In hybrid conflicts of any intensity, hostilities (operations) are an element of other (non-force) actions mutually coordinated according to a single plan, mainly economic, political, diplomatic, informational, psychological, cyber, cognitive, etc. This creates destabilizing internal and external processes in the state that is the object of aggression (concern and discontent of the population, migration, acts of civil disobedience, etc.). The article examines the effective organizational and technical countermeasures against hybrid threats, national cyber defense systems in the developed countries. The article also presents the results of the investigations into the effects of the information hybrid threats through cyberspace on social, technical, socio and technical systems. The composition of the system of early efficient detection of the above hybrids is proposed. The results of the structural and parametric synthesis of the system are described. The recommendations related to the system implementation are given. A number of sufficient components for the effective design and development of the national cyber defense system of the state are proposed.
{"title":"Prevent and Reduce the Risk of Implementing the Main Cybersecurity Threats","authors":"Y. Danyk, S. Vdovenko, S. Voloshko","doi":"10.47839/ijc.21.1.2515","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2515","url":null,"abstract":"In hybrid conflicts of any intensity, hostilities (operations) are an element of other (non-force) actions mutually coordinated according to a single plan, mainly economic, political, diplomatic, informational, psychological, cyber, cognitive, etc. This creates destabilizing internal and external processes in the state that is the object of aggression (concern and discontent of the population, migration, acts of civil disobedience, etc.). The article examines the effective organizational and technical countermeasures against hybrid threats, national cyber defense systems in the developed countries. The article also presents the results of the investigations into the effects of the information hybrid threats through cyberspace on social, technical, socio and technical systems. The composition of the system of early efficient detection of the above hybrids is proposed. The results of the structural and parametric synthesis of the system are described. The recommendations related to the system implementation are given. A number of sufficient components for the effective design and development of the national cyber defense system of the state are proposed.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84120231","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}
The space expansion-contraction operator was originally developed to solve mathematical programming problems. However, it can be successfully applied to solve the problem of ellipsoidal approximation of the information set in the state space analytically specified. In this case, a main property of the operator - space compression is used to minimize the approximating ellipsoid by a multidimensional volume. The paper shows the use of the specified expansion-contraction operator to approximate a set of attainability of the linear control system as an example. The main goal of the paper is to give analytical and geometric representations of the specified operator in order to show its action in the approximation problem. For this purpose, the paper shows an analytical derivation of the operator and a geometric illustration of each parameter of the operator. The results of minimum approximation modeling by this operator compared with other known solutions have been also presented. The simulation results are given both numerically and graphically. Based on the results of comparison, conclusions are made and recommendations are given in the use of ellipsoidal approximation of information sets according to different criteria for minimizing the approximating ellipsoid. Typical examples of ellipsoidal approximation, which show when it is expedient to use the proposed of expansion-contraction operator, have been given.
{"title":"Stretch-Contract Operator in the Ellipsoidal Approximation of the Minkowski Sum of Convex Sets","authors":"O. V. Sholokhov","doi":"10.47839/ijc.21.1.2517","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2517","url":null,"abstract":"The space expansion-contraction operator was originally developed to solve mathematical programming problems. However, it can be successfully applied to solve the problem of ellipsoidal approximation of the information set in the state space analytically specified. In this case, a main property of the operator - space compression is used to minimize the approximating ellipsoid by a multidimensional volume. The paper shows the use of the specified expansion-contraction operator to approximate a set of attainability of the linear control system as an example. The main goal of the paper is to give analytical and geometric representations of the specified operator in order to show its action in the approximation problem. For this purpose, the paper shows an analytical derivation of the operator and a geometric illustration of each parameter of the operator. The results of minimum approximation modeling by this operator compared with other known solutions have been also presented. The simulation results are given both numerically and graphically. Based on the results of comparison, conclusions are made and recommendations are given in the use of ellipsoidal approximation of information sets according to different criteria for minimizing the approximating ellipsoid. Typical examples of ellipsoidal approximation, which show when it is expedient to use the proposed of expansion-contraction operator, have been given.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84999385","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}
Recurrent neural networks (RNN) based on a long short-term memory (LSTM) are used for predicting the future out of a given set of time series data. Usually, only one future time step is predicted. In this article, the capability of LSTM networks for a wide look into the future is explored. The time series data are taken from the evolution of share prices from stock trading. As expected, the longer the view into the future the stronger the deviations between prediction and reality. However, strange memory effects are observed. They range from periodic predictions (with time periods of the order of one month) to predictions that are an exact copy of a long-term sequence from far previous data. The trigger mechanisms for recalling memory in LSTM networks seem to be rather independent of the behaviour of the time-series data within the last “sliding window" or “batch". Similar periodic predictions are also observed for GRU networks and if the trainable parameters are reduced drastically. A better understanding of the influence of regularisations details of RNNs may be helpful for improving their predictive power.
