Ethar Abdul Wahhab Hachim, Methaq Talib Gaata, Thekra Abbas
Cloud computing is becoming an essential technology for many organizations that are dynamically scalable and employ virtualized resources as a service done over the Internet. The security and privacy of the data stored in the cloud is cloud providers' main target. Every person wants to keep his data safe and store it in a secure place. The user considers cloud storage the best option to keep his data confidential without losing it. Authentication in the trusted cloud environment allows making knowledgeable authorization decisions for access to the protected individual's data. Voice authentication, also known as voice biometrics, depends on an individual's unique voice patterns for identification to access personal and sensitive data. The essential principle for voice authentication is that every person's voice differs in tone, pitch, and volume, which is adequate to make it uniquely distinguishable. This paper uses voice metric as an identifier to determine the authorized customers that can access the data in a cloud environment without risk. The Convolution Neural Network (CNN) architecture is proposed for identifying and classifying authorized and unauthorized people based on voice features. In addition, the 3DES algorithm is used to protect the voice features during the transfer between the client and cloud sides. In the testing, the experimental results of the proposed model achieve a high level of accuracy, reaching about 98%, and encryption efficiency metrics prove the proposed model's robustness against intended attacks to obtain the data.
{"title":"Voice-Authentication Model Based on Deep Learning for Cloud Environment","authors":"Ethar Abdul Wahhab Hachim, Methaq Talib Gaata, Thekra Abbas","doi":"10.30630/joiv.7.3.1303","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1303","url":null,"abstract":"Cloud computing is becoming an essential technology for many organizations that are dynamically scalable and employ virtualized resources as a service done over the Internet. The security and privacy of the data stored in the cloud is cloud providers' main target. Every person wants to keep his data safe and store it in a secure place. The user considers cloud storage the best option to keep his data confidential without losing it. Authentication in the trusted cloud environment allows making knowledgeable authorization decisions for access to the protected individual's data. Voice authentication, also known as voice biometrics, depends on an individual's unique voice patterns for identification to access personal and sensitive data. The essential principle for voice authentication is that every person's voice differs in tone, pitch, and volume, which is adequate to make it uniquely distinguishable. This paper uses voice metric as an identifier to determine the authorized customers that can access the data in a cloud environment without risk. The Convolution Neural Network (CNN) architecture is proposed for identifying and classifying authorized and unauthorized people based on voice features. In addition, the 3DES algorithm is used to protect the voice features during the transfer between the client and cloud sides. In the testing, the experimental results of the proposed model achieve a high level of accuracy, reaching about 98%, and encryption efficiency metrics prove the proposed model's robustness against intended attacks to obtain the data.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106273","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}
Image retrieval is the process of finding images in the database that are similar to the query image by measuring how close the feature values of the query image are to other images. Image retrieval is currently dominated by approaches that combine several different representations or features. The optimal weight of each feature is needed in combining the image features such as color features, texture features, and shape features. In this study, we use a multi-layer perceptron artificial neural network (MLP) method to obtain feature weights automatically and simultaneously look for optimal weights. The color moment is used to find nine color features, Gray Level Co-occurrence Matrix (GLCM) to find four texture features, and Hu Moment to find seven shape features totaling 20 neurons and all of these features become the input layer in our MLP network. Three neurons in output layers become the automatic weight of each feature. These weights are used to combine each feature's role in obtaining the relevant image. Euclidean Distance is used to measure similarity. The average precision values obtained using automatic feature weights are 93.94% for the synthetic dataset, 91.19% for the Coil-100 dataset, and 54.31% for the Wang dataset. These results have an average difference of 5.06% with the target so automatic feature weighting works well. This value is obtained at a hidden layer size of 11 and a learning rate of 0.1. In addition, the use of automatic feature weighting gives more accurate results compared to manual feature weighting.
