Journal of Innovations in Computer Science and Engineering (JICSE)

Abstract Abstract— The brain is a complex organ that undergoes changes with age, and predicting brain age is crucial for monitoring brain health. It provides valuable insights into brain function and helps in the prevention of neurological diseases. This research predicts brain age through age classification based on fMRI data from the HCP dataset, consisting of individuals aged 22 to 36 years. After training a graph convolutional neural network, the model achieved an accuracy of 0.73 on the test data, demonstrating an improvement over previous studies on the same dataset. An evolutionary approach was then applied to optimize the selection of brain regions using a Genetic Algorithm to identify important and informative regions. This selection and optimization process maintained good predictive accuracy while reducing the number of brain regions. The results indicate that, despite using only half the original number of brain regions (8 regions), the model's accuracy remained at 0.65, showing only a slight decline. This highlights the significance of these regions in brain age classification. Identifying these key regions can contribute to the early diagnosis of brain and neurological diseases, enabling experts to better understand and manage the brain aging process.

Abstract Over the past few years, the study of complex networks as an interdisciplinary subject has yielded numerous insights. Communication links within these networks have been found to play a crucial role in shaping the implementation of dynamic processes. Recursive graphs are a class of complex networks whose internal structure is governed by recurrent relations. Among these, line graphs are especially important because they represent the communication links within the network as nodes. Studying the heterogeneity, or irregularity, of different graph models is a fundamental research issue in complex and social network analysis. In this article, we investigate the mapping between graph robustness and heterogeneity metrics and their equivalent metrics in line graphs. Specifically, we analyze the distribution of eigenvalues and important indices of heterogeneity in recursive and line graphs. We also examine the changes in heterogeneity of recursive line graphs with the introduction of a set of important heterogeneity indices. Our approach is broadly applicable to a wide range of indicators and complex networks beyond those discussed in this study.

Abstract The concept of six degrees of separation stands as a significant phenomenon, positing that any two independent entities worldwide can connect through a chain of no more than six acquaintances. This article delves into the study of this phenomenon across various network models, aiming to quantify the rates of information propagation, idea dissemination, disease transmission, and predictive trends in society and economics. We extend the examination beyond the conventional notion of "six degrees of separation" by investigating the factors impacting degrees of separation and Milgram's condition in complex networks. Our objective is to elucidate that the actual degree of separation within a network is intricately tied to its structure and various parameters. Instead of being a universal rule, this concept can be construed as a condition that networks must satisfy. We explore Milgram's condition in diverse network models, encompassing random, small-world, and scale-free networks, while scrutinizing the impact of the frequency and length of cycles on degrees of separation. We introduce a novel criterion, termed multiplicity within the network and assess its relationship with the Hamming distance. We evaluate the effectiveness of Milgram's condition and degrees of separation in the context of these two parameters. Our findings underscore the close association between Milgram's condition and degrees of separation with the specific network model and its structure.

Abstract Parkinson's Disease (PD) is a prevalent neurological disorder marked by motor symptoms such as rigidity and tremors. Accurate and timely assessment of disease severity is essential for judging the efficacy of various treatment interventions. This study presents an innovative approach that employs computer vision technology paired with advanced deep learning techniques to enable precise evaluations of Parkinson's severity.

Leveraging the high accuracy of Kinect cameras in capturing essential movement patterns, our proposed system employs advanced convolutional neural networks, specifically incorporating mechanisms from the Spatial-Temporal Graph Convolutional Network (STGCN) and the Two-Stream Adaptive Graph Convolutional Network (2SAGCN). These architectures are adept at detecting movement anomalies and generating precise quantitative severity measures. To further enhance the performance of the 2SAGCN, we introduce distinct temporal and spatial attention modules, resulting in improved classification outcomes. The model achieves outstanding metrics, with accuracy, precision,recall,and F1 score recorded at 94.14 ± 0.26, 98.1 ± 0.12, 98.6 ± 0.05,and98.2 ± 0.02, respectively The severity classification framework distinguishes between11specific classes of Parkinson's symptoms, which are derived from 9 distinct motion categories.Within this framework, class 0 represents healthy individuals, while classes 0 to 1 correspond to varying degrees of severity in Parkinson's symptoms, resulting in a comprehensive classification system encompassing 99 distinct outcomes.

