Computer Science
Loading...
ISSN 1508-2806
e-ISSN: 2300-7036
Issue Date
2025
Volume
Vol. 26
Number
No. 2
Description
Journal Volume
Computer Science
Vol. 26 (2025)
Projects
Pages
Articles
Treextrust: topic-aware computational trust based on interaction experience, reputation of users with similarity and path algebra of graph in social networks
(Wydawnictwa AGH, 2025) Tran, Dinh Que; Pham, Phuong Thanh
The trust measure is the confidence or reliability among users or peers, which has been studied widely in online social networks. Most trust models are currently based on the concepts of interaction trust and reputation trust; however, various forms of interactions and analyses of the interaction contexts have not been considered fully for trust estimation. Moreover, the mechanism for computing reputation trust based on propagation lacks a clear foundation and is expensive in computation. The purpose of this paper is to present a family of computational trust models (called TreeXTrust) to estimate the trust degree of a user truster on another user trustee. Our model is a mathematical formulation that is based on an aggregation of topic-aware experience trust with various forms of interactions and topic-aware reputation trust with users’ similarity and operators on path algebra in a graph. We conducted experiments to evaluate the impacts of interaction forms and users’ interests on experience trust and the correlation of experience trust and reputation trust on overall trust estimation. Our experimental results demonstrated the following: (i) interest degrees influenced experience trust more than interaction ones did; (ii) a community’s evaluation of some trustee affected an overall trust estimation more than a truster’s individual evaluation did. Our family of models outperformed the state-of-the-art methods that have been presented in the literature and is a framework for selecting and implementing a suitable model of computational trust for our problem at hand.
Detection and forecasting of Parkinson disease progression from speech signal features using multi-layer perceptron and LSTM
(Wydawnictwa AGH, 2025) Majid, Ali; Hina, Shakir; Asia, Samreen; Sohaib, Ahmed
Accurate diagnosis of Parkinson′s disease, especially in its early stages, can be a challenging task. The application of machine learning (ML) techniques has helped improve the diagnostic accuracy of Parkinson′s disease (PD) detection but integration of diagnostic features in ML models for the prediction of disease progression has remained an unexplored research avenue. In this research work, Long Short Term Memory (LSTM) was trained using diagnostic features on Parkinson patients speech signals, to predict the disease progression while a Multilayer Perceptron (MLP) was trained on the same diagnostic features to detect PD. Diagnostic features were selected using two well known feature selection methods named Relief F and Sequential Forward Selection method. The integration of feature selection methods in LSTM model has resulted in PD progression forecast with an accuracy of 88.7%. Furthermore, with the application of input diagnostic features on MLP, PD stage was accurately detected with an accuracy of 98.63%, precision of 97.64% and recall of 98.8% showing model robustness and efficiency for its potential application in health care.
Using splitter ordering heuristics to improve bisimulation in probabilistic model checking
(Wydawnictwa AGH, 2025) Mohagheghi, Mohammadsadegh; Salehi, Khayyam
Model checking is used to verify computer-based and cyber-physical systems, but faces challenges due to state space explosion. Bisimulation minimization reduces states in transition systems, easing this issue. Probabilistic bisimulation further simplifies models with stochastic behaviors. Recent techniques aim to improve the time complexity of iterative methods in computing probabilistic bisimulation for stochastic systems with nondeterministic behaviors. In this paper, we propose several techniques to accelerate iterative processes to partition the state space of a given probabilistic model to its bisimulation classes. The first technique applies two ordering heuristics for choosing splitter blocks. The second technique uses hash tables to reduce the running time and the average time complexity of the standard iterative method. The proposed approaches are implemented and run on several conventional case studies and reduce the running time by one order of magnitude on average.
Intrusion detection with machine learning: a two-step federated approach using the CIC IoT 2023 dataset
(Wydawnictwa AGH, 2025) Jakotiya, Komal; Shirsath, Vishal; Inamadar, Sharanabasava
The main objective of the planned effort is to provide analytical analyses of current intrusion detection systems grounded on ML algorithms. Furthermore, examined in this work are the useful data sets and several techniques already in use to develop an effective IDS using single, hybrid, and ensemble machine learning algorithms. The approaches in the literature have then been investigated under several criteria to provide a clear road and direction for the next projects that will be successful. Nowadays, companies of all kinds include an intrusion detection system (IDS), which inhibits cybercrime to protect the network, resources, and private data. Many strategies have been suggested and implemented up till now to prevent uncivil behaviour. Since machine learning (ML) approaches are successful, the proposed approach applied several ML models for the intrusion detection system. The CIC IoT 2023 Dataset is the one applied in this paper, and a two-step process for Intrusion detection was proposed. Tested with several techniques including random forest, XGBoost, logistic regression, MLP model, and RNN. Following fine-tuning, the federated learning model using neural networks had the best accuracy – 99.84%.
Information – modern theories
(Wydawnictwa AGH, 2025) Krzanowski, Roman
This review deviates from the usual approach to the topic of information by not focusing on Shannon’s Theory of Communication (TOC) and the related or derived concepts. In addition, we do not talk at length about information in relation to knowledge, data, communication, information processing, or similar concepts. Instead, we endeavor to reappraise our understanding of information without favoring any specific perspective. We know a lot about information, and the various conceptualizations of information presented in this paper are proof of this. Nevertheless, we also show that some lingering unresolved questions remain about the nature of information. To somewhat stem the appearance of further new concepts of information, we consider two perspectives, namely ontological and epistemic, and posit that we can potentially reduce all information variants to just these concepts. We then look at two general theories of information: the General Definition of Information (GDI) and the General Theory of Information (GTI), arguing that the GTI appears to be the better of these two options because it is more fundamental and comprehensive with deep metaphysical roots. Finally, we review some recent studies about information’s physical nature, such as for information and mass, meaningful physical information, and the persistence of information. This review, like all reviews, is selective and synthetic, but the extensive reference list provides the necessary resources to explore the discussed ideas in greater detail, as well as study the recent works on the nature of information.