{"title":"Automatic Weight of Color, Texture, and Shape Features in Content-Based Image Retrieval Using Artificial Neural Network","authors":"Akmal Akmal, Rinaldi Munir, Judhi Santoso","doi":"10.30630/joiv.7.3.1184","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1184","url":null,"abstract":"Image retrieval is the process of finding images in the database that are similar to the query image by measuring how close the feature values of the query image are to other images. Image retrieval is currently dominated by approaches that combine several different representations or features. The optimal weight of each feature is needed in combining the image features such as color features, texture features, and shape features. In this study, we use a multi-layer perceptron artificial neural network (MLP) method to obtain feature weights automatically and simultaneously look for optimal weights. The color moment is used to find nine color features, Gray Level Co-occurrence Matrix (GLCM) to find four texture features, and Hu Moment to find seven shape features totaling 20 neurons and all of these features become the input layer in our MLP network. Three neurons in output layers become the automatic weight of each feature. These weights are used to combine each feature's role in obtaining the relevant image. Euclidean Distance is used to measure similarity. The average precision values obtained using automatic feature weights are 93.94% for the synthetic dataset, 91.19% for the Coil-100 dataset, and 54.31% for the Wang dataset. These results have an average difference of 5.06% with the target so automatic feature weighting works well. This value is obtained at a hidden layer size of 11 and a learning rate of 0.1. In addition, the use of automatic feature weighting gives more accurate results compared to manual feature weighting.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136107221","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}
Nur Khairunnisa Noorhizama, Zubaile Abdullah, Shahreen Kasim, Isredza Rahmi A Hamid, Mohd Anuar Mat Isa
One of the major challenges the university faces is to provide real-time verification of their student's degree certification upon request by other parties. Conventional verification systems are typically costly, time-consuming and bureaucratic against certificate credential misconduct. In addition, the forgery of graduation degree certificates has become more efficient due to easy-to-use scanning, editing, and printing technologies. Therefore, this research proposes verifying Ph.D. certificates using QR codes on the Ethereum blockchain to address certificate verification challenges. Blockchain technology ensures tamper-proof and decentralized management of degree certificates as the certificates stored on the blockchain are replicated across the network. The issuance of certificates requires the use of the issuer's private key, thus preventing forgery. The system was developed using Solidity for the smart contract, PHP, HTML/CSS for the web-based implementation, and MetaMask for blockchain integration. User testing confirmed the successful implementation and functionality of the system. Users can add, update, and delete certificates, generate and scan QR codes, and receive instant verification feedback. The verification system effectively meets all requirements, providing a robust solution for validating Ph.D. certificates. Future research may focus on scalability and adoption, privacy and data protection, user experience, and integration with existing systems. Other researchers can optimize the verification system for widespread adoption and utilization by exploring these areas. This research contributes to securing and efficiently verifying academic certificates using QR codes on the Ethereum blockchain. Ultimately, this work advances the field of certificate verification and promotes trust in academic credentials.
{"title":"Verification of Ph.D. Certificate using QR Code on Blockchain Ethereum","authors":"Nur Khairunnisa Noorhizama, Zubaile Abdullah, Shahreen Kasim, Isredza Rahmi A Hamid, Mohd Anuar Mat Isa","doi":"10.30630/joiv.7.3.1584","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1584","url":null,"abstract":"One of the major challenges the university faces is to provide real-time verification of their student's degree certification upon request by other parties. Conventional verification systems are typically costly, time-consuming and bureaucratic against certificate credential misconduct. In addition, the forgery of graduation degree certificates has become more efficient due to easy-to-use scanning, editing, and printing technologies. Therefore, this research proposes verifying Ph.D. certificates using QR codes on the Ethereum blockchain to address certificate verification challenges. Blockchain technology ensures tamper-proof and decentralized management of degree certificates as the certificates stored on the blockchain are replicated across the network. The issuance of certificates requires the use of the issuer's private key, thus preventing forgery. The system was developed using Solidity for the smart contract, PHP, HTML/CSS for the web-based implementation, and MetaMask for blockchain integration. User testing confirmed the successful implementation and functionality of the system. Users can add, update, and delete certificates, generate and scan QR codes, and receive instant verification feedback. The verification system effectively meets all requirements, providing a robust solution for validating Ph.D. certificates. Future research may focus on scalability and adoption, privacy and data protection, user experience, and integration with existing systems. Other researchers can optimize the verification system for widespread adoption and utilization by exploring these areas. This research contributes to securing and efficiently verifying academic certificates using QR codes on the Ethereum blockchain. Ultimately, this work advances the field of certificate verification and promotes trust in academic credentials.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136107395","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}
