Volume 12 | Issue 5

 Abstract

The widespread adoption of on-demand mobility services has spurred significant advancements in cab management systems. However, existing solutions often exhibit limitations in areas such as real-time optimization, user experience personalization, and integration with sustainable transportation strategies. This review paper critically examines current cab management systems, dissecting their strengths, shortcomings, and underlying technological approaches. Through a comparative analysis, recurrent patterns and potential areas for improvement are identified. Informed by this assessment, the paper proposes a conceptual framework for a next-generation cab management system. This enhanced system aims to leverage advanced optimization algorithms, machine learning techniques, and innovative incentive mechanisms to achieve greater efficiency, rider satisfaction, driver empowerment, and alignment with environmentally conscious transportation goals.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

cab management, ride-sharing, optimization algorithms, machine learning, user experience, sustainable mobility

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Agricultural fruit diseases cause economic losses to far mers. Monitoring the health of the traditional pomegra nate crop and diagnosing disease is highintensity, diffic ult and timeconsuming. However, recent advances in i mage processing and computer vision offer opportuniti es for disease detection in pomegranate plants. In this a rticle, we provide an overview of the imaging technique s used to detect pomegranate disease. In this article, we provide an overview of the methods used to detect pom egranate diseases. We also discuss the challenges of dia gnosing diseases in images and highlight the potential o f deep learning to achieve accurate diagnosis.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Pomegranate, K-means, SVM (support vector machine), CNN, Softmax layer

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The proliferation in phishing attacks highlights the importance of strong cybersecurity protocols.. In this study, we present an innovative methodology that harnesses machine learning techniques to enhance the detection of phishing websites. Phishing attempts persist as a considerable risk to both individuals and organizations, underscoring the essential requirement for enhanced detection methods.. Leveraging the power of machine learning, our study outlines a systematic methodology for identifying phishing websites. We begin with a thorough data collection process, followed by preprocessing steps to refine the dataset. Feature extraction methods are then utilized to capture pertinent patterns suggestive of phishing endeavors. The core of our approach lies in the application of various machine learning algorithms for classification, enabling the automated identification of phishing websites. By conducting thorough tests and assessments, we showcase the efficiency and resilience of our detection system. By contributing to the advancement of cybersecurity measures, this research aims to empower users and organizations in combating phishing threats, thereby fostering a safer online environment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Phishing, Machine Learning, Cybersecurity, Detection Mechanisms, Feature Extraction, Classification Algorithms.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Through communication, people can engage and share thoughts and feelings. There are several obstacles in the way of the deaf community's social interactions. The individuals use sign language to communicate with one other. In order to communicate with regular people, a technology can convert sign languages into a form that is understandable. The goal of this project is to create a real-time text-to-Indian Sign Language (ISL) translation system. Most of the work is done by hand. In this paper, we present a deep learning technique for classifying signs using a convolutional neural network. Using the numerical signs and the Python-based Keras convolutional neural network implementation, we first build a classifier model. Phase two involved using a second real-time system that located the Region of Interest in the frame that displays the bounding box using skin segmentation. The segmented region is fed into the classifier model in order to forecast the sign. For the identical subject, the system's accuracy rate is 99.56%; in low light, it is 97.26%. The classifier was seen to be becoming better with different background and angle of image capture. Our approach focuses on the RGB camera system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Deep learning, convolutional neural networks, regions of interest, and real-time systems.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Sign language serves as a vital mode of communi- cation for the Deaf and Hard of Hearing (DHH) community, yet barriers persist in its recognition and translation. This project addresses these challenges through innovative technological solu- tions. The primary objective of this study is to develop a robust system for sign language recognition and translation, aiming to enhance communication accessibility for the DHH community. Leveraging advancements in machine learning and computer vision, the project seeks to overcome existing limitations and revolutionize inclusive communication technologies. The project employs a multifaceted approach, integrating Long Short-Term Memory (LSTM) networks and MediaPipe technology to ac- curately detect and interpret sign language gestures. Through extensive training and validation processes, the system is opti- mized to achieve high levels of accuracy and efficiency in real- world scenarios. The developed system demonstrates exceptional performance, achieving a recognition accuracy rate of 98% for sign language gestures. Moreover, it seamlessly translates these gestures into both spoken and written English and Marathi, offering real-time, context-aware translations. This project rep- resents a significant advancement in addressing communication barriers for the DHH community. By providing an accessible and inclusive means of communication, the developed system has the potential to revolutionize interactions and promote equality across diverse domains. The success of this endeavor underscores the importance of leveraging technology to foster inclusivity and enhance the quality of life for individuals with hearing impairments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, MediaPipe, OpenCV, LSTM Neu- ral Network, Sign Language, PIL, GoogleTrans

