Pub Date : 2023-06-12DOI: 10.15625/1813-9663/18172
B. Cao
Shrimp farming is one of the highest potential areas in the coastal provinces of Vietnam. The technical level of shrimp farming is developing strongly in the direction of high technology based on applying modern equipment and machinery. However, the efficiency of shrimp farming is still not high, the monitoring and control of the actuators are mainly manual. Shrimp farmers are not interested in using smart controllers for shrimp farms. In this article, the author evaluates the limitations of the current controllers and proposes a multi-function controller which is suitable for the practical requirements of high-tech shrimp farms (HTSFs) with significant functions such as soft configuration, overload protection, and engine damage warning for actuator devices. In addition, the proposed controller also allows monitoring and automatically controlling HTSFs on a mobile application.
{"title":"AN IMPROVEMENT DESIGN OF MULTI-FUNCTION CONTROLLER FOR HIGH-TECH SHRIMP FARM","authors":"B. Cao","doi":"10.15625/1813-9663/18172","DOIUrl":"https://doi.org/10.15625/1813-9663/18172","url":null,"abstract":"Shrimp farming is one of the highest potential areas in the coastal provinces of Vietnam. The technical level of shrimp farming is developing strongly in the direction of high technology based on applying modern equipment and machinery. However, the efficiency of shrimp farming is still not high, the monitoring and control of the actuators are mainly manual. Shrimp farmers are not interested in using smart controllers for shrimp farms. In this article, the author evaluates the limitations of the current controllers and proposes a multi-function controller which is suitable for the practical requirements of high-tech shrimp farms (HTSFs) with significant functions such as soft configuration, overload protection, and engine damage warning for actuator devices. In addition, the proposed controller also allows monitoring and automatically controlling HTSFs on a mobile application.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82172989","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}
Pub Date : 2023-06-12DOI: 10.15625/1813-9663/18067
Khang Nguyen, Viet V. Nguyen, Nga Mai, An H. Nguyen, An Nguyen
Human gait analysis is a promising method of researching on human activities like walking or sitting. It reflects the habits of one person and can be observed in any activity that person performs. The patterns in human movements are influenced by many factors, including physiology, social, psychological, and health factors. Differences in limb movements help identify gait patterns, which are often measured using inertial measurement unit sensors (IMU) like gyroscopes and accelerometers placed in various locations throughout the body. This paper analyses the combination of IMU sensors and electromyography sensors (EMG) to improve the identification accuracy of human movements. We propose the hybrid convolutional neural network (CNN) and long short-term memory neuron network (LSTM) for the human gait analysis problem to achieve an accuracy of 0.9418, better than other models including pure CNN models. By using CNN's image classification advancements, we analyse multivariate time series sensor signals by using a sliding window to transform sensor data into image representation and principal component analysis (PCA) to reduce the data dimensionality. To tackle the dataset imbalance issue, we re-weight our model loss by the inverse effective number of samples in each class. We use the human gait HuGaDB dataset with unique characteristics, for gait analysis.
