their mood. It also mentions the use of computer vision and machine learning for facial expression recognition. Another aspect involves creating a mood-based music player that recommends songs based on the user's mood in real-time, enhancing customer satisfaction. The project highlights the growing importance of music in people's lives and the need for improved music emotion recognition methods using an artificial bee colony algorithm to enhance the structure of neural networks and achieve better recognition results and faster processing.

International Journal of Data Science and Analytics, Dec 6, 2023

As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networ... more As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networks-based IoT, a plethora of IoT mobile devices (IMD) must contend with the increasing processing demands of time-critical tasks. The dynamic nature of the environment raises novel challenges for networks that use mobile edge computing. As a proactive response to these issues, the concept of ultra-dense IoT with Mobile Edge Computing has emerged. Within this architecture, Integrated Mobile Devices (IMDs) can save power and preserve their internal processing resources by offloading compute-intensive tasks to servers located at the network's periphery (the "edge"). Nevertheless, the increased efficiency comes at the cost of greater transmission overhead, leading to an elevated delay. To achieve an ideal equilibrium between energy preservation and latency reduction, we propose a new optimization problem that focuses on minimizing both energy utilization and latency in ultra-dense IoT networks with multiple users and tasks. This issue entails the complex optimization of concurrent user (IMD) associations, computation offloading decisions, and resource allocations. To achieve a fair distribution of network load and maximize the utilization of computational resources, we integrate multi-step computation offloading methodologies into the issue formulation. Finally, the Adaptive Particle Swarm Optimization (PSO) technique is utilized as an intelligent way of solving the problem. Significantly, our methodology exhibits a noteworthy improvement over traditional Particle Swarm Optimization (PSO) techniques, resulting in a substantial decrease in overall expenses, encompassing reductions that span from 20 to 65%.

International Journal of Advanced Research in Science, Communication and Technology, May 25, 2024

Zenodo (CERN European Organization for Nuclear Research), Mar 16, 2023

Simply put, a blockchain is a distributed database or public ledger of all digital transactions o... more Simply put, a blockchain is a distributed database or public ledger of all digital transactions or events that occur and are shared between participating parties. Blockchains are used in cryptocurrencies such as Bitcoin and Ethereum. After unanimous approval of the vast majority of users connected to the system, every transaction recorded in the public registry is considered duly verified. Once the information is added to the system, it cannot be deleted. Blockchain maintains an immutable and verifiable record of every transaction that has taken place in cryptocurrency history. Bitcoin is the best-known application of blockchain technology today. Bitcoin is a peer-to-peer digital currency that operates without the need for a central authority. On the other hand, the blockchain technology that underpins Bitcoin has proven to work flawlessly and is used for various purposes in the financial and non-financial sectors of the global economy. The main hypothesis behind this research is that blockchain technology has the potential to facilitate the attainment of decentralized consensus in the context of digital and online interactions. Participating organizations have the opportunity to know beyond doubt that a particular digital event has occurred as a result of the development of an indisputable record in a public ledger. This can be achieved by following the steps outlined in the previous sentence. It opens the door to the transition from a centralized digital economy to a democratic, open and scalable economy. With the potential to completely change the game, this technology is just beginning, ushering in an era of game-changing changes that open up countless possibilities. This white paper provides an introduction to blockchain technology and a fascinating array of specific applications in finance and other industries. Below, we look at the frontline challenges and business opportunities that exist in this fundamental technology that will dramatically revolutionize our digital world. Simply put, a blockchain is a distributed database or public ledger of all digital transactions or events that occur and are shared between participating parties. Blockchains are used in cryptocurrencies such as Bitcoin and Ethereum. After unanimous approval of the vast majority of users connected to the system, every transaction recorded in the public registry is considered duly verified. Once the information is added to the system, it cannot be deleted. Blockchain maintains an immutable and verifiable record of every transaction that has taken place in cryptocurrency history. Bitcoin is the best-known application of blockchain technology today. Bitcoin is a peer-to-peer digital currency xvi | P a g e that operates without the need for a central authority. On the other hand, the blockchain technology that underpins Bitcoin has proven to work flawlessly and is used for various purposes in the financial and non-financial sectors of the global economy. The main hypothesis behind this research is that blockchain technology has the potential to facilitate the attainment of decentralized consensus in the context of digital and online interactions. Participating organizations have the opportunity to know beyond doubt that a particular digital event has occurred as a result of the development of an indisputable record in a public ledger. This can be achieved by following the steps outlined in the previous sentence. It opens the door to the transition from a centralized digital economy to a democratic, open and scalable economy. With the potential to completely change the game, this technology is just beginning, ushering in an era of game-changing changes that open up countless possibilities. This white paper provides an introduction to blockchain technology and a fascinating array of specific applications in finance and other industries. Below, we look at the frontline challenges and business opportunities that exist in this fundamental technology that will dramatically revolutionize our digital world.

