Promising Projects

Project Title: نظام متكامل للذكاء الاصطناعي وإنترنت الأشياء لتعزيز مرونة المنزل المستدام

Description:
يقدم هذا البحث نظاماً هجيناً متكاملاً يدمج بين تقنيات إنترنت الأشياء (IoT) والذكاء الاصطناعي على الحافة (Edge AI) لتعزيز مفهوم (مرونة المنازل (Home Resilience)) في مواجهة التحديات البيئية والخدمية الحادة، مثل تذبذب شبكات الطاقة، والعواصف الترابية، ومخاطر السلامة الصامتة. يعتمد النظام المقترح على معمارية معالجة ثنائية النواة (Master-Slave Architecture)؛ حيث يقوم متحكم (Arduino Mega 2560) بمعالجة البيانات القادمة من شبكة المستشعرات البيئية وتطبيق خوارزميات اتخاذ القرار مسبقة الأوزان، بينما يعمل متحكم (WeMos D1 - ESP8266) كبوابة اتصالات لاسلكية لبث البيانات لحظياً عبر خادم ويب محلي وتحديث لوحة التحكم التفاعلية للمستخدم كل ثانيتين.

Uploaded At: 2026-07-02 17:21:02

Project Title: Smart Lecture Follower: A Real-Time Speech-Driven Lecture Synchronization System for Intelligent Educational Environments

Description:
Smart Lecture Follower is an intelligent real-time lecture synchronization system that automatically aligns spoken lecture content with written educational materials. The system integrates OpenAI Whisper ASR for speech transcription, intelligent document processing (PDF/DOCX/TXT), text normalization, and fuzzy matching algorithms to continuously identify and highlight the exact paragraph being discussed by the lecturer — with no manual intervention required. Key innovations include: (1) real-time speech-to-paragraph matching operating in 5-second audio intervals, (2) fuzzy matching engine handling pronunciation differences and speech variability without requiring exact text match, (3) offline deployment with no cloud infrastructure dependency, (4) multilingual recognition support including Arabic and English, and (5) a five-layer architecture covering Input, Speech Processing, Document Analysis, Matching, and Visualization. Performance evaluation shows 98.2% matching accuracy in quiet environments at normal speaking speeds, with sub-2-second response latency across all tested conditions. The system directly addresses SDG 4 (Quality Education) and SDG 10 (Reduced Inequalities) by providing critical accessibility support for non-native speakers, students with attention difficulties, and learners in multilingual environments. Built with Python, OpenAI Whisper, and a modular desktop architecture.

Uploaded At: 2026-06-29 19:13:09

Project Title: Predictions Using the Neuro-AI Prosthetic Control System With Human Digital Twin and Predictive Reflex Intelligence

Description:
This project proposed an intelligent neuroprosthetic control system to liberate patients from sensory isolation and delayed reflex response associated with conventional artificial limbs. The proposed system consists of a multisensory electronic skin, an acquisition unit based on Arduino Mega, AI Cortex and Human Digital Twin for the real-time monitoring, prediction of danger, and reflex action to protect the person. In this case, the prototype developed can be a set of twenty distributed sensors covering both key sensory functions such as human skin. It typically has nine temperature sensors, five force sensors, and six moisture sensors. Sensor data also gets processed to produce pain index, injury risk, detected state and recommended motor response. Human Digital Twin serves to visualize and analyze the digital surrogate of a prosthetic limb; based on all physiological parameters, Predictive Reflex Intelligence layer can raise premonitory alerts and even execute automated decisions before we reach an injury risk. The integrated hardware sense, AI and digital twin visualization in a unified platform enhances safety, interpretability and user awareness contrary to the conventional microcontroller-only prosthetic control. It has high potential for smart prosthetics, rehabilitation robotics, medical assistive devices to enhance human-machine interaction systems.

Uploaded At: 2026-06-29 18:25:19

Project Title: DOXY . The interactive Quadruped robot

Description:
DOXY project represents a modern approach to mobile robotics, moving away from traditional
wheeled designs toward more versatile legged locomotion. Quadruped robots are inspired by
nature, mimicking the stability and agility of four-legged animals to overcome challenges that limit
conventional machines. The primary advantage of this design lies in its superior adaptability; while
wheeled robots require smooth, flat surfaces to operate effectively, a quadruped system like
Doxy can navigate uneven terrain, step over obstacles, and maintain balance in complex
environments

Uploaded At: 2026-07-06 03:05:32

Project Title: Hybrid cooling system for solar panels using Geothermal and phase change materials

Description:
Photovoltaic (PV) panels are an important renewable energy source, but their efficiency decreases with increasing operating temperature, particularly in hot climates such as Iraq. This study investigates a hybrid cooling system combining Phase Change Material (PCM) and geothermal cooling to enhance the thermal and electrical performance of PV panels.Paraffin wax (RT42) was used as PCM to absorb excess heat during peak solar radiation, while a geothermal loop assisted in heat dissipation and PCM regeneration.
Experimental measurements of temperature, voltage, current, power output, and efficiency were conducted and compared with a conventional PV panel under outdoor conditions. The results indicated that the hybrid cooling system effectively reduced PV operating temperature and improved thermal stability. Consequently, the cooled panel achieved
higher electrical output and efficiency compared to the conventional system. The integration of PCM with geothermal cooling proved to be a sustainable and effective approach for improving PV performance in hot environments.