{"title":"HUMAN GAIT ANALYSIS USING HYBRID CONVOLUTIONAL NEURAL NETWORKS","authors":"Khang Nguyen, Viet V. Nguyen, Nga Mai, An H. Nguyen, An Nguyen","doi":"10.15625/1813-9663/18067","DOIUrl":"https://doi.org/10.15625/1813-9663/18067","url":null,"abstract":"Human gait analysis is a promising method of researching on human activities like walking or sitting. It reflects the habits of one person and can be observed in any activity that person performs. The patterns in human movements are influenced by many factors, including physiology, social, psychological, and health factors. Differences in limb movements help identify gait patterns, which are often measured using inertial measurement unit sensors (IMU) like gyroscopes and accelerometers placed in various locations throughout the body. \u0000 \u0000This paper analyses the combination of IMU sensors and electromyography sensors (EMG) to improve the identification accuracy of human movements. We propose the hybrid convolutional neural network (CNN) and long short-term memory neuron network (LSTM) for the human gait analysis problem to achieve an accuracy of 0.9418, better than other models including pure CNN models. By using CNN's image classification advancements, we analyse multivariate time series sensor signals by using a sliding window to transform sensor data into image representation and principal component analysis (PCA) to reduce the data dimensionality. To tackle the dataset imbalance issue, we re-weight our model loss by the inverse effective number of samples in each class. We use the human gait HuGaDB dataset with unique characteristics, for gait analysis.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81786918","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}
Pub Date : 2023-06-12DOI: 10.15625/1813-9663/18025
Thi Bich Diep Nguyen, Trung-Nghia Phung, T. Vu
Sign languages are independent languages of deaf communities. The translation from normal languages (i.e., Vietnamese Language - VL) as long as other sign languages to Vietnamese sign language (VSL) is a meaningful task that breaks down communication barriers and improves the quality of life for the deaf community. In this paper, we experimented with and proposed several methods for building and improving models for the VL to VSL translation task. We presented a data augmentation method to improve the performance of our neural machine translation models. Using an initial dataset of 10k bilingual sentence pairs, we were able to obtain a new dataset of 60k sentence pairs with a perplexity score no more than 1.5 times that of the original dataset. Experiments on the original dataset showed that rule-based models achieved the highest BLEU score of 68.02 among the translation models. However, with the augmented dataset, the Transformer model achieved the best performance with a BLEU score of 89.23, which is significantly better than that of other conventional approach methods.
{"title":"A STUDY OF DATA AUGMENTATION AND ACCURACY IMPROVEMENT IN MACHINE TRANSLATION FOR VIETNAMESE SIGN LANGUAGE","authors":"Thi Bich Diep Nguyen, Trung-Nghia Phung, T. Vu","doi":"10.15625/1813-9663/18025","DOIUrl":"https://doi.org/10.15625/1813-9663/18025","url":null,"abstract":"Sign languages are independent languages of deaf communities. The translation from normal languages (i.e., Vietnamese Language - VL) as long as other sign languages to Vietnamese sign language (VSL) is a meaningful task that breaks down communication barriers and improves the quality of life for the deaf community. In this paper, we experimented with and proposed several methods for building and improving models for the VL to VSL translation task. We presented a data augmentation method to improve the performance of our neural machine translation models. Using an initial dataset of 10k bilingual sentence pairs, we were able to obtain a new dataset of 60k sentence pairs with a perplexity score no more than 1.5 times that of the original dataset. Experiments on the original dataset showed that rule-based models achieved the highest BLEU score of 68.02 among the translation models. However, with the augmented dataset, the Transformer model achieved the best performance with a BLEU score of 89.23, which is significantly better than that of other conventional approach methods.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"118 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74439139","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}
Pub Date : 2023-06-12DOI: 10.15625/1813-9663/18136
Phuong Pham Ngoc, Chung Tran Quang, Mai Luong Chi
Current adaptive-based speech synthesis techniques are based on two main streams: 1. Fine-tuning the model using small amounts of adaptive data, and 2. Conditionally training the entire model through a speaker embedding of the target speaker. However, both of these methods require adaptive data to appear during training, which makes the training cost to generate new voices quite expensively. In addition, the traditional TTS model uses a simple loss function to reproduce the acoustic features. However, this optimization is based on incorrect distribution assumptions leading to noisy composite audio results. We introduce the Adapt-TTS model that allows high-quality audio synthesis from a small adaptive sample without training to solve these problems. Key recommendations: 1. The Extracting Mel-vector (EMV) architecture allows for a better representation of speaker characteristics and speech style; 2. An improved zero-shot model with a denoising diffusion model (Mel-spectrogram denoiser) component allows for new voice synthesis without training with better quality (less noise). The evaluation results have proven the model's effectiveness when only needing a single utterance (1-3 seconds) of the reference speaker, the synthesis system gave high-quality synthesis results and achieved high similarity.