Industrial Engineering Journal, 2024

Health has been the primary area of interest in human welfare, especially fetal health. Fetal hea... more Health has been the primary area of interest in human welfare, especially fetal health. Fetal heart abnormalities are the most widespread congenital anomaly that leads to the cause of infant mortality related to congenital disabilities. Several techniques have come into existence for this purpose. The deformed heart can be differentiated from the normal heart based on several parameters such as the size of auricles, ventricles, valve and position of heart, area, circumference, and perimeter. One of the methods to detect the anomalies in fetal heart is by applying advanced Image Processing techniques to enhance the properties of the image that could improve the performance of the artificial intelligence algorithms. This proposed system is the primary framework for diagnosing the prenatal ventricular septal defects (PVSD). The first step is to denoise the US images using enhanced anisotropic diffusion Enhanced Perona Malik Filter (EPMF), followed by K-means clustering segmentation method as the second step, and finally, VGG-16 architecture was implemented with the pre-trained weights from the database. The original image is compared with the reference image in terms of different parameters using a VGG16 deep learning algorithm to predict PVSD anomalies at the early stage of pregnancy. VGG-16 is the first attempt to diagnose prenatal ventricular septal defects to achieve an accuracy of 90%. This proposed system will give a second opinion for the doctors in diagnosing the abnormalities at the early stages.

Industrial Engineering Journal, 2024

OpenAI created and published ChatGPT, an AI chatbot, in November 2022. It was produced using supe... more OpenAI created and published ChatGPT, an AI chatbot, in November 2022. It was produced using supervised and reinforcement learning approaches and is built on top of OpenAI's GPT-3.5 and GPT-4 families of big language models. With the creation of artificial intelligence, a new era in computer science has dawned. The sigmoid curve is frequently used to analyze innovative technology, with a sluggish take off when a new technology is invented, followed by a quick speed of development dependent on how advantageous it is. This is true despite the fact that artificial intelligence was created in 1950 by John McCarthy, who is now regarded as its founder, and earlier by Alan Turning, who examined its mathematical implications. As a result, technology develops as more people use it. We believe that AI will mark the beginning of an entirely novel sigmoid curve. Following the maturity of ChatGPT, computational intelligence has now achieved a new height. AI is now growing at a 21% annual rate, establishing an entirely novel market in this extremely competitive sector. The ChatGPT characteristics, paradigm, and data analysis procedure were all represented in this work.

