293 hasil
Menampilkan 1–20 · 0,36 detik · RSS
International Journal of Intelligent Computing and Information Sciences
ISSN 2535-1710 · Ain Shams University, Faculty of Computer and Information Science · 293 artikel di indeks
-
Artikel Jurnal Teks lengkap
Temporal Trust Decay with Adaptive Differential Privacy for Blockchain-Based Sybil Resistance
Trust systems in decentralized blockchain networks commonly treat reputation as permanent, creating a vulnerability in which a user can accumulate trust through honest behavior, go dormant, and later return to exploit their stored reputation. This paper proposes a temporal trust-adaptive…
-
Artikel Jurnal Teks lengkap
E-COMMERCE FAKE PRODUCTS' REVIEWS DETECTION USING NLP AND DEEP LEARNING
E-commerce has become widely used in recent years. Online E-commerce platforms use online text reviews and rates of products for marketing these products. New online buyers and customers mainly consider these online reviews and rates before their online purchases. Unfortunately, many of these…
-
Artikel Jurnal Teks lengkap
Stock Market Prices Prediction using Deep Learning v5
Abstract: Stock market price prediction entails forecasting future stock prices and trends based on historical data and various market indicators. Financial news and user generated text are also essential for investors to make informed investment decisions. Stock market price prediction presents a…
-
Artikel Jurnal Teks lengkap
Knowledge-Augmented Question Answering: A Taxonomy, Critical Review, and Practical Guidelines
Knowledge-augmented question answering (KAQA) aims to improve answer accuracy, robustness, and interpretability by integrating external knowledge into neural QA systems. Over the last decade, KAQA evolved from explicit knowledge graph (KG) reasoning to retrieval-augmented generation (RAG) and large…
-
Artikel Jurnal Teks lengkap
A Design of an Intelligent Micro Human Expression Recognition Using Optimized Compact Network and Machine Learning Approach
Abstract: Micro-Expressions (ME) refer to very quick facial movements which are direct signs of someone's real emotional state, especially when they try to hide their emotions. It is extremely difficult to determine these subtle signals correctly because they last only for a fraction of a…
-
Artikel Jurnal Teks lengkap
Comprehensive Survey of Artificial Intelligence Techniques for Disease Detection in Histopathological Images
Abstract: Histopathological image analysis plays a central role in disease diagnosis, especially cancer, where early detection improves patient outcomes. With the growth of digital pathology and artificial intelligence (AI), machine learning and deep learning approaches have transformed…
-
Artikel Jurnal Teks lengkap
Efficient Abstractive Text Summarization with Large Language Models: A Focused Survey
Recent advances in Large Language Models (LLMs) have significantly improved the quality of abstractive text summarization. However, the high computational cost and memory requirements of these models limit their practical adoption, particularly in resource-constrained environments. This focused…
-
Artikel Jurnal Teks lengkap
ENHANCING USER ACTIVITY PREDICTION IN LBSN THROUGH GENERALIZED SEQUENTIAL PATTERN MINING
Location-based social networks (LBSNs) generate extensive user check-in data that reflect mobility behaviors and activity preferences. These check-ins reveal frequent sequential short-term mobility patterns that can be exploited to predict users’ upcoming activities and next locations with higher…
-
Artikel Jurnal Teks lengkap
OTC-DTI a Bayesian Optimization DTI Framework for Drug repurposing...