{"title":"ADAPT-TTS: HIGH-QUALITY ZERO-SHOT MULTI-SPEAKER TEXT-TO-SPEECH ADAPTIVE-BASED FOR VIETNAMESE","authors":"Phuong Pham Ngoc, Chung Tran Quang, Mai Luong Chi","doi":"10.15625/1813-9663/18136","DOIUrl":"https://doi.org/10.15625/1813-9663/18136","url":null,"abstract":"Current adaptive-based speech synthesis techniques are based on two main streams: 1. Fine-tuning the model using small amounts of adaptive data, and 2. Conditionally training the entire model through a speaker embedding of the target speaker. However, both of these methods require adaptive data to appear during training, which makes the training cost to generate new voices quite expensively. In addition, the traditional TTS model uses a simple loss function to reproduce the acoustic features. However, this optimization is based on incorrect distribution assumptions leading to noisy composite audio results. We introduce the Adapt-TTS model that allows high-quality audio synthesis from a small adaptive sample without training to solve these problems. Key recommendations: 1. The Extracting Mel-vector (EMV) architecture allows for a better representation of speaker characteristics and speech style; 2. An improved zero-shot model with a denoising diffusion model (Mel-spectrogram denoiser) component allows for new voice synthesis without training with better quality (less noise). The evaluation results have proven the model's effectiveness when only needing a single utterance (1-3 seconds) of the reference speaker, the synthesis system gave high-quality synthesis results and achieved high similarity.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79513707","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}
Pub Date : 2023-06-12DOI: 10.15625/1813-9663/18099
N. D. Dien, Luy Tan Nguyen, L. Lãi, Tran Thanh Hai
This paper introduces an optimal tracking controller for robot manipulators with saturation torques. The robot model is presented as a strict-feedback nonlinear system. Firstly, the position tracking control problem is transformed into the optimal tracking control problem. Subsequently, the saturated optimal control law is designed. The optimal control law is determined through the solution of the Hamilton-Jacobi-Bellman (HJB) equation. We use a reinforcement learning algorithm with only one neural network (NN) to approximate the solution of the equation HJB. The technique of experience replay is used to relax a persistent citation condition. By Lyapunov analysis, the tracking and the approximation errors are uniformly ultimately bounded (UUB). Finally, the simulation on a robot manipulator with saturation torques is performed to verify the efficiency of the proposed controller.
{"title":"OPTIMAL TRACKING CONTROL FOR ROBOT MANIPULATORS WITH INPUT CONSTRAINT BASED REINFORCEMENT LEARNING","authors":"N. D. Dien, Luy Tan Nguyen, L. Lãi, Tran Thanh Hai","doi":"10.15625/1813-9663/18099","DOIUrl":"https://doi.org/10.15625/1813-9663/18099","url":null,"abstract":"This paper introduces an optimal tracking controller for robot manipulators with saturation torques. The robot model is presented as a strict-feedback nonlinear system. Firstly, the position tracking control problem is transformed into the optimal tracking control problem. Subsequently, the saturated optimal control law is designed. The optimal control law is determined through the solution of the Hamilton-Jacobi-Bellman (HJB) equation. We use a reinforcement learning algorithm with only one neural network (NN) to approximate the solution of the equation HJB. The technique of experience replay is used to relax a persistent citation condition. By Lyapunov analysis, the tracking and the approximation errors are uniformly ultimately bounded (UUB). Finally, the simulation on a robot manipulator with saturation torques is performed to verify the efficiency of the proposed controller.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"117 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80481124","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}
Pub Date : 2023-03-29DOI: 10.15625/1813-9663/17641
N. D. Dien, Luy Tan Nguyen, L. Lãi
This paper introduces an optimal tracking controller for robot manipulators with asymmetrically saturated torques and partially - unknown dynamics based on a reinforcement learning method using a neural network. Firstly, the feedforward control inputs are designed based on the backstepping technique to convert the tracking control problem into the optimal tracking control problem. Secondly, a cost function of the system with asymmetrically saturated input is defined, and the constrained Hamilton-Jacobi-Bellman equation is built, which is solved by the online reinforcement learning algorithm using only a single neural network. Then, the asymmetric saturation optimal control rule is determined. Additionally, the concurrent learning technique is used to relax the demand for the persistence of excitation conditions. The built algorithm ensures that the closed-loop system is asymptotically stable, the approximation error is uniformly ultimately bounded (UUB), and the cost function converges to the near-optimal value. Finally, the effectiveness of the proposed algorithm is shown through comparative simulations.