Mokhamad Amin Hariyadi, Juniardi Nur Fadila, Hafizzudin Sifaulloh
This research endeavor aims to evaluate the effectiveness of the robot's direction control system by employing PID (Proportional Integral Derivative) output and utilizing wireless communication LoRa E32 433MHz. The experimental robot used in this study was a tank model robot equipped with 4 channels of control. LoRa was implemented in the robot control system, in conjunction with an Android control application, through serial data communication. The LoRa E32 module system was selected based on its established reliability in long-range communication applications. However, encountered challenges included the sluggishness of data transmission when using LoRa for transferring control data and the decreased performance of the robot under Non-Line of Sight conditions. To overcome these challenges, the PID method was employed to generate control data for the robot, thereby minimizing the error associated with controlling its movements. The PID system utilized feedback from a compass sensor (HMC5883L) to evaluate the setpoint data transmitted by the user, employing Kp, Ki, and Kd in calculations to enable smooth movements toward the setpoint. The findings of this study regarding the direct control of the robot using wireless LoRa E32 communication demonstrated an error range of 0.6% to 13.34%. A trial-and-error approach for control variables determined the optimal values for Kp, Ki, and Kd as 10, 0.1, and 1.5, respectively. Future investigations can integrate additional methodologies to precisely and accurately determine the PID constants (Kp, Ki, and Kd) mathematically.
{"title":"433Mhz based Robot using PID (Proportional Integral Derivative) for Precise Facing Direction","authors":"Mokhamad Amin Hariyadi, Juniardi Nur Fadila, Hafizzudin Sifaulloh","doi":"10.30630/joiv.7.3.1841","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1841","url":null,"abstract":"This research endeavor aims to evaluate the effectiveness of the robot's direction control system by employing PID (Proportional Integral Derivative) output and utilizing wireless communication LoRa E32 433MHz. The experimental robot used in this study was a tank model robot equipped with 4 channels of control. LoRa was implemented in the robot control system, in conjunction with an Android control application, through serial data communication. The LoRa E32 module system was selected based on its established reliability in long-range communication applications. However, encountered challenges included the sluggishness of data transmission when using LoRa for transferring control data and the decreased performance of the robot under Non-Line of Sight conditions. To overcome these challenges, the PID method was employed to generate control data for the robot, thereby minimizing the error associated with controlling its movements. The PID system utilized feedback from a compass sensor (HMC5883L) to evaluate the setpoint data transmitted by the user, employing Kp, Ki, and Kd in calculations to enable smooth movements toward the setpoint. The findings of this study regarding the direct control of the robot using wireless LoRa E32 communication demonstrated an error range of 0.6% to 13.34%. A trial-and-error approach for control variables determined the optimal values for Kp, Ki, and Kd as 10, 0.1, and 1.5, respectively. Future investigations can integrate additional methodologies to precisely and accurately determine the PID constants (Kp, Ki, and Kd) mathematically.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106127","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}
Huge datasets are important to build powerful pipelines and ground well to new images. In Computer Vision, the most basic problem is image classification. The classification of images may be a tedious job, especially when there are a lot of amounts. But CNN is known to be data-hungry while gathering. How can we build some models without much data? For example, in the case of Sign Language Recognition (SLR). One type of Sign Language Recognition system is vision-based. In Indonesian Sign Language dataset has a relatively small sample image. This research aims to classify sign language images using Computer Vision for Sign Language Recognition systems. We used a small dataset, Indonesian Sign Language. Our dataset is listed in 26 classes of alphabet, A-Z. It has loaded 12 images for each class. The methodology in this research is few-shot learning. Based on our experiment, the best accuracy for few-shot learning is Mnasnet1_0 (85.75%) convolutional network model for Matching Networks, and loss estimation is about 0,43. And the experiment indicates that the accuracy will be increased by increasing the number of shots. We can inform you that this model's matching network framework is unsuitable for the Inception V3 model because the kernel size cannot be greater than the actual input size. We can choose the best algorithm based on this research for the Indonesian Sign Language application we will develop further.
