Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Covid-19 Detection Using Convolutional Neural Networks (CNN) Classification Algorithm
No full textCorona Virus, also known as COVID-19, is one of the new viruses in 2019. Viruses caused by an animal or human diseases are called coronaviruses. Coronavirus will direct respiration in humans. Humans who are exposed to the coronavirus will experience a respiratory infection. The research that will be made helps classify X-rays of the lungs of patients affected by the coronavirus. In this study, the classification of coronaviruses focuses on three classes, namely Covid, Normal, and Viral Pneumonia. This study uses a lung X-ray image dataset. This study has four folders, namely Scenario 1, Scenario 2, Scenario 3, and Scenario 4. This study will use the Convolutional Neural Network (CNN) method by using an architectural model including Convolutional 2D, activation layers, max-pooling layer, dropout layer, flatten, and dense layer. After building the model, the results of accuracy, precision, recall, and f1-score will be obtained in each scenario. The result of the accuracy of Scenario 1 is 97.87%. In Scenario 2, the accuracy is 94.84%, Scenario 3 is 91.66%, and Scenario 4 is 91.41%.
 
Live Forensic to Identify the Digital Evidence on the Desktop-based WhatsApp
No full textThe live forensics method was used to acquire lawful digital evidence data from device memory in the WhatsApp application, particularly for desktop-based WhatsApp. There has been little research on live forensics on desktop-based WhatsApp applications. These studies involve mimicking crime cases in cyberspace using the Instant Messenger application. Much of the acquisition process is completed only once, even though many possible conditions may arise during the purchase process. Investigators or experts can employ digital evidence data discovery to identify crimes that have occurred. The stages of research in detecting digital evidence are data collecting, the examination process, and the acquisition of analysis and reporting outcomes. During the data-gathering phase, a case simulation dataset was obtained. The examination process stage results in the integrity of the duplicated data; data reduction is performed on data related to fundamental operating system components, influential application features, and incomplete data. According to the investigation findings, there are difficulties in looking for digital evidence, and the features of each digital evidence vary. The simulation file contained many reports on the finds of digital evidence. As a data acquisition method, the characteristics of live forensics are limited to the data retrieval process in RAM. Based on these findings, it is possible to conclude that the data collection and examination processing were completed effectively. The analysis results were acquired, and the report was presented with the indicated digital evidence. Further study can be paired with chip-off procedures on RAM devices for data recovery
Classification of Rupiah to Help Blind with The Convolutional Neural Network Method
Get PDFCurrency is an item humans require as a medium of exchange in transactions, including those with vision impairments. It can be challenging for certain blind people to identify currencies. This research aimed to help blind people identify nominal currency when in the transaction. Deep Learning with the CNN algorithm and preprocessing with a sequential model were used in this research. This algorithm is modeled as neurons in the human brain that communicate and learn patterns. Data collecting, preprocessing, testing, and evaluation are this research stage. Six hundred eighty-one datasets are used, consisting of IDR 50.000, IDR 75.000, and IDR 100.000. Model testing was carried out with different iterations of 5, 10, 15, and 20 epochs. Different epoch values will affect the time it takes the model to learn, but the length of the learning process will result in more accurate models. The highest result obtained from all epoch tests is 100%. The class prediction results for the 69 test data show that they can be predicted based on the actual class, indicating that the model is adequate. The results of this classification might be used to construct a smartphone app that would assist visually challenged people in recognizing the nominals.
 
A Security Framework for Secure Host-to-Host Environments
Get PDFData security is an infrastructure designed to protect and secure data from unauthorized access, data manipulation, malfunction, destruction, and inappropriate data disclosure. Currently, organizations widely use data transfer to validate and verify data using different media particularly in host-to-host connections. This research focuses on data exchanged (end-to-end communication) using Multi Protocol Label Switching (MPLS), metro ethernet, and Software Defined Wide Area Network (SD-WAN) network architecture with third parties. This research aims to develop a design and analysis framework for verifying data transferred from one host to another in ABC organization by applicable security standards that are appropriate and follow its needs to help the organization. Furthermore, the analysis result is used as materials for drafting a cybersecurity framework through the three standards ISO/EIC 27001:2013, NIST SP800-161, and ITU-T X.805. The methodology used in this study is the comparative analysis of three frameworks, requirement analysis, and content analysis to develop a framework. The framework proposed of eight security dimensions, five threats, and providing mitigation is expected to enhance the security system of data exchange on host-to-host connections in ABC organization.
