Dr.Yogesh Mali - Academia.edu (original) (raw)

Papers by Dr.Yogesh Mali

In book: Smart Systems: Innovations in Computing, 2024

Due to the Social Metaverse’s distinctive architectural foundation, numerous other cyber dangers ... more Due to the Social Metaverse’s distinctive architectural foundation, numerous other cyber dangers might materialize. The foundation of privacy protection in the metaverse is the encryption and anonymization of user data. Users can freely trade information and do business within the Social Metaverse by using these decentralized, networked, interoperable platforms. The Social Metaverse’s vulnerability to social cyber dangers including phishing, ransomware, data hacking, identity theft, and virus attacks is another barrier. In the metaverse, data can be kept in a variety of places, including servers, databases, edge, fog, and cloud computing plat-forms. We discussed Social Metaverse platforms and applications. We also mention potential study directions throughout the report. In addition to being a remarkable contribution on its own, we think that we discussed the potential solutions to mitigate risk in the metaverse (PDF) Cyber Threats in Social Metaverse and Mitigation Techniques

Springer Nature, 2024

The medical care industry is seeing a critical change with the coming of Web 3.0 innovations and ... more The medical care industry is seeing a critical change with the coming of Web 3.0 innovations and the combination of blockchain. It investigates the capability of utilizing Web 3.0 and blockchain to foster play-to-acquire applications in the medical services area. Play-to-procure applications encourage people to participate in well-being related exercises and award them with advanced resources or tokens. By uniting the power of Web 3.0, which engages decentralized and secure partnerships, with block-chain's straightforwardness and perpetual nature, these applications might conceivably modify how we approach clinical benefits and empower individuals to expect control over their thriving. We propose an idea of play-to-procure applications and examine how Web 3.0 and blockchain can upset the medical services scene. It investigates the advantages, challenges, and moral contemplations related to fostering these applications. Also, the part features certifiable models and contextual analyses that show the extraordinary force of play-to-acquire applications in advancing sound ways of behaving and engaging people to assume command over their wellbeing.

IJARSCT, 2024

In this paper, we propose a job title recommendation system using a combination of Natural Langua... more In this paper, we propose a job title recommendation system using a combination of Natural Language Processing (NLP) techniques and machine learning. We implement a TF-IDF Vectorizer and cosine similarity to recommend jobs based on user inputs like skills, experience, industry, and role category. The system was built using Python and integrated into a user-friendly interface using Streamlit, enabling personalized recommendations. We evaluate the accuracy of recommendations and discuss potential improvements

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

The demand for automated attendance management systems has significantly increased in educational... more The demand for automated attendance management systems has significantly increased in educational institutions and corporate environments where manual methods are prone to inefficiencies and errors. This paper presents a real-time, facial recognition-based attendance system developed using Flask, OpenCV, and machine learning techniques. The system employs OpenCV's Haar Cascade classifier for face detection and the K-Nearest Neighbours (KNN) algorithm for face recognition. During user registration, the system captures 10 images per individual to ensure robust recognition across various facial expressions. The web interface, built using Flask, facilitates user interaction for managing attendance records stored in CSV format. The system achieves an accuracy of 92% under optimal lighting conditions, though performance decreases to 80% in low-light environments. Recognition is completed in approximately 2 seconds, making the system suitable for real-time applications in classrooms or offices. Despite handling real-time image streaming efficiently, challenges such as reduced accuracy when handling obstructions like masks or glasses remain. Future enhancements will explore the integration of deep learning models, such as Convolutional Neural Networks (CNNs), to improve robustness and scalability. This system demonstrates the potential of facial recognition technology for automating attendance tracking, with significant applications in both educational and corporate sectors

CRC Press Taylor & Frances , 2024

This book explores the need for a data-centric AI approach and its application in the multidiscip... more This book explores the need for a data-centric AI approach and its application in the multidisciplinary domain, compared to a model-centric approach. It examines the methodologies for data-centric approaches, the use of data-centric approaches in different domains, the need for edge AI and how it differs from cloud-based AI. It discusses the new category of AI technology, "data-centric AI" (DCAI), which focuses on comprehending, utilizing, and reaching conclusions from data. By adding machine learning and big data analytics tools, data-centric AI modifies this by enabling it to learn from data rather than depending on algorithms. It can therefore make wiser choices and deliver more precise outcomes. Additionally, it has the potential to be significantly more scalable than conventional AI methods.