{"title":"Closer Look at Image Classification for Indonesian Sign Language with Few-Shot Learning Using Matching Network Approach","authors":"Irma Permata Sari","doi":"10.30630/joiv.7.3.1320","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1320","url":null,"abstract":"Huge datasets are important to build powerful pipelines and ground well to new images. In Computer Vision, the most basic problem is image classification. The classification of images may be a tedious job, especially when there are a lot of amounts. But CNN is known to be data-hungry while gathering. How can we build some models without much data? For example, in the case of Sign Language Recognition (SLR). One type of Sign Language Recognition system is vision-based. In Indonesian Sign Language dataset has a relatively small sample image. This research aims to classify sign language images using Computer Vision for Sign Language Recognition systems. We used a small dataset, Indonesian Sign Language. Our dataset is listed in 26 classes of alphabet, A-Z. It has loaded 12 images for each class. The methodology in this research is few-shot learning. Based on our experiment, the best accuracy for few-shot learning is Mnasnet1_0 (85.75%) convolutional network model for Matching Networks, and loss estimation is about 0,43. And the experiment indicates that the accuracy will be increased by increasing the number of shots. We can inform you that this model's matching network framework is unsuitable for the Inception V3 model because the kernel size cannot be greater than the actual input size. We can choose the best algorithm based on this research for the Indonesian Sign Language application we will develop further.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106128","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}
Diyar Jamal Hamad, Khirota Gorgees Yalda, Nicolae Țăpuș
The quality of service is not the same in all parts of the network. Some areas experience a low level and others a higher level of fixed quality services. The shortcomings in legacy networks encouraged researchers to find a new paradigm of the network to obviate legacy networks' deficiencies. The effort to create network services is called Quality of Service (QoS). Software-Defined Networking (SDN) focuses on separating the control layer from the data layer, and their communication is done through a central controller named SDN controller. After separation, the data layer moves the packets through the network according to the commands it receives from the controller. The controller obtains applications (QoS requests), translates them to low-level instructions, and implements them in the data layer. In this paper, we create an infrastructure for Quality of Service (QoS) in tree topology using a meter table per flow in Software Defined Networking Floodlight open-source controller. Meters are introduced into the OpenFlow protocol version 1.3, which calculates the packet rates allocated to them and allows control of those packet rates. Meters are directly connected to flow entry. Any flow entry can determine a meter in its command collection, which calculates and supervises the sum of all flow entries to which it is connected. When we get statistics from the meter table in each switch, we manage the network and affect the routing algorithms.
