Computing and Informatics (E-Journal - Institute of Informatics, SAS, Bratislava)
Not a member yet
1506 research outputs found
Sort by
Is Transfer Learning Helpful for Neural Combinatorial Optimization Applied to Vehicle Routing Problems?
Get PDFRecently, combinatorial optimization problems have aroused a great deal of interest in Machine Learning, leading to interesting advances in Neural Combinatorial Optimization (NCO): the study of data-driven solvers for NP-Hard problems based on neural networks. This paper studies the benefit of Transfer Learning for NCO by evaluating how model training can be improved taking advantage of knowledge learned while solving similar tasks. We focus, in particular, on two famous routing problems: the Traveling Salesman Problem (TSP) and the Vehicle Routing Problem (VRP). The latter being a generalization of the former, we study the effect of applying Transfer Learning from a model trained to solve TSP while training a model learning to solve the Capacitated VRP (CVRP). We present adaptations of a state-of-the-art NCO model for implementing Transfer Learning. Our results based on extensive empirical experiments in different settings show that Transfer Learning may help to speed up the training process while being more sample efficient
Smart Cities Security Threat Landscape: A Review
Get PDFThere has been a swift rise in the development of smart cities. This evolution has been prompted by the rise in emerging technologies such as edge computing, IoT, data science, and analytics. Combining these technologies has paved the way for new, automated systems for managing and monitoring procedures and industries, resulting in increased efficiency and improved quality of life. While these interconnected services assist in managing the growing population in the urban environments through efficient service delivery and increased operational efficiency, they also increase the risk of adversary threats, security, and privacy challenges to smart cities. This paper presents the holistic view of the security landscape and highlights the security threats, challenges, and risks to the smart city environment
Danmaku Text Clustering Algorithm Based on Feature Extension and Word-Pair Filtering OBTM
Get PDFThe danmaku text clustering is a hot topic in online video reviews. Given the problem of unsatisfactory clustering accuracy caused by short text and many new words, the danmaku text clustering algorithm based on feature extension and word-pair filtering OBTM is proposed. First, a new-word discovery algorithm based on weight optimization is proposed to retain the features of new words in the danmaku text. Then, the internal information and external knowledge of new words are used to expand the features of the danmaku text for reduced feature sparsity. Furthermore, the OBTM topic model based on word-pair filtering is designed to eliminate noise features. Finally, the Single-Pass algorithm based on cluster center iteration is proposed to obtain the clustering results of topic feature words. Experimental results show that the algorithm proposed in this paper is 13.33 %, 8.52 %, 6.25 % higher than the OBTM, Word2vec+BTM, OurE.Drift* algorithm, respectively, in terms of clustering accuracy
Scaling Subgraph Matching by Improving Ullmann Algorithm
Get PDFGraphs are widely used to model complicated data semantics in many application domains. Subgraph isomorphism checking (an NP-complete problem) is a regular operation with this kind of data. In this paper, we propose an improvement of Ullmann algorithm, a well-known subgraph isomorphism checker. Our new algorithm is called Ullmann-ONL. It utilizes a new search ordering and L-levels of vertex neighborhoods (NL) to confine the search space of Ullmann algorithm. Our performance study shows that Ullmann-ONL outperforms previously proposed algorithms with a wide margin
A Graph Transformation Approach for Modeling and Verification of UML 2.0 Sequence Diagrams
Get PDFUnified Modeling Language (UML) 2.0 Sequence Diagrams (UML 2.0 SD) are used to describe interactions in software systems. These diagrams must be verified in the early stages of software development process to guarantee the production of a reliable system. However, UML 2.0 SD lack formal semantics as all UML specifications, which makes their verification difficult, especially if we are modeling a critical system where the automation of verification is necessary. Communicating Sequential Processes (CSP) is a formal specification language that is suited for analysis and has many automatic verification tools. Thus, UML and CSP have complementary aspects, which are modeling and analysis. Recently, a formalization of UML 2.0 SD using CSP has been proposed in the literature; however, no automation of that formalization exists. In this paper, we propose an approach on the basis of the above formalization and a visual modeling tool to model and automatically transform UML 2.0 SD to CSP ones; thus, the existing CSP model checker can verify them. This approach aims to use UML 2.0 SD for modeling and CSP and its tools for verification. This approach is based on graph transformation, which uses AToM3 tool and proposes a metamodel of UML 2.0 SD and a graph grammar to perform the mapping of the latter into CSP. Failures-Divergence Refinement (FDR) is the model checking tool used to verify the behavioral properties of the source model transformation such as deadlock, livelock and determinism. The proposed approach and tool are illustrated through a case study
RGN-Net: A Global Contextual and Multiscale Information Association Network for Medical Image Segmentation
Get PDFSegmentation of medical images is a necessity for the development of healthcare systems, particularly for illness diagnosis and treatment planning. Recently, convolutional neural networks (CNNs) have gained amazing success in automatically segmenting medical images to identify organs or lesions. However, the majority of these approaches are incapable of segmenting objects of varying sizes and training on tiny, skewed datasets, both of which are typical in biomedical applications. Existing solutions use multi-scale fusion strategies to handle the difficulties posed by varying sizes, but they often employ complicated models more suited to broad semantic segmentation computer vision issues. In this research, we present an end-to-end dual-branch split architecture RGN-Net that takes the benefits of the two networks into greater account. Our technique may successfully create long-term functional relationships and collect global context data. Experiments on Lung, MoNuSeg, and DRIVE reveal that our technique reaches state-of-the-art benchmarks in order to evaluate the performance of RGN-Net