IEEE, 2024

In recent years, the significance of data mining algorithms has increased with the fast growth of... more In recent years, the significance of data mining algorithms has increased with the fast growth of data. Elements are often repeated when dealing with transitions that fetch data. Therefore, one of the most essential issues in data mining is mining common item collections. Here we tackle an algorithm that finds common elements appearing in transitions and tries to split the data accordingly into different tables, called vertical fragmentation. This gives you high time efficiency. Here we use FP growth for the mining phase. Another smart splitting method has been proposed that converts the database into separate tables.

IEEE, 2024

Malicious URLs promoting threats like phishing and malware result in massive financial losses wor... more Malicious URLs promoting threats like phishing and malware result in massive financial losses worldwide. Automated identification of such URLs before users access them is crucial for cybersecurity. This paper investigates various machine learning techniques for accurately detecting malicious URLs. Models like decision trees, random forests, KNN and naive Bayes are evaluated on a dataset of over 500,000 URLs. Ensemble models random forest and extra trees deliver the best performance, with over 91% accuracy in distinguishing benign and malicious URLs. However, class imbalance remains a challenge with minority malicious types often having lower precision. Comparative assessment demonstrates feasibility of using ensemble machine learning for automated malicious URL detection. With sufficient examples and feature engineering, tree-based models can be effectively employed to identify threats and strengthen cyber defense.

IEEE, 2024

Cancer of the bone marrow, often known as Acute Lymphoblastic Leukemia (ALL), is characterized by... more Cancer of the bone marrow, often known as Acute Lymphoblastic Leukemia (ALL), is characterized by the unchecked growth of lymphoid progenitor cells. It affects both children and adults and is the most prevalent form of childhood cancer. There have been considerable advances in the diagnosis and treatment of acute lymphoblastic leukemia in recent years. The ability to accurately assess risk and develop an appropriate treatment strategy relies on a diagnosis that takes into account all relevant clinical, morphological, cytogenetic, and molecular aspects. However, in order to enhance survival and quality of life for those afflicted by this aggressive hematological malignancy, more research and clinical trials are required to address the issues associated with resistance, relapse, and long-term toxicity. Therefore, in this research a deep optimized convolutional neural network is proposed for the early detection and diagnosis of ALL. The deep optimized CNN model architecture comprises of five convolutional blocks with 13 conv layers, 5 max pool layers. The proposed deep optimized CNN model is tuned using the hyperparameters such as epochs, batch size and optimizers namely Adam and Adamax. Out of the two optimizers, the proposed deep optimized CNN model has outperformed using Adam optimizer with the points of accuracy and precision as 0.96 and 0.95 respectively.

IEEE, 2024

Customary capacity the board methods are turning out to be less powerful for dealing with this hu... more Customary capacity the board methods are
turning out to be less powerful for dealing with this huge
volume of information because of the improvement of server
farms and the unforeseen ascent away requirements. By
eliminating the capacity control exercises out of the genuine
information stockpiling media and placing them in the product
layer of a concentrated regulator, Programming Characterized
Stockpiling offers an answer for this issue. An insightful
programming stack named "programming characterized
foundation" may deal with reasonable product equipment. A
software engineer known as programming characterized
capacity controls information capacity assets without the
utilization of real equipment. Making the capacity engineering
of a genuine Programming Characterized Stockpiling
framework with no reenactment or imitating is an exorbitant
and unsafe technique. Subsequently, the framework should be
recreated prior to being utilized, in actuality. In this manner,
virtualized proving grounds for such frameworks should be
reenacted before genuine execution and sending. In this article,
we evaluate software-defined storage engineering using the
Programming Described Association (PDA) test framework,
Mini-net. This framework is designed, assembled, and ready to
advance without revisiting the established assembly structure.
The core components of Mini-net have been modified to
address data distribution challenges in contemporary SD
storage and to scale storage capacity appropriately within this
simulated environment