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The research analysis on sign language crosses multiple fields and academic areas. These days, the two primary fields of research in gesture recognition are data glove use and visual sign language recognition. While the latter records the user's hand features with the camera for the purpose of identifying and translating sign language, the former uses the information collected by the sensor for these purposes. Deaf and hard to hearing individuals typically employ sign language as a form to interact both within and outside of their own community. In this language, communication is facilitated through hand gestures, which is particularly essential for individuals who are deaf and mute. The goal of SLR is to recognize these hand signals and translate them into spoken or written language.Within this domain, hand signs are classified into types: dynamic and static. While recognizing static hand gestures is generally easier, the recognition of both dynamic and static gestures is valued by the community. Hand gestures could be recognized using Deep Learning Computer Vision and Deep Neural Network concepts (Convolution Neural Network designs). The model will learn to recognize the hand gesture photos over the course of an epoch.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Hand gestures, computer vision, text-to-speech, convolution neural networks, and recognition of sign language

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Nowadays the Mastercard blackmail is the best issue and by and by there is need to fight against the Visa deception. "Visa blackmail is the most well-known approach to cleaning untidy money, likewise making the wellspring of resources at this point not conspicuous." On steady timetable, the financial trades are made on tremendous aggregate in overall market and hence recognizing charge card distortion development is trying undertaking. As earlier (Against Mastercard blackmail Suite) is familiar with separate the questionable activities yet it is significant simply on individual trade not for other monetary equilibrium trade. To Vanquishes issues of we propose artificial intelligence method using 'Hidden Closeness', to perceive typical acknowledges and lead for other monetary equilibrium trade. Area of charge card distortion trade from gigantic volume dataset is irksome, so we propose case decline procedures to decreases the data dataset and a while later find sets of trade with other monetary offset with ordinary credits and lead.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

credit card fraud, fraudulent activities, SVM (SUPPORT VECTOR MACHINE), Harr cascade Algorithm, Face Recognition.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the digital age, the security and integrity of communi cation and data transfer has become important. Centralized syste ms face challenges in managing data confidentiality, preventing ta mpering, and ensuring authenticity. To solve these problems, this article proposes a new way to create secure communication and data transfer using blockchain technology. Known for its distribution and immutability, blockchain has a unique advantage in increa sing security and trust. By leveraging decentralized blockchain da ta, encryption mechanisms and smart contracts, we can create a strong infrastructure for secure communication and data transmission. Key elements of the process include self-governance using blo ckchainbased digital signatures, data encryption using strong encr yption algorithms, smart contracts automati on, decentralized management for redundancy and fault tolerance,and an immutable audit method for transparency and accountability. . Thanks to the integration of blockchain technology, users can enjoy enhanced security, privacy and accuracy in communicationand data transfer activities. The system reduces the risks with unauthorized access, interception and leakage of information on by ensuring that only authorized individuals access and interact with data. This article provides concept and design considerations for using secure communication and data transfer using blockchain technology. It highlights the benefits and challenges associated with these systems and provides insight into future research directions to improve their effectiveness and application potential.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

blockchain, secure communication, decentralization cryptography, access control, smart contracts, data encryption, authentication, data integrity, trust, privacy protection

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Recommendation system is an essential part of any E- commerce website. The main aim of the system is to provide effective suggestions to the user. Generally, a lot of methods are used for the filtering but Interactive recommendations is the trending methods. This paper implements the Interactive recommendations based on Neural networks. The IR can be further modified into chatbots. Chatbots are the part of the system where the user can interact by themselves with the system to get what they really expect. Such systems improve the user experience and increase the business profits. Further this way is much faster than other methods. The System Analytics gives the glimpse of how the conclusions are drawn or how the products are selected. The Analytics is another important part of any system as it graphically or pictorially represents the system and makes it easy to understand. This part is essential for the owner as this will help to visualize the highly bought products and the users who bought it which can be used to give more suggestions to the users. The consideration of more than one purchases of the user allows a more detailed and accurate suggestions. This is where the neural networks come into consideration as they store all the previous interactions and not only single interaction.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Interactive Recommendation (IR), System Analytics, Neural Network, Chatbots

