Computer Science Journal (AGH University of Science and Technology, Krakow)
Not a member yet
476 research outputs found
Sort by
Performance Evaluation of A Lightweight Consensus Protocol for Blockchaini IoT Networks
Full text linkThe consensus protocol is essential in practically every blockchain application. Most of these existing blockchain consensus protocols need massive computationalcapabilities, substantial energy consumption, and dependency on monetary stakes. These shortcomings in the mainstream consensus approach lead to their unsuitability for low-resource applications like IoT. As a result of this work, a lightweight consensus process referred as Delegated Proof of Accessibility(DPoAC) is implemented and evaluated. DPoAC makes use of Shamir secret sharing, Proof of Stake (PoS) with random selection, and the Inter-PlanetaryFile System (IPFS). The DPoAC operation is composed of four modules: secret generation and distribution, retrieval of secret shares, block creation andverification, and block rewards and penalty. A detailed description of DPoAC has been provided and implemented in JavaScript and experimental resultsdemonstrate that our solution meets the necessary performance and security requirements for a lightweight scalable protocol for IoT systems.
 
OPTCHAIN: AN ADVANCED OPTIMIZATION METHOD FOR ENHANCING IOT DATA SECURITY VIA BLOCKCHAIN
Full text linkThe increased use of IoT devices in various domains generates abundant data traffic. Securing this data during transfer and storage is essential. Blockchain is now a trending technology to provide security to the data. However, it is observed that blockchain performs poorly while managing large volume data. To mitigate this issue, an advanced Optchain method to reduce the data size before submitting it to the blockchain network is introduced in this paper. This method first classifies data as relevant and irrelevant and then applies compression to the appropriate data to reduce size. This reduces storage requirements, improves processing efficiency, ensures faster transactions, and lowers cost. The proposed method is tested for healthcare IoT data. Compared to current systems, the evaluation findings of the suggested solution show a notable reduction in data size. As data is reduced, it is easily managed by the blockchain network. Thus, the proposed Optchain method provides better security to the IoT-generated data
A PARALLEL APPROACH FOR METAHEURISTICS SOLVING THE LABS PROBLEM USING CPU AND GPU
Full text linkThe paper contributes to solving the low autocorrelation binary sequence (LABS) problem that remains an open hard-optimization problem with many applications. The current direction of research is focused on developing algorithms dedicated to parallel architectures such as GPGPU or multi-core CPUs. The paper follows this direction and proposes new heuristics developed from the steepest-descent local search algorithm that extends the notion of a neighborhood of a given sequence. The introduced algorithms utilise the parallel nature of multicore CPUs and provide an effective method of solving the LABS problem. The efficiency levels of SDSL and the new algorithm are presented; to ensure an effective comparison, they were both implemented in the same manner. The comparison shows that exploring the larger neighborhood improves the efficiency of the search method
Energy Efficient and QoS Aware Trustworthy Routing Protocol for Manet Using Hybrid Optimization Algorithms
Full text linkThe potential for wireless mobile computing applications has significantly increased in recent years thanks to advancements in wireless communication and internet service technology. A collection of mobile nodes that can be randomly arranged and created without the aid of any pre-existing network architecture or centralised administration is known as a Mobile Ad hoc Network (MANET). Mobile devices in this network rely on battery power, so it\u27s critical to reduce their energy usage. Furthermore, communication with them is difficult due to their susceptibility to several security risks. As a result, the research suggested a reliable routing protocol that is both energy-efficient and QoS-aware. Levy Flight-centred Shuffled Shepherd Dynamic Source Routing (LF-SSO-DSR) protocol is used in the route discovery scheme\u27s first stages to find the best way out of a group of options chosen based on QoS criteria. Additionally, hybrid Firefly and Whale Optimization Algorithms (FFWHO) are used to handle high energy consumption and discover the ideal values and fit function for the goal parameter (i.e., energy). WOA conducts a global search, but later on, in the algorithm, it conducts a local search, which can successfully find the routing path that complies with the QoS requirements. The security challenges in MANETS present the most difficult assignment. The reliability of each mobile node is assessed by taking into account factors such as the node\u27s location, mobility speed, energy use, number of involved transmissions, neighbour list, etc. The research project then suggested the Intelligent Dynamic Trust (IDT) paradigm as a means of supplying security in wireless networks. For secure routing in mobile ad hoc networks, this paradigm combines beta reputation trust and dynamic trust. Network Simulator 3.36 software was used to conduct the performance analysis. Several performance metrics, including throughput, energy consumption, packet delivery ratio, jitter, end-to-end delay, packet loss rate, detection rate, and routing overhead, are used to assess the suggested approach. This outcome shows that the suggested strategy works better than other cutting-edge approaches respectively