{"title":"Performance Assessment of QoS metrics in Software Defined Networking using Floodlight Controller","authors":"Diyar Jamal Hamad, Khirota Gorgees Yalda, Nicolae Țăpuș","doi":"10.30630/joiv.7.3.1288","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1288","url":null,"abstract":"The quality of service is not the same in all parts of the network. Some areas experience a low level and others a higher level of fixed quality services. The shortcomings in legacy networks encouraged researchers to find a new paradigm of the network to obviate legacy networks' deficiencies. The effort to create network services is called Quality of Service (QoS). Software-Defined Networking (SDN) focuses on separating the control layer from the data layer, and their communication is done through a central controller named SDN controller. After separation, the data layer moves the packets through the network according to the commands it receives from the controller. The controller obtains applications (QoS requests), translates them to low-level instructions, and implements them in the data layer. In this paper, we create an infrastructure for Quality of Service (QoS) in tree topology using a meter table per flow in Software Defined Networking Floodlight open-source controller. Meters are introduced into the OpenFlow protocol version 1.3, which calculates the packet rates allocated to them and allows control of those packet rates. Meters are directly connected to flow entry. Any flow entry can determine a meter in its command collection, which calculates and supervises the sum of all flow entries to which it is connected. When we get statistics from the meter table in each switch, we manage the network and affect the routing algorithms.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106132","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}
Meri Azmi, Deni Satria, Farhan Rinsky Mulya, Yance Sonatha, Dwi Sudarno Putra
The industrial sector's growth has led to an increase in the number of industrial products available in the market. However, this has made it more challenging for retail merchants to choose which items to sell due to the overwhelming number of options. The seller must carefully consider various factors such as the type, quality, and probability of selling the goods to turn a profit. This research proposes a group decision support system to assist retail sellers in selecting the products to sell. The system is designed to process various information on comparing retail products against specific criteria, enabling sellers to make quick and accurate decisions. To achieve optimal results, this study combines three methods in the decision-making calculation process: Fuzzy Logic, EDAS, and Borda methods. The Fuzzy Logic method is used to assign a value to an unclear criterion, followed by the EDAS method ranking process, and ending with the combination of the decision-making results using the Borda method. The group decision support system is web-based and has been proven to provide effective solutions for retail business actors to increase sales and reduce losses. By using this system, retail sellers can make informed decisions about their products, enabling them to optimize their profits and reduce their risks. In conclusion, the increase in the number of industrial products has created challenges for retail merchants, but this research proposes a solution in the form of a group decision support system. Combining Fuzzy Logic, EDAS, and Borda methods results in an effective decision-making process that allows retail sellers to make informed decisions and achieve their business goals.
{"title":"A Web-based Group Decision Support System for Retail Product Sales a Case Study on Padang, Indonesia","authors":"Meri Azmi, Deni Satria, Farhan Rinsky Mulya, Yance Sonatha, Dwi Sudarno Putra","doi":"10.30630/joiv.7.3.1331","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1331","url":null,"abstract":"The industrial sector's growth has led to an increase in the number of industrial products available in the market. However, this has made it more challenging for retail merchants to choose which items to sell due to the overwhelming number of options. The seller must carefully consider various factors such as the type, quality, and probability of selling the goods to turn a profit. This research proposes a group decision support system to assist retail sellers in selecting the products to sell. The system is designed to process various information on comparing retail products against specific criteria, enabling sellers to make quick and accurate decisions. To achieve optimal results, this study combines three methods in the decision-making calculation process: Fuzzy Logic, EDAS, and Borda methods. The Fuzzy Logic method is used to assign a value to an unclear criterion, followed by the EDAS method ranking process, and ending with the combination of the decision-making results using the Borda method. The group decision support system is web-based and has been proven to provide effective solutions for retail business actors to increase sales and reduce losses. By using this system, retail sellers can make informed decisions about their products, enabling them to optimize their profits and reduce their risks. In conclusion, the increase in the number of industrial products has created challenges for retail merchants, but this research proposes a solution in the form of a group decision support system. Combining Fuzzy Logic, EDAS, and Borda methods results in an effective decision-making process that allows retail sellers to make informed decisions and achieve their business goals.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106268","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}
Unbalanced conditions in the dataset often become a real-world problem, especially in machine learning. Class imbalance in the dataset is a condition where the number of minority classes is much smaller than the majority class, or the number is insufficient. Machine learning models tend to recognize patterns in the majority class more than in the minority class. This problem is one of the most critical challenges in machine learning research, so several methods have been developed to overcome it. However, most of these methods only focus on binary datasets, so few methods still focus on multiclass datasets. Handling unbalanced multiclass is more complex than handling unbalanced binary because it involves more classes than binary class datasets. With these problems, we need an algorithm with features that can support adjustments to the difficulties that arise in multiclass unbalanced datasets. One of the algorithms that have features for adjustment is the ensemble algorithm, namely Xtreme Gradient Boosting. Based on the research, our proposed method with Xtreme Gradient Boosting showed better results than the other classification and ensemble algorithms on eight datasets with five evaluation metrics indicators such as balanced accuracy, the geometric-mean, multiclass area under the curve, true positive rate, and true negative rate. In future research, we suggest combining methods at the data level and Xtreme Gradient Boosting. With the performance increase in Xtreme Gradient Boosting, it can be a solution and reference in the case of handling multiclass imbalanced problems. Besides, we also recommended testing with datasets in the form of categorical and continuous data.
