All of the articles in this proceedings volume have been presented at the AISTC’25 “First International Conference on Artificial Intelligence, Smart Technologies and Communications” during 14-15 April 2025 in Chlef-Algeria. These articles have been peer reviewed by the members of the Technical Committee...

Lung cancer ranks among the foremost causes of cancer-related mortality, and early identification is essential for enhancing survival rates. This research introduces a deep learning methodology employing a customised VGG16 convolutional neural network model for the autonomous classification of lung cancer....

This paper introduces Symbiotic AI (SAI), an architecture based on machine learning framework that mimics self-improvement mechanisms of a real brain. It incorporates an Automated Feedback Loop (AFL) that retrains the model on misclassified data, enhancing adaptability and classification. This framework...

Early and precise diagnosis of leukemia subtypes directly impacts the determination of optimal treatment strategies and patient survival rates. Traditional methods often rely on manual microscopic examination of blood and bone marrow samples, which can be time-consuming and prone to human error. In this...

Intrusion detection systems (IDS) play an important role in protecting the networks from increasingly complex cyber-attacks, albeit their effectiveness is often compromised due to the high dimensionality of data and lack of optimization for gainfully trained models. To address these issues, we suggest...

The automatic detection of breast cancer is crucial for early diagnosis, monitoring disease progression, and verifying treatment effectiveness. Recently, deep learning has demonstrated increasing effectiveness due to the availability of diverse image databases and the emergence of new, more efficient...

Obtaining higher-resolution Chest X-ray (CXR) images is often affected by significant challenges, resulting in low-resolution (LR) images that lead to misinterpretations which in turn impede accurate diagnosis. To address these limitations, we introduce in this paper an Iterative Transform-Spatial Feature...

Drug discovery is a critical domain that has a profound impact on healthcare and pharmaceutical development. It consists of several steps, which are expensive, time-consuming operation, and characterized by low success rates. Recently, Deep learning (DL) is considered as a powerful tool to accelerate...

Image captioning facilitates the matching of visual understanding and language comprehension by helping machines to narrate images in human terms. This paper details the applications of Convolutional Neural Networks (CNNs) fused with Bidirectional Long Short Term Memory BiLSTM neural networks with attention...

The rise of social networks has increased user interactions but also led to a surge in fake accounts, threatening privacy and security. These fraudulent profiles undermine trust and facilitate misinformation, making their detection crucial. This study proposes an improved machine learning approach using...

Alzheimer’s disease is a gradient degeneration of essential cognitive activities that mainly affects elderly individuals. Diagnosis of Alzheimer’s disease by neuropsychological assessments is considered an important step in disease management. However, using a single neuropsychological assessment technique...

The drug research and discovery field has heavily contributed to medicine throughout the years, providing more treatment options and a variety of new molecule combinations. However, Traditional methods are often characterized by extensive trial, error, and lengthy timelines. This led to the need to pursue...

Medical imaging is one of the essential technology used today for diagnosis as it provides detailed insight into internal heart structures, facilitates early detection of diseases and guides doctors in making treatment decisions. However, despite advances in technology, cardiac image segmentation remains...

Node coverage is a critical metric for wireless sensor networks, as it impacts the target area’s monitoring capabilities. However, achieving optimal coverage faces challenges due to limited node resources, large network scale, and complex operating conditions. This study proposes an artificial humming-bird...

The inventory of water surfaces is vital for the survival of the human race and the preservation of the ecosystem. Several approaches and methods have been developed to extract water bodies, the principal tool currently used for this task is deep learning. The major problem is the need...

Efficiently solving Constraint Satisfaction Problems (CSPs) remains a major challenge in artificial intelligence and operations research. The complexity increases significantly for non-binary CSPs, where constraints involve multiple variables. Generalized Hypertree Decomposition (GHD) has proven to be...

Early detection of Type 2 Diabetes Mellitus (T2D) is crucial for mitigating complications. Current diagnostic methods remain invasive, costly, and inaccessible in resource-limited settings. This paper explores machine learning (ML) for a non-invasive T2D screening, focusing on the impact of feature selection....

With the growing use of Internet of Things (IoT) devices in distributed systems, securing these networks has become a significant challenge because of their susceptibility to attacks. Intrusion detection systems have been proposed to identify attacks in IoT networks. These systems require continuous...

In this paper, we employ a deep learning technique for individual recognition based on the use of ear images as a biometric trait. This methodology relies on advanced deep learning techniques to optimize individual identification. to evaluate our approach, we have exploited the Mathematical analysis...

Bond graph modeling provides a unified and structured approach for analyzing complex multi-domain systems. These systems often involve interactions between multiple physical domains such as mechanical, electrical, hydraulic, thermal, and chemical. The challenge lies in correctly identifying the domain...

Achieving accurate estimation remains a major challenge and a key research topic in the software industry. There is an increasing use of Deep Learning (DL) in the field of software effort estimation. In this paper the Chicken Swarm Optimization (CSO) algorithm is applied to a feed-forward deep neural...

The prediction of amyloidogenicity in peptides and proteins remains a focal point of ongoing bioinformatics. The crucial step in this field is to apply advanced computational methodologies. Many recent approaches to predicting amyloidogenicity within proteins are highly based on evolutionary motifs and...

Soil quality prediction (SQP) is essential for many fields such as: agriculture, civil engineering and environmental applications. Traditional SQP assessment methods are often time-consuming and resource-intensive. This study explores the application of four machine learning models: RBFN, LightGBM, XGBoost,...

Welding plays a pivotal role across various industries as an assembly process. During its execution, certain defects and imperfections are likely to emerge. To rectify these imperfections without compromising the integrity of the components, techniques such as non-destructive testing through radiology...

Image processing has expanded widely with the popularization of AI tools. Indeed, images processed based on AI algorithms have been used to improve many fields such as medicine, education, intelligent surveillance and document processing. In this context, we have developed a system based on deep learning,...

This study examines an IoT-based smart soil fertility prediction system for Algerian agriculture. With many farmers applying fertilizers without prior soil nutrient assessment and limited access to laboratory analysis, we developed and tested a prototype IoT soil monitoring system at Si Yahi pilot farm...

The integration of blockchain, fog computing, offers a transformative approach to secure healthcare data management. This paper proposes a decentralized platform that leverages blockchain for immutability and transparency, with Proof of Authority (PoA) consensus, where fog nodes act as validators, and...

This challenge is known as the load balancing problem in cloud computing. It is an optimization issue aimed at minimizing the response time and waiting time of multiple tasks requested by various clients, which are processed using a set of resources with limited computing and storage capacities. The...

Cloud computing is essential for modern technology. Resource allocation and task scheduling are critical parts of cloud computing. A novel task scheduling and VM allocation (TSVMP) in cloud computing are proposed to reduce energy and resource consumption. Task scheduling and VM allocation compose the...

Point-of-interest (POI) recommendation systems help users discover locations that align with their interests and past behaviors. These systems often use Collaborative Filtering (CF), which relies on measuring similarities between users or items to make recommendations. The most common methods for assessing...

Significant issues with identity management, access control, and data and network security arise from the extensive cross-sector integration of IoT. Making sure the components of IoT are secure is essential since it is becoming a target for cyberattacks like malware and DDoS. IoT systems deal with sensitive...