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Machine literacy ways have revolutionized the field of healthcare by enabling accurate and timely complaint vaticination. The capability to prognosticate multiple conditions contemporaneously can significantly ameliorate early opinion and treatment, leading to better case issues and reduced healthcare costs. This exploration paper explores the operation of machine literacy algorithms in prognosticating multiple conditions, fastening on their benefits, challenges, and unborn directions. We present an overview of colorful machine literacy models and data sources generally used for complaint vaticination. Also, we bandy the significance of point selection, model evaluation, and the integration of multiple data modalities for enhanced complaint vaticination. The exploration findings punctuate the eventuality of machine literacy inmulti-disease vaticination and its implicit impact on public health. Once further, I'm applying machine literacy model to identify that a person is affected with many complaint or not. This training model takes a sample data and train itself for prognosticating complaint.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning Disease Prediction, Disease data, Machine Learning.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Sign Language Recognition and Translation to English and Marathi is a project that aims at enhancing communication between the deaf and the hard of hearing (DHH) community with the hearing populace. Sign language, which is the primary means of communication among DHH, is often a barrier to various aspects such as education, health care, employment and social interactions. This project seeks to eliminate this communication barrier using state-of-the-art technology by recognizing sign-language gestures for spoken and written language in English and Marathi--two majorly spoken languages. The project serves an essential purpose of improving communication between the Deaf-Hard of Hearing (DHH) community and the general population. A primary form of communication used by DHH is sign language, which remains problematic in different areas such as education, health care, jobs or even social interaction. In order to solve this problem, cutting-edge technologies are utilized in order to create an innovative solution which can detect sign language gestures and translate them into spoken or written forms in both English as well as one of the major Indian languages - Marathi.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, MediaPipe, OpenCV, LSTM Neural Network, Sign Language

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

One of the most vital senses for any individual is the ability to see. Unfortunately, millions of people worldwide grapple with vision impairments, which pose significant challenges in terms of communication and accessing information. This struggle often hinders their ability to navigate safely and independently. To address this issue, the proposed work seeks to transform the visible world into an auditory one. This transformation will be achieved by harnessing real-time object detection technology, empowering individuals with vision impairments to move autonomously without external assistance. Through the application of image processing and machine learning, the program can swiftly identify objects in real time using the camera and convey their locations to blind users through voice output. The inability to differentiate between objects has given rise to numerous problems, and this innovative technology aims to provide a solution.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Object Detection, Android Application, YOLO, CNN (Convolutional Neural Network), Visually Impaired people, Computer Vision, Algorithms

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

An online platform is under development for a college's placement management system, aimed at optimizing the recruitment process and fostering better communication among students, educational institutions, and potential employers. This system will serve as a centralized hub for managing student information, encompassing personal details, academic records, technical competencies, and career aspirations. Additionally, it will enable students to register online for placement opportunities, apply for relevant positions, and monitor their application progress seamlessly. Employers will gain access to a dedicated portal to search for suitable candidates, schedule interviews, and engage with students and placement officers efficiently. Furthermore, the system's implementation will advance toward a paperless environment by digitizing the entire placement procedure, thereby reducing paperwork and promoting environmental sustainability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Web development, Authorization, Student, Admin, TPO, College

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Fashion holds significant sway in our everyday lives, serving as a mirror of our personal style and identity. Yet, navigating the world of fashion and personal style presents challenges, particularly in choosing outfits that flatter individual body types and shapes. This process often proves daunting and time-consuming, leading to indecision and a lack of confidence in one's appearance. To tackle these hurdles, this study aims to develop an ML-based Outfit Suggestion System. Introducing an innovative approach, this system harnesses machine learning methodologies, including deep learning, computer vision, and natural language processing. By scrutinizing an extensive dataset encompassing clothing items and body shape attributes, the system furnishes tailored outfit recommendations designed to suit individual body types and shapes. This research marks a notable stride in the evolution of fashion recommendation systems, offering a promising avenue for fashion enthusiasts seeking personalized outfit guidance across varied contexts.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fashion Recommendation, Clothing Recommendation, Machine Learning, Fashion Dataset, Body Shape Analysis, Body Type Analysis, Body Types, Fashion

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Choosing outfits that complement our body types can be challenging and time-consuming, leading to uncertainty and a lack of confidence. This study aims to address these challenges by developing a Machine Learning- based Outfit Suggestion System. This innovative system utilizes various machine learning techniques, such as deep learning, computer vision, and natural language processing, to analyze a vast dataset containing clothing items and body shape attributes. By doing so, it provides personalized outfit recommendations tailored to individual body types. This research represents a significant advancement in fashion recommendation systems, offering a promising solution for fashion enthusiasts seeking personalized outfit suggestions across different contexts.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Style Advice, Apparel Suggestions, AI-driven Fashion Guidance, Apparel Dataset, Physique Assessment, Physique Analysis, Body Structures, Apparel Trends.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract--Cryptocurrency markets exhibit high volatility, making accurate price prediction a challenging task. This paper shows us a good approach to cryptocurrency price prediction using deep learning techniques, specifically Long Short-Term Memory (LSTM) neural networks. The study utilizes historical cryptocurrency data (BTC-USD1.csv) and applies preprocessing techniques to prepare the dataset for model training. The LSTM model is trained on this data to forecast short-term price movements. Findings show how well the model works to forecast cryptocurrency values, giving traders and investors valuable information.The paper concludes with discussions on the implications of the findings and suggestions for future research directions in the field of financial forecasting using deep learning.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cryptocurrency, Price Prediction, Deep Learning, LSTM, Neural Networks, Financial Forecasting