{"title":"On Strange Memory Effects in Long–term Forecasts using Regularised Recurrent Neural Networks","authors":"Arthur Lerke, H. Hessling","doi":"10.47839/ijc.21.1.2513","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2513","url":null,"abstract":"Recurrent neural networks (RNN) based on a long short-term memory (LSTM) are used for predicting the future out of a given set of time series data. Usually, only one future time step is predicted. In this article, the capability of LSTM networks for a wide look into the future is explored. The time series data are taken from the evolution of share prices from stock trading. As expected, the longer the view into the future the stronger the deviations between prediction and reality. However, strange memory effects are observed. They range from periodic predictions (with time periods of the order of one month) to predictions that are an exact copy of a long-term sequence from far previous data. The trigger mechanisms for recalling memory in LSTM networks seem to be rather independent of the behaviour of the time-series data within the last “sliding window\" or “batch\". Similar periodic predictions are also observed for GRU networks and if the trainable parameters are reduced drastically. A better understanding of the influence of regularisations details of RNNs may be helpful for improving their predictive power.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86075913","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}
M. Sarosa, Mokhamad Hadi Wijaya, H. Tolle, A. E. Rakhmania
Chatbot can be utilized as an interactive learning media for students. It can be implemented using modular system by dividing the courses into several modular based on the course contents. The proposed program contributes positively to the integration of object-oriented programming into Google classroom by broadening the service without being limited by space, time and number of students, and also helps in increasing students’ interest in learning. The proposed model was meant to establish interactive conversation to understand the concept of Oracle Academy Java Foundation material based on students’ level of understanding when organizing exercise items. The program was applied in three different classes and found to have increased the final exam results with an average difference of 0.60 points from the scale of maximum 10 points from the conventional learning group. The value of post-test was also observed to have increased by 0.39 points from the given pre-test. In general, implementation of chatbot could improve the quality of learning.