Springer, 2023

As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networ... more As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networks-based IoT, a plethora of IoT mobile devices (IMD) must contend with the increasing processing demands of time-critical tasks. The dynamic nature of the environment raises novel challenges for networks that use mobile edge computing. As a proactive response to these issues, the concept of ultra-dense IoT with Mobile Edge Computing has emerged. Within this architecture, Integrated Mobile Devices (IMDs) can save power and preserve their internal processing resources by offloading compute-intensive tasks to servers located at the network's periphery (the "edge"). Nevertheless, the increased efficiency comes at the cost of greater transmission overhead, leading to an elevated delay. To achieve an ideal equilibrium between energy preservation and latency reduction, we propose a new optimization problem that focuses on minimizing both energy utilization and latency in ultra-dense IoT networks with multiple users and tasks. This issue entails the complex optimization of concurrent user (IMD) associations, computation offloading decisions, and resource allocations. To achieve a fair distribution of network load and maximize the utilization of computational resources, we integrate multi-step computation offloading methodologies into the issue formulation. Finally, the Adaptive Particle Swarm Optimization (PSO) technique is utilized as an intelligent way of solving the problem. Significantly, our methodology exhibits a noteworthy improvement over traditional Particle Swarm Optimization (PSO) techniques, resulting in a substantial decrease in overall expenses, encompassing reductions that span from 20 to 65%.

2023 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)

Knee Magnetic Resonance Images

With the character of low maintenance, cloud computing provides an economical and efficient solut... more With the character of low maintenance, cloud computing provides an economical and efficient solution for sharing group resource among cloud users. Unfortunately, sharing data in a multi-owner manner while preserving data and identity privacy from an un trusted cloud is still a challenging issue, due to the frequent change of the membership. A secure multi owner data sharing scheme, named Mona, for dynamic groups in the cloud is proposed. By leveraging group signature and dynamic broadcast encryption techniques, any cloud user can anonymously share data with others. Meanwhile, the storage overhead and encryption computation cost of our scheme are independent with the number of revoked users. In addition, to it analyzing the security of the scheme with rigorous proofs, and demonstrate the efficiency of the scheme in the experiments.

Complexity, 2020

Magnetic resonance imaging (MRI) is precise and efficient for interpreting the soft and hard tiss... more Magnetic resonance imaging (MRI) is precise and efficient for interpreting the soft and hard tissues. Moreover, for the detailed diagnosis of varied diseases such as knee rheumatoid arthritis (RA), segmentation of the knee magnetic resonance image is a challenging and complex task that has been explored broadly. However, the accuracy and reproducibility of segmentation approaches may require prior extraction of tissues from MR images. The advances in computational methods for segmentation are reliant on several parameters such as the complexity of the tissue, quality, and acquisition process involved. This review paper focuses and briefly describes the challenges faced by segmentation techniques from magnetic resonance images followed by an overview of diverse categories of segmentation approaches. The review paper also focuses on automatic approaches and semiautomatic approaches which are extensively used with performance metrics and sufficient achievement for clinical trial assist...

International Journal of Innovative Technology and Exploring Engineering, 2020

The explosion of numerous medical images lead to the development of many different techniques to ... more The explosion of numerous medical images lead to the development of many different techniques to provide an accurate result. Although the signal to noise ratio (SNR), resolution and speed of magnetic resonance imaging technology have increased, still magnetic resonance images are affected by noise, contrast, and artifacts. To provide the image content or features relevant to diagnosis, contrast enhancement and reduction of noise with preservation of actual content should be carried out. The purpose of this paper is to present a critical review of different types of noises with an overview of diverse techniques for denoising and contrast enhancement for magnetic resonance images and discuss the advantages and limitations of these techniques with broad ideology

International Journal of Advanced Trends in Computer Science and Engineering, 2019

Traditionally methods developed for agriculture focused on the specific functionality/ domain-dep... more Traditionally methods developed for agriculture focused on the specific functionality/ domain-dependent such as temperature, humidity pressure, etc and lacks of knowledge base for smart irrigation. In modern generation, the volume of information gathered by numerous sensors over a period, with a diverse series of applications nowadays, is acknowledged by means of Internet of things. Grounded by the properties of an application, the IoT strategies drive outcome in large volume and instantaneous streams of data. Implementing analytics for a large volume of data stream to find novel information, further predict understandings to produce precise and decisions to control a vigorous method that introduces IoT in a well-meaning model for industrial production besides a eminence of life refining technology. Machine learning (deep learning) eases the analytics and knowledge in the IoT domain, the major perspective is to use machine learning (deep learning) in IoT. Hence, in this paper we discuss a systematic review to determine different methods in agriculture practices.

