Azerbaijan Journal of High Performance Computing最新文献

{"title":"A NEW APPROACH TO IMPROVE CNN PERFORMANCE IN ANOMALY DETECTION FOR IOT NETWORKS BASED ON THE ALGORITHM ADABOOST","authors":"Z. Jahangiri, Nasser Modiri, Zahra Tayyebi Qasabeh","doi":"10.32010/26166127.2022.5.2.212.235","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.212.235","url":null,"abstract":"Since the increase in internet attacks brings much damage, it is essential to take care of the security of network activities. networks must use different security systems, such as intrusion detection systems, to deal with attacks. This research proposes a reliable approach for intrusion detection systems based on anomaly networks. The network traffic data sets are large and unbalanced, affecting intrusion detection systems' performance. The imbalance has caused the minority class to be incorrectly identified by conventional data mining algorithms. By ignoring the example of this class, we tried to increase the overall accuracy, while the correct example of the minority class protocols is also essential. In the proposed method, network penetration detection based on the combination of multi-dimensional features and homogeneous cumulative set learning was proposed, which has three stages: the first stage, based on the characteristics of the data, several original datasets of raw data or datasets criteria are extracted. Then, the original feature datasets are combined to form multiple comprehensive feature datasets. Finally, the same basic algorithm is used to train different comprehensive feature datasets for the multi-dimensional subspace of features. An initial classifier is trained, and the predicted probabilities of all the basic classifiers are entered into a meta-module. In this research, an AdaBoost meta-algorithm has been used for unbalanced data according to a suitable design. Also, various single CNN models and multi-CNN fusion models have been proposed, implemented, and trained. This evaluation is done with the NSL-KDD dataset to solve some of the inherent problems of the KDD'99 dataset. Simulations were performed to evaluate the performance of the proposed model on the mentioned data sets. This proposed method's accuracy and detection rate obtained better results than other methods.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132659698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"THE SOLUTIONS TO ORGANIZE DATA FOR TRAFFIC INFRASTRUCTURE MANAGMENT COMBINED","authors":"Trinh Cong Duy, Tran Anh Kiet","doi":"10.32010/26166127.2022.5.2.326.338","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.326.338","url":null,"abstract":"In the 4.0 revolution, almost every problem is gradually being solved by technology; the pillars are still Cloud Computing, Big Data, AI, and IoT. Among these problems, the problem of the transport sector is fundamental. Because of its unique characteristics, the analysis and collection of survey data are challenging. The unique feature of the data of each transport infrastructure project is that the data is extensive and has many different formats; the information is updated regularly every year according to the process of conserving, renovating, and renovating. Upgrade if using the traditional way of storing and representing data, like the way database management systems and software are used, will not meet the demand. Therefore, it is necessary to implement a solution to build specialized databases, with a special organizational plan according to industry characteristics and the ability to integrate data from specialized applications to have linkage and unity data between authorities. This will be a data platform for exploitation and sharing for professional management work between authorities in the city and the whole country. The planning and maintenance of transportation infrastructure is a practical application. However, there is now interest in a new area of ​​navigation applications in maritime transport and electronic charts. This feature requires GIS support. The transportation system is an essential factor serving the travel needs of the people, helping the production process to take place continuously and operate normally. In our country, transportation is more and more focused. Our country has been building an increasingly complete and developed transportation system; transport infrastructure is considered essential in promoting our country’s economic, cultural and social activities. This paper proposes a solution to organize traffic infrastructure management data in combination with digital maps. Application to edit data of transportation infrastructure information for Hai Chau and Son Tra districts. At the same time, we have also integrated most of the famous map platforms in the world, such as Google Map, BingMap, OpenStreetMap, HereMap, and IOTLink","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123045368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"OPTIMIZING PARALLELISM IN UNITY WITH JOB SYSTEM TOOL","authors":"Rustam Eyniyev","doi":"10.32010/26166127.2022.5.2.183.192","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.183.192","url":null,"abstract":"Every day the gaming industry is developing faster and faster. Especially the popularity of games increased during the pandemic, as many people were forced to stay at home for a long time and play games in their free time. With the increasing popularity of games, the requirements for the games themselves also increase. As a result, modern games require large computer resources. However, not all people can afford to buy computers with the most expensive video cards, many expensive CPUs, and many RAMs and other components. In order to make games accessible to users with weaker devices, developers have few options. At the moment, there are two main ways to solve this problem. The first is to host games on the cloud, and the second is to optimize games for weaker devices. To optimize games, you can use various methods, including a package Job System for Unity. The Job System is one of the main components for working with threads in an Entity Component System (ECS). Also, in the future, in games with the Unity engine, parallelization between weak devices and High-Performance Computing (HPC) technologies will be combined and implemented using cloud technologies. In the future, when this happens, it will help developers, gamers, and even companies providing cloud services.