{"title":"OPTIMAL TRACKING CONTROL FOR ROBOT MANIPULATORS WITH ASYMMETRIC SATURATION TORQUES BASED ON REINFORCEMENT LEARNING","authors":"N. D. Dien, Luy Tan Nguyen, L. Lãi","doi":"10.15625/1813-9663/17641","DOIUrl":"https://doi.org/10.15625/1813-9663/17641","url":null,"abstract":"This paper introduces an optimal tracking controller for robot manipulators with asymmetrically saturated torques and partially - unknown dynamics based on a reinforcement learning method using a neural network. Firstly, the feedforward control inputs are designed based on the backstepping technique to convert the tracking control problem into the optimal tracking control problem. Secondly, a cost function of the system with asymmetrically saturated input is defined, and the constrained Hamilton-Jacobi-Bellman equation is built, which is solved by the online reinforcement learning algorithm using only a single neural network. Then, the asymmetric saturation optimal control rule is determined. Additionally, the concurrent learning technique is used to relax the demand for the persistence of excitation conditions. The built algorithm ensures that the closed-loop system is asymptotically stable, the approximation error is uniformly ultimately bounded (UUB), and the cost function converges to the near-optimal value. Finally, the effectiveness of the proposed algorithm is shown through comparative simulations.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"62 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77725625","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}
Pub Date : 2023-03-14DOI: 10.15625/1813-9663/18081
M. Long, Tran Huu Toan, Tran Van Hung, T. Anh, Nguyen Hoang Hieu, Nguyen Thi Phuong Ha
This study presented an improved adaptive nonlinear terminal sliding mode control technique for the manipulator robot to achieve better adaptability and faster finite-time convergence. First, an adaptive self-updating algorithm will be developed to relax the problems of fixed control gain for the main proposed controller. Next, an adaptive neural network estimator is applied by estimating the robot dynamics to increase the tracking control performance. In addition, a compensator-typed robust controller also is designed to guarantee the robustness, continuity, and smoothing properties of the control system. To verify the effectiveness of the proposed method, besides applying the Lyapunov theorem, the comparative numerical simulation results will be provided in more detail.
{"title":"ADAPTIVE NONSINGULAR TERMINAL SLIDING MODE CONTROL FOR MANIPULATOR ROBOT","authors":"M. Long, Tran Huu Toan, Tran Van Hung, T. Anh, Nguyen Hoang Hieu, Nguyen Thi Phuong Ha","doi":"10.15625/1813-9663/18081","DOIUrl":"https://doi.org/10.15625/1813-9663/18081","url":null,"abstract":"This study presented an improved adaptive nonlinear terminal sliding mode control technique for the manipulator robot to achieve better adaptability and faster finite-time convergence. First, an adaptive self-updating algorithm will be developed to relax the problems of fixed control gain for the main proposed controller. Next, an adaptive neural network estimator is applied by estimating the robot dynamics to increase the tracking control performance. In addition, a compensator-typed robust controller also is designed to guarantee the robustness, continuity, and smoothing properties of the control system. To verify the effectiveness of the proposed method, besides applying the Lyapunov theorem, the comparative numerical simulation results will be provided in more detail.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88383045","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}
Pub Date : 2023-03-14DOI: 10.15625/1813-9663/18028
Nguyen Trung Tuan, L. Giang, Pham Huy Thong, N. Luong, Le Minh Tuan, UY Nguyenquoc, Le Minh Hoang
The prediction of weather changes, such as rainfall, clouds, floods, and storms, is critical in weather forecasting. There are several sources of input data for this purpose, including radar and observational data, but satellite remote sensing images are the most commonly used due to their ease of collection. In this paper, we present a novel method for weather nowcasting based on Mamdani complex fuzzy inference with multiple band input data. The proposed approach splits the process into two parts: the first part converts the multiple band satellite images into real and imaginary parts to facilitate the rule process, and the second part uses the Spatial CFIS+ algorithm to generate the predicted weather state, taking into account factors such as cloud, wind, and temperature. The use of MapReduce helps to speed up the algorithm's performance. Our experimental results show that this new method outperforms other relevant methods and demonstrates improved prediction accuracy.