Smart Water Management Using Intelligent Digital Twins
Get PDFProviding and distributing fresh water to large communities is a major global concern. In addition to its scarcity as well as to its wastage, this vital resource is being affected by challenging environmental conditions. New approaches are, therefore, urgently needed for an optimized, fair, and efficient use of fresh water. The adoption of emergent technologies is giving high hopes to reach this objective. Among these technologies, digital twin is attracting increasing attention from the academic and industrial committees. This attention is particularly motivated by its expected values to any sector, including process optimization, cost reduction, and time to market shortening. In the specific field of water management, several solutions are being proposed, especially to detect leak detection and test water assets under a variety of working constraints. These solutions are still lacking intelligence and autonomy throughout the loop of data acquisition and processing as well as asset control and service generation and delivery. To this end, we are proposing in this paper a new framework based on multi-agent systems and DT paradigm to close gaps within this loop. Our multi-agent system is responsible of running data analytics mechanisms in order to assess water consumption and generate relevant feedbacks to users using, among others, a rewarding system to select the appropriate pricing policies. It is also responsible of simulating asset operations under specific working constraints for the purpose of failure and/or defect detection
Boosted Performance, Quick Response, and Better QoS Using IoT Plus
Get PDFThe Internet of Things (IoT), as a concept, was not officially named until 1999 where it was still used by big computer and communication companies. It is the connection between objects anywhere, anytime, using internet communication. IoT is one of the network concepts which are growing rapidly in the last few years. The connected devices reach billions which leads to a huge increase in data transfer through the network. This rapid increase of transferred data is overloading network servers which result in more processing and routing time. Fog computing and cloud computing paradigms extend the edge of the network, thus enabling a new variety of applications and services. In this research, we focus on the processing and routing time, moreover, we present a new model in the application layer of the IoT system to classify IoT applications according to their valued data. Also, we work on modeling the fog computing architecture and use the cell operator as the main fog center to store data and compare its performance with the traditional model. We present a comparative study with the traditional IoT architecture based on classifying applications and define a priority for each application. We aim to give solutions to lower data transmission time, reduce routing processes, decrease internet usages, increase response speed, deliver important and sensitive data first, improve the quality of services, enhance the overall performance of IoT systems by depending on fog network as the main layer for processing and storing data, then by giving each application a priority value to be served according to it where the application with the highest priority is served first on the network. Our method which is based on static priority shows better performance and management against the RWS and DRAG method which are based on many parameters to take a decision
Character and Word Embeddings for Phishing Email Detection
Get PDFPhishing attacks are among the most common malicious activities on the Internet. During a phishing attack, cybercriminals present themselves as a trusted organization or individual. Their goal is to lure people to enter their private information, such as passwords and bank card numbers, while believing that nothing malicious is happening. The attack often starts with a phishing email, which is an email that is very similar to a legitimate email, but usually contains links to malicious websites or uses some other techniques to mislead victims. To prevent phishing attacks, it is crucial to detect phishing emails and remove them from email inbox folders. In this paper, a neural network based phishing email detection model is proposed. In comparison to some earlier approaches, our model does not use manually engineered input features. It learns character and word embeddings directly from email texts, and uses them to extract local and global features using convolutional and recurrent layers, respectively. Our model is tested on the two commonly used datasets for phishing email detection, the SpamAssassin Public Corpus and Nazario Phishing Corpus, and it achieves an accuracy of 99.81 % and F_1-score of 99.74 %, which is on par or better than the current state-of-the-art approaches
Prediction of Significant Wave Height Based on Gated Recurrent Unit and Sequence-to-Sequence Networks in the Taiwan Strait
Get PDFWave forecasting approaches based on deep learning techniques have recently made a great progress. In this study, we developed a deep learning model based on Gated Recurrent Unit (GRU) and sequence-to-sequence neural networks (GRUS), to improve the forecasting accuracy of significant wave heights for the Taiwan Strait, where ocean waves and winds own their unique characteristics. The performances of our proposed GRUS model and the other deep learning models based on WaveNet and Long Short-Term Memory (LSTM) were compared by means of wind and wave observations at three buoys in the study area. Model parameters were optimized by means of various model experiments. Performance comparison illustrates that our proposed GRUS model outperforms the other models in 24-hour Hs forecasting, while the GRUS has extraordinary ability for short-term prediction (prediction horizon is less than 6 h). Moreover, for high wave states prediction (e.g., wave height over 4 m), the GRUS has the strongest prediction ability among the models, in which forecasted wave heights are mostly lower than the corresponding observations.