Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Food Fraud Prevention using a Blockchain-Based System: Case Study Slaughterhouse in Sidoarjo
Get PDFData consistency and security are the most important thing to pay attention to in the supply chain of foodstuffs derived from livestock. However, the length of the existing supply chain and the lack of facilities to store and maintain the correctness of livestock data are problems in ensuring the security of the data. The use of blockchain in livestock has existed in Indonesia, but its scope is only to agriculture or only a tiny part of the livestock supply chain. Therefore, this research was conducted to develop the application of a blockchain-based livestock supply chain system in Indonesia. This research begins with conducting a literature study, analyzing the slaughterhouses. Then the development of a blockchain system for the food supply chain was carried out. System validation was carried out through interviews with the head of the slaughterhouses, breeders, and wholesalers. The results state that the system helps ensure the security of food supply chain data from livestock. However, the problem that has not been resolved is the validation process of data on the weight loss of foodstuffs in the supply chain process. This technique is expected to be used for halal certification in the future.
 
Towards Generating Unit Test Codes Using Generative Adversarial Networks
No full textUnit testing is one of the critical software development steps to ensure the software’s quality. Unit testing is often neglected despite its importance since it requires a significant amount of time and effort from the software developers to write them. Existing automated testing generating systems from past research still have shortcomings due to the limitations of the Genetic Algorithm (GA) in generating the appropriate unit test codes. This study explores the feasibility of using Generative Adversarial Networks (GAN) models to generate unit test code with the ability of GAN to cover GA’s drawbacks. We perform experimentations using four state-of-the-art GAN models to generate basic unit test codes and compare the results by analyzing the generated output codes using novel metrics proposed from past studies and performing a qualitative evaluation of the generated outputs. The results show that the generated codes have satisfactory quality scores (BLEU-2 of around 99%) from the models and adequate diversity scores (NLL-Div and NLL-Gen) in most models. Our study shows positive indications and potential in the use of GAN for automatic unit test code generation and suggests recommendations for future studies in GAN-based unit test code generation system
Implementation of CNN-MLP and CNN-LSTM for MitM Attack Detection System
Get PDFMan in the Middle (MitM) is one of the attack techniques conducted for eavesdropping on data transitions or conversations between users in some systems secretly. It has a sizeable impact because it could make the attackers will do another attack, such as website or system deface or phishing. Deep Learning could be able to predict various data well. Hence, in this study, we would like to present the approach to detect MitM attacks and process its data, by implementing hybrid deep learning methods. We used 2 (two) combinations of the Deep Learning methods, which are CNN-MLP and CNN-LSTM. We also used various Feature Scaling methods before building the model and will determine the better hybrid deep learning methods for detecting MitM attack, as well as the feature selection methods that could generate the highest accuracy. Kitsune Network Attack Dataset (ARP MitM Ettercap) is the dataset used in this study. The results prove that CNN-MLP has better results than CNN-LSTM on average, which has the accuracy rate respectively at 99.74%, 99.67%, and 99.57%, and using Standard Scaler has the highest accuracy (99.74%) among other scenarios.
Man in the Middle (MitM) is one of the attack techniques conducted for eavesdropping on data transitions or conversations between users in some systems secretly. It has a sizeable impact because it could make the attackers will do another attack, such as website or system deface or phishing. Deep Learning could be able to predict various data well. Hence, in this study, we would like to present the approach to detect MitM attacks and process its data, by implementing hybrid deep learning methods. We used 2 (two) combinations of the Deep Learning methods, which are CNN-MLP and CNN-LSTM. We also used various Feature Scaling methods before building the model and will determine the better hybrid deep learning methods for detecting MitM attack, as well as the feature selection methods that could generate the highest accuracy. Kitsune Network Attack Dataset (ARP MitM Ettercap) is the dataset used in this study. The results prove that CNN-MLP has better results than CNN-LSTM on average, which has the accuracy rate respectively at 99.74%, 99.67%, and 99.57%, and using Standard Scaler has the highest accuracy (99.74%) among other scenarios
Sybil Attack Prediction on Vehicle Network Using Deep Learning
Get PDFVehicular Ad Hoc Network (VANET) or vehicle network is a technology developed for autonomous vehicles in Intelligent Transportation Systems (ITS). The communication system of VANET is using a wireless network that is potentially being attacked. The Sybil attack is one of the attacks that occur by broadcasting spurious information to the nodes in the network and could cause a crippled network. The Sybil strikes the network by camouflaging themselves as a node and providing false information to nearby nodes. This study is conducted to predict the Sybil attack by analyzing the attack pattern using a deep learning algorithm. The variables exerted in this research are time, location, and traffic density. By implementing a deep learning algorithm enacting the Sybil attack pattern and combining several variables, such as time, position, and traffic density, it reaches 94% of detected Sybil attacks.