To further enhance the model’s accuracy, we have implemented strategies such as transfer learning and data 3D augmentation. This research marks a significant step forward in the realm of non-invasive, quantitative assessments of Parkinson's Disease, showcasing the potential of cutting-edge technology and state-of-the-art neural network architectures.

Abstract Abstract— Deep learning has emerged as a transformative technology in ophthalmology, addressing critical challenges in the diagnosis and management of eye diseases such as diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), and central serous chorioretinopathy (CSCR). These conditions, among the leading causes of preventable blindness, require accurate and timely detection, which is often limited by traditional diagnostic methods due to inefficiency and the complexity of interpretation. The goal of this study is to examine the applications of deep learning in the diagnosis of ophthalmic diseases and to help researchers gain a better understanding of recent advances in model development, identify challenges associated with widespread implementation of these models in real-world applications, and outline future research directions in this area. Methodologically, recent studies using convolutional neural networks (CNNs), vision transformers, and hybrid models demonstrate high diagnostic accuracy and potential for early disease detection. Applications extend beyond disease diagnosis to lesion segmentation, disease progression monitoring, and personalized treatment planning. Deep learning systems have demonstrated comparable or superior diagnostic performance to human experts in detecting diseases such as DR and glaucoma. Despite these advances, challenges remain, including limited generalizability, data bias, and the need for explainable AI models to foster clinical trust and adoption. Addressing these challenges through improved model transparency, diverse datasets, and ethical frameworks will be critical to integrating deep learning into routine ophthalmic practice. This review highlights the significant advances in deep learning-driven ophthalmology and outlines a path for future research to optimize its clinical implementation.

Abstract Image captioning aims at automatically generating description of an image in natural language. This is a challenging problem in the field of artificial intelligence that has recently received significant attention in the computer vision and natural language processing. Among the existing approaches, visual retrieval based methods have been shown to be highly effective. These approaches search for similar images, then build a caption for the query image based on the captions of the retrieved images. In this study, we present a method for visual retrieval based image captioning, in which we use a multi criteria decision making algorithm to effectively combine several criteria with proportional impact weights to retrieve the most relevant caption for the query image. The main idea of the proposed approach is to design a mechanism to retrieve more semantically relevant captions with the query image and then selecting the most appropriate caption by imitation of the human act based on a weighted multi-criteria decision making algorithm. Experiments conducted on MS COCO benchmark dataset have shown that proposed method provides much more effective results compared to the state-of-the-art models.

Abstract The de Bruijn graph, initially proposed as a topological architecture for interconnection networks, offers unique attributes. These graphs are regular, Eulerian, and Hamiltonian, boasting a small diameter close to optimal connectivity. Their low average distance, small diameter, and high connectivity contribute to remarkable fault tolerance against both node and edge failures. Comprehensively, these graphs serve as pivotal components in word-representing networks, finding applications in various scientific and engineering domains, particularly in genome assembly. They play a significant role in bioinformatics, information theory, coding, communication networks, and multiprocessors. Additionally, de Bruijn graphs are utilized in peer-to-peer (P2P) networks and distributed hash tables (DHT), demonstrating their versatility. Moreover, de Bruijn graphs can serve as a robust infrastructure for modeling online/offline user behavior. In this article, we delve into the different types of de Bruijn graphs and their unique properties from a graph theory perspective. Our focus is on evaluating the reliability of these graphs concerning resilience, fragility, and vulnerability to random failures and targeted attacks on both nodes and edges.

Abstract Abstract— This study examines the impact of using artificial intelligence chatbots on improving the quality of life for women with multiple sclerosis (MS) in Iran. Using a qualitative method and semi-structured interviews, the experiences of women participating in relation to the functionality of AI chatbots were analyzed. The findings indicate that chatbots can play a significant role as supportive and informational tools in managing the disease, reducing anxiety, and improving communication for these women. Additionally, these tools assist in organizing daily tasks and reducing feelings of loneliness. Although some participants pointed to an excessive reliance on chatbots, overall, the results show more positive effects compared to the disadvantages of this technology. Ultimately, the research suggests that future studies should explore the psychological and ethical impacts of using chatbots more deeply. Ultimately, the research suggests that future studies should explore the psychological and ethical impacts of using chatbots more deeply. Ultimately, the research suggests that future studies should explore the psychological and ethical impacts of using chatbots more deeply.