IEEE, 2024

Bone marrow cancer, commonly referred to as Acute Lymphoblastic Leukemia (ALL), is marked by the ... more Bone marrow cancer, commonly referred to as Acute Lymphoblastic Leukemia (ALL), is marked by the rapid proliferation of immature lymphoid cells. This condition affects both children and adults, standing as the most common type of cancer in children. Recent years have seen considerable advancements in diagnosing and treating ALL. Precise risk assessment and the formulation of an effective treatment plan hinge on a comprehensive diagnostic approach that incorporates clinical, morphological, cytogenetic, and molecular data. Nevertheless, to improve survival rates and the quality of life for individuals battling this aggressive blood cancer, further research and clinical trials are imperative to overcome challenges related to drug resistance, relapse, and long-term side effects. Accordingly, this research introduces a highly optimized deep learning model, specifically a deep optimized convolutional neural network (CNN), for the early detection and classification of ALL. The advanced CNN architecture features five convolutional blocks, including 11 convolutional layers and 4 max pooling layers. The optimization of this deep CNN model involved tuning hyper parameters such as epochs, batch size, and the use of specific optimizers, namely Adam and Adamax. Among these, the model achieved superior performance with the Adam optimizer, demonstrating high levels of accuracy and precision, at 0.93 and 0.91 respectively.

IEEE, 2024

—Malicious URLs, posing threats such as phishing and malware, cause significant financial losses ... more —Malicious URLs, posing threats such as phishing and
malware, cause significant financial losses globally. Detecting these
URLs automatically before users access them is essential for cyber
security. This study explores various machine learning techniques
to accurately identify malicious URLs. Decision trees, random
forests, K-nearest neighbors (KNN), and naive Bayes models are
assessed using a dataset containing over 700,000 URLs. Ensemble
models like random forest and extra trees exhibit superior
performance, achieving over 93% accuracy in distinguishing
between benign and malicious URLs. However, class imbalance
remains a challenge, with minority malicious types often exhibiting
lower precision. Comparative analysis highlights the feasibility of
employing ensemble machine learning for automated malicious
URL detection. With adequate examples and feature engineering,
tree-based models can effectively identify threats and bolster cyber
defense.

Revista Electronica De Veterinaria, 2024

In a period of rapid technological advancement, the traditional methods of taking attendance of c... more In a period of rapid technological advancement, the traditional methods of taking attendance of cattle after coming from grazing yard is done by normal counting as this have become inefficient and outdated. To overcome this issue, an Automatic Attendance Monitoring System (AAMS) using Closed-Circuit Television (CCTV) technology has been introduced as a solution. These abstracts highlight its key features and benefits. The Automated Attendance Monitoring System through CCTV uses the power of computer vision and machine learning (ML) for attendance monitoring. Using CCTV cameras in big dairy farms cows & buffalos are monitored. This can be also been implemented in grazing yards systems to analyse unique identification of data. That data will be cross-analysed using the database to record the attendance by colour, breed, and most importantly RFID tag. This system analyses accuracy the in-out time of cattle’s using this recognition system. In training data, with multiple images of individual cow or buffalo from all angles & features are captured. Up to 30000-50000 images will be generated with supporting to that closed circuit images of all RFID implanted at ears of cattle. If the image captured by CCTV and the images in the database match, then attendance will be done and the report submitted. To build this system, the Python language was used. For developing systems, software is required, such as PyCharm or Spyder. We also need some libraries, like the OpenCV library and the Cattle Recognition library. The CNN algorithm is used for cattle recognition. Django, HTML, CSS, JavaScript, MySQL, and Bootstrap technologies will be used. In conclusion, the Automatic Attendance Monitoring System through CCTV provides an effective solution for the traditional attendance system. Provides high security and accuracy.

