Bulletin of Computer Science and Electrical Engineering

The CNN model developed in this study demonstrated remarkable performance, achieving an outstanding validation accuracy of 99.96%