Abstract Abstract— Voice Pathology Detection (VPD) aims to identify voice impairments through the analysis of speech signals, providing a foundation for developing diagnostic tools in advanced healthcare services to the public. This paper contributes to the development of efficient and accurate models based on deep learning (DL) for automatic VPD using sustained vowels of speech data. Therefore, this study explores the comparative efficacy of Mel-Frequency Cepstral Coefficients (MFCCs) and Linear Predictive Coding (LPC) as acoustic features extracted from vowels /i/, /a/, and /u/. Using the AVFAD database, we utilized and optimized a Convolutional Neural Network (CNN) as a DL model to classify healthy and pathological voices, prioritizing both accuracy and computational efficiency for real-time applications. Our findings reveal that 20 MFCC features extracted from vowel /i/ achieve the highest accuracy, with the optimal model reaching approximately 88% on test data. Our findings reveal that 20 MFCC features extracted from vowel /i/ achieve the highest accuracy, with the optimal model reaching approximately 88% on test data.

Abstract Covering all edges in a graph with a small set of vertices is one of the most fundamental graph problems which is called the minimum vertex cover problem. In the literature different strategies have been employed to find near-optimal minimum vertex cover set in different kinds of graphs.
In this work, two efficient algorithms (i.e., MAxA and MAxAR) are introduced to find the minimum vertex cover set in any unweighted undirected graph. The proposed construction algorithms have two main steps in each iteration which explore neighborhoods of minimum degree vertices to find and select appropriate vertices for the cover set. Until all of the edges are removed or selected in the algorithms, these two steps are performed iteratively. The proposed algorithms have been implemented on DIMACS, BHOSLIB, and other benchmarks where experimental results show that the proposed algorithms outperform other relevant methods in terms of time and cardinality of vertex cover set.

Abstract Tokenization is a critical stage in text preprocessing and presents numerous challenges in languages like Persian, where there is no deterministic word boundary. These challenges include the identification of multi-function morphemes, separation of punctuation marks, omission of spaces between tokens, and handling extra spaces inside words.



Typically, the evaluation of tokenizers focuses on overall performance, and test data does not necessarily cover all challenging linguistic phenomena. As a result, strengths and weaknesses of tokenizers in addressing specific challenges are not independently assessed. This paper examines the challenges posed by the Persian script in detecting word boundaries and evaluates the performance of seven tokenizers in handling these issues. A test set of 4091 tokens across 483 sentences was prepared, with 1010 considered as challenging tokens. The tokenizers were evaluated using this dataset.



The results indicate varying performance among tokenizers when dealing with Persian orthography. Some tokenizers performed better in separating compound words, while others excelled in identifying and preserving zero-length joiners (half-space). A detailed comparison reveals that no tokenizer fully addresses all challenges, highlighting the need for improved algorithms and more sophisticated solutions for Persian word boundary detection.



By introducing a comprehensive benchmark and identifying the strengths and weaknesses of available tokenizers, this study paves the way for the development of better Persian language processing tools.

Abstract Structural reliability analysis (SRA) is associated with complex calculations and large number of simulations. In this paper, machine learning (ML) methods are integrated with SRA to reduce the overall intricacy and computational cost of direct SRA methods, such as the Monte Carlo simulation (MCS) method. An SRA is conducted in this paper on post-tensioned concrete members under the influence of prestress loss, and their reliability indices are obtained through the MCS method. The results of the SRA are used to create a database for data fitting of the ML algorithms. The algorithms are compared to find the most accurate ML model to be applied on the problem at hand. For the SRA, different stochastic parameters with specified probabilistic distributions are considered for the numerical models, and nonlinear dynamic analyses are conducted on them. Using the labeled data resulted from the SRA, five ML algorithms are compared; (i) linear regression, (ii) random forest, (iii) artificial neural network, (iv) k-nearest neighbors, (v) extreme gradient boosting. R-squared and root mean squared error are considered as the metrics used for the comparison of the ML models. Bayesian search is used for hyperparameter optimization of algorithms. The performance of the linear regression algorithm (R2=0.67 and RMSE=0.26) indicates that the SRA problems are highly nonlinear and linear algorithms cannot precisely map the relationships in data. However, the results show that extreme gradient boosting has the finest accuracy with R2=0.9 and RMSE=0.04. Additionally, its predicted values mostly have relative errors of less than ±30%.