Data security is an infrastructure designed to protect and secure data from unauthorized access, data manipulation, malfunction, destruction, and inappropriate data disclosure. Currently, organizations widely use data transfer to validate and verify data using different media particularly in host-to-host connections. This research focuses on data exchanged (end-to-end communication) using Multi Protocol Label Switching (MPLS), metro ethernet, and Software Defined Wide Area Network (SD-WAN) network architecture with third parties. This research aims to develop a design and analysis framework for verifying data transferred from one host to another in ABC organization by applicable security standards that are appropriate and follow its needs to help the organization. Furthermore, the analysis result is used as materials for drafting a cybersecurity framework through the three standards ISO/EIC 27001:2013, NIST SP800-161, and ITU-T X.805. The methodology used in this study is the comparative analysis of three frameworks, requirement analysis, and content analysis to develop a framework. The framework proposed of eight security dimensions, five threats, and providing mitigation is expected to enhance the security system of data exchange on host-to-host connections in ABC organization
Memory-based Collaborative Filtering on Twitter Using Support Vector Machine Classification
No full textNowadays, watching films at home is one of people's entertainment. Netflix is a service provider for watching films and provides many types of film genres. However, of the many films available, it makes users confused to choose which film to watch first. The solution to the problem is a system that provides recommendations for the best films to watch based on user ratings. Twitter is still people's favorite social media to express their feelings, thoughts, and criticisms. In this system, tweets serve as input data that will be processed into data with rating values. This research implemented a recommendation system based on user ratings from tweets using collaborative filtering combined with Support Vector Machine (SVM) classification and implemented it on user-based and item-based. The test results in this study show that Collaborative Filtering gets the best RMSE value results on item-based 0.5911 and 0.8162 on user-based. The Support Vector Machine (SVM) classification algorithm using hyperparameter tuning produces item-based values with a precision of 85.03% and recall of 90.71%, while user-based values with a precision of 87.75% and recall of 88.95%.Nowadays, watching films at home is one of people's entertainment. Netflix is a service provider for watching films and provides many types of film genres. However, of the many films available, it makes users confused to choose which film to watch first. The solution to the problem is a system that provides recommendations for the best films to watch based on user ratings. Twitter is still people's favorite social media to express their feelings, thoughts, and criticisms. In this system, tweets serve as input data that will be processed into data with rating values. This research implemented a recommendation system based on user ratings from tweets using collaborative filtering combined with Support Vector Machine (SVM) classification and implemented it on user-based and item-based. The test results in this study show that Collaborative Filtering gets the best RMSE value results on item-based 0.5911 and 0.8162 on user-based. The Support Vector Machine (SVM) classification algorithm using hyperparameter tuning produces item-based values with a precision of 85.03% and recall of 90.71%, while user-based values with a precision of 87.75% and recall of 88.95%
Hierarchical Clustering and Deep Learning for Short-Term Load Forecasting with Influenced Factors
Get PDFStable and reliable electricity is one of the essential things that must be maintained by the transmission system operator (TSO). That can be achieved when the TSO is able to set the balance between demand and production. To maintain the balance between production and demand, TSO should estimate how much demand must be served. In order to do that, the next day short-term load forecasting is an essential step that TSO should be done. Generally, load forecasting can be done through conventional techniques such as least square, time series, etc. However, this method has been sought over time as the electricity demand is increasing significantly over the years. Hence, this paper proposed another approach for short-term load forecasting using Deep Neural Networks, widely known as Long Short-Term Memory (LSTM). In addition, this paper clusters historical electrical loads to obtain similar patterns into several clusters before forecasting. We also explored other influence factors in the observed days, such as weather conditions and the human activity cycle represented by holidays, in a neural network-based classification model to predict the targeted clusters of electrical loads. East Java sub-system is used as the test system to investigate the efficacy of the proposed load forecasting method. From the simulation results, it is found that the proposed method could provide a better forecast on all indicators compared to the conventional method, as indicated by MaxAPE and MAPE are around 4,91% and 2,02%, while the RMSE is 112,08 MW.