CRC Press eBooks, Apr 19, 2024

The healthcare industry is witnessing a significant transformation with the advent of Web 3.0 tec... more The healthcare industry is witnessing a significant transformation with the advent of Web 3.0 technologies and the integration of blockchain. It explores the potential of leveraging Web 3.0 and blockchain to develop play-to-earn apps in the healthcare sector. Play-to-earn apps incentivize individuals to engage in health-related activities and reward them with digital assets or tokens. By consolidating the force of Web 3.0, which empowers decentralized and secure alliance, with blockchain’s straightforwardness and unchanging nature, these applications can possibly alter the manner in which we approach medical services and enable people to assume command over their prosperity. The chapter suggests a concept of play-to-earn apps and discuss how Web 3.0 and blockchain can revolutionize the healthcare landscape. It explores the benefits, challenges, and ethical considerations associated with developing these apps. Additionally, the chapter highlights real-world examples and case studies that demonstrate the transformative power of play-to-earn apps in promoting healthy behaviors and empowering individuals to take control of their health.

Any wireless network is built on the mutually reinforcing pillars of privacy and security. Securi... more Any wireless network is built on the mutually reinforcing pillars of privacy and security. Security measures often cover data connections, physical security, outside threats, and internal node operations. Whereas privacy covers the selective exchange of data among a network's various entities. To provide privacy to networks, a large number of algorithms have been proposed by researchers in the past. Most of these algorithms utilize Graph-based anonymization approaches like l-diversity, k-anonymity, etc. These models do not scale well. Thus, this text proposes a machine learning-based block chain powered privacy preservation protocol. The proposed protocol will perform attribute-based privacy with high efficiency due to the use of block chain architecture and will improve the overall Quality of Service of the network due to the integration of machine learning in the system.

Real Estate Application: Managing Transactions between Brokers and Developers, streamlines proper... more Real Estate Application: Managing Transactions between Brokers and Developers, streamlines property transactions with seamless communication and collaboration. It automates property listing, negotiation, and closing, saving time and reducing errors. The built-in CRM system tracks leads and enables data-driven decisions. The analytics system provides insights into the real estate market and customer behavior. Secure and scalable, the application integrates with other systems. An essential tool for brokers and developers, enhancing efficiency and profitability.

Enhanced Pin Entry Mechanism for ATM Machine by Defending Shoulder Surfing Attacks

Lecture notes in networks and systems, 2024

The objective of the coal mining cap proposed in this exploration is to give protection to excava... more The objective of the coal mining cap proposed in this exploration is to give protection to excavators by cautioning them. However long the individual is conveying the defensive cap, the parts might be all referenced. The result of the cap module is refreshed consistently for every model, refreshing the cloud with continuous information. Those wearable gadgets can share their facts or recover it from distinct sources way to the web of factors. On the off threat that there may be a threat, alerts are given to the enterprise and the digger. The making of wearable computer systems and general enrollment has particularly helped the headway of wearable innovation. Consequently, this wearable system carries a massive variety of sensors that allow it to interface with extraordinary parts and upgrade the safety of the digger. The hardware has coordinated statistics gathering, facts the board, and information correspondence parts. The DHT11 temperature and dampness sensor was utilized. There are times when the intensity and dampness levels in mines are too high and the tractor bites the dust. Anybody inside the mines ought to have respiratory issues because of those gases being delivered, which could prompt suffocation.

IEEE, Dec 13, 2023

At the time of surgery, the entire gloves will protect the surgeon from blood borne antibodies an... more At the time of surgery, the entire gloves will protect the surgeon from blood borne antibodies and the surgical carving tools from bacteria on the skin of the physicians. However, glove prick is very common, and perforation rates are as high as 71%. When treating people with highly contagious diseases like HIV-AIDS, Hepatitis, there are extremely high chances of doctors being affected. This tool can be used for forensic investigations, laboratory testing, and other tasks in addition to performing surgical procedures. It can also be used by sewage cleaners. The objective of this venture is to offer therapy to clinical experts who are presented to various microscopic organisms while carrying out methodology on patients. The specialists are made aware of the cut by tracking down it in a glove, empowering them to make the fitting move.