Uploaded At: 2026-07-06 02:58:54

Project Title: نظام آمن للتحقق الحيوي متعدد العوامل للدفع الإلكتروني والتحقق من الهوية باستخدام التعرف على أوردة الكف، وبصمة الإصبع، والتشفير الهجين

Description:
يهدف مشروع إلى تطوير نظام متقدم للتحقق الحيوي متعدد العوامل يوفر مستوى عالياً من الأمان في عمليات التحقق من الهوية والدفع الإلكتروني. يعتمد النظام على دمج تقنيتي التعرف على أوردة الكف وبصمة الإصبع للتحقق من هوية المستخدم، مما يقلل من مخاطر انتحال الهوية والتزوير مقارنة بوسائل التحقق التقليدية.

تبدأ عملية التسجيل بجمع عدة عينات من أوردة الكف وبصمات الأصابع لإنشاء هوية حيوية فريدة لكل مستخدم. بعد ذلك، تتم معالجة القوالب الحيوية وحمايتها باستخدام بنية تشفير هجينة تدعى Xeillia قبل تخزينها بشكل آمن على الخادم المركزي Xea. وعند تنفيذ عملية تحقق أو دفع إلكتروني، يقوم النظام أولاً بالتحقق من أوردة الكف، ثم ينتقل إلى التحقق من بصمة الإصبع، ولا يتم اعتماد العملية إلا بعد نجاح المرحلتين معاً.

تم تطوير النظام باستخدام C# وASP.NET Core لبناء خدمات الخلفية (Backend)، وPostgreSQL لإدارة وتخزين البيانات، وFlutter لتطوير واجهة المستخدم، مع استخدام Flutter FFI للتكامل مع أجهزة القياسات الحيوية ومكتباتها الأصلية. كما يتضمن المشروع محرك عرض ذكي يعتمد على النماذج اللغوية الكبيرة (LLM) لتحسين عرض البيانات، وتوضيح سير العمليات، ودعم تجربة المستخدم أثناء العرض والتفاعل مع النظام.

يوفر مشروع حلاً عملياً قابلاً للتوسع يمكن تطبيقه في القطاعات المصرفية، وأنظمة الدفع الإلكتروني، والهوية الرقمية، والجهات الحكومية، والمؤسسات التي تتطلب مستويات عالية من الأمان والموثوقية في التحقق من هوية المستخدمين.

Uploaded At: 2026-07-05 20:07:26

Project Title: Safe Stride: A Wearable Smart Shoe and AI-Powered Mobile System for Prediction Obstacles in Real-Time for the Impaired People

Description:
Safe Step is an integrated smart system designed to help visually impaired individuals navigate safely and independently by combining a smart shoe with an AI-powered app. The shoe uses a suite of sensors to detect nearby obstacles, slopes, and falls, while the app employs computer vision and AI algorithms to instantly detect obstacles, people, and traffic signs via the phone's camera or an external camera, depending on the user's preference.

The system integrates data from the shoe and the app to make real-time decisions and sends audible and vibration alerts to the user. It can also send emergency notifications, including the user's location, to family members or caregivers in the event of a fall or other serious danger.

The project aims to improve user safety, reduce reliance on white canes, and enhance independence and quality of life by leveraging AI, IoT, and embedded systems into a practical, low-cost, and scalable solution.

Uploaded At: 2026-07-06 01:48:08

Project Title: Autonomous Rescue and Emergency System

Description:
The Autonomous Rescue and Emergency System (ARES) is an intelligent Unmanned Ground Vehicle (UGV) engineered for search and rescue operations, hazard evaluation, and tactical exploration in disaster environments. Built on an omnidirectional Mecanum-wheeled drivetrain with closed-loop encoders, ARES features a dual-processor configuration combining a Raspberry Pi Pico 2 W for low-level sensor telemetry (GPS, gas, temperature, and ultrasonic distance) and an ESP32-CAM co-processor driving a dual-axis pan-and-tilt servo turret. At the Ground Control Station (GCS), a Flask-based server coordinates real-time telemetry tracking and streams live video processed via edge-accelerated YOLOv8 models for automated fire and survivor detection, utilizing a thermal fusion algorithm for low-visibility operations.