{"title":"Extreme Gradient Boosting Algorithm to Improve Machine Learning Model Performance on Multiclass Imbalanced Dataset","authors":"Yoga Pristyanto, Zulfikar Mukarabiman, Anggit Ferdita Nugraha","doi":"10.30630/joiv.7.3.1102","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1102","url":null,"abstract":"Unbalanced conditions in the dataset often become a real-world problem, especially in machine learning. Class imbalance in the dataset is a condition where the number of minority classes is much smaller than the majority class, or the number is insufficient. Machine learning models tend to recognize patterns in the majority class more than in the minority class. This problem is one of the most critical challenges in machine learning research, so several methods have been developed to overcome it. However, most of these methods only focus on binary datasets, so few methods still focus on multiclass datasets. Handling unbalanced multiclass is more complex than handling unbalanced binary because it involves more classes than binary class datasets. With these problems, we need an algorithm with features that can support adjustments to the difficulties that arise in multiclass unbalanced datasets. One of the algorithms that have features for adjustment is the ensemble algorithm, namely Xtreme Gradient Boosting. Based on the research, our proposed method with Xtreme Gradient Boosting showed better results than the other classification and ensemble algorithms on eight datasets with five evaluation metrics indicators such as balanced accuracy, the geometric-mean, multiclass area under the curve, true positive rate, and true negative rate. In future research, we suggest combining methods at the data level and Xtreme Gradient Boosting. With the performance increase in Xtreme Gradient Boosting, it can be a solution and reference in the case of handling multiclass imbalanced problems. Besides, we also recommended testing with datasets in the form of categorical and continuous data.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106272","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}
There has been an increased reliance on interconnected Cyber-Physical Systems (CPS) applications. This reliance has caused tremendous growth in high assurance challenges. Due to the functional interdependence between the internal systems of CPS applications, the utilities' ability to reliably provide services could be disrupted if security threats are not addressed. To address this challenge, we propose a multi-level, multi-agent detection and response architecture built on the formalisms of Hidden Markov Models (HMM) and Markov Decision Processes (MDP). We have evaluated the performance of the proposed architecture on one of the critical smart grid applications, Advanced Metering Infrastructure (AMI). This paper utilizes a simulation tool called SecAMI for performance evaluation. A Stealthy attack scenario contains multiple distinct multi-stage attacks deployed concurrently in a network to compromise the system and stop several critical services in a CPS. The results show that the proposed architecture effectively detects and responds to stealthy attack scenarios against Cyber-Physical Systems. In particular, the simulation results show that the proposed system can preserve the availability of more than 93% of the AMI network under stealthy attacks. A future study may evaluate the effectiveness of various stealthy attack strategies and detection and response systems. The high availability of any AMI should be protected against new attack techniques. The proposed system will also determine a distributed IDS's efficient placement for intrusion detection sensors and response nodes within an AMI.