Deleted Journal, Jan 25, 2024

The process of accomplishing strategic objectives by concentrating on effects as opposed to attri... more The process of accomplishing strategic objectives by concentrating on effects as opposed to attrition-based destruction is known as effects-based operations, or EBO. Finding important nodes in an adversary network is a critical step in the EBO process for a successful implementation. In this paper, propose a network-based method to identify the most influential nodes by combining network centrality and optimization. To determine the node influence, the adversary's network structure is analyzed using degree and between centralities. Given the dynamic nature of the adversary network struct 1 ure and the centrality results, an optimization model that takes resource constraints into account chooses the key nodes. Our findings demonstrate that various network properties, such as between and degree centralities, influence the priorities of nodes as targets, and that using an optimization model yields better priorities with decreasing marginal properties. There is a discussion of the implications for theory and sensible decision-making.

The Coal Mining Head protector planned on this paper intends to offer protection to diggers throu... more The Coal Mining Head protector planned on this paper intends to offer protection to diggers through alerted them. All of the parts may be implied given that the individual is conveying the defensive cap. Every model's result from the cap module is refreshed ceaselessly, and that implies that continuous information is refreshed in the cloud. The Web of Things (IOT) permits these wearable contraptions to impart their information or recover it from different sources. The chief and the digger are given alerts, expecting there is a peril present. The advancement of wearable innovation has enormously profited from all inclusive enlistment and wearable PC systems. Thusly, this wearable gadget has various sensors that empower it to speak with different parts and work on the digger's protection. Information assortment, data the executives, and data correspondence portions are completely coordinated into the gear. A temperature and moistness sensor (DHT11) was utilized. How much intensity and dampness in mines will sporadically go excessively far and become lethal for the backhoe. The freedom of those gases ought to cause breathing troubles for anybody inside the mines and could bring about suffocation. In the impossible occasion that at least one of these pieces surpass the cutoff, an alert is shipped off both the base Authorizer and the digger.

In book: Smart Systems: Innovations in Computing, 2024

Springer Nature, 2024

IJARSCT, 2024

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

CRC Press Taylor & Frances , 2024

IEEE, 2024

Revista Electronica De Veterinaria, 2024

CRC Press eBooks, Apr 19, 2024

Enhanced Pin Entry Mechanism for ATM Machine by Defending Shoulder Surfing Attacks

Lecture notes in networks and systems, 2024

IEEE, Dec 13, 2023

Deleted Journal, Jan 25, 2024

Springer, 2024

Due to the Social Metaverse’s distinctive architectural foundation,numerous other cyber dangers m... more Due to the Social Metaverse’s distinctive architectural foundation,numerous other cyber dangers might materialize. The foundation of privacy protec-tion in the metaverse is the encryption and anonymization of user data. Users canfreely trade information and do business within the Social Metaverse by using thesedecentralized, networked, interoperable platforms. The Social Metaverse’s vulnera-bility to social cyber dangers including phishing, ransomware, data hacking, identitytheft, and virus attacks is another barrier. In the metaverse, data can be kept in avariety of places, including servers, databases, edge, fog, and cloud computing plat-forms. We discussed Social Metaverse platforms and applications. We also mentionpotential study directions throughout the report. In addition to being a remarkablecontribution on its own, we think that we discussed the potential solutions to mitigaterisk in the metaverse

CRC Press Taylor & Frances , 2024

Advancements in computational intelligence, which encompasses artificial intelligence, machine le... more Advancements in computational intelligence, which encompasses artificial intelligence, machine learning, and data analytics, have revolutionized the way we process and analyze biomedical and health data. These techniques offer novel approaches to understanding complex biological systems, improving disease diagnosis, optimizing treatment plans, and enhancing patient outcomes. Computational Intelligence and Blockchain in Biomedical and Health Informatics introduces the role of computational intelligence and blockchain in the biomedical and health informatics fields and provides a framework and summary of the various methods. The book emphasizes the role of advanced computational techniques and offers demonstrative examples throughout. Techniques to analyze the impacts on the biomedical and health informatics domains are discussed along with major challenges in deployment. Rounding out the book are highlights of the transformative potential of computational intelligence and blockchain in addressing critical issues in healthcare from disease diagnosis and personalized medicine to health data management and interoperability along with two case studies. This book is highly beneficial to educators, researchers, and anyone involved with health data.