Stable and reliable electricity is one of the essential things that must be maintained by the transmission system operator (TSO). That can be achieved when the TSO is able to set the balance between demand and production. To maintain the balance between production and demand, TSO should estimate how much demand must be served. In order to do that, the next day short-term load forecasting is an essential step that TSO should be done. Generally, load forecasting can be done through conventional techniques such as least square, time series, etc. However, this method has been sought over time as the electricity demand is increasing significantly over the years. Hence, this paper proposed another approach for short-term load forecasting using Deep Neural Networks, widely known as Long Short-Term Memory (LSTM). In addition, this paper clusters historical electrical loads to obtain similar patterns into several clusters before forecasting. We also explored other influence factors in the observed days, such as weather conditions and the human activity cycle represented by holidays, in a neural network-based classification model to predict the targeted clusters of electrical loads. East Java sub-system is used as the test system to investigate the efficacy of the proposed load forecasting method. From the simulation results, it is found that the proposed method could provide a better forecast on all indicators compared to the conventional method, as indicated by MaxAPE and MAPE are around 4,91% and 2,02%, while the RMSE is 112,08 MW
The Application of The Manhattan Method to Human Face Recognition
Get PDFIn face recognition, the input image used will be converted into a simple image, which will then be analyzed. The analysis was carried out by calculating the distance of data similarity. In the process of measuring data similarity distances, they often experience problems implementing complex algorithm formulas. This research will solve this problem by implementing the Manhattan method as a method of measuring data similarity distances. In this study, it is hoped that the Manhattan method can be used properly in the process of matching test images and training images by calculating the proximity distance between the two variables. The distance sought is the shortest distance; the smaller the distance obtained, the higher the level of data compatibility. The image used in this study was converted into grayscale to facilitate the facial recognition process by thresholding, namely the process of converting a grayscale image into a binary image. The binary image of the test data is compared with the binary image of the training data. The image used in this study is in the Joint Photographic Experts Group (JPEG) format. Testing was carried out with 20 respondents, with each having two training images and two test images. The research was conducted by conducting experiments as many as 20 times. Facial recognition research using the Manhattan method obtains an accuracy of 70%. The image lighting used as the dataset influenced the accuracy results obtained in this study. Based on the results of this study, it can be concluded that the Manhattan method is not good for use in facial recognition research with poor lighting.In face recognition, the input image used will be converted into a simple image, which will then be analyzed. The analysis was carried out by calculating the distance of data similarity. In the process of measuring data similarity distances, they often experience problems implementing complex algorithm formulas. This research will solve this problem by implementing the Manhattan method as a method of measuring data similarity distances. In this study, it is hoped that the Manhattan method can be used properly in the process of matching test images and training images by calculating the proximity distance between the two variables. The distance sought is the shortest distance; the smaller the distance obtained, the higher the level of data compatibility. The image used in this study was converted into grayscale to facilitate the facial recognition process by thresholding, namely the process of converting a grayscale image into a binary image. The binary image of the test data is compared with the binary image of the training data. The image used in this study is in the Joint Photographic Experts Group (JPEG) format. Testing was carried out with 20 respondents, with each having two training images and two test images. The research was conducted by conducting experiments as many as 20 times. Facial recognition research using the Manhattan method obtains an accuracy of 70%. The image lighting used as the dataset influenced the accuracy results obtained in this study. Based on the results of this study, it can be concluded that the Manhattan method is not good for use in facial recognition research with poor lighting
Disease Detection in Banana Leaf Plants using DenseNet and Inception Method
Get PDFDiseases that attack banana plants can affect the growth and productivity of the fruit produced. The disease can be identified by looking at changes in the pattern and color of the leaves. Infected leaves will experience an increased transpiration process and the photosynthesis process is almost non-existent. Furthermore, disease on banana leaves can cause yield losses of up to 50%. Therefore, early detection is needed so that diseases on banana leaves can be overcome as soon as possible by using deep learning. This study aims to compare the performance of DenseNet and Inception methods in detecting disease on banana leaves. DenseNet is a transfer learning architecture model with fewer parameters and computations to achieve good performance. Inception, on the other hand, is a transfer learning architectural model that applies cross-channel correlation, executes at lower resolution inputs, and avoids spatial dimensions. In conducting the test, this study uses several data handling schemes to test the two methods, namely without data handling, under-sampling, and oversampling. Furthermore, the data is separated into training data and test data with a ratio of 80:20. The result is that the model using the DenseNet method with an oversampling scheme is superior to other models with a percentage value of 84.73% accuracy, 84.80% precision, 84.73% recall, and 84.62% f1 score. In addition, the machine learning model using the DenseNet method in all schemes is also superior to the machine