2015 International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT), 2015

Vehicles download the data when passing through a drive through the road (RSU) and then share the... more Vehicles download the data when passing through a drive through the road (RSU) and then share the data after travelling outside the coverage of RSU.A key issue of downloading cooperative data is how effectively data is shared among them self. Developing an application layer data exchange protocol for the coordination of vehicles to exchange data according to their geographic locations. Coordinated sharing can avoid medium access control (MAC) layer collisions and the hidden terminal effect can be avoided in the multi-hop transmission. A salient feature of the application layer data exchange protocol, in the voluntary services, Vehicles purchase the requested data from service provider via RSUs. The project, intends to propose a cooperative data sharing with secure framework for voluntary services in special vehicles networks (VANETs). We also concentrate on security in the process of downloading data and sharing. Applicants to ensure exclusive access to data applied and security of the vehicles involved in the implementation.

2013 International Conference on Optical Imaging Sensor and Security (ICOSS), 2013

Spam is also known as junk mail or Unsolicited Commercial Email (UCE) which has become major prob... more Spam is also known as junk mail or Unsolicited Commercial Email (UCE) which has become major problem for the sustainability of the internet and global commerce. Everyday millions of the spam mails are sent over internet to targeted population to advertise services, products and dangerous software etc. A number of spam detection algorithms have been proposed to classify emails on content based, but could not gain accuracy. Our proposed work mainly focuses on cognitive (spam) words for classification. This feature is sequential unique and closed patterns which are extracted from the message content. We show that this feature have good impact in classifying spam from legitimate messages. Our method, which can be easily implemented, compares amiably with respect to popular algorithms, like Logistic Regression, Neural Network, Naive Bayes and Random Forest using polynomial kernel as filter. We outperform the accuracy higher compared to related methods. In addition our method is resilient against irrelevant and bothersome words.

Industrial Engineering Journal, 2024

The hand gesture recognition project aims to develop a real-time system capable of detecting and ... more The hand gesture recognition project aims to develop a real-time system capable of detecting and recognizing hand gestures from a video stream captured by a webcam. The system utilizes the MediaPipe and OpenCV libraries for hand tracking and gesture recognition. The project involves capturing video frames from the webcam, preprocessing the frames, detecting hand landmarks using MediaPipe, and recognizing specific gestures based on the detected landmarks. Once a gesture is recognized, the system displays the corresponding text overlay on the video frame using OpenCV. The project is designed to provide a user-friendly interface for interpreting hand gestures, enabling applications such as gesture-based control systems, sign language translation, and interactive user interfaces. OpenCV is a widely used open-source computer vision and machine learning software library. It provides a wide range of functionalities for image and video processing, MediaPipe is an open-source framework for building multimodal (e.g., video, audio) applied ML pipelines. It provides ready-to-use ML solutions for various tasks.

Industrial Engineering Journal, 2024

Personalized e-learning systems powered by AI represent a transformative approach to education. T... more Personalized e-learning systems powered by AI represent a transformative approach to education. These systems aim to revolutionize traditional learning by tailoring the experience for individual students. By leveraging AI, data analytics, and natural language processing, these systems dynamically adjust learning paths, conduct assessments, and provide immediate feedback. This reshapes the educational paradigm. Personalized e-learning systems create interactive and collaborative learning environments. This promotes engagement between peers and sharing of knowledge. By encouraging natural language interactions and social learning, these systems enhance the effectiveness of instruction and deepen understanding. The research emphasizes the need to customize learning to cater to diverse student needs, considering their skills, speed, and learning styles. Through exploring intelligent tutoring systems, adaptive learning methodologies, and self-regulated learning principles, the paper elucidates the complexities of personalized education. These AI-powered e-learning systems hold the potential to revolutionize the way we learn and educate ourselves.

