Computing and Informatics (E-Journal - Institute of Informatics, SAS, Bratislava)
Not a member yet
1506 research outputs found
Sort by
Cost-Effective Scheduling and Load Balancing Algorithms in Cloud Computing Using Learning Automata
Get PDFCloud computing is a distributed computing model in which access is based on demand. A cloud computing environment includes a wide variety of resource suppliers and consumers. Hence, efficient and effective methods for task scheduling and load balancing are required. This paper presents a new approach to task scheduling and load balancing in the cloud computing environment with an emphasis on the cost-efficiency of task execution through resources. The proposed algorithms are based on the fair distribution of jobs between machines, which will prevent the unconventional increase in the price of a machine and the unemployment of other machines. The two parameters Total Cost and Final Cost are designed to achieve the mentioned goal. Applying these two parameters will create a fair basis for job scheduling and load balancing. To implement the proposed approach, learning automata are used as an effective and efficient technique in reinforcement learning. Finally, to show the effectiveness of the proposed algorithms we conducted simulations using CloudSim toolkit and compared proposed algorithms with other existing algorithms like BCO, PES, CJS, PPO and MCT. The proposed algorithms can balance the Final Cost and Total Cost of machines. Also, the proposed algorithms outperform best existing algorithms in terms of efficiency and imbalance degree
MDM-YOLO: Research on Object Detection Algorithm Based on Improved YOLOv4 for Marine Organisms
Get PDFVision-based underwater object detection technology is a hot topic of current research. In order to address the issues of low accuracy and high missed rate of marine life detection, an object detection algorithm called MDM-YOLO (Marine Detection Model with YOLO) for marine organisms based on improved YOLOv4 is proposed. To improve the network's capacity for feature extraction, a multi-branch architecture CSBM is integrated into the backbone. Based on this, the feature fusion structure introduces shuffle attention to reinforce the focus on important information. The experimental results demonstrate that the MDM-YOLO algorithm increases the mean average precision (mAP) by 2.31 % compared to the YOLOv4 algorithm on the Underwater Robot Picking Contest (URPC) dataset. Moreover, on the RSOD dataset and PASCAL VOC dataset, MDM-YOLO obtained an mAP of 87.54 % and 86.87 %, respectively. According to these advancements, the MDM-YOLO model is more suitable for the identification of items on the seafloor
Correlation Coefficient Measure of Intuitionistic Fuzzy Graphs with Application in Money Investing Schemes
Get PDFIntuitionistic fuzzy graphs are extensions of fuzzy graphs that preserve the dualism characteristics of fuzzy graphs and have a stronger capacity to describe ambiguity in actual decision-making issues than fuzzy graphs. In this research paper, the Laplacian energy and correlation coefficient of intuitionistic fuzzy graphs are computed for finding group decision-making problems that are supported by intuitionistic fuzzy preference relations. We propose a novel method for calculating establishments' comparative position loads by manipulating the undecided corroboration of IFPR and the correlation coefficient of one personality IFPR to the other items. As a result, we comprehend a large number of establishments in the detailed IFPR and devise a correlation coefficient process to investigate the significance of alternatives and the best of the alternatives. Finally, we present a collaborative decision-making technique in a money-investing scheme, and that idea may be devised in disparate beneficial investing schemes
BERTDom: Protein Domain Boundary Prediction Using BERT
Get PDFThe domains of a protein provide an insight on the functions that the protein can perform. Delineation of proteins using high-throughput experimental methods is difficult and a time-consuming task. Template-free and sequence-based computational methods that mainly rely on machine learning techniques can be used. However, some of the drawbacks of computational methods are low accuracy and their limitation in predicting different types of multi-domain proteins. Biological language modeling and deep learning techniques can be useful in such situations. In this study, we propose BERTDom for segmenting protein sequences. BERTDOM uses BERT for feature representation and stacked bi-directional long short term memory for classification. We pre-train BERT from scratch on a corpus of protein sequences obtained from UniProt knowledge base with reference clusters. For comparison, we also used two other deep learning architectures: LSTM and feed-forward neural networks. We also experimented with protein-to-vector (Pro2Vec) feature representation that uses word2vec to encode protein bio-words. For testing, three other bench-marked datasets were used. The experimental results on benchmarks datasets show that BERTDom produces the best F-score as compared to other template-based and template-free protein domain boundary prediction methods. Employing deep learning architectures can significantly improve domain boundary prediction. Furthermore, BERT used extensively in NLP for feature representation, has shown promising results when used for encoding bio-words. The code is available at https://github.com/maryam988/BERTDom-Code
Architecture of a Function-as-a-Service Application
Get PDFServerless computing and Function-as-a-Service (FaaS) are programming paradigms that have many advantages for modern, distributed and highly modular applications. However, the process of transforming a legacy, monolithic application into a set of functions suitable for a FaaS environment can be a complex task. It may be questionable whether the obvious advantages received from such a transformation outweigh the effort and resources spent on it. In this paper we present our continuing research aimed at the transformation of legacy applications into the FaaS paradigm. Our test subject is an airport visibility system, a sub-class of the meteorological services required for airport operations. We have chosen to modularize the application, divide it into parts that can be implemented as functions in the FaaS paradigm, and provide it with a simple cloud-based data management layer. The tools that we are using are Apache OpenWhisk for FaaS and Airflow for workflow management, Apache Airflow for workflow management and NextCloud for cloud storage. Only a part of the original application has been transformed, but it already allows us to draw some conclusions and especially start forming a generalized picture of a Function-as-a-Service application