Vehicular Ad Hoc Network (VANET) or vehicle network is a technology developed for autonomous vehicles in Intelligent Transportation Systems (ITS). The communication system of VANET is using a wireless network that is potentially being attacked. The Sybil attack is one of the attacks that occur by broadcasting spurious information to the nodes in the network and could cause a crippled network. The Sybil strikes the network by camouflaging themselves as a node and providing false information to nearby nodes. This study is conducted to predict the Sybil attack by analyzing the attack pattern using a deep learning algorithm. The variables exerted in this research are time, location, and traffic density. By implementing a deep learning algorithm enacting the Sybil attack pattern and combining several variables, such as time, position, and traffic density, it reaches 94% of detected Sybil attacks
Forecasting Pneumonia Toddler Mortality Using Comparative Model ARIMA and Multilayer Perceptron
Get PDFPneumonia is an inflammatory lung disease that causes the second largest number of deaths in Indonesia after Dengue Hemorrhagic Fever (DHF). In 2021, there was an increase in cases of 7.8% compared to the previous year, and was exacerbated by the Covid-19 pandemic. Predictive methods were needed to predict and compare the ARIMA and MLP methods, where the results of the best methods were selected for long-term forecasting. The research data used was from January 2014 – December 2021, with a total of 96 data. In choosing the best method, the basic error calculations used were Mean Absolute Deviation, Mean Squared Error, and Mean Absolute Percentage Error. This study aims to build a predictive model for the next period of pneumonia under-five mortality. These results can be used for government policy-making related to mortality prevention for the next period. The results showed that the MLP method was superior to ARIMA. Testing 28 mortality rate data using the final test result showed that the best method was MLP, with a hidden layer value of 2.2, a learning rate of 0.3, and an error percentage of 1.27%. The prediction results of the overall mortality rate of pneumonia under five in 2022 was predicted to be 136 people.
Pneumonia is an inflammatory lung disease that causes the second largest number of deaths in Indonesia after Dengue Hemorrhagic Fever (DHF). In 2021, there was an increase in cases of 7.8% compared to the previous year, and was exacerbated by the Covid-19 pandemic. Predictive methods were needed to predict and compare the ARIMA and MLP methods, where the results of the best methods were selected for long-term forecasting. The research data used was from January 2014 – December 2021, with a total of 96 data. In choosing the best method, the basic error calculations used were Mean Absolute Deviation, Mean Squared Error, and Mean Absolute Percentage Error. This study aims to build a predictive model for the next period of pneumonia under-five mortality. These results can be used for government policy-making related to mortality prevention for the next period. The results showed that the MLP method was superior to ARIMA. Testing 28 mortality rate data using the final test result showed that the best method was MLP, with a hidden layer value of 2.2, a learning rate of 0.3, and an error percentage of 1.27%. The prediction results of the overall mortality rate of pneumonia under five in 2022 was predicted to be 136 people
Time Series Temperature Forecasting by using ConvLSTM Approach, Case Study in Jakarta
Get PDFClimate change has occurred in several countries, especially in tropical countries such as Indonesia. It causes extreme temperature changes in several Indonesian areas, especially Jakarta, one of the world's most populated cities. The population of Jakarta causes the activities carried out by residents to be disturbed by extreme temperature changes. In addition, drastic temperature changes also affect the energy consumption used by residents. Therefore, it is necessary to predict temperature to determine future temperature conditions so that residents can plan their activities. Temperature forecast can be done in several ways, one of which uses a machine learning approach. This research uses a deep learning model called the Convolutional Long Short-Term Memory (ConvLSTM). Moreover, we also compare the model with Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM). We use temperature data taken from the ERA-5 period years 2018 to 2020 located in Kemayoran, Jakarta, Indonesia. This research aims to investigate the accuracy of short-term temperature forecasting by using these three models. The model is built to predict short-term temperatures for 1, 3, and 7 days ahead. The performance of the three methods is measured by calculating the Root Mean Square Error (RMSE), Mean Square Error (MAE), and Coefficient Correlation (CC). The result shows that the LSTM performs better than the other methods to forecast 1, 3, and 7 days, i.e., with the lowest RMSE, MAE, and higher CC.