Abstract Abstract—Extracting organizational duties from legal documents is a critical yet challenging task, particularly in low-resource languages like Persian. This paper presents an innovative approach that integrates state-of-the-art Named Entity Recognition (NER) with advanced segmentation techniques and Large Language Models (LLMs) to accurately identify and extract duties assigned to organizations from Persian legal texts. Leveraging the power of the BERT-based model for NER, we enhance the recognition of relevant entities and ensure precise linkage to target organizations. Our method involves segmenting documents into sentences with an enhanced POS-based tokenizer, followed by the retrieval of contextually relevant segments based on the detected entities. We then explore the effectiveness of different LLM configurations, including a hierarchical approach that leverages both small and large models. Our experiments demonstrate that the hierarchical approach, combining ’Llama-3.1-8B’ and ’gpt-4o’, achieves an F1-score of 0.7901, significantly outperforming single-model approaches. This research underscores the potential of LLMs in legal text analysis, paving the way for more advanced tools in Natural Language Processing. Future work will include testing on a broader range of organizations, refining prompt engineering techniques, and enhancing model interpretability.

Abstract In this paper, all-optical photonic crystal two bit adder based on nonlinear ring resonator is designed. The proposed structures includes threshold detectors and junctions. In our proposed structure, in order to resolve the low transmission problem in input junction, an enhanced junction is cascaded by a threshold detector to implement full adder cells. By cascading two optimized full adder a two bit adder has been designed. Nonlinear rods of the proposed structures are made of Silicon nanocrystal to create the required frequency shift for implementation of the proposed structures. In order to evaluate the performance of the proposed structures, the plane wave expansion and finite difference time domain methods are used. The proposed optimized full adder cell occupy an area about 340 µm2 with maximum power 5 W for switching mechanism. Our simulation results show that the proposed full adder can operate with a bit rate of more than 580 Gbits/s.

Abstract Moore and Shannon introduced a probabilistic model in which network nodes are assumed to be completely reliable, and communication links or edges can fail with a given probability, such as p. The main problem is determining the probability that the network will remain connected under these conditions, meaning establishing a route between the source and destination terminals. If all links are operational with the same probability of p, the reliability of the entire network is described as a function of p, leading to the reliability polynomial of the network. Moore and Shannon proposed their reliability analysis on specific networks known as hammock networks. Such networks can be well adapted to array-based circuits such as FinFET, VSFET, MOSFET, NEMS, and CNFETs. In this article, focusing on hammock networks, we utilize their combination to design and implement MOS-based transistors, i.e., nMOS and pMOS, and implement basic logical gates based on such networks. To determine the reliability polynomial coefficients, various methods have been presented, most of which exhibit computational complexity due to the recursive property. In practice, for circuits with large orders and sizes, the exact calculation of reliability polynomial coefficients falls into the NP-hard complexity class. In this study, while reviewing the existing problems, efficient methods have been employed to determine the polynomial coefficients of reliability. To ensure fair and accurate comparisons and evaluations, simulation results are utilized to extract performance and reliability measures for all circuits. The reliability of the investigated networks is then compared and analyzed.

Abstract Abstract— Intent detection and slot filling are crucial for understanding human language and are essential for creating intelligent virtual assistants, chatbots, and other interactive systems that interpret user queries accurately. Recent advancements, especially in transformer-based architectures and large language models (LLMs), have significantly improved the effectiveness of intent detection and slot filling. This paper, proposes a method for effectively utilizing low volume fine-tuning data samples to enhance the natural language comprehension of lightweight language models, yielding a nimble and efficient approach. Our approach involves augmenting new data while increasing model layers to enhance understanding of desired intents and slots. We explored various synonym replacement methods and prompt-generated data samples created by large language models. To prevent semantic meaning disturbance, we established a lexical retention list containing non-O slots to preserve the sentence's core meaning. This strategy enhances the model's slot precision, recall, F1-score, and exact match metrics by 1.41%, 1.8%, 1.61%, and 3.81%, respectively, compared to not using it. The impact of increasing model layers was studied under different layer arrangement scenarios. Our results show that our proposed solution outperforms the baseline by 10.95% and 4.89% in exact match and slot F1-score evaluation metrics.