Adaptive Evolutionary Multitasking to Solve Inter-Domain Path Computation Under Node-Defined Domain Uniqueness Constraint: New Solution Encoding Scheme
Get PDFIn multi-domain networks, the efficiency of path computation becomes more and more important. The Inter-Domain Path Computation under Node-defined Domain Uniqueness Constraint (IDPC-NDU) is a recently investigated problem where its objective is to determine the effective routing path between two nodes that traverses every domain at most once. IDPC-NDU is NP-Hard, so the approximation approaches are suitable to deal with this problem for large instances. Multifactorial Evolutionary Algorithm (MFEA) is an emerging research topic in the field of evolutionary computation that can efficiently tackle multiple optimization problems at the same time. This study proposed an approach based on the combination of the Adaptive Multifactorial Evolutionary Algorithm (dMFEA-II) and Dijkstra algorithm for solving IDPC-NDU. The encoding and evaluating methods based on the permutation representation are also introduced, and the new individual representation is always to produce valid solutions. The proposed algorithm is evaluated on two types of instances. Simulation results demonstrate the superior performance of the proposed algorithm in comparison with the existing algorithms in terms of the quality of the solution
Implementation of a Social Network Information Dissemination Model Incorporating Negative Relationships
Get PDFFor the study of information dissemination in online social networks, most existing information dissemination models include only positive relationships, ignoring the existence and importance of negative relationships, and do not consider the influence of inter-individual relationship polarity on dissemination. To solve these problems, we propose a social network information dissemination model incorporating negative relationships in this paper. Drawing on the state concept of the SIR (Susceptible Infected Recovered) model, the three types of SIR states are subdivided into five sub-states. Combining the advantages of the viewpoint evolution model, the influence of relational polarity on node attitudes is added to the modeling of the propagation process. The experiment proves that the method proposed in this paper can show more specifically the changing trend in the number of propagation nodes with different attitudes and portray the process of information propagation in online social networks
Ensemble Based Feature Extraction and Deep Learning Classification Model with Depth Vision
Get PDFIt remains a challenging task to identify human activities from a video sequence or still image due to factors such as backdrop clutter, fractional occlusion, and changes in scale, point of view, appearance, and lighting. Different appliances, as well as video surveillance systems, human-computer interfaces, and robots used to study human behavior, require different activity classification systems. A four-stage framework for recognizing human activities is proposed in the paper. As part of the initial stages of pre-processing, video-to-frame conversion and adaptive histogram equalization (AHE) are performed. Additionally, watershed segmentation is performed and, from the segmented images, local texton XOR patterns (LTXOR), motion boundary scale-invariant feature transforms (MoBSIFT) and bag of visual words (BoW) based features are extracted. The Bidirectional gated recurrent unit (Bi-GRU) and the Bidirectional long short-term memory (Bi-LSTM) classifiers are used to detect human activity. In addition, the combined decisions of the Bi-GRU and Bi-LSTM classifiers are further fused, and their accuracy levels are determined. With this Dempster-Shafer theory (DST) technique, it is more likely that the results obtained from the analysis are accurate. Various metrics are used to assess the effectiveness of the deployed approach
Steganography Approach to Image Authentication Using Pulse Coupled Neural Network
Get PDFThis paper introduces a model for the authentication of large-scale images. The crucial element of the proposed model is the optimized Pulse Coupled Neural Network. This neural network generates position matrices based on which the embedding of authentication data into cover images is applied. Emphasis is placed on the minimalization of the stego image entropy change. Stego image entropy is consequently compared with the reference entropy of the cover image. The security of the suggested solution is granted by the neural network weights initialized with a steganographic key and by the encryption of accompanying steganographic data using the AES-256 algorithm. The integrity of the images is verified through the SHA-256 hash function. The integration of the accompanying and authentication data directly into the stego image and the authentication of the large images are the main contributions of the work
BVFB: Training Behavior Verification Mechanism for Secure Blockchain-Based Federated Learning
Get PDFThere are still two problems of the existing methods of defending against poisoning attacks of the blockchain-based federated learning: 1) It is difficult to accurately identify the nodes under attack; 2) The effect of the model is greatly affected when the number of malicious nodes exceeds a half. So, an innovative secure mechanism is proposed for blockchain-based federated learning, which is called the training behavior verification mechanism. The mechanism describes the consistent training behavior rules of nodes by constructing the training behavior model, and distinguishes honest nodes from malicious nodes by comparing the differences in training behavior models on the training behavior verification algorithm. Experiments show that the new mechanism can effectively resist more than half of the label-flipping attacks and backdoor attacks, and has the advantages of higher stability and higher accuracy than methods such as Krum, Trimmed Mean, and Median