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In today's dynamic urban environments, efficient cab management systems are crucial for seamless transportation and passenger satisfaction. This paper presents the design and implementation of a cab management system built with Flutter for a mobile frontend and Firebase for a robust backend. Our primary focus lies on optimizing the driver-rider matching process to ensure timely cab allocation and minimize wait times. The paper details the system architecture, outlining how Flutter's cross-platform capabilities create a user-friendly mobile application for both riders and drivers. Firebase's real-time functionality is leveraged to facilitate efficient communication and data exchange between app users and the backend system. We delve into the core aspects of our driver-rider matching algorithm, explaining how it considers various factors to optimize connections. This may include factors like driver location, rider destination, and real- time traffic conditions (if implemented). By implementing this cab management system, we aim to demonstrate the effectiveness of Flutter and Firebase in building a scalable and optimized solution for matching cab drivers with riders. The paper concludes by discussing the potential benefits of this system for transportation service providers and riders alike, emphasizing improved efficiency and user satisfaction.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cab management, Flutter, firebase,Driver-rider matching, Optimization, Real-time communication,alability, Efficiency, User satisfaction, Transportation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the vast landscape of machine learning, the emergence of adversarial threats has cast a shadow over the reliability and security of deployed models. With the proliferation of sophisticated attacks aimed at undermining the integrity of machine learning systems, the imperative for robust defenses has never been more pronounced. Against this backdrop, this paper embarks on a comprehensive journey through the adversarial landscape, surveying the myriad threats and safeguards that define the contemporary discourse in machine learning security. Under the banner of "Navigating the Adversarial Landscape," this survey endeavors to shed light on the intricate interplay between adversarial attacks and defensive strategies. By analyzing the life structures of ill- disposed dangers and examining the viability of existing protections, this try looks to outfit per users with a nuanced comprehension of the difficulties and open doors intrinsic in defending AI frameworks. As we embark on this expedition, we delve into the nuanced nuances of adversarial attacks, encompassing a spectrum of techniques ranging from subtle perturbations to outright manipulations. From white-box to black-box attacks, and from transfer to physical assaults, we unravel the diverse tactics employed by adversaries to subvert machine learning systems. However, amidst the looming specter of adversarial threats, glimmers of hope emerge through the pursuit of robust defense mechanisms. Through adversarial training, robust optimization, and certified defenses, among other strategies, researchers endeavor to fortify machine learning models against adversarial incursions. Ultimately, the quest to navigate the adversarial landscape represents not only a technical challenge but also a moral imperative in safeguarding the integrity and trustworthiness of machine learning systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning Security, Robustness, Vulnerabilities, White-Box Attacks, Black-Box Attacks, Transfer Attacks, Physical Attacks, Defense Mechanisms, Adversarial Training, Robust Optimization, Feature Denoising, Certified Defense

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the ever-evolving landscape of music consumption, the development of intelligent recommendation systems has become imperative to enhance user experience. This research paper introduces a pioneering approach to music recommendation by integrating advanced Convolutional Neural Networks (CNN) with face expression recognition. The proposed system aims to personalize music suggestions by analyzing users' facial expressions, extracting emotional cues, and aligning them with the corresponding auditory preferences. The convolutional neural network component of the system is designed to learn intricate patterns and features from music spectrograms, capturing both the audio content and underlying emotional nuances. Simultaneously, facial expression recognition technology is employed to discern users' emotional states during music listening sessions. By fusing these two modalities, our system strives to create a holistic understanding of users' preferences, considering both explicit musical features and implicit emotional responses. To achieve this integration, we leverage machine learning architectures for music analysis and facial expression recognition. A wide variety of facial expressions and musical genres are included in the dataset that the model is trained on. Additionally, the research explores the challenges and opportunities associated with combining these distinct modalities, such as data preprocessing, feature extraction, and model fusion. This research contributes to the ongoing discourse on the fusion of multimodal technologies for more nuanced and personalized recommendation systems, paving the way for innovative applications in the intersection of music and affective computing.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Music, CNN, Expression, Feature Extraction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

We propose a new approach for playing music automatically using facial emotion Current methods often involve manually recording music, using computer-based tools, or classifying sounds. Instead, we recommend manually changing the way you rank and play. We use convolutional neural networks for emotion recognition. Pygame and Tkinter are available for down load. Our proposed method will reduce the calculation time as well as reduce the total cost of obtaining results and building the system, thus improving the overall accuracy of the system. The testing was done on the FER2013 dataset. Capture face with built in camera. Feature extraction is performed on facial images to direct emotions such as happiness, anger, sadness, surprise and neutrality

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Face Recognition, Feature extraction, Emotion detection, Convolutional Neural Network, Pygame

  License

Creative Commons Attribution 4.0 and The Open Definition