Climate change has occurred in several countries, especially in tropical countries such as Indonesia. It causes extreme temperature changes in several Indonesian areas, especially Jakarta, one of the world's most populated cities. The population of Jakarta causes the activities carried out by residents to be disturbed by extreme temperature changes. In addition, drastic temperature changes also affect the energy consumption used by residents. Therefore, it is necessary to predict temperature to determine future temperature conditions so that residents can plan their activities. Temperature forecast can be done in several ways, one of which uses a machine learning approach. This research uses a deep learning model called the Convolutional Long Short-Term Memory (ConvLSTM). Moreover, we also compare the model with Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM). We use temperature data taken from the ERA-5 period years 2018 to 2020 located in Kemayoran, Jakarta, Indonesia. This research aims to investigate the accuracy of short-term temperature forecasting by using these three models. The model is built to predict short-term temperatures for 1, 3, and 7 days ahead. The performance of the three methods is measured by calculating the Root Mean Square Error (RMSE), Mean Square Error (MAE), and Coefficient Correlation (CC). The result shows that the LSTM performs better than the other methods to forecast 1, 3, and 7 days, i.e., with the lowest RMSE, MAE, and higher CC
QSAR Study of Larvicidal Phytocompounds as Anti-Aedes Aegypti by using GA-SVM Method
Get PDFAedes aegypti is one of the most dangerous mosquitoes that can cause several deadly diseases, such as dengue fever, Chikungunya, Zika, and jaundice with high mortality rate. For now, no specific drug has been found that can cure the disease caused by Aedes Aegypti. One possible solution for handling this problem is to inhibit the growth and development of Aedes aegypti larvae. This study aims to implement Genetic Algorithm-Support Vector Machine to develop Quantitative Structure-Activity Relationship model for identification larvicidal phytocompounds as anti-aedes-aegypti. Hyperparameter tuning was performed to improve the performance of the models. Based on the result, we found that the best model was developed by the RBF kernel with the value of and score are 0.64 and 0.64, respectively.Aedes aegypti is one of the most dangerous mosquitoes that can cause several deadly diseases, such as dengue fever, Chikungunya, Zika, and jaundice with high mortality rate. For now, no specific drug has been found that can cure the disease caused by Aedes Aegypti. One possible solution for handling this problem is to inhibit the growth and development of Aedes aegypti larvae. This study aims to implement Genetic Algorithm-Support Vector Machine to develop Quantitative Structure-Activity Relationship model for identification larvicidal phytocompounds as anti-aedes-aegypti. Hyperparameter tuning was performed to improve the performance of the models. Based on the result, we found that the best model was developed by the RBF kernel with the value of and score are 0.64 and 0.64, respectively.
Aedes aegypti is one of the most dangerous mosquitoes that can cause several deadly diseases, such as dengue fever, Chikungunya, Zika, and jaundice with high mortality rate. For now, no specific drug has been found that can cure the disease caused by Aedes Aegypti. One possible solution for handling this problem is to inhibit the growth and development of Aedes aegypti larvae. This study aims to implement Genetic Algorithm-Support Vector Machine to develop Quantitative Structure-Activity Relationship model for identification larvicidal phytocompounds as anti-aedes-aegypti. Hyperparameter tuning was performed to improve the performance of the models. Based on the result, we found that the best model was developed by the RBF kernel with the value of and score are 0.64 and 0.64, respectively
Vehicle Detection Monitoring System using Internet of Things
Get PDFThe overcapacity of vehicle numbers is one of the significant causes of the traffic congestion problem on Indonesia roadways. The government applies a One-way system (SSA) as one proposed solution to unravel the congestion. However, several congestion points are still found during the SSA implementation. Thus, this research offers an alternative method to detect congestion using IoT technology. The system automatically enumerates the number, classifies the type, and computes the speed averages of vehicles to identify the severity of congestion based on the Indonesian Highway Capacity Manual (IHCM) published by the Ministry of Public Works 2014. We utilize ultrasonic sensors to detect the vehicles and send the data to the server in real time. The research successfully develops an IoT system for traffic congestion detection. Communication between nodes and API can be done well. Data exchange involving encryption and decryption with AES-256 is successfully done. The website application developed in this research successfully show the severity level of the congestion and their vehicle numbers. The average accuracy of the system is 78,97%. The system detected more vehicles than actual numbers due to the misreading value of the sensors.The overcapacity of vehicle numbers is one of the significant causes of the traffic congestion problem on Indonesia roadway. The government applies a One-way system (SSA) as one proposed solution to unravel the congestion. However, several congestion points are still found during the SSA implementation. Thus, this research offers an alternative method to detect congestion using IoT technology. The system automatically enumerates the number, classifies the type, and computes the speed averages of vehicles to identify the severity of congestion based on the Indonesian Highway Capacity Manual (IHCM) published by the Ministry of Public Works 2014. We utilize ultrasonic sensors to detect the vehicles and send the data to the server in real-time. The research successfully develops an IoT system for traffic congestion detection. Communication between nodes and API can be done well. Data exchange involving encryption and decryption with AES-256 is successfully done. Website application developed in this research is successfully show the severity level of the congestion and their vehicle numbers. The average accuracy of the system is 78,97%. The system detected more vehicles than actual numbers due to the misreading value of the sensors