Drug repurposing offers a faster, lower-cost alternative to de novo drug development, particularly for chronic and neurodegenerative diseases where conventional discovery pipelines are slow and resource-intensive. This paper proposes OTC-DTI (Optimized Transformer-CNN Drug-Target Interaction), a…
-
Artikel Jurnal Teks lengkap
Benchmarking Robust Change Detection under Blur and Cloud Occlusion on LIM-CD and JL1-CD Datasets
Robust change detection (CD) in optical remote sensing imagery is critical for reliable monitoring in real-world conditions, where spatial degradation and atmospheric effects often corrupt observations. While recent deep CD models, such as transformer-based and state-space architectures, have…
-
Artikel Jurnal Teks lengkap
Quantum Leap in Healthcare: A Comparative Analysis of AI/ML and Quantum Computing for Healthcare opportunities of the new era
The healthcare sector is undergoing rapid transformation driven by advances in artificial intelligence and machine learning, with quantum computing emerging as the next major breakthrough. This paper presents a comparative analysis of classical AI/ML and quantum computing applications in…
-
Artikel Jurnal Teks lengkap
Evaluating Construct Validity and Algorithmic Bias in AI Generated Text Detection: A Corpus-Based Audit of Pre-AI Academic Writing
The purpose of this research was to evaluate construct validity of AI generated text detection systems using an examination of a genre segmented corpus of pre-existing academic work that was created prior to the advent of such technology. Using 68 scholarly articles published between 1991 to 2003…
-
Artikel Jurnal Teks lengkap
Training-Free Retrieval-Augmented Classification of Breast Cancer Histopathology Using Frozen Pathology Foundation Models
Breast cancer is one of the most commonly diagnosed cancers in women, and histopathological examination of biopsy tissue is still the diagnostic gold standard. Deep learning has advanced histopathology classification, but most systems share two costs that are easy to overlook: they need…
-
Artikel Jurnal Teks lengkap
A Novel Quality Metric for Content-aware Image Retargeting: Preservation of Objects' Relative Spatial Position
Content-aware image retargeting quality assessment is crucial for evaluating how well retargeting algorithms preserve important visual information while adapting images to different aspect ratios. Existing quality metrics focus primarily on structural similarity, edge preservation, and individual…
-
Artikel Jurnal Teks lengkap
A NORMAL PROMPTING BASED APPROACH FOR ARABIC INTENT CLASSIFICATION
Intent classification in natural language processing (NLP) plays a vital role in identifying users’ intentions from their spoken or written inputs. This task becomes particularly challenging in Arabic due to the language’s rich morphology and inherent ambiguity. Although recent advances in deep…
-
Artikel Jurnal Teks lengkap
A COMPREHENSIVE SURVEY ON AI-ENHANCED CYBER THREAT DETECTION: MODELS, DATASETS, AND METRICS,
The escalation of cyber threats in both frequency and complexity has posed significant challenges to traditional cybersecurity mechanisms. In response to these evolving threats, Use of Artificial Intelligence in Thwarting Cyber Threats The use of AI is increasingly becoming essential to fortify…
-
Artikel Jurnal Teks lengkap
SOLVING MATH WORD PROBLEMS IN THE ERA OF DEEP LEARNING AND LARGE LANGUAGE MODELS: A COMPREHENSIVE SURVEY
Solving Math Word Problems (MWPs) demands the mixed integration of natural language comprehension and mathematical reasoning. This paper conducts a comprehensive study of MWP solvers evolution, tracing their development from Traditional Approaches reaching modern Large Language Models (LLMs). We…
-
Artikel Jurnal Teks lengkap
A Federated Compression Framework for Optimized Transformer-Based Sentiment Analysis
Sentiment analysis is a key task in natural language processing, widely used to extract public opinion in domains such as politics, marketing, and healthcare. Although transformer-based models have significantly improved sentiment classification accuracy, their large computational and memory…
-
Artikel Jurnal Teks lengkap
A SURVEY OF TRANSFORMER AND LARGE LANGUAGE MODEL STRATEGIES FOR CLINICAL ABBREVIATION DISAMBIGUATION: A SPECTRUM OF PARADIGMS
The clinical narrative is a treasure trove of patient information, yet its value is often obscured by a high density of ambiguous abbreviations. For years, resolving this ambiguity was a classic supervised learning problem, held back by data scarcity and the need to create custom models for each…
-
Artikel Jurnal Teks lengkap
Recommender Systems Evolution: Challenges and Future Directions
Recommender systems have become a foundational component in modern digital platforms, shaping how users discover information, products, and services. Their ability to analyze user behavior, model preferences, and anticipate future needs has made them indispensable across a wide range of domains…