Computing and Informatics (E-Journal - Institute of Informatics, SAS, Bratislava)
Not a member yet
1506 research outputs found
Sort by
Attribute-Based Access Control Policy Generation Approach from Access Logs Based on the CatBoost
Get PDFAttribute-based access control (ABAC) has higher flexibility and better scalability than traditional access control and can be used for fine-grained access control of large-scale information systems. Although ABAC can depict a dynamic, complex access control policy, it is costly, tedious, and error-prone to manually define. Therefore, it is worth studying how to construct an ABAC policy efficiently and accurately. This paper proposes an ABAC policy generation approach based on the CatBoost algorithm to automatically learn policies from historical access logs. First, we perform a weighted reconstruction of the attributes for the policy to be mined. Second, we provide an ABAC rule extraction algorithm, rule pruning algorithm, and rule optimization algorithm, among which the rule pruning and rule optimization algorithms are used to improve the accuracy of the generated policies. In addition, we present a new policy quality indicator to measure the accuracy and simplicity of the generated policies. Finally, the results of an experiment conducted to validate the approach verify its feasibility and effectiveness
UDP-YOLO: High Efficiency and Real-Time Performance of Autonomous Driving Technology
Get PDFIn recent years, autonomous driving technology has gradually appeared in our field of vision. It senses the surrounding environment by using radar, laser, ultrasound, GPS, computer vision and other technologies, and then identifies obstacles and various signboards, and plans a suitable path to control the driving of vehicles. However, some problems occur when this technology is applied in foggy environment, such as the low probability of recognizing objects, or the fact that some objects cannot be recognized because the fog's fuzzy degree makes the planned path wrong. In view of this defect, and considering that automatic driving technology needs to respond quickly to objects when driving, this paper extends the prior defogging algorithm of dark channel, and proposes UDP-YOLO network to apply it to automatic driving technology. This paper is mainly divided into two parts: 1. Image processing: firstly, the data set is discriminated whether there is fog or not, then the fogged data set is defogged by defogging algorithm, and finally, the defogged data set is subjected to adaptive brightness enhancement; 2. Target detection: UDP-YOLO network proposed in this paper is used to detect the defogged data set. Through the observation results, it is found that the performance of the model proposed in this paper has been greatly improved while balancing the speed
Vigilant Salp Swarm Algorithm for Feature Selection
Get PDFFeature selection (FS) averts the consideration of unwanted features which may tend the classification algorithm to classify wrongly. Choosing an optimal feature subset from the given set of features is challenging due to the complex associations present within the features. In non-convex conditions, the gradient-based algorithms suffer due to local optima or saddle points with respect to initial conditions where swarm intelligence algorithms pose a higher chance to converge over the global optima. The Salp Swarm Algorithm (SSA) proposed by Mirjalili et al. is based on the chaining behaviour of sea salps but the algorithm lacks diversity in the exploration stage. Rectifying the exploratory behaviour and testing the algorithm against the FS problem is the motivation behind this work. Three variants of the algorithm are proposed, of which the Vigilant Salp Swarm Algorithm (VSSA) inherits the vigilant mechanism in Grey Wolf Optimizer (GWO), the second variant and the third variant replace a simple crossover operator and shuffle crossover operator instead of the follower's position update mechanism used in the VSSA to form Vanilla Crossover VSSA (VCVSSA) and Shuffle Crossover VSSA (SCVSSA)
Mobile Edge Computing Based Immersive Virtual Reality Streaming Scheme
Get PDFRecently, new services using virtual reality (VR)/augmented reality (AR) have appeared and then exploded in entertainment fields like video games and multimedia contents. In order to efficiently provide these services to users, an infrastructure for mobile cloud computing with powerful computing capabilities is widely utilized. However, existing mobile cloud system utilizes a cloud server located at a relatively long distance, so that there are problems that a user is not effectively provided with personalized immersive multimedia service. So, this paper proposes the home VR streaming system that can provide fast content access time and high immersiveness by using mobile edge computing (MEC)
Computational Intelligent Models for Alzheimer's Prediction Using Audio Transcript Data
Get PDFAlzheimer's dementia (AD) is characterized by memory loss, which is one of the earliest symptoms to develop. In this study, we investigated audio transcript data of patients with Alzheimer's dementia. The study involved the use of three intelligent computational approaches: conventional machine learning (Support Vector Machine, Random Forest, Decision Tree), sequential deep learning (LSTM, bidirectional LSTM, CNN-LSTM), and transfer learning (BERT, XLNet) models for automatic detection of linguistic indicators for early diagnosis of Alzheimer's dementia. These models were trained on the DementiaBank clinical transcript dataset. The grid search tuning approach is used for tuning the values of the hyperparameters. Text vectorization is done using the Term Frequency-Inverse Document Frequency (TF-IDF) information retrieval approach. TF-IDF is based on the Bag of Words (BoW) paradigm, which deals with the less and more relevant words in a transcript. Results were evaluated and compared using several performance metrics. The state-of-the-art techniques implemented on DementiaBank dataset in our methodology achieved better performance in terms of accuracy. Transfer learning models showed better classification results in comparison to sequential deep learning models. However, sequential deep learning models outperformed traditional machine learning models. Overall, in terms of accuracy, BERT and XLNet were the most accurate, with accuracy of 93 % and 92 %, respectively
Dynamic Network Representation Learning Method Based on Improved GRU Network
Get PDFAs social networks have been rapidly growing, traditional network representation learning methods are struggling to accurately characterize their dynamic changes, and to output effective node classification and link prediction. To address this problem, this paper proposes IproGRU, a dynamic network representation learning method based on an improved Gated Recurrent Unit (GRU) network to improve the dynamic network representation. First, the method quickly generates embedding for an influenced node by sampling and aggregating features of its neighboring nodes when the network changes. Second, it updates the embedding of the influenced node on time series by the improved GRU network to fully adapt to the changes of the dynamic network. Experimental results on node classification and link prediction for three datasets of dynamic networks show that the proposed method improves the accuracy by 5–10 % on average from those of the traditional Node2vec and GraphSAGE methods and has a slight advantage over Graph Convolutional Networks (GCNs). The results demonstrate that our method is effective for dynamic network representation.