Industrial Engineering Journal, 2024

Brain tumors are a significant health concern globally, with early and accurate detection being c... more Brain tumors are a significant health concern globally, with early and accurate detection being critical for effective treatment and improved patient outcomes. This paper presents an innovative approach for brain tumor detection and classification using a two-level diagnosis system. The proposed system combines advanced medical imaging techniques with artificial intelligence algorithms to enhance the accuracy and efficiency of brain tumor diagnosis. Furthermore, the proposed system incorporates an expert system that integrates medical knowledge and decision-making rules. The expert system refines the diagnosis results by considering additional clinical parameters, patient history, and expert opinions, ensuring a comprehensive and accurate diagnosis. This research contributes significantly to the field of medical imaging and artificial intelligence, offering a robust and reliable solution for brain tumor detection and classification. The proposed system has the potential to revolutionize clinical practices, leading to early diagnosis, personalized treatment plans, and ultimately, improved outcomes for patients with brain tumors.

Industrial Engineering Journal, 2024

Brain tumors are a significant health concern globally, with early and accurate detection being c... more Brain tumors are a significant health concern globally, with early and accurate detection being critical for effective treatment and improved patient outcomes. This paper presents an innovative approach for brain tumor detection and classification using a two-level diagnosis system. The proposed system combines advanced medical imaging techniques with artificial intelligence algorithms to enhance the accuracy and efficiency of brain tumor diagnosis. Furthermore, the proposed system incorporates an expert system that integrates medical knowledge and decision-making rules. The expert system refines the diagnosis results by considering additional clinical parameters, patient history, and expert opinions, ensuring a comprehensive and accurate diagnosis. This research contributes significantly to the field of medical imaging and artificial intelligence, offering a robust and reliable solution for brain tumor detection and classification. The proposed system has the potential to revolutionize clinical practices, leading to early diagnosis, personalized treatment plans, and ultimately, improved outcomes for patients with brain tumors.

Industrial Engineering Journal, 2024

Our project discusses a proposed solution for tracking a person's emotions using a network of cam... more Our project discusses a proposed solution for tracking a person's emotions using a network of cameras and adjusting lighting, music, and ambiance accordingly to improve their mood. It also mentions the use of computer vision and machine learning for facial expression recognition. Another aspect involves creating a mood-based music player that recommends songs based on the user's mood in real-time, enhancing customer satisfaction. The project highlights the growing importance of music in people's lives and the need for improved music emotion recognition methods using an artificial bee colony algorithm to enhance the structure of neural networks and achieve better recognition results and faster processing.

International Journal of Data Science and Analytics, Dec 6, 2023

As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networ... more As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networks-based IoT, a plethora of IoT mobile devices (IMD) must contend with the increasing processing demands of time-critical tasks. The dynamic nature of the environment raises novel challenges for networks that use mobile edge computing. As a proactive response to these issues, the concept of ultra-dense IoT with Mobile Edge Computing has emerged. Within this architecture, Integrated Mobile Devices (IMDs) can save power and preserve their internal processing resources by offloading compute-intensive tasks to servers located at the network's periphery (the "edge"). Nevertheless, the increased efficiency comes at the cost of greater transmission overhead, leading to an elevated delay. To achieve an ideal equilibrium between energy preservation and latency reduction, we propose a new optimization problem that focuses on minimizing both energy utilization and latency in ultra-dense IoT networks with multiple users and tasks. This issue entails the complex optimization of concurrent user (IMD) associations, computation offloading decisions, and resource allocations. To achieve a fair distribution of network load and maximize the utilization of computational resources, we integrate multi-step computation offloading methodologies into the issue formulation. Finally, the Adaptive Particle Swarm Optimization (PSO) technique is utilized as an intelligent way of solving the problem. Significantly, our methodology exhibits a noteworthy improvement over traditional Particle Swarm Optimization (PSO) techniques, resulting in a substantial decrease in overall expenses, encompassing reductions that span from 20 to 65%.