{"title":"A Detection and Response Architecture for Stealthy Attacks on Cyber-Physical Systems","authors":"Tawfeeq Shawly","doi":"10.30630/joiv.7.3.1323","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1323","url":null,"abstract":"There has been an increased reliance on interconnected Cyber-Physical Systems (CPS) applications. This reliance has caused tremendous growth in high assurance challenges. Due to the functional interdependence between the internal systems of CPS applications, the utilities' ability to reliably provide services could be disrupted if security threats are not addressed. To address this challenge, we propose a multi-level, multi-agent detection and response architecture built on the formalisms of Hidden Markov Models (HMM) and Markov Decision Processes (MDP). We have evaluated the performance of the proposed architecture on one of the critical smart grid applications, Advanced Metering Infrastructure (AMI). This paper utilizes a simulation tool called SecAMI for performance evaluation. A Stealthy attack scenario contains multiple distinct multi-stage attacks deployed concurrently in a network to compromise the system and stop several critical services in a CPS. The results show that the proposed architecture effectively detects and responds to stealthy attack scenarios against Cyber-Physical Systems. In particular, the simulation results show that the proposed system can preserve the availability of more than 93% of the AMI network under stealthy attacks. A future study may evaluate the effectiveness of various stealthy attack strategies and detection and response systems. The high availability of any AMI should be protected against new attack techniques. The proposed system will also determine a distributed IDS's efficient placement for intrusion detection sensors and response nodes within an AMI.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136107385","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}
Purwadi Purwadi, Nor Azman Abu, Othman Bin Mohd, Bagus Adhi Kusuma
Hyperspectral image technology in land classification is a distinct advantage compared to ordinary RGB and multispectral images. This technology has a wide spectrum of electromagnetic waves, which can be more detailed than other types of imagery. Therefore, with its hyperspectral advantages, the characteristics of an object should have a high probability of being recognized and distinguished. However, because of the large data, it becomes a challenge to lighten the computational burden. Hyperspectral has a huge phenomenon that makes computations heavy compared to other types of images because this image is 3D. The problem faced in hyperspectral image classification is the high computational load, especially if the spatial resolution of the image also has mixed pixel problems. This research uses EO-1 satellite imagery with a spatial resolution of 30 meters and a mixed pixel problem. This study uses a classification method to lighten the computational burden and simultaneously increase the value of classification accuracy. The method used is satellite image pre-processing, including geometric correction and image enhancement using FLAASH while the corrections are geometric correction and atmospheric correction. Then to lighten the computational burden, the steps carried out are using the Slab and PCA method. After obtaining the characteristics, they are entered into a guided learning model using a support vector machine (SVM) for the five-class or multiclass classification. Moreover, the imbalance learning method is proven to produce increased accuracy. The best results were achieved by the ADASYN method with an accuracy of 96.58%, while the computational time became faster with the feature extraction method.
{"title":"Mixed Pixel Classification on Hyperspectral Image Using Imbalanced Learning and Hyperparameter Tuning Methods","authors":"Purwadi Purwadi, Nor Azman Abu, Othman Bin Mohd, Bagus Adhi Kusuma","doi":"10.30630/joiv.7.3.1758","DOIUrl":"https://doi.org/10.30630/joiv.7.3.1758","url":null,"abstract":"Hyperspectral image technology in land classification is a distinct advantage compared to ordinary RGB and multispectral images. This technology has a wide spectrum of electromagnetic waves, which can be more detailed than other types of imagery. Therefore, with its hyperspectral advantages, the characteristics of an object should have a high probability of being recognized and distinguished. However, because of the large data, it becomes a challenge to lighten the computational burden. Hyperspectral has a huge phenomenon that makes computations heavy compared to other types of images because this image is 3D. The problem faced in hyperspectral image classification is the high computational load, especially if the spatial resolution of the image also has mixed pixel problems. This research uses EO-1 satellite imagery with a spatial resolution of 30 meters and a mixed pixel problem. This study uses a classification method to lighten the computational burden and simultaneously increase the value of classification accuracy. The method used is satellite image pre-processing, including geometric correction and image enhancement using FLAASH while the corrections are geometric correction and atmospheric correction. Then to lighten the computational burden, the steps carried out are using the Slab and PCA method. After obtaining the characteristics, they are entered into a guided learning model using a support vector machine (SVM) for the five-class or multiclass classification. Moreover, the imbalance learning method is proven to produce increased accuracy. The best results were achieved by the ADASYN method with an accuracy of 96.58%, while the computational time became faster with the feature extraction method.","PeriodicalId":32468,"journal":{"name":"JOIV International Journal on Informatics Visualization","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136107387","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：