聊天机器人可以作为学生的互动学习媒体。可以根据课程内容将课程划分为几个模块，采用模块化系统实现。该方案不受空间、时间和人数的限制，扩大了服务范围，为面向对象编程融入谷歌课堂做出了积极贡献，也有助于提高学生的学习兴趣。所提出的模型旨在建立交互式对话，以基于学生在组织练习项目时的理解水平来理解Oracle Academy Java Foundation材料的概念。在3个不同的班级中应用了该课程，结果发现，与常规学习组的满分10分相比，期末考试成绩平均提高了0.60分。后测的值也比给定的前测增加了0.39点。总的来说，聊天机器人的实施可以提高学习质量。
{"title":"Implementation of Chatbot in Online Classes using Google Classroom","authors":"M. Sarosa, Mokhamad Hadi Wijaya, H. Tolle, A. E. Rakhmania","doi":"10.47839/ijc.21.1.2516","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2516","url":null,"abstract":"Chatbot can be utilized as an interactive learning media for students. It can be implemented using modular system by dividing the courses into several modular based on the course contents. The proposed program contributes positively to the integration of object-oriented programming into Google classroom by broadening the service without being limited by space, time and number of students, and also helps in increasing students’ interest in learning. The proposed model was meant to establish interactive conversation to understand the concept of Oracle Academy Java Foundation material based on students’ level of understanding when organizing exercise items. The program was applied in three different classes and found to have increased the final exam results with an average difference of 0.60 points from the scale of maximum 10 points from the conventional learning group. The value of post-test was also observed to have increased by 0.39 points from the given pre-test. In general, implementation of chatbot could improve the quality of learning.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88501805","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}
Bohdan Chernetskyi, V. Kharchenko, Alexandr Orehov
The article is devoted to the development of a monitoring system based on wireless sensor networks. The purpose of the article is to implement a system for environmental monitoring using wireless sensor networks, as well as to solve the problem of covering the area with this network. Wireless sensor networks and their involvement in environmental monitoring are investigated and interactions between wireless networks and data communication protocols are described. The monitoring system is considered and analyzed. An experiment is conducted in which it has been checked at what maximum distance the temperature parameters can be transmitted, the experiment is conducted with and without interference. Routing algorithms for how they work and how parameters (temperature) are transmitted from sensors to the server are considered. A terrestrial monitoring system layout for environmental monitoring is investigated and developed based on Zigbee wireless sensor network construction technology, given that it can be added to this network new units or their replacement. The Mesh topology is selected and the separate physical devices that are the nodes of this network are identified. Nodes are also designed, using modules from Digi called XBee as a base station for Arduino sensors and as a ZigBee data base. These nodes are investigated for noise immunity and stability using flame, smoke and temperature sensors. The study found that XBee nodes are very unstable working near Wi-Fi routers and interfering in the form of forest. The conclusion about the result of the experiment is formulated, as well as how the system can be further upgraded, which can be added and what parameters can be observed. The proposed method for the location of the ground forest fire monitoring system’s equipment ensures full control and the flame detection preciseness.
{"title":"Wireless Sensor Network based Forest Fire Early Detection Systems: Development and Implementation","authors":"Bohdan Chernetskyi, V. Kharchenko, Alexandr Orehov","doi":"10.47839/ijc.21.1.2522","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2522","url":null,"abstract":"The article is devoted to the development of a monitoring system based on wireless sensor networks. The purpose of the article is to implement a system for environmental monitoring using wireless sensor networks, as well as to solve the problem of covering the area with this network. Wireless sensor networks and their involvement in environmental monitoring are investigated and interactions between wireless networks and data communication protocols are described. The monitoring system is considered and analyzed. An experiment is conducted in which it has been checked at what maximum distance the temperature parameters can be transmitted, the experiment is conducted with and without interference. Routing algorithms for how they work and how parameters (temperature) are transmitted from sensors to the server are considered. A terrestrial monitoring system layout for environmental monitoring is investigated and developed based on Zigbee wireless sensor network construction technology, given that it can be added to this network new units or their replacement. The Mesh topology is selected and the separate physical devices that are the nodes of this network are identified. Nodes are also designed, using modules from Digi called XBee as a base station for Arduino sensors and as a ZigBee data base. These nodes are investigated for noise immunity and stability using flame, smoke and temperature sensors. The study found that XBee nodes are very unstable working near Wi-Fi routers and interfering in the form of forest. The conclusion about the result of the experiment is formulated, as well as how the system can be further upgraded, which can be added and what parameters can be observed. The proposed method for the location of the ground forest fire monitoring system’s equipment ensures full control and the flame detection preciseness.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88582450","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}
D. C. R. Novitasari, Putri Wulandari, Dina Zatusiva Haq
Cervical cancer is a deadly disease attacking women. It represents 6.6% of all female cancers. The stadium of cervical cancer is determined based on the presence of carcinoma. The cervical cancer classification system can be used to help medical workers to analyze the stadium of cervical cancer. In this study, cervical cancer stages were divided into five classes, namely, normal cervix, stadium I, stadium II, stadium III, and stadium IV based on colposcopy images. The proposed method is one of deep learning methods, that is convolutional neural network (CNN) using deep residual network (ResidualNet) architecture. This study compared ResidualNet-18, ResidualNet-50, and ResidualNet-101 models and some conventional methods. The comparison results show that ResidualNet is more accurate than conventional methods. From the experiment, based on the accuracy value and elapsed time, ResidualNet-50 is worth using for cervical cancer classification. The result of this evaluation is higher than the maximum achievement of the ResidualNet-18 architecture. In addition, the elapsed time of the classification process using the ResidualNet-50 architecture with the accuracy, sensitivity, and specificity values reaching 100% is shorter than ResidualNet-101, which is 4397 s.