International Journal of Advanced Research in Science, Communication and Technology, May 25, 2024

Zenodo (CERN European Organization for Nuclear Research), Mar 16, 2023

Simply put, a blockchain is a distributed database or public ledger of all digital transactions o... more Simply put, a blockchain is a distributed database or public ledger of all digital transactions or events that occur and are shared between participating parties. Blockchains are used in cryptocurrencies such as Bitcoin and Ethereum. After unanimous approval of the vast majority of users connected to the system, every transaction recorded in the public registry is considered duly verified. Once the information is added to the system, it cannot be deleted. Blockchain maintains an immutable and verifiable record of every transaction that has taken place in cryptocurrency history. Bitcoin is the best-known application of blockchain technology today. Bitcoin is a peer-to-peer digital currency that operates without the need for a central authority. On the other hand, the blockchain technology that underpins Bitcoin has proven to work flawlessly and is used for various purposes in the financial and non-financial sectors of the global economy. The main hypothesis behind this research is that blockchain technology has the potential to facilitate the attainment of decentralized consensus in the context of digital and online interactions. Participating organizations have the opportunity to know beyond doubt that a particular digital event has occurred as a result of the development of an indisputable record in a public ledger. This can be achieved by following the steps outlined in the previous sentence. It opens the door to the transition from a centralized digital economy to a democratic, open and scalable economy. With the potential to completely change the game, this technology is just beginning, ushering in an era of game-changing changes that open up countless possibilities. This white paper provides an introduction to blockchain technology and a fascinating array of specific applications in finance and other industries. Below, we look at the frontline challenges and business opportunities that exist in this fundamental technology that will dramatically revolutionize our digital world. Simply put, a blockchain is a distributed database or public ledger of all digital transactions or events that occur and are shared between participating parties. Blockchains are used in cryptocurrencies such as Bitcoin and Ethereum. After unanimous approval of the vast majority of users connected to the system, every transaction recorded in the public registry is considered duly verified. Once the information is added to the system, it cannot be deleted. Blockchain maintains an immutable and verifiable record of every transaction that has taken place in cryptocurrency history. Bitcoin is the best-known application of blockchain technology today. Bitcoin is a peer-to-peer digital currency xvi | P a g e that operates without the need for a central authority. On the other hand, the blockchain technology that underpins Bitcoin has proven to work flawlessly and is used for various purposes in the financial and non-financial sectors of the global economy. The main hypothesis behind this research is that blockchain technology has the potential to facilitate the attainment of decentralized consensus in the context of digital and online interactions. Participating organizations have the opportunity to know beyond doubt that a particular digital event has occurred as a result of the development of an indisputable record in a public ledger. This can be achieved by following the steps outlined in the previous sentence. It opens the door to the transition from a centralized digital economy to a democratic, open and scalable economy. With the potential to completely change the game, this technology is just beginning, ushering in an era of game-changing changes that open up countless possibilities. This white paper provides an introduction to blockchain technology and a fascinating array of specific applications in finance and other industries. Below, we look at the frontline challenges and business opportunities that exist in this fundamental technology that will dramatically revolutionize our digital world.

Industrial Engineering Journal, 2024

Health has been the primary area of interest in human welfare, especially fetal health. Fetal hea... more Health has been the primary area of interest in human welfare, especially fetal health. Fetal heart abnormalities are the most widespread congenital anomaly that leads to the cause of infant mortality related to congenital disabilities. Several techniques have come into existence for this purpose. The deformed heart can be differentiated from the normal heart based on several parameters such as the size of auricles, ventricles, valve and position of heart, area, circumference, and perimeter. One of the methods to detect the anomalies in fetal heart is by applying advanced Image Processing techniques to enhance the properties of the image that could improve the performance of the artificial intelligence algorithms. This proposed system is the primary framework for diagnosing the prenatal ventricular septal defects (PVSD). The first step is to denoise the US images using enhanced anisotropic diffusion Enhanced Perona Malik Filter (EPMF), followed by K-means clustering segmentation method as the second step, and finally, VGG-16 architecture was implemented with the pre-trained weights from the database. The original image is compared with the reference image in terms of different parameters using a VGG16 deep learning algorithm to predict PVSD anomalies at the early stage of pregnancy. VGG-16 is the first attempt to diagnose prenatal ventricular septal defects to achieve an accuracy of 90%. This proposed system will give a second opinion for the doctors in diagnosing the abnormalities at the early stages.