Uploaded At: 2026-07-05 23:18:27

Project Title: Intelligent Load Balancing In 4G/LTE Networks Using Reinforcement Learning For The Arbaeen Pilgrimage

Description:
This project presents an intelligent load balancing and congestion control framework for 4G/LTE networks using reinforcement learning to optimize network performance under high-density traffic conditions. Implemented in the ns-3 simulator, the proposed system employs a mode-aware controller that dynamically switches between normal, load-balancing, and emergency modes based on real-time network KPIs. A TD3-based reinforcement learning agent optimizes Cell Individual Offset (CIO) values to improve user distribution, reduce congestion, and enhance throughput and packet delivery. The framework is evaluated using an Arbaeen pilgrimage scenario, demonstrating superior performance compared with conventional rule-based load balancing approaches while maintaining adaptive and reliable network operation.

Uploaded At: 2026-07-05 04:38:05

Project Title: Deep Learning and Transformer-Based Architectures for Iraqi Arabic Sentiment Analysis on Social Media

Description:
Sentiment analysis of dialectal Arabic, particularly the Iraqi dialect, poses significant challenges for Natural Language Processing (NLP) systems due to the informal nature, morphological complexity, and scarcity of annotated resources for this language variety. This project proposes a comprehensive two-track deep learning approach to classify Iraqi Arabic social media text into positive, negative, and neutral sentiment categories. The first track employs pre-trained FastText Arabic word embeddings with traditional deep learning architectures, namely Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. The second track fine-tunes the MARBERT Transformer model, which was specifically pre-trained on large scale Arabic social media data. A manually annotated dataset of 4,177 Iraqi Arabic tweets was compiled and subjected to a rigorous dialect-specific preprocessing pipeline. Experimental results demonstrate that MARBERT achieves the highest performance with an accuracy of 93.88% and a macro-F1 score of 93.89%, significantly outperforming all FastText-based baselines. Among the traditional models, CNN yields the best results with 88.61% accuracy, followed by DNN at 88.01% and LSTM at 86.21%. These findings confirm that domain-specific Transformer models are highly effective for dialectal Arabic
sentiment analysis

Uploaded At: 2026-07-05 11:37:46

Project Title: AI-Powered Pothole Detection and Road Condition Monitoring Using Smartphone Cameras

Description:
One of the major challenges is the maintenance of roads, which directly affects traffic
safety and vehicle longevity. Potholes are one of the most frequent road defects,
causing accidents, vehicle damage and higher maintenance costs, especially in
developing countries. The project proposes an economical intelligent road monitoring
system that uses the camera of a smartphone attached to a vehicle to automatically
detect the potholes and send alerts to the drivers and the location to the maintenance
authorities.The proposed system uses YOLOv11x deep learning model for real-time
pothole detection. The Roboflow platform was used to collect a dataset of 4,136 road
images under various lighting conditions, road environments and camera viewpoints.
Images were manually annotated with bounding boxes and data augmentation
techniques were employed to improve generalization of the model. The trained model
was quantized to INT8 for smartphone deployment, which resulted in a smaller model
size and faster inference speed. A mobile application was built with Flutter for real
time detection and visualization. Experimental results achieved 91.9% [email protected]
with an inference speed of 8-12 frames per second on mobile devices. The results
indicate that smartphone-based pothole detection can be an effective, scalable and
cost-effective approach to road condition monitoring, leading to safer transportation
and more efficient road maintenance operations.

Uploaded At: 2026-07-05 13:53:48

Project Title: Smart Firefighting Vehicle

Description:
Fires pose a significant threat to human life, property, and infrastructure, especially in hazardous or enclosed
environments that are difficult for firefighters to access quickly and safely. With rapid technological
advancements, employing smart systems and modern technologies has become essential to minimize human and
material losses resulting from fires. This research aims to design and implement a smart fire engine capable of
detecting and responding to fire sources automatically or semi-automatically, thus reducing human intervention
and increasing the efficiency of firefighting operations. In this project, a working prototype of a smart robotic fire
truck was designed and implemented using an Arduino Mega 2560 board as the main control unit. A set of sensors,
such as a flame sensor to detect the source of a fire, was connected, along with DC motors to control the vehicle's
movement and a small water pump to extinguish the fire upon detection. The system was programmed using
Arduino C to control sensor readings and make appropriate decisions, enabling the vehicle to move automatically
towards the source of the flame. Once a suitable distance is reached, the water pump is activated to extinguish the
fire. The system was also tested in a small-scale simulation environment to ensure its accuracy and speed of
response to the fire source. The project results showed that the system is capable of detecting and responding to
fires quickly and effectively within a specified distance. The use of sensors improved guidance accuracy and
reduced the error rate. Furthermore, the tests demonstrated that the system can operate autonomously without
direct human intervention, enhancing the potential for using this technology in hazardous environments or hardto-reach, enclosed spaces.

Uploaded At: 2026-07-01 04:08:37