{"title":"Cervical Cancer Diagnosis System using Convolutional Neural Network ResidualNet","authors":"D. C. R. Novitasari, Putri Wulandari, Dina Zatusiva Haq","doi":"10.47839/ijc.21.1.2518","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2518","url":null,"abstract":"Cervical cancer is a deadly disease attacking women. It represents 6.6% of all female cancers. The stadium of cervical cancer is determined based on the presence of carcinoma. The cervical cancer classification system can be used to help medical workers to analyze the stadium of cervical cancer. In this study, cervical cancer stages were divided into five classes, namely, normal cervix, stadium I, stadium II, stadium III, and stadium IV based on colposcopy images. The proposed method is one of deep learning methods, that is convolutional neural network (CNN) using deep residual network (ResidualNet) architecture. This study compared ResidualNet-18, ResidualNet-50, and ResidualNet-101 models and some conventional methods. The comparison results show that ResidualNet is more accurate than conventional methods. From the experiment, based on the accuracy value and elapsed time, ResidualNet-50 is worth using for cervical cancer classification. The result of this evaluation is higher than the maximum achievement of the ResidualNet-18 architecture. In addition, the elapsed time of the classification process using the ResidualNet-50 architecture with the accuracy, sensitivity, and specificity values reaching 100% is shorter than ResidualNet-101, which is 4397 s.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84572637","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}
A simple and easy to implement but very effective algorithm for solving real-value parameter optimization problems is introduced in this paper. The main idea of the algorithm is to perform a local search repeatedly on a prospective subregion where the optimal solution may be located. The local search randomly samples a number of solutions in a given subregion. If a new best-so- far solution has been found, the center of the search subregion is moved based on the new best-so-far solution and the size of the search subregion is gradually reduced by a predefined shrinking rate. Otherwise, the center of the search is not moved and the size of the search subregion is reduced using a predefined shrinking rate. This process is repeated for a number of instances so that the search is focused on a gradually smaller and smaller prospective subregion. To enhance the likelihood of achieving an optimal solution, many rounds of this repeated local search are performed. Each round starts with a smaller and smaller initial search space. According to the experiment results, the proposed algorithm, though very simple, can outperform some well-known optimization algorithms on some testing functions.