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125349576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A MODIFIED FUZZY SUPPORT VECTOR MACHINE CLASSIFICATION-BASED APPROACH FOR EMOTIONAL RECOGNITION USING PHYSIOLOGICAL SIGNALS","authors":"Mohammad Bagher Menhaj","doi":"10.32010/26166127.2022.5.2.286.317","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.286.317","url":null,"abstract":"Emotional state recognition has become an essential topic for human–robot interaction researches that diverted and covers a wide range of topics. By specifying emotional expressions, robots can identify the significant variables of human behavior and apply them to communicate in a very human-like fashion and develop interaction possibilities. The multimodality and spontaneity nature of human emotions make them hard to be recognized by robots. Each modality has its advantages and limitations, which, along with the unstructured behavior of spontaneous facial expressions, make several challenges for the proposed approaches in the literature. The most important of these approaches is based on a combination of explicit feature extraction methods and manual modality. This paper proposes a modified fuzzy support vector machine (FSVM) classification-based approach for emotional recognition using physiological signals. The main contribution of this study includes applying various data extraction indices and proper kernels for the FSVM classification method and evaluating the signal's richness in experimental tests. The developed emotional recognition method is also compared with conventional SVM and other existing state-of-the-art emotional recognition algorithms. The comparison results show an improved accuracy of the developed method over other approaches.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123901958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DEEP RECURRENT NEURAL NETWORK MODELS FOR FORECASTING SHORT-TERM WIND SPEED","authors":"Navid Atashfaraz, M. Manthouri, Arash Hosseini","doi":"10.32010/26166127.2022.5.2.169.182","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.169.182","url":null,"abstract":"Wind speed/power has received increasing attention worldwide due to its renewable nature and environmental friendliness. Wind power capacity is rapidly increasing with the global installed, and the wind industry is growing into a large-scale business. We are looking for wind speed prediction to use wind power better. In this research, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Simple Recurrent Neural Network (Simple RNN), and LSTM-GRU in the subset of artificial intelligence algorithms are used to predict wind speed. The data used in this study are related to the 10-minute wind speed data. In the first study on this dataset, we obtained significant results. To compare the deep recurrent models created, we implement four neural network models: Stacked Auto Encoder, Denoising Auto Encoder, Stacked Denoising Auto Encoder, and Feed-Forward presented in the research of others on this dataset. According to the RMSE statistical index, the LSTM network is worth 0.0222 for a short time and performs better than others in this dataset.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121109066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"REGISTRATION OF DRONES THROUGH BLOCKCHAINS","authors":"Ayla Babazade, A. Gurtov","doi":"10.32010/26166127.2022.5.2.318.325","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.318.325","url":null,"abstract":"This paper explores the potential use of blockchain technology to register drones. Using blockchain, a unique and tamper-proof identifier can be assigned to each drone, enabling real-time tracking, secure data exchange, and improved compliance with regulations and laws. This paper argues that integrating blockchain into drone registration can increase security, transparency, and efficiency.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117090931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SHORT-TERM WIND SPEED FORECASTING USING DEEP VARIATIONAL LSTM","authors":"Navid Atashfaraz","doi":"10.32010/26166127.2022.5.2.254.272","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.254.272","url":null,"abstract":"Wind speed and power at wind power stations affect the efficiency of a wind farm, so accurate wind forecasting, a nonlinear signal with high fluctuations, increases security and better efficiency than wind power. We are looking for wind speed for a wind farm in Iran. In this research, a combined neural network created from variational autoencoder (VAE), long-term, short-term memory (LSTM), and multilayer perceptron (MLP) for dimension Reduction and encoding is proposed for predicting short-term wind speeds. The data used in this research is related to the statistics of 10 minutes of wind speed in 10- meter, 30-meter, and 40-meter wind turbines, the standard deviation of wind speed, air temperature, and humidity. To compare the proposed model (V- LSTM-MLP), we implemented three deep neural network models, including Stacked Auto-Encoder (SAE), recurrent neural networks (Regular LSTM), and hybrid model Encoder-Decoder recurrent network (LSTM-Encoder-MLP) presented on this dataset. According to the RMSE statistical index, the proposed model is worth 0.1127 for a short time and performs better than other types on this dataset.