64 hasil
Menampilkan 1–20 · 0,23 detik · RSS
Journal of Computing and Communication
ISSN 2636-3577 · Misr International University (MIU) · 64 artikel di indeks
-
Artikel Jurnal Teks lengkap
AgriVision: An Offline-First Edge AI System for Crop Disease Detection and Severity Estimation Using YOLO-Based Instance Segmentation in Low-Resource Agriculture
The spread of crop diseases is a major threat to food supply and agricultural productivity. Existing AI-based diagnostic solutions, however, face significant deployment challenges in rural farming areas due to their reliance on continuous internet connectivity and limited accessibility in…
-
Artikel Jurnal Teks lengkap
An AI-Driven Multimodal Emotion-Aware Application Based on Internal Family Systems Therapy
The present study aims to explore the rising trend of mental health support systems utilizing AI technology to provide personalized and accessible care. However, such systems often remain limited to unimodal text-based interaction with users and lack emotional understanding. Therefore, this paper…
-
Artikel Jurnal Teks lengkap
OpsMind: An AI-Assisted Decision-Support Framework for Intelligent IT Service Management
With enterprises processing more service requests, while striving to preserve operational efficiency and adherence to Service Level Agreements (SLAs), the ITSM environments are rising in complexity. Artificial Intelligence (AI) has already been used to automate ticket classification or chatbot…
-
Artikel Jurnal Teks lengkap
An Improved Business Intelligence Framework for Educational Data Mining and Learning Analytics
Artificial decision-support systems that accurately predict student academic performance while providing interpretable insights are increasingly important for higher education. Although Educational Data Mining (EDM) has achieved strong predictive performance, many existing approaches emphasize…
-
Artikel Jurnal Teks lengkap
3D CNN-Based ADHD Classification Integrated with Adaptive Learning Strategies for Academic Performance Enhancement
One of the most prevalent neurodevelopmental conditions affecting students is Attention Deficit Hyperactivity Disorder (ADHD). Understanding and supporting people with ADHD remains a significant challenge in both clinical and educational settings. This study proposes a deep learning model for…
-
Artikel Jurnal Teks lengkap
An Empirical Evaluation of Raw Text, Light Stemming, and Root Extraction for Arabic Plagiarism Detection
Arabic plagiarism detection is particularly difficult because a single word can appear in many surface forms depending on prefixes, suffixes, and derivational patterns. While many studies emphasize semantic modelling, we observed that the role of basic morphological preprocessing is still not…
-
Artikel Jurnal Teks lengkap
CAMPR-HABS: Context-Aware Multi-objective Persona Recommendation for Hybrid Autonomous Bike-sharing Systems
Bike-sharing has become the main part of urban mobility worldwide and a central element in the development and management of smart cities. Urban bike-sharing networks are increasingly moving toward mixed fleets that bring together traditional docked bikes and self-driving autonomous ones. This…
-
Artikel Jurnal Teks lengkap
Hybrid Approach Combining CLIP and Diffusion Models with Low-Rank Adaptation for Domain-Specific Image Generation
Text-to-image generation has emerged as a transformative technology in artificial intelligence, enabling the creation of visually coherent and contextually relevant images from textual descriptions. This paper presents a novel hybrid framework that combines Contrastive Language-Image Pretraining…
-
Artikel Jurnal Teks lengkap
DEEP Learning Based Handwritten Recognition using Checkerboard Pattern
This research addresses Egypt's Vision 2030 by developing an AI system for automating optical character recognition for documents. This paper uses a deep learning to eliminate manual data entry and improve data accuracy, saving time and resources for organizations, which aligns with the Vision's…
-
Artikel Jurnal Teks lengkap
Advancing Speech Therapy with AI: A Comparative Analysis of Speech Recognition Models
In recent years, advancements in speech recognition technology have significantly impacted various fields, particularly in speech therapy and pronunciation training. Automated Speech Recognition (ASR) systems are extensively utilized to support individuals, notably children with speech impairments…
-
Artikel Jurnal Teks lengkap
A Hybrid Ensemble Machine Learning Framework for Used Car Price Prediction in Egypt with Real-Time Web Integration
Accurately predicting used car prices in emerging economies is a persistent challenge due to volatile market dynamics, limited data availability, and weak valuation transparency. This study proposes a hybrid ensemble machine learning framework designed specifically for the Egyptian automotive…
-
Artikel Jurnal Teks lengkap
Analyzing Public opinion on Climate Change via Twitter: A Machine Learning Approach Using Historical Data
Examining public perspective regarding critical issues such as climate change in the context of a vast social media stream necessitates a computational approach. This study provides an initial benchmark of five classical machine learning classifiers (Multinomial Naive Bayes, Logistic Regression…
-
Artikel Jurnal Teks lengkap
DEEP Learning Based Handwritten Recognition using Checkerboard Pattern
This research addresses Egypt's Vision 2030 by developing an AI system for automating optical character recognition for documents. This paper uses a deep learning to eliminate manual data entry and improve data accuracy, saving time and resources for organizations, which aligns with the Vision's…
-
Artikel Jurnal Teks lengkap
An Optimized Classification and Regression Tree Algorithm by Combining Feature Selection Methods
Feature selection is the process of removing features from the data set that are irrelevant with respect to the task that is to be performed. Also, Feature selection can be extremely useful in reducing the dimensionality of the data to be processed by the classifier, reducing execution time and…
-
Artikel Jurnal Teks lengkap
Smart Access: Integrating Facial and Voice Biometrics with AI-Driven Deepfake and Spoofing Mitigation
Smart Access (SA) is a modern, contactless access control system powered by artificial intelligence, designed to provide secure entry for spaces like offices, hospitals, hotels, and research facilities. Unlike traditional systems that rely on keys, PIN codes, RFID cards, or costly biometric…
-
Artikel Jurnal Teks lengkap
Improving Spoken Language Identification in Noisy Environment Based on Feature Reduction Using PCA
Automatic Spoken Language Identification (ASLID) is essential for effective multilingual communication, especially in real-world environments characterized by noise and acoustic variability where noise significantly impacts performance. This research introduces a robust ASLID framework that…
-
Artikel Jurnal Teks lengkap
Voting Ensemble Learning for Multilingual Sentiment Analysis: A Comparative Study
Multilingual sentiment analysis (MSA) faces many challenges due to language differences, cultural considerations, and data sparsity across languages. Although ensemble learning shows promise for improving robustness and accuracy by combining classifiers, there are relatively few systematic…
-
Artikel Jurnal Teks lengkap
Exploring Thematic Structures in Surah Al-Baqarah using TF-IDF, Dimensionality Reduction, and K-means Clustering
This research work delineates a computational investigation into the thematic structures of all verses from Surah Al-Baqarah usingunsupervised semantic clustering. Given the unique character of Quranic Arabic, the data was pre-processed in a manner aligning with the specific text, starting with…
-
Artikel Jurnal Teks lengkap
Recent Studies and A Review about Detection of Cyber Threats in Cloud Security using Artificial Intelligence
Cloud computing has significantly transformed the IT industry through cost-efficient solutions, offering scalable Data. In the cloud, data may be more vulnerable than data on on-site premises. However, its rapid adoption has also introduced new cyber security risks as systems become increasingly…
-
Artikel Jurnal Teks lengkap
SpamML: An Efficient Framework for Detecting Spam Emails Using Machine Learning
Spam detection or anti-spam techniques are methods to identify and filter out unwanted, unsolicited, or malicious emails, commonly known as spam. These techniques aim to enhance email security, reduce the risk of phishing attacks, and improve the overall user experience. The prediction of spam…