Volume 13 | Issue 5 |

 Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by challenges in communication, behavior, and social interaction. Early detection of ASD is crucial for effective intervention, yet access to diagnostic tools remains limited in many regions. This study explores the application of machine learning techniques to develop a predictive model for ASD screening. Using a publicly available dataset, we preprocess and analyze features such as age, gender, and behavioral scores to train multiple algorithms, including Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Random Forest. The Random Forest algorithm demonstrated the highest accuracy, precision, and recall, achieving an Area Under the Curve (AUC) of approximately 1.0. A user-friendly web interface was developed using Streamlit to facilitate accessibility. Our results highlight the potential of machine learning as a preliminary screening tool for ASD, particularly in resource-constrained settings.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Autism Spectrum Disorder, Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Random Forest

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project aims to design and implement a Flask -based web application for automated leaf nutrition and disease classification. The application allows for the users to uploads a leaf image or capture one in real time using a webcam or mobile camera. The system uses OpenCV for preprocessing and a CNNor Mobile Net-based deep learning model to analyze the leaf. The model classifies the leaf into categories such as "healthy","Nutrientdeficient" or diseased. The platform ensures real time processing, displaying results on a user-friendly web interface.The application is built using flaskfor the backend.HTML,CSS Bootstrap for the frontend and TensorFlow orPyTorch for deep learning it is deployed on cloud platforms like python Anywhere making it a practical tool for smart agriculture .

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Flask web application,Leaf disease detection, Leaf nutrient classification, Image classification, Deep learning, CNN (Convolutional Neural Network), Mobile Net, OpenCV preprocessing, Real-time image analysis, Webcam integration, Mobile camera support, User-friendly interface.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Intellectual property rights (IPRs) in the contemporary knowledge economy have a central function to support innovation while influencing the manner in which knowledge is disseminated worldwide. Yet, there are conflicts between safeguarding creators' rights, providing public access to ideas, and dealing with socio-economic imbalances in knowledge dissemination. This article examines the ways in which IPRs have developed, how they influence innovation and access, and what obstacles they create to equal knowledge sharing on the global level

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Trade Marks, Patent, India

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A real-time human detection and people counting system designed for surveillance, crowd monitoring, and behavioral analytics. The system leverages the YOLOv8 deep learning model for accurate and high-speed object detection, combined with the DeepSORT tracking algorithm to ensure consistent identity tracking across video frames, even under occlusion or dense crowd conditions. A motion detection module based on frame differencing and contour analysis dynamically triggers detection only when significant movement is detected, reducing unnecessary computation and improving responsiveness. The graphical user interface (GUI), developed using Python's Tkinter library, allows users to manage video streams, adjust sensitivity, and view live statistics including real-time person count and motion alerts. Experimental results show that the system achieves high detection precision (up to 92.1%) and recall (98%) with a mean average precision (mAP) of 0.971, and maintains a real-time frame rate of 20-30 FPS on GPU hardware. Comparative analysis with the SSD (Single Shot Detector) model demonstrates that YOLOv8 provides superior performance in accuracy and tracking robustness, making it well-suited for both indoor and outdoor deployments. This work demonstrates the viability of deploying intelligent vision-based systems in scalable real-world applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Computer Vision ,DeepSORT, GUI, Human Detection,kalman filter, Motion Detection, Python, Real-Time Tracking, Surveillance, YOLOv8

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract: Introduction: To offer insights that help enhance practitioner well-being and patient care, this study investigates the difficulties mental health practitioners encounter in their day-to-day contact with patients, looking at the psychological, mental, and professional demands of working in this field. Methodology: The lived experiences of mental health professionals dealing with patients in various settings are explored in this qualitative study using a phenomenological method. The study aims to understand how these professionals view and handle daily professional, emotional, and mental challenges when interacting with patients. Results: The three major themes, Psychological Progression, Therapeutic Evolution, and Supportive Formation, emphasize the significant aspects of the experiences of mental health professionals, such as mental and emotional growth, techniques for coping with emotional stress, and approaches to improving patient involvement and social engagement. Discussion: Psychological progression fosters growth through resilience, self-care, and professional development. Therapeutic evolution enhances mental health care through improved strategies, resilience, and continuous professional growth. Supportive development in mental health counseling fosters resilience, ethical care, and professional balance to enhance client outcomes and practitioner well-being. Conclusion: This study explores the many challenges that mental health professionals face. It explored the challenges of mental health professionals with their mental health, as well as their coping and emotional regulation techniques. It discussed mental health professionals' self-care and how they follow specific standards to maintain their personal and professional ethics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Index Terms - Mental health, professionals, well-being, therapy, phenomenology.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A hybrid power generation system combining solar energy and wind energy offers a sustainable, off-grid solution for charging mobile phones and laptops. This system utilizes solar panels and wind turbines to harness renewable energy from both sunlight and wind, which is then stored in a battery bank for later use. The system integrates a hybrid charge controller that optimizes the use of both energy sources, ensuring efficient storage and energy distribution. A DC-to-USB converter or inverter is used to provide power to mobile phones and laptops. This paper discusses the system's components, functionality, and potential benefits for remote or off-grid locations, aiming to reduce reliance on traditional grid electricity. The system makes use of a battery to store the energy generated by both the power generators. This battery supply is now connected through the inverter for usage. The system provides 2 types of outputs. 1 USB outputs for 1 x 5V DC mobile charging ports and 1 x 230V AC port with current limitation for charging laptops only. The system is fitted with 4 wheels for ease of movement making it very portable. It can easily be used near bus stops, garden, historical monuments, zoo, college campus, corporate parks, footpaths, open parking and more.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

SOLAR ,WIND,BATTERY,CIRCUIT BOARD, INTRODUCTION TO HYBRID SYSTEM,TYPES OF HYBRID SYSTEM,

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Modern surveillance, security, and airspace mon- itoring systems rely heavily on flying object detection. The challengeisintheexactdetectionoffast-movingairborneobjects including drones, birds, planes, and balloons especially under varying lighting, altitude, and background clutter conditions. This paper presents HawkEye, a deep learning-based ensemble system combining YOLO (You Only Look Once) and DETR (DEtection TRansformer) models, to provide improved accuracy and robustness in flying object identification. The model is trained on the Flying Objects OB 100 dataset, which coversmany aerial scenarios. The paper offers two key approaches:The paper proposes two primary techniques: (1) DOLO, ahybrid architecture combining YOLO's real-time efficiency with DETR's; and (2) an ensemble learning approach combining several YOLO versions with DETR

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

FlyingObjectDetection,YOLO,DETR,Ensem- ble Learning, Deep Learning, Computer Vision.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study investigates the pivotal role of strategic partnerships in fostering technological innovation within the contemporary business landscape. By analyzing the benefits, challenges, and critical success factors of such collaborations, the research elucidates how organizations leverage complementary expertise, shared resources, and market synergies to achieve competitive advantages. The study explores various partnership models--horizontal alliances, vertical partnerships, joint ventures, and research consortia--through real-world case studies, including Airbnb's collaboration with payment giants and the unsuccessful Uber-Toyota-Volvo autonomous driving alliance. A novel ADeCuMaS framework is proposed to guide organizations in crafting and sustaining effective partnerships. The findings underscore the importance of aligned goals, robust governance, collaborative culture, and continuous adaptation for unlocking the transformative potential of strategic alliances.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Strategic Partnerships, Technological Innovation, ADeCuMaS Framework, Synergistic Innovation, Market Expansion, Risk Mitigation, Collaborative Culture

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Signature Verification Is An Important Aspect Of Contemporary Security Systems, As It Verifies The Authenticity Of A Person Through His Or Her Own Handwritten Signature. As More And More Systems Rely On Digital Systems, There Is A Greater Demand For Automated, Precise, And Effective Signature Verification Systems. Conventional Signature Verification Techniques Include Manual Verification Or Simple Automated Methods, Which Are Time-Consuming And Susceptible To Errors. This Paper Introduces A Novel Signature Verification Method With Convolutional Neural Networks (Cnns) That Utilize Deep Learning Methods To Examine And Validate Signatures. Through The Combination Of A CNN-Based Model With An Easy-To-Use Streamlit Frontend, This System Provides An End-User-Friendly Experience For Real-Time Verification Of Handwritten Signatures. The New Approach Is To Preprocess The Input Signature Images Through Normalization Of Their Sizes, Conversion Into Grayscale, And Improvement Of Their Quality For Uniformity. The Preprocessed Signature Images Are Then Input Into A CNN Model That Extracts The Hierarchical Features, Including Edges, Textures, And Shapes, Automatically, Through A Sequence Of Convolutional And Pooling Layers. This Allows The Model To Extract Efficiently The Subtle Differences Between Authentic And Fake Signatures. The CNN Model Is Trained On A Labeled Dataset Of Authentic And Forged Signatures Using Backpropagation To Adjust The Weights And Enhance The Accuracy Of The Model. The CNN Model Architecture Involves Several Convolutional Layers Followed By Fully Connected Layers, Which Forms A Strong Foundation For Classification. The Model Is Then Deployed Into A Streamlit-Based Frontend Where Users Can Upload Signature Images To Be Verified. Streamlit Offers An Interactive And Light-Weight Environment, Allowing Users To See The Outcome Of The Signature Verification In Real-Time. The System Provides A Yes Or No Output On Whether The Uploaded Signature Is Genuine Or Fake Depending On The Predictions Of The CNN Model. The Streamlit Interface Also Offers A Friendly Presentation Of The Process, Displaying The Uploaded Signature, The Analysis Of The CNN, And The Final Verification Outcome. This Method Has Great Benefits Compared To The Conventional Methods, Such As Higher Accuracy, Scalability, And Capability To Process Large Datasets. The Application Of CNNs In Signature Verification Guarantees High-Level Feature Extraction And Reduces Human Error. Furthermore, The Application Of Streamlit Makes The System Easier To Use And More Accessible, Making It Applicable In Various Fields, Ranging From Banking To Legal Systems. The Integration Of CNN-Based Signature Authentication And Streamlit Frontend Is An Advanced Solution To This Important Security Problem.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Convolutional neural network (CNN); Signature verification; Pre-processing, Pre-trained Model, Fine-tuning, Classification.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Delivery drones are revolutionizing the logistics industry by incorporating state-of-the-art technology to streamline the delivery process. Utilizing advanced navigation systems such as GPS and autonomous flight controls, these drones are capable of reaching precise delivery points in both urban and remote locations. With enhanced imaging and sensor technology, they can detect obstacles and ensure safe, accurate landings. Real-time communication through cellular and satellite networks provides continuous tracking and oversight, allowing for optimized logistics management. Intelligent flight path algorithms minimize delivery time and maximize efficiency, while modern power solutions, including LiPo batteries and advanced energy management systems, ensure prolonged flight and dependable service. These drones are designed to handle a wide variety of payloads, including sensitive goods, enhancing the efficiency, scalability, and safety of last-mile delivery operations in diverse conditions

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Autonomous navigation, Last-mile logistics, Mission Planner, Real-time monitoring, Wireless communication

  License

Creative Commons Attribution 4.0 and The Open Definition