Abstract Abstract— Performance-based design of bridges requires prediction of different damage states of components. (RC) piers are key components in bridge system, which may experience severe damages during earthquakes. Therefore, seismic damage assessment of RC bridges depends strongly on predicting failure modes RC piers. Using machine learning for damage evaluation of structures is becoming increasingly popular in earthquake engineering. This study implements three different machine learning techniques to capture different damage limit states of RC bridge piers under seismic loading. For this purpose, three machine learning techniques including K-Nearest Neighbors (KNN), Artificial Neural Networks (ANNs) and decision tree regressions were utilized for predicting four damage states of a RC bridge piers tested experimentally under seismic excitations based on drift limits. The efficiency of the three algorithms in damage prediction of RC piers were compared.

The efficiency of the three algorithms in damage prediction of RC piers were compared. The efficiency of the three algorithms in damage prediction of RC piers were compared.

Abstract Protection of computer systems is a challenge facing the users, who usually define passwords, fingerprints, face detection patterns, and other identification solutions in order to secure their systems against the misuse and unauthorized access. Nevertheless, these solutions are effective in preventing anonymous people from logging in to the system. If a user leaves a system unlocked for a while or a password has already been disclosed for any reason, such trivial solutions will then fail to secure the system. In this study we introduces new dynamic features considering the time, category and type of the applications a user uses and use them in combination with existing operation-related features in a anomaly detection framework for user authentication. A combination of operation-related and application-related features are then taken into account to create a base profile for each authenticated user in order to detect any unauthorized access. The proposed method can secure systems even if an unauthorized access occurs. In other words, this method compares the current user’s behaviour with the base profile of authenticated user momentarily. If an anomaly is detected, that user is recognized as an unauthorized user and will then be prohibited from working with the system or asked to undergo a two-step authentication process.

Abstract Process mining is a new research area that bridges the gap between data science and process science. Among the subfields of process mining, predictive process monitoring aims to predict process features such as the next event, outcome, and remaining time. In recent years, increasing research has been conducted in the area of remaining time prediction.
In this paper, we present an interpretable method for remaining time prediction. Interpretability is an advantageous feature for a prediction method, because it provides the necessary advice and warnings to the organization’s experts during the process execution when it is used in a recommender system. In the proposed method, we utilize distance metric learning methods to develop a distance function for process events. The distance function can be used to find the most similar cases to the intended case, and then the remaining time of the similar cases is used as the indicator of the remaining time of the intended case. Our proposed method has been evaluated on three datasets, and the evaluations revealed that it significantly outperforms the state-of-the-art baseline in two datasets while achieving comparable accuracy in the third dataset. Additionally, our proposed method provides interpretation, while the competitor methods are not interpretable.

Abstract In this paper, a neural approach based on Long Short-Term Memory (LSTM) neural networks is proposed to diagnose patients suffering from Parkinson’s Disease (PD). Considering the movement disorders caused by PD, the proposed method investigates the gait cycle pattern of subjects based on vertical Ground Reaction Force (vGRF) measured by 16 wearable sensors placed in subjects' shoes. In this study, it is shown that the temporal patterns of the gait cycle are different for healthy persons and patients. Therefore, by using a recurrent structure like LSTM, able to analyze the dynamic nature of the gait cycle, the proposed method extracts the temporal patterns to diagnose patients from healthy persons. To reduce the number of data dimensions, the sequences of corresponding sensors measuring vGRF in different feet are combined by subtraction. This method analyzes the temporal pattern of time series collected from different sensors, without extracting special features representing statistics of different parts of the gait cycle. Indeed, the method can extract temporal features based on learning, without using expert knowledge. Finally, the Accuracy and F1 Score of the model trained with all data is $99.87\%$, and $96.66\%$ respectively.

Abstract The stock market plays an imperative role in the entire financial market. The intricate and multifaceted nature of the stock market poses a challenge for investors seeking to establish a reliable and profitable trading approach. This paper aims to address this issue by leveraging two methodologies based on Deep Reinforcement Learning (DRL), namely Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG), incorporating Convolutional Neural Network (CNN) and Gate Recurrent Unit (GRU) architectures, along with an attention mechanism to boost the decision making based on time-series stock data. This adaptation enables the model to focus on essential features and time periods within the stock data, leading to more successful and higher-quality trading choices. Following extensive experimentation and analysis, our proposed RLbased trading demonstrates improved accuracy and profitability compared to similar approaches. The proposed methodology strives to offer investors a dependable and lucrative trading strategy, ultimately leading to a more prosperous and efficient stock trading experience.