Research on Event Extraction Model Based on Semantic Features of Chinese Words
Get PDFEvent Extraction (EE) is an important task in Natural Language Understanding (NLU). As the complexity of Chinese structure, Chinese EE is more difficult than English EE. According to the characteristics of Chinese, this paper designed a Semantic-GRU (Sem-GRU) model, which integrates Chinese word context semantics, Chinese word glyph semantics and Chinese word structure semantics. And this paper uses the model for Chinese Event Trigger Extraction (ETE) task. The experiment is compared in two tasks: ETE and Named Entity Recognition (NER). In ETE, the paper uses ACE 2005 Chinese event dataset to compare the existing research, the effect reaches 75.8 %. In NER, the paper uses MSRA dataset, which reaches 90.3 %, better than other models
Exposing AI Generated Deepfake Images Using Siamese Network with Triplet Loss
Get PDFGenerative Adversarial Networks have gained popularity mainly due to their ability to create fake human faces. The remarkable detail with which such images have been created in the past few years has exceeded the ability of humans to differentiate between these fake images and real images. Such images have been known to be capable of deceiving the face recognition systems with certain success as well. Forensic systems being developed nowadays take into account adversarial attacks in order to create a more comprehensive detection approaches. Different GAN algorithms such as StackGAN, StyleGAN use different architectures to produce images. Since the underlying technique is different from one another it is difficult for any single detection algorithm trained on one kind of GAN to detect fake images generated from some other kind of GAN. In this research we use a siamese network with triplet loss function to provide a generic solution for detection of GAN generated images or deepfake images. Extensive experiments have been conducted to analyze the effectiveness of the proposed approach. The results show that the siamese triplet loss network performs significantly better than the contemporary approaches with accuracy exceeding 90 % in most experiments
Short Term Load Forecasting for Smart Grids Using Apache Spark and a Modified Transformer Model
Get PDFSmart grid is an advanced electrical grid that enables more efficient distribution of electricity. It counters many of the problems presented by renewable energy sources such as variability in production through techniques like load forecasting and dynamic pricing. Smart grid generates massive amounts of data through smart meters, this data is used to forecast future load to adjust distribution. To process all this data, big data analysis is necessary. Most existing schemes use Apache Hadoop for big data processing and various techniques for load forecasting that include methods based on statistical theory, machine learning and deep learning. This paper proposes using Apache Spark for big data analysis and a modified version of the transformer model for forecasting load profiles of households. The modified transformer model has been tested against several state-of-the-art machine learning models. The proposed scheme was tested against several baseline and state-of-the-art machine learning models and evaluated in terms of the RMSE, MAE, MedAE and R2 scores. The obtained results show that the proposed model has better performance in terms of RMSE and R2 which are the preferred metrics when evaluating a regression model on data with a large number of outliers
Optimization of Columnar NoSQL Data Warehouse Model with Clarans Clustering Algorithm
Get PDFIn order to perfectly meet the needs of business leaders, decision-makers have resorted to the integration of external sources (such as Linked Open Data) in the decision-making system in order to enrich their existing data warehouses with new concepts contributing to bring added value to their organizations, enhance its productivity and retain its customers. However, the traditional data warehouse environment is not suitable to support external Big Data. To deal with this new challenge, several researches are oriented towards the direct conversion of classical relational data warehouse to a columnar NoSQL data warehouse, whereas the existing advanced works based on clustering algorithms are very limited and have several shortcomings. In this context, our paper proposes a new solution that conceives an optimized columnar data warehouse based on CLARANS clustering algorithm that has proven its effectiveness in generating optimal column families. Experimental results improve the validity of our system by performing a detailed comparative study between the existing advanced approaches and our proposed optimized method