{"title":"A Real-Value Parameter Function Optimization Algorithm using Repeated Adaptive Local Search","authors":"S. Auwatanamongkol","doi":"10.47839/ijc.21.1.2519","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2519","url":null,"abstract":"A simple and easy to implement but very effective algorithm for solving real-value parameter optimization problems is introduced in this paper. The main idea of the algorithm is to perform a local search repeatedly on a prospective subregion where the optimal solution may be located. The local search randomly samples a number of solutions in a given subregion. If a new best-so- far solution has been found, the center of the search subregion is moved based on the new best-so-far solution and the size of the search subregion is gradually reduced by a predefined shrinking rate. Otherwise, the center of the search is not moved and the size of the search subregion is reduced using a predefined shrinking rate. This process is repeated for a number of instances so that the search is focused on a gradually smaller and smaller prospective subregion. To enhance the likelihood of achieving an optimal solution, many rounds of this repeated local search are performed. Each round starts with a smaller and smaller initial search space. According to the experiment results, the proposed algorithm, though very simple, can outperform some well-known optimization algorithms on some testing functions.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85094685","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}
Extending the lifetime of Wireless Sensor Networks (WSN) is an important issue due to the mission assigned to these networks. The sensors collect data relevant to a specific field. Then, the sensors send the collected data to a base station where it is analyzed, and a suitable reaction can be taken. Sensors in WSN depend on a battery with limited energy to do their work. Data transmission and receiving consume energy, which may lead to the loss of the whole network or some of the essential nodes. For this reason, energy must be preserved as long as possible to prolong the network lifetime. Several types of research were presented with different approaches to minimize power consumption. In this paper, we present a hybrid technique that includes two population-based algorithms: genetic algorithm (GA) and artificial bee colony (ABC) with clustering approaches. This proposed novel technique aims to reduce the dissipation of power consumption per sensor node in the WSN, and as a consequence, the lifetime of the WSN is extended. The ABC algorithm was used to improve an initial population, which was used in the GA. Also, we used two approaches of clustering; clustering based on genetic algorithm and K-means clustering beside LEACH protocol. The experimental results show that the proposed approach approved its efficiency in lifetime extending through an increasing number of the operational nodes per round and transmission.
{"title":"Utilizing Genetic Algorithm and Artificial Bee Colony Algorithm to Extend the WSN Lifetime","authors":"Sawsan Alshattnawi, Lubna Afifi, Amani Shatnawi, Malek Barhoush","doi":"10.47839/ijc.21.1.2514","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2514","url":null,"abstract":"Extending the lifetime of Wireless Sensor Networks (WSN) is an important issue due to the mission assigned to these networks. The sensors collect data relevant to a specific field. Then, the sensors send the collected data to a base station where it is analyzed, and a suitable reaction can be taken. Sensors in WSN depend on a battery with limited energy to do their work. Data transmission and receiving consume energy, which may lead to the loss of the whole network or some of the essential nodes. For this reason, energy must be preserved as long as possible to prolong the network lifetime. Several types of research were presented with different approaches to minimize power consumption. In this paper, we present a hybrid technique that includes two population-based algorithms: genetic algorithm (GA) and artificial bee colony (ABC) with clustering approaches. This proposed novel technique aims to reduce the dissipation of power consumption per sensor node in the WSN, and as a consequence, the lifetime of the WSN is extended. The ABC algorithm was used to improve an initial population, which was used in the GA. Also, we used two approaches of clustering; clustering based on genetic algorithm and K-means clustering beside LEACH protocol. The experimental results show that the proposed approach approved its efficiency in lifetime extending through an increasing number of the operational nodes per round and transmission.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81413374","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}
Zana Azeez Kakarash, Hawkar Saeed Ezat, Shokhan Ali Omar, Nawroz Fadhil Ahmed
In recent years, due to the non-linear nature, complexity, and irregularity of time series, especially in energy consumption and climate, studying this field has become very important. Therefore, this study aims to provide a high accuracy and efficiency hybrid approach to time series forecasting. The proposed model is called EDFPSO-SVR (Empirical Mode Decomposition- Discrete Wavelet Transform- Feature selection with Particle Swarm Optimization-Support Vector Regression). In the proposed hybrid approach, the first step is to decompose the signal into the Intrinsic Mode Functions (IMF) component using the Empirical Mode Decomposition (EMD) algorithm. In the second step, each component is transformed into subsequences of approximation properties and details by converting the Wavelets. In the third step, the best feature is extracted by the PSO algorithm. The purpose of using the PSO algorithm is feature extraction and error minimization of the proposed approach. The fourth step, using time vector regression, has dealt with time series forecasting. Four data sets in two different fields have been used to evaluate the proposed method. The two datasets are electric load of England and Poland, and the other two datasets are related to the temperature of Australia and Belgium. Evaluation criteria include MSE, RMSE, MAPE, and MAE. The evaluation results of the proposed method with other Principal component analysis (PCA) feature extraction algorithms, and comparisons with methods and studies in this field, indicate the proper performance of the proposed approach.