Industrial Engineering Journal, 2024

OpenAI created and published ChatGPT, an AI chatbot, in November 2022. It was produced using supe... more OpenAI created and published ChatGPT, an AI chatbot, in November 2022. It was produced using supervised and reinforcement learning approaches and is built on top of OpenAI's GPT-3.5 and GPT-4 families of big language models. With the creation of artificial intelligence, a new era in computer science has dawned. The sigmoid curve is frequently used to analyze innovative technology, with a sluggish take off when a new technology is invented, followed by a quick speed of development dependent on how advantageous it is. This is true despite the fact that artificial intelligence was created in 1950 by John McCarthy, who is now regarded as its founder, and earlier by Alan Turning, who examined its mathematical implications. As a result, technology develops as more people use it. We believe that AI will mark the beginning of an entirely novel sigmoid curve. Following the maturity of ChatGPT, computational intelligence has now achieved a new height. AI is now growing at a 21% annual rate, establishing an entirely novel market in this extremely competitive sector. The ChatGPT characteristics, paradigm, and data analysis procedure were all represented in this work.

Springer, 2023

As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networ... more As the Internet of Things (IoT) evolves and is integrated into cutting-edge Smart Vertical Networks-based IoT, a plethora of IoT mobile devices (IMD) must contend with the increasing processing demands of time-critical tasks. The dynamic nature of the environment raises novel challenges for networks that use mobile edge computing. As a proactive response to these issues, the concept of ultra-dense IoT with Mobile Edge Computing has emerged. Within this architecture, Integrated Mobile Devices (IMDs) can save power and preserve their internal processing resources by offloading compute-intensive tasks to servers located at the network's periphery (the "edge"). Nevertheless, the increased efficiency comes at the cost of greater transmission overhead, leading to an elevated delay. To achieve an ideal equilibrium between energy preservation and latency reduction, we propose a new optimization problem that focuses on minimizing both energy utilization and latency in ultra-dense IoT networks with multiple users and tasks. This issue entails the complex optimization of concurrent user (IMD) associations, computation offloading decisions, and resource allocations. To achieve a fair distribution of network load and maximize the utilization of computational resources, we integrate multi-step computation offloading methodologies into the issue formulation. Finally, the Adaptive Particle Swarm Optimization (PSO) technique is utilized as an intelligent way of solving the problem. Significantly, our methodology exhibits a noteworthy improvement over traditional Particle Swarm Optimization (PSO) techniques, resulting in a substantial decrease in overall expenses, encompassing reductions that span from 20 to 65%.

2023 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)

Knee Magnetic Resonance Images

With the character of low maintenance, cloud computing provides an economical and efficient solut... more With the character of low maintenance, cloud computing provides an economical and efficient solution for sharing group resource among cloud users. Unfortunately, sharing data in a multi-owner manner while preserving data and identity privacy from an un trusted cloud is still a challenging issue, due to the frequent change of the membership. A secure multi owner data sharing scheme, named Mona, for dynamic groups in the cloud is proposed. By leveraging group signature and dynamic broadcast encryption techniques, any cloud user can anonymously share data with others. Meanwhile, the storage overhead and encryption computation cost of our scheme are independent with the number of revoked users. In addition, to it analyzing the security of the scheme with rigorous proofs, and demonstrate the efficiency of the scheme in the experiments.