learning model using the Inception method.Diseases that attack banana plants can affect the growth and productivity of the fruit produced. The disease can be identified by looking at changes in the pattern and color of the leaves. Infected leaves will experience an increased transpiration process and the photosynthesis process is almost non-existent. Furthermore, disease on banana leaves can cause yield losses of up to 50%. Therefore, early detection is needed so that diseases on banana leaves can be overcome as soon as possible by using deep learning. This study aims to compare the performance of DenseNet and Inception methods in detecting disease on banana leaves. DenseNet is a transfer learning architecture model with fewer parameters and computations to achieve good performance. Inception, on the other hand, is a transfer learning architectural model that applies cross-channel correlation, executes at lower resolution inputs, and avoids spatial dimensions. In conducting the test, this study uses several data handling schemes to test the two methods, namely without data handling, under-sampling, and oversampling. Furthermore, the data is separated into training data and test data with a ratio of 80:20. The result is that the model using the DenseNet method with an oversampling scheme is superior to other models with a percentage value of 84.73% accuracy, 84.80% precision, 84.73% recall, and 84.62% f1 score. In addition, the machine learning model using the DenseNet method in all schemes is also superior to the machine learning model using the Inception method
Increased Accuracy on Image Classification of Game Rock Paper Scissors using CNN
No full textRock Paper Scissors is one of the most popular games in the world, because of their easy and simple way to play among young and elderly people. The point of this game is to do the draw or just to find out who loses or wins. The pandemic conditions made people unable to meet face-to-face and could only play this game virtually. To carry out this activity in a virtual way, this research facilitates a model in the form of image classification to distinguish the hand gestures s in the form of rock, paper, and scissors. This classification process utilizes the Convolutional Neural Network (CNN) method. This method is one type of artificial neural network in terms of image classification. CNN uses three stages, namely convolutional layer, pooling layer, and fully connected layer. The implementation of this method for hand gesture classification in the form of rock, scissors, and paper images in this study shows an increased average accuracy towards the previous study from 97.66% to 99%.Rock Paper Scissors is one of the most popular games in the world, because of their easy and simple way to play among young and elderly people. The point of this game is to do the draw or just to find out who loses or wins. The pandemic conditions made people unable to meet face-to-face and could only play this game virtually. To carry out this activity in a virtual way, this research facilitates a model in the form of image classification to distinguish the hand gestures s in the form of rock, paper, and scissors. This classification process utilizes the Convolutional Neural Network (CNN) method. This method is one type of artificial neural network in terms of image classification. CNN uses three stages, namely convolutional layer, pooling layer, and fully connected layer. The implementation of this method for hand gesture classification in the form of rock, scissors, and paper images in this study shows an increased average accuracy towards the previous study from 97.66% to 99%
Mask Detection Using Convolutional Neural Network Algorithm
Get PDFThe World Health Organizations and the Ministry of Health of the Republic of Indonesia have required the use of masks to suppress the spread of COVID-19. WHO provides guidance on how to use a good mask to cover the mouth and nose. This study aims to detect the correct use of masks using the Convolutional Neural Network. CNN is a popular Deep Learning algorithm for image data classification problems. The Mask Usage Detector is built with the help of a pre-trained MobileNetV2 model with an architecture that supports media that has minimum computations. This study will also compare the performance of three optimization methods from CNN, namely Adam, SGD, and RMSprop in detecting the use of masks. Performance will be seen from the test results by analyzing the values of accuracy, precision, and recall. The dataset used is in the form of image data of 2,029 images for 2 categories, namely "masked" and "unmasked". A total of 1,623 images were used as training data and 406 images for test data. Based on the testing process, the accuracy of each optimization is 93.84% with Adam optimization, 84.48% with SGD optimization, and 93.10% with RMSprop optimization. With the proposed model, this study obtains the performance results of the three CNN optimizations, and it is concluded that adam's optimization gives better performance results than the other two optimizations.
The World Health Organizations and the Ministry of Health of the Republic of Indonesia have required the use of masks to suppress the spread of COVID-19. WHO provides guidance on how to use a good mask to cover the mouth and nose. This study aims to detect the correct use of masks using the Convolutional Neural Network. CNN is a popular Deep Learning algorithm for image data classification problems. The Mask Usage Detector is built with the help of a pre-trained MobileNetV2 model with an architecture that supports media that has minimum computations. This study will also compare the performance of three optimization methods from CNN, namely Adam, SGD, and RMSprop in detecting the use of masks. Performance will be seen from the test results by analyzing the values of accuracy, precision, and recall. The dataset used is in the form of image data of 2,029 images for 2 categories, namely "masked" and "unmasked". A total of 1,623 images were used as training data and 406 images for test data. Based on the testing process, the accuracy of each optimization is 93.84% with Adam optimization, 84.48% with SGD optimization, and 93.10% with RMSprop optimization. With the proposed model, this study obtains the performance results of the three CNN optimizations, and it is concluded that adam's optimization gives better performance results than the other two optimizations