{"title":"Time Series Forecasting Based on Support Vector Machine Using Particle Swarm Optimization","authors":"Zana Azeez Kakarash, Hawkar Saeed Ezat, Shokhan Ali Omar, Nawroz Fadhil Ahmed","doi":"10.47839/ijc.21.1.2520","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2520","url":null,"abstract":"In recent years, due to the non-linear nature, complexity, and irregularity of time series, especially in energy consumption and climate, studying this field has become very important. Therefore, this study aims to provide a high accuracy and efficiency hybrid approach to time series forecasting. The proposed model is called EDFPSO-SVR (Empirical Mode Decomposition- Discrete Wavelet Transform- Feature selection with Particle Swarm Optimization-Support Vector Regression). In the proposed hybrid approach, the first step is to decompose the signal into the Intrinsic Mode Functions (IMF) component using the Empirical Mode Decomposition (EMD) algorithm. In the second step, each component is transformed into subsequences of approximation properties and details by converting the Wavelets. In the third step, the best feature is extracted by the PSO algorithm. The purpose of using the PSO algorithm is feature extraction and error minimization of the proposed approach. The fourth step, using time vector regression, has dealt with time series forecasting. Four data sets in two different fields have been used to evaluate the proposed method. The two datasets are electric load of England and Poland, and the other two datasets are related to the temperature of Australia and Belgium. Evaluation criteria include MSE, RMSE, MAPE, and MAE. The evaluation results of the proposed method with other Principal component analysis (PCA) feature extraction algorithms, and comparisons with methods and studies in this field, indicate the proper performance of the proposed approach.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72736472","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}
Article opens series of works devoted to profile-oriented software quality assessment. In this article the concept of software requirements profiling for subsequent software requirements profile quality assessment is analyzed and developed. The main result of the article is the development of the software requirements profile quality model. The model describes the following: characteristics and attributes of software requirements and their classification features; characteristics and attributes of software requirements profile and their classification features; semantics and syntax of software requirements. The article is based on analysis and use of the following standards: ISO/IEC 25012:2008, ISO/IEC/IEEE 29148:2018, ISO/IEC/IEEE 29148:2011. Examples of software requirements profile quality model are introduced. The suggested approach is used for the development of terms of reference or draft of a new standard. For example, the model is used for an assessment draft of the new standard “Requirements to computer security of NPP Instrumentation and Control Systems (NPP I&C)” developed by the Ukrainian state regulatory body. As a result of the development of the software requirements profile quality model, a set of propositions for improving the quality of the standard as a branch of the profile for NPP I&C cybersecurity are implemented.
{"title":"Software Requirements Profile Quality Model","authors":"O. Gordieiev, V. Kharchenko, D. Gordieieva","doi":"10.47839/ijc.21.1.2524","DOIUrl":"https://doi.org/10.47839/ijc.21.1.2524","url":null,"abstract":"Article opens series of works devoted to profile-oriented software quality assessment. In this article the concept of software requirements profiling for subsequent software requirements profile quality assessment is analyzed and developed. The main result of the article is the development of the software requirements profile quality model. The model describes the following: characteristics and attributes of software requirements and their classification features; characteristics and attributes of software requirements profile and their classification features; semantics and syntax of software requirements. The article is based on analysis and use of the following standards: ISO/IEC 25012:2008, ISO/IEC/IEEE 29148:2018, ISO/IEC/IEEE 29148:2011. Examples of software requirements profile quality model are introduced. The suggested approach is used for the development of terms of reference or draft of a new standard. For example, the model is used for an assessment draft of the new standard “Requirements to computer security of NPP Instrumentation and Control Systems (NPP I&C)” developed by the Ukrainian state regulatory body. As a result of the development of the software requirements profile quality model, a set of propositions for improving the quality of the standard as a branch of the profile for NPP I&C cybersecurity are implemented.","PeriodicalId":37669,"journal":{"name":"International Journal of Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88194485","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：