Naïve Bayes-Support Vector Machine Combined BERT to Classified Big Five Personality on Twitter
Get PDFTwitter is one of the most popular social media used to interact online. Through Twitter, a person's personality can be determined based on that person's thoughts, feelings, and behavior patterns. A person has five main personalities likes Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. This study will make five personality predictions using the Naïve Bayes method – Support Vector Machine, Synthetic Minority Over Sampling Technique (SMOTE), Linguistic Inquiry Word Count (LIWC), and Bidirectional Encoder from Transformers Representations (BERT). A questionnaire was distributed to people who used Twitter to collect and become a dataset in this research. The dataset obtained will be processed into SMOTE to balance the data. Linguistic Inquiry Word Count is used as a linguistic feature and BERT will be used as a semantic approach. The Naïve Bayes method is used to perform the weighting and the Support Vector Machine is used to classify Big Five Personalities. To help improve accuracy, the Optuna Hyperparameter Tuning method will be added to the Naïve Bayes Support Vector Machine model. This study has an accuracy of 87.82% from the results of combining SMOTE, BERT, LIWC, and Tuning where the accuracy increases from the baseline.Twitter is one of the most popular social media used to interact online. Through Twitter, a person's personality can be determined based on that person's thoughts, feelings, and behavior patterns. A person has five main personalities likes Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. This study will make five personality predictions using the Naïve Bayes method – Support Vector Machine, Synthetic Minority Over Sampling Technique (SMOTE), Linguistic Inquiry Word Count (LIWC), and Bidirectional Encoder from Transformers Representations (BERT). A questionnaire was distributed to people who used Twitter to collect and become a dataset in this research. The dataset obtained will be processed into SMOTE to balance the data. Linguistic Inquiry Word Count is used as a linguistic feature and BERT will be used as a semantic approach. The Naïve Bayes method is used to perform the weighting and the Support Vector Machine is used to classify Big Five Personalities. To help improve accuracy, the Optuna Hyperparameter Tuning method will be added to the Naïve Bayes Support Vector Machine model. This study has an accuracy of 87.82% from the results of combining SMOTE, BERT, LIWC, and Tuning where the accuracy increases from the baseline
Measuring the effect of Users' Privacy Concerns on the Use of Jakarta Smart City Mobile Application (JAKI)
Get PDFJakarta Kini (JAKI) is a super-app developed by Jakarta Smart City that offers a one-stop service to help citizens connect and communicate with the Government. It is undeniable that the use of mobile applications can indeed facilitate people's activities, but on the other hand, it also poses risks and raises concerns in terms of privacy. The purpose of this study is to assess the impact of users' privacy concerns on their tendency to use the JAKI mobile application. To measure the privacy concern, we conduct an online survey of the users of JAKI. The hypothesis and research model were formulated to assess the users' privacy concerns based on the Mobile Users' Information Privacy Concerns (MUIPC) theory, with additional factors, namely prior privacy experience and awareness, as the antecedents. As a result, we found that MUIPC had a significant effect on negatively influencing the intention to use the JAKI application. Our study contributes as a starting point in exploring privacy research in the context of a smart city in Indonesia. Additionally, this study proved that the IPC scales that were originally designed for English-based countries could also be adapted to Bahasa Indonesia and utilized in the Indonesian context.
Jakarta Kini (JAKI) is a super-app developed by Jakarta Smart City that offers a one-stop service to help citizens connect and communicate with the Government. It is undeniable that the use of mobile applications can indeed facilitate people's activities, but on the other hand, it also poses risks and raises concerns in terms of privacy. The purpose of this study is to assess the impact of users' privacy concerns on their tendency to use the JAKI mobile application. To measure the privacy concern, we conduct an online survey of the users of JAKI. The hypothesis and research model were formulated to assess the users' privacy concerns based on the Mobile Users' Information Privacy Concerns (MUIPC) theory, with additional factors, namely prior privacy experience and awareness, as the antecedents. As a result, we found that MUIPC had a significant effect on negatively influencing the intention to use the JAKI application. Our study contributes as a starting point in exploring privacy research in the context of a smart city in Indonesia. Additionally, this study proved that the IPC scales that were originally designed for English-based countries could also be adapted to Bahasa Indonesia and utilized in the Indonesian context