Complexity, 2020

Magnetic resonance imaging (MRI) is precise and efficient for interpreting the soft and hard tiss... more Magnetic resonance imaging (MRI) is precise and efficient for interpreting the soft and hard tissues. Moreover, for the detailed diagnosis of varied diseases such as knee rheumatoid arthritis (RA), segmentation of the knee magnetic resonance image is a challenging and complex task that has been explored broadly. However, the accuracy and reproducibility of segmentation approaches may require prior extraction of tissues from MR images. The advances in computational methods for segmentation are reliant on several parameters such as the complexity of the tissue, quality, and acquisition process involved. This review paper focuses and briefly describes the challenges faced by segmentation techniques from magnetic resonance images followed by an overview of diverse categories of segmentation approaches. The review paper also focuses on automatic approaches and semiautomatic approaches which are extensively used with performance metrics and sufficient achievement for clinical trial assist...

International Journal of Innovative Technology and Exploring Engineering, 2020

The explosion of numerous medical images lead to the development of many different techniques to ... more The explosion of numerous medical images lead to the development of many different techniques to provide an accurate result. Although the signal to noise ratio (SNR), resolution and speed of magnetic resonance imaging technology have increased, still magnetic resonance images are affected by noise, contrast, and artifacts. To provide the image content or features relevant to diagnosis, contrast enhancement and reduction of noise with preservation of actual content should be carried out. The purpose of this paper is to present a critical review of different types of noises with an overview of diverse techniques for denoising and contrast enhancement for magnetic resonance images and discuss the advantages and limitations of these techniques with broad ideology

International Journal of Advanced Trends in Computer Science and Engineering, 2019

Traditionally methods developed for agriculture focused on the specific functionality/ domain-dep... more Traditionally methods developed for agriculture focused on the specific functionality/ domain-dependent such as temperature, humidity pressure, etc and lacks of knowledge base for smart irrigation. In modern generation, the volume of information gathered by numerous sensors over a period, with a diverse series of applications nowadays, is acknowledged by means of Internet of things. Grounded by the properties of an application, the IoT strategies drive outcome in large volume and instantaneous streams of data. Implementing analytics for a large volume of data stream to find novel information, further predict understandings to produce precise and decisions to control a vigorous method that introduces IoT in a well-meaning model for industrial production besides a eminence of life refining technology. Machine learning (deep learning) eases the analytics and knowledge in the IoT domain, the major perspective is to use machine learning (deep learning) in IoT. Hence, in this paper we discuss a systematic review to determine different methods in agriculture practices.

2015 International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT), 2015

Vehicles download the data when passing through a drive through the road (RSU) and then share the... more Vehicles download the data when passing through a drive through the road (RSU) and then share the data after travelling outside the coverage of RSU.A key issue of downloading cooperative data is how effectively data is shared among them self. Developing an application layer data exchange protocol for the coordination of vehicles to exchange data according to their geographic locations. Coordinated sharing can avoid medium access control (MAC) layer collisions and the hidden terminal effect can be avoided in the multi-hop transmission. A salient feature of the application layer data exchange protocol, in the voluntary services, Vehicles purchase the requested data from service provider via RSUs. The project, intends to propose a cooperative data sharing with secure framework for voluntary services in special vehicles networks (VANETs). We also concentrate on security in the process of downloading data and sharing. Applicants to ensure exclusive access to data applied and security of the vehicles involved in the implementation.

2013 International Conference on Optical Imaging Sensor and Security (ICOSS), 2013

Spam is also known as junk mail or Unsolicited Commercial Email (UCE) which has become major prob... more Spam is also known as junk mail or Unsolicited Commercial Email (UCE) which has become major problem for the sustainability of the internet and global commerce. Everyday millions of the spam mails are sent over internet to targeted population to advertise services, products and dangerous software etc. A number of spam detection algorithms have been proposed to classify emails on content based, but could not gain accuracy. Our proposed work mainly focuses on cognitive (spam) words for classification. This feature is sequential unique and closed patterns which are extracted from the message content. We show that this feature have good impact in classifying spam from legitimate messages. Our method, which can be easily implemented, compares amiably with respect to popular algorithms, like Logistic Regression, Neural Network, Naive Bayes and Random Forest using polynomial kernel as filter. We outperform the accuracy higher compared to related methods. In addition our method is resilient against irrelevant and bothersome words.