Abstract Emotion recognition in text is a growing area in Natural Language Processing ( NLP ), essential for improving human-computer interactions by allowing systems to interpret emotional expressions. While much progress has been made in English, Persian emotion recognition has seen limited devel- opment due to resource constraints and linguistic challenges. In this study, we address these gaps by leveraging two key Persian datasets, ArmanEmo and ShortEmo, to train an efficient emotion recognition model. Using FaBERT, a BERT-based model optimized for Persian, we employ interme- diate fine-tuning on a large collection of informal and formal Persian texts to enhance the model’s adaptability to colloquial language. This step significantly improves comprehension of Persian text
variations, as reflected in reduced perplexity scores. Our final evaluations, incorporating accuracy, precision, recall, and F1 score metrics, demonstrate that this fine-tuned FaBERT model achieves strong performance in emotion recognition, providing a promising approach for NLP in low-resource languages...

Abstract Abstract—Traditional Long Short-Term Memory (LSTM) networks are effective for handling sequential data but have limitations such as gradient vanishing and difficulty in capturing long-term dependencies, which can impact their performance in dynamic and risky environments like stock trading. To address these limitations, this study explores the usage of the newly introduced Extended Long Short-Term Memory (xLSTM) network in combination with a deep reinforcement learning (DRL) approach for automated stock trading. Our proposed method utilizes xLSTM networks in both actor and critic components, enabling effective handling of time series data and dynamic market environments. Proximal Policy Optimization (PPO), with its ability to balance exploration and exploitation, is employed to optimize the trading strategy. Experiments were conducted using financial data from major tech companies over a comprehensive timeline, demonstrating that the xLSTM-based model outperforms LSTM-based methods in key trading evaluation metrics, including cumulative return, average profitability per trade, maximum earning rate, maximum pullback, and Sharpe ratio. These findings mark the potential of xLSTM for enhancing DRL-based stock trading systems.

Abstract With the advent of new technologies, using various formats of digital gadgets is becoming widespread. In today's world, where everyday tasks are inevitable without technology, this extensive use of computers paves the way for malicious activity. Malware is one of the well-known and widely used means utilized for doing destructive activities by malicious attackers. Producing malware from scratch is somewhat difficult, so attackers tend to obfuscate existing malware and prepare it to become an unrecognizable program. Since creating new malware from an old one using obfuscation is a creative task, there are some drawbacks to identifying obfuscated malwares. In this research, we propose a solution to overcome this problem by converting the code to an image in the first step and then using a semi-supervised approach combined with contrastive learning. In this case, an obfuscation in the malware bytecode corresponds to an augmentation in the image. Hence, by utilizing meaningful augmentations, which simulate some obfuscation changes and combine them to generate complex ambiguity procedures, our proposed solution is able to construct, learn, and detect a wide range of obfuscations. This work addresses two issues: 1) malware classification despite the data deficiency and 2) obfuscated malware detection by training on non-obfuscated malwares. According to the results, the proposed method overcomes the data shortage problem in malware classification, as its accuracy is 90.1% when just 10% of data is used for training the model. Moreover, training on basic malwares without obfuscation achieved 96.21 percent accuracy in detecting obfuscated malware.

Abstract The Social Internet of Things (SIoT) enhances device interoperability through social relationships but introduces significant trust management challenges in dynamic, resource-constrained environments. Existing machine learning-based trust models often rely on static training data or centralized architectures, limiting their adaptability and scalability in real-world SIoT deployments. This paper proposes GossipTrust, a novel decentralized trust model that integrates fog computing with adaptive control mechanisms for robust trust management. Our approach deploys machine learning models on fog nodes to enable distributed trust computation while minimizing resource constraints on individual devices. The core innovation combines a MAPE-K (Monitor, Analyze, Plan, Execute, and Knowledge) control loop for real-time attack detection with a gossip learning protocol that allows fog nodes to collaboratively refine trust models through peer-to-peer updates without central coordination. Experimental results demonstrate that GossipTrust significantly outperforms baseline models, achieving 13% higher accuracy, 14% higher success rate, 10% higher F-measure, and 12% lower loss across various trust attack scenarios. The proposed solution effectively addresses key SIoT challenges, including scalability, adaptability, and resource efficiency.