{"title":"A NOVEL METHOD FOR WEATHER NOWCASTING BASED ON SPATIAL COMPLEX FUZZY INFERENCE WITH MULTIPLE BAND INPUT DATA","authors":"Nguyen Trung Tuan, L. Giang, Pham Huy Thong, N. Luong, Le Minh Tuan, UY Nguyenquoc, Le Minh Hoang","doi":"10.15625/1813-9663/18028","DOIUrl":"https://doi.org/10.15625/1813-9663/18028","url":null,"abstract":"The prediction of weather changes, such as rainfall, clouds, floods, and storms, is critical in weather forecasting. There are several sources of input data for this purpose, including radar and observational data, but satellite remote sensing images are the most commonly used due to their ease of collection. In this paper, we present a novel method for weather nowcasting based on Mamdani complex fuzzy inference with multiple band input data. The proposed approach splits the process into two parts: the first part converts the multiple band satellite images into real and imaginary parts to facilitate the rule process, and the second part uses the Spatial CFIS+ algorithm to generate the predicted weather state, taking into account factors such as cloud, wind, and temperature. The use of MapReduce helps to speed up the algorithm's performance. Our experimental results show that this new method outperforms other relevant methods and demonstrates improved prediction accuracy.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"2006 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86945313","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}
Pub Date : 2023-03-03DOI: 10.15625/1813-9663/16675
Cong Thanh Bui, V. Cao, Minh Hoang, Quang Uy Nguyen
The Dempster-Shafer (DS) theory of evidence is frequently used to combine multipe supervised machine learning models into a robust fusion-based model. However, using the DS theory to create a fusion model from multiple one-class classifications (OCCs) for network anomaly detection is a challenging task. First, the lack of attack data leads to the difficulty in estimating an appropriate threshold for the OCC models to distinguish between normal and abnormal samples. Second, it is also very challenging to find the weight of OCCs that corresponds to the contribution of each OCC model in the fusion model. In this paper, we attempt to solve the above issues in order to make the DS theory applicable for constructing OCC-based fusion models. Specifically, we propose two novel methods for automatically choosing the appropriate threshold of OCCs and for estimating the weight of individual OCCs in fusion-based models. Thanks to that, we develop an One-class Fusion-based Anomaly Detection model (OFuseAD) from multiple single OCCs. The proposed model is evaluated on ten well-known network anomaly detection problems. The experimental results show that the performance of OFuseAD is improved on almost all tested datasets using two metrics: accuray and F1-score. The visualization results provides the insight into the characteristics of OFuseAD.