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115636260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A SURVEY ON CHALLENGES OF FEDERATED LEARNING","authors":"S. Aliyev","doi":"10.32010/26166127.2022.5.2.273.285","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.2.273.285","url":null,"abstract":"Federated Learning is a new paradigm of Machine Learning. The main idea behind FL is to provide a decentralized approach to Machine Learning. Traditional ML algorithms are trained in servers with data collected by clients, but data privacy is the primary concern. This is where FL comes into play: all clients train their model locally and then share it with a global model in the server and receive it back. However, FL has problems, such as possible cyberattacks, aggregating most appropriately, scaling the non-IID data, etc. This paper highlights current attacks, defenses, pros and cons of aggregating methods, and types of non-IID data based on publications in this field.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133754079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PROVIDE A METHOD IMPROVING TEMPERATURE CONTROL IN SMART BUILDINGS BASED IN SLICING TECHNIQUE AND CLUSTERING IOT NETWORK BASED ON COMPOSITION","authors":"Armin Rabieifard, Lida Naderlou, Zahra Tayyebi Qasabeh","doi":"10.32010/26166127.2022.5.1.94.111","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.1.94.111","url":null,"abstract":"Today, energy consumption is important in calculating the heating and cooling loads of residential, industrial, and other units. In order to calculate, design, and select the heating-cooling system, a suitable method of consumption and cost analysis is needed to prepare the required data for air conditioning motors and design an intelligent system. In this research, a method for balancing the temperature of an intelligent building in the context of the Internet of Things is presented based on a combination of network cutting and clustering techniques. In order to achieve the optimization of the algorithm in this method, it is necessary to convert heterogeneous data into homogeneous data, which was done by introducing a complex network and appropriate clustering techniques. In this method, information was collected by the IoT, and a graph matrix of these data was generated, then recorded by an artificial intelligence method and a combination of three methods of hierarchical clustering, Gaussian mixture, and K-means for comparison with the preliminary results. Finally, due to the reliability of the K-means method and the use of majority voting for weights, the K-means method reached 0.4 and was selected as the clustering method. The main part of the proposed method is based on different classifications in Appropriate criteria that were evaluated. Acceptable results were recorded so that with the minimum value of 88% and the highest value of about 100, the results of the proposed method can be confirmed. All hypotheses of the method can be declared possible and acceptable.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122324992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BLOCKCHAIN CONCEPTS, ARCHITECTURE, CHARACTERISTICS AND CHALLENGES: A SURVEY","authors":"Zahra Tayyebi Qasabeh, Seyyed Sajjad Mousavi","doi":"10.32010/26166127.2022.5.1.33.51","DOIUrl":"https://doi.org/10.32010/26166127.2022.5.1.33.51","url":null,"abstract":"The blockchain is a revolutionary technology transforming how assets are managed digitally and securely on a distributed network. Blockchain decentralized technology can solve distrust problems of the traditional centralized network and enhance the privacy and security of data. It provides a distinct way of storing and sharing data through blocks chained together. The blockchain is highly appraised and endorsed for its decentralized infrastructure and peer-to-peer nature. However, much research about the blockchain is shielded by Bitcoin. But blockchain could be applied to a variety of fields far beyond Bitcoin. Blockchain has shown its potential for transforming the traditional industry with its essential characteristics: decentralization, persistency, anonymity, and audibility. Undoubtedly, blockchain technology can significantly change the global business environment and lead to a paradigm shift in the functioning of the business world. However, to unlock the tremendous potential, various challenges in the adoption and viability of blockchain technology must be addressed before we can see the legal, economic, and technical viability of this technology in the operation of various business applications. In this study, the fundamental concepts of blockchain are discussed at the beginning, and the way it works and its architecture is mentioned, and since all technologies face challenges, this technology is no exception and has challenges based on the works related to the challenges It is mentioned.","PeriodicalId":275688,"journal":{"name":"Azerbaijan Journal of High Performance Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121383969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}