Automatic indexation of Cultural Heritage 3D object
No full textThere has been significant evolution in the fields of 3D digitization thanks to the development of 3D reconstruction and geometry processing. The results of digitization researches have been widely applied in many fields, especially in Cultural Heritage and Archaeology. Reconstruction, characterization and annotation of components forming 3D objects have become an effective tool for research, conservation and promotion of archaeological relics. The aim of this paper is to propose a process of 3D model reconstruction, segmentation and annotation on the basis of a enhanced corresponding 2D dataset. A machine learning method is used for the semantic segmentation of 2D images, thereby label, annotate and reconstruct a 3D model based upon links between distinctive invariant features, orientation of images, and depth map of images.The initial result as a data basis for research, reconstruction and identification of parts in 3D objects is applied in the reconstruction of archaeological relics, object identification, 3D printing, etc. Our work uses the datacollected from the Museum of Cham Sculpture – DaNang and the Myson QuangNam sanctuary in VietNam, to carry out the proposed method
INFORMATION - MODERN THEORIES
Full text linkThis 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
PSO-WESRGAN: A NOVEL DOCUMENT IMAGE SUPER RESOLUTION
No full textOne of the major challenges of document images that can hinder readability and the analysis of information is low resolution, typically caused by low-pixel density scanning or excessive compression to save storage space. This results in images lacking fine details, making it difficult to recognize important information. Super-resolution techniques are essential to addressing these issues. These techniques enhance image quality by increasing resolution while maintaining fine details. The PSO-WESRGAN is an innovative method, which combines wavelet processing, deep transfer learning, and particle swarm optimization (PSO). Wavelet processing analyzes image detail at diverse scales and orientations, while transfer-based deep learning advantages pre-trained models on vast image datasets. By integrating PSO, the method’s efficiency is enhanced through optimal exploration of the solution space to identify the best parameters for the super-resolution model. Experimental results demonstrate the effectiveness of this approach and pave the way for future advances in document image resolution
CAN ARTIFICIAL INTELLIGENCE PREDICT A TSUNAMI?
Full text linkn this article, we build a model for tsunami simulation based on physics-informed neural networks and the finite difference method. We then check how the numerical results obtained using these two methods differ from each other. Assuming that the finite difference method gives accurate results, we estimate the error resulting from the use of physics-informed neural networks. We compare this estimate with surveys conducted among computer science students in order to assess the level of public trust among specialists in the numerical results obtained using artificial intelligence tools. In particular, we assess how reliable tsunami predictions obtained using physics-informed neural networks are and what the public perceptionof the reliability of such predictions is
RECONSTRUCTION OF MUON BUNDLES IN KM3NET DETECTORS USING MACHINE LEARNING METHODS: on behalf of the KM3NeT collaboration
No full textThe KM3NeT Collaboration is installing the ARCA and ORCA neutrino detectorsat the bottom of the Mediterranean Sea. The focus of ARCA is neutrinoastronomy, while ORCA is optimised for neutrino oscillation studies. Bothdetectors are already operational in their intermediate states and collect valuabledata, including the measurements of the muons produced by cosmic rayinteractions in the atmosphere. This work explores the potential of machinelearning models for the reconstruction of muon bundles, which are multi-muonevents. For this, data collected with intermediate detector configurations ofARCA and ORCA was used in addition to simulated data from the envisagedfinal configurations of those detectors. Prediction of the total number of muonsin a bundle as well as their total energy and even the energy of the primarycosmic ray is presented.
PREFACE: 2ND INTERNATIONAL WORKSHOP ON MACHINE LEARNING AND QUANTUM COMPUTING APPLICATIONSIN MEDICINE AND PHYSICS
Full text linkThis is a preface for the special issue including extended versions of the selected papers submitted to 2ND INTERNATIONAL WORKSHOP ON MACHINE LEARNING AND QUANTUM COMPUTING APPLICATIONSIN MEDICINE AND PHYSICS