{"title":"ONE-CLASS FUSION-BASED LEARNING MODEL FOR ANOMALY DETECTION","authors":"Cong Thanh Bui, V. Cao, Minh Hoang, Quang Uy Nguyen","doi":"10.15625/1813-9663/16675","DOIUrl":"https://doi.org/10.15625/1813-9663/16675","url":null,"abstract":"The Dempster-Shafer (DS) theory of evidence is frequently used to combine multipe supervised machine learning models into a robust fusion-based model. However, using the DS theory to create a fusion model from multiple one-class classifications (OCCs) for network anomaly detection is a challenging task. First, the lack of attack data leads to the difficulty in estimating an appropriate threshold for the OCC models to distinguish between normal and abnormal samples. Second, it is also very challenging to find the weight of OCCs that corresponds to the contribution of each OCC model in the fusion model. In this paper, we attempt to solve the above issues in order to make the DS theory applicable for constructing OCC-based fusion models. Specifically, we propose two novel methods for automatically choosing the appropriate threshold of OCCs and for estimating the weight of individual OCCs in fusion-based models. Thanks to that, we develop an One-class Fusion-based Anomaly Detection model (OFuseAD) from multiple single OCCs. The proposed model is evaluated on ten well-known network anomaly detection problems. The experimental results show that the performance of OFuseAD is improved on almost all tested datasets using two metrics: accuray and F1-score. The visualization results provides the insight into the characteristics of OFuseAD.","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86077271","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}
Pub Date : 2023-03-03DOI: 10.15625/1813-9663/17591
Nam-Thang Hoang, V. Tong, H. Tran, Cong-Son Duong, Tran-Le-Tuan Nguyen
Today, the Software-defined Network, with its advantages such as greater reliability via automation, more efficient network management, cost-savings, and faster scalability, is increasingly being deployed in many network systems and network operators. The most common deployment architecture is a distributed system with the existence of many independent domains, each controlled by an SDN controller. One of the well-known applications in SDN is server selection and routing. However, deploying server and route selection in distributed and heterogeneous SDN networks faces two issues. First, the lack of global views of the whole system is because the inter-communication between SDN domains has not been standardized for the distributed and heterogeneous SDN network. To solve this issue, we use our previous work, an open East-West interface called SINA, to adaptively guarantee the network state consistency of the distributed SDN network with multiple domains. Secondly, selecting the path for packet transmission based only on the current network states of a local SDN domain is ineffective as it can bring over-utilization to several links and under-utilization to others. Predicting the link cost of the whole path from the source to the destination is necessary. Therefore, this paper proposes an LSTM-based link cost prediction for the server and route selection mechanism in a distributed and heterogeneous SDN network. The experimental results show that our proposal improves up to 15% of link utilization, reduces 10% of packet loss, and obtains the lowest servers’response time compared to benchmarks
{"title":"LSTM-BASED SERVER AND ROUTE SELECTION IN DISTRIBUTED AND HETEROGENEOUS SDN NETWORK","authors":"Nam-Thang Hoang, V. Tong, H. Tran, Cong-Son Duong, Tran-Le-Tuan Nguyen","doi":"10.15625/1813-9663/17591","DOIUrl":"https://doi.org/10.15625/1813-9663/17591","url":null,"abstract":"Today, the Software-defined Network, with its advantages such as greater reliability via automation, more efficient network management, cost-savings, and faster scalability, is increasingly being deployed in many network systems and network operators. The most common deployment architecture is a distributed system with the existence of many independent domains, each controlled by an SDN controller. One of the well-known applications in SDN is server selection and routing. However, deploying server and route selection in distributed and heterogeneous SDN networks faces two issues. First, the lack of global views of the whole system is because the inter-communication between SDN domains has not been standardized for the distributed and heterogeneous SDN network. To solve this issue, we use our previous work, an open East-West interface called SINA, to adaptively guarantee the network state consistency of the distributed SDN network with multiple domains. Secondly, selecting the path for packet transmission based only on the current network states of a local SDN domain is ineffective as it can bring over-utilization to several links and under-utilization to others. Predicting the link cost of the whole path from the source to the destination is necessary. Therefore, this paper proposes an LSTM-based link cost prediction for the server and route selection mechanism in a distributed and heterogeneous SDN network. The experimental results show that our proposal improves up to 15% of link utilization, reduces 10% of packet loss, and obtains the lowest servers’response time compared to benchmarks","PeriodicalId":15444,"journal":{"name":"Journal of Computer Science and Cybernetics","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83627460","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：