Volume 13 | Issue 10 |

 Abstract

Technical interviews for software engineering roles demand both deep technical competence and the ability to communicate solutions clearly and confidently. Candidates typically prepare using a patchwork of resources -- coding platforms, textual guides on system design, recorded mock interviews -- none of which provide an integrated, adaptive, and evidence-backed training pipeline. HireIQ is an AI-integrated web platform designed to replace that fragmentation with a single, end-to-end preparation ecosystem. The platform first ingests a candidate's resume and profile and produces a tailored, prioritized skill inventory using layout-aware parsing and transformer-based embeddings. Using that profile, HireIQ generates company- and role-specific roadmaps, micro-projects, and question sequences that combine coding problems, system-design cases, and behavioral prompts. Mock interviews are delivered in both synchronous and asynchronous modes; responses are captured multimodally (audio + transcript + optional video + code / whiteboard sketches) and evaluated by a suite of specialized graders: a sandboxed code judge for correctness and complexity, transformer-based semantic scorers for explanatory answers, and prosody/voice models for delivery and confidence. Session scoring uses temporally aware, window-consistency fusion to stabilize judgments and produce session-level reports with confidence intervals. All automated judgments are supplemented with human-readable evidence (transcript highlights, failing test cases, design checklist gaps) to make feedback actionable. HireIQ also embeds fairness-aware model training and operational privacy controls (consented video capture, encryption, minimal retention) to reduce bias and protect candidates. This document describes HireIQ's architecture, algorithms, evaluation strategy (including data collection, human rater alignment, ablation and fairness studies), sample report templates, and a staged deployment plan. The platform's goals are to (1) accelerate measurable improvement in candidate readiness, (2) provide interpretable, reproducible feedback comparable to expert evaluation, and (3) scale to institutions and training programs while protecting candidate privacy and fairness.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI, Interview preparation, Interview Assistant, Chatbot, Natural Language Processing, Web development, Sentiment Analysis, Voice-based interaction, Job Interview Simulation, Personalized Feedback System, Recruitment, Company-specific roadmap, Career Development

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Phishing websites have become one of the most common ways attackers trick people into sharing sensitive details like passwords and banking information. Since new fake websites are created every day, traditional methods such as blacklists are not always effective. In this paper, we present PhishGuard, a system designed to detect phishing websites using machine learning. The system extracts features from website URLs, page content, and SSL certificates, and then applies classification algorithms to predict whether the site is genuine or fake. Our experiments show that Random Forest performed better than other models, achieving about 96% accuracy. With this approach, PhishGuard provides an additional layer of online security and helps reduce the risk of phishing attacks.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Phishing Detection, Machine Learning, Website Security, Online Fraud Prevention

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Building modern websites requires significant technical expertise, time, and resources. Many individuals and small businesses struggle to create professional and functional websites due to limited technical knowledge. The AI Website Builder project introduces an intelligent system that uses artificial intelligence to automate website creation. By leveraging Natural Language Processing (NLP), machine learning, and pre-trained design models, the system can generate responsive, customizable, and user-friendly websites from simple text-based user inputs. This reduces development time, cost, and dependency on expert programmers, making website development accessible to all.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Website Builder, NLP, Machine Learning, Automation, Web Development

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Decentralized voting using Ethereum blockchain is a secure, transparent and tamper-proof way of conducting online voting. It is a decentralized application built on the Ethereum blockchain network, which allows participants to cast their votes and view the voting results without the need for intermediaries. In this system, votes are recorded on the blockchain, making it impossible for anyone to manipulate or alter the results. The use of smart contracts ensures that the voting process is automated, transparent, and secure. The use of the blockchain technology and the implementation of a decentralized system provide a reliable and cost- effective solution for conducting trustworthy and fair elections.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

" Blockchain-BasedSecure Voting system for Local Governance"

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Rent All is a peer-to-peer rental platform designed to connect item owners with renters in a secure, reliable, and affordable manner. The system allows users to list electronics and household items, search for products, make rentals, process payments, and exchange reviews. It addresses the growing need for sustainable consumption by reducing idle resources and promoting a sharing economy. Key features of Rent All include verified user accounts, secure payment integration, and in-app messaging for trust and transparency. The project demonstrates how technology-driven platforms can provide affordable access to resources while supporting sustainability and reducing waste.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Peer-to-peer rental, Sharing economy, Sustainability, Secure transactions, RentAll, Online platform, Item listing, Reviews.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents the development and evaluation of a mobile application designed for real-time plant disease detection using a convolutional neural network (CNN) model deployed with TensorFlow Lite and implemented through the Flutter framework. The EcoGate Android application is an innovative mobile solution developed using Java/XML and integrated with Firebase Realtime Database to promote sustainable gardening and eco-friendly practices. The app combines multiple intelligent modules into a single platform: an E-commerce marketplace for gardening tools and eco-products, a leaf disease detection system that leverages machine learning for early plant health monitoring, an AI-powered chatbot offering real-time gardening tips and problem-solving guidance, and a video learning module that provides curated gardening tutorials. Users can purchase eco-products, diagnose plant issues by uploading leaf images, receive instant AI-based recommendations, and access educational resources to improve their gardening skills. By integrating real-time data storage and AI-driven features, EcoGate enhances user engagement, fosters sustainable environmental practices, and bridges the gap between technology and eco-conscious living. The importance of early disease detection in plants cannot be overstated, as it plays a crucial role in preventing the spread of diseases and ensuring optimal crop yield. Traditional methods of plant disease detection involve manual inspection by experts, which is time-consuming, subjective, and not scalable for large agricultural operations. Other existing solutions, such as cloud- based machine learning models, require continuous internet access, leading to latency issues and dependency on network availability. These limitations highlight the need for a more efficient and accessible solution. In this context, the proposed mobile application stands out by offering a real-time, offline capability that is both efficient and user-friendly. The application utilizes the camera package in Flutter to access the device's camera and continuously capture frames. These frames are then processed using a TensorFlow Lite model, which has been optimized for mobile devices. The model was trained on a comprehensive dataset consisting of various plant diseases, enabling it to accurately classify and identify disease symptoms from the captured images. The methodology section of this paper details the entire devel- opment process, including dataset preparation, model training, and conversion to TensorFlow Lite. The dataset comprises labeled images of healthy and diseased plants, covering a wide range of common plant diseases such as leaf blight, rust, and powdery mildew. Data augmentation techniques were employed to increase the diversity and size of the dataset, thereby enhancing the model's robustness. The CNN model architecture was chosen for its effectiveness in image classification tasks, and it was trained using TensorFlow with parameters optimized for high accuracy and generalization. Post-training, the model was converted to TensorFlow Lite format, involving quantization techniques to reduce the model size while maintaining performance, thus ensuring smooth and efficient inference on mobile devices. The mobile application development phase leveraged Flutter for its cross-platform capabilities and expressive UI components. The user interface was designed to be intuitive and accessible, with key screens including a home screen, a live scanning interface, and a result display. The home screen provides users with information and instructions, while the scanning interface displays the live camera feed along with real-time detection results. Upon detection of a disease, the application displays detailed information about the disease, including possible treat- ments and preventive measures. Performance evaluation of the application was conducted to assess its accuracy, latency, and user experience. The model achieved an accuracy of 95%, with a precision of 93%, recall of 94%, and an F1-score of 93% on the test dataset. Real-time performance metrics indicated that the application processes frames at a rate of 15 frames per second, with a detection latency of approximately 200 milliseconds. User feedback from preliminary testing highlighted high satisfaction with the app's speed and accuracy, emphasizing its practical utility in real-world agricultural scenarios. The discussion section of the paper analyzes the results, com- paring the proposed solution with existing methods. The proposed mobile application outperforms traditional manual inspection and cloud-based solutions in terms of speed, accessibility, and user convenience. These limitations suggest directions for future research, including improving the model's robustness, expanding the dataset to cover more plant diseases, and integrating addi- tional features such as disease treatment recommendations and a user-friendly interface for educational purposes. In conclusion, this research demonstrates the feasibility and effectiveness of using a mobile application for real-time plant disease detection. By integrating a TensorFlow Lite model with the Flutter framework, the application provides a practical and accessible tool for farmers and agricultural professionals, aiding in early disease detection and contributing to enhanced agricultural productivity. Future work will focus on refining the model and application, aiming to further support the agricultural community in combating plant diseases and ensuring sustainable crop production.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

EcoGate - Leveraging AI and Mobile Technology for Smart Plant Care

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Chronic disease significantly affects health on a global scale. Deep machine learning algorithms have found widespread application in the diagnosis of chronic diseases. Early diagnosis and treatment reduce the chance of a disease getting worse and, as a result, raise related mortality. Applying this approach to a dataset of optical coherence tomography images, we demonstrate performance comparable to that of human experts in classifying age related macular degeneration and diabetic macular edema. We also provide a more transparent and interpretable diagnosis by highlighting the regions recognized by the neural network. This paper proposes a final year project that develops and evaluates deep-learning pipelines to detect early signs of chronic diseases from medical imagining modalities. The study includes dataset collection and curation, image preprocessing, model design, performance evaluation and explainability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI-Based Early Detection of Chronic Diseases Using Medical Imaging: Use deep learning to detect early signs of diseases like cancer or diabetes from X-rays or MRI scans.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Recently, the Internet of Things (IoT) and computer vision technologies find useful in different applications, especially in healthcare. IoT driven healthcare solutions provide intelligent solutions for enabling substantial reduction of expenses and improvisation of healthcare service quality. At the same time, Diabetic Retinopathy (DR) can be described as permanent blindness and eyesight damage because of the diabetic condition in humans. Accurate and early detection of DR could decrease the loss of damage. Computer-Aided Diagnoses (CAD) model based on retinal fundus image is a powerful tool to help experts diagnose DR. Some traditional Machine Learning (ML) based DR diagnoses model has currently existed in this study. The recent developments of Deep Learning (DL) and its considerable achievement over conventional ML algorithms for different applications make it easier to design effectual DR diagnosis model. With this motivation, this paper presents a novel IoT and DL enabled diabetic retinopathy diagnosis model (IoTDL-DRD) using retinal fundus images. The presented Internet of Things Deep Learning- Diabetic Retinopathy Diagnosis (IoTDL-DRD) technique utilizes IoT devices for data collection purposes and then transfers them to the cloud server to process them. Followed by, the retinal fundus images are preprocessed to remove noise and improve contrast level. Next, mayfly optimization based region growing (MFORG) based segmentation technique is utilized to detect lesion regions in the fundus image. Moreover, densely connected network (DenseNet) based feature extractor and Long Short Term Memory (LSTM) based classifier is used for effective DR diagnosis. Furthermore, the parameter optimization of the LSTM method can be carried out by Honey Bee Optimization (HBO) algorithm. For evaluating the improved DR diagnostic outcomes of the IoTDL-DRD technique, a comprehensive set of simulations were carried out. A wide ranging comparison study reported the superior performance of the proposed method.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Computer aided diagnosis, deep learning, diabetic retinopathy, fundus images, honey bee optimization.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Rapid urban growth, deforestation, and natural disasters are driving substantial land cover changes worldwide, posing significant challenges to sustainable development and environmental stewardship. Conventional change detection methods, such as image differencing and manual classification, often require intensive effort and deliver inconsistent accuracy under varying environmental conditions. GeoAlert is introduced as an AI-powered change monitoring system that automates the multi-temporal detection of land cover change using satellite imagery from high-resolution sensors, including Landsat-8 and Sentinel-2. The system preprocesses raw satellite data, aligns images, and applies advanced deep learning models, notably U-Net and Siamese CNN architectures, for per-pixel land cover classification and systematic change mapping. Changes identified are visualized via thematic maps and shared on a cloud-based dashboard, providing near-real-time alerts to stakeholders. In a comprehensive case study focusing on Hyderabad, India, GeoAlert achieved 89% classification accuracy, notably outperforming traditional image differencing approaches that scored 74%. These results highlight GeoAlert's potential as a scalable, robust decision-support tool for urban planners, environmental managers, and policy-makers in rapidly changing landscapes.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Change Detection, Remote Sensing, Deep Learning, Siamese Network, U-Net, Landsat-8, Sentinel-2, Cloud Computing, Urban Growth, Environmental Monitoring

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The College Portal System for Student Exam Form Submission and Verification is a role-based, web-driven platform developed to streamline exam form handling in academic institutions. The system is divided into three modules: PH1 for students, PH2 for teachers, and PH3 for accounts staff. Students log in using email and OTP, upload exam forms and payment proofs, and monitor application status. Teachers verify or reject submissions in a first-come, first-verify order with remarks, while accounts staff validate payment proofs and confirm financial clearance. This centralized, paperless system improves accuracy, efficiency, and transparency while reducing delays and manual errors. It enhances communication and accountability among stakeholders, ensuring a faster and more reliable examination process

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

College Portal System, Exam Form Submission, Student Dashboard, Teacher Verification, Accounts Dashboard, Role-Based Access, Paperless Workflow, Academic Administration, Secure Authentication, Transparency

  License

Creative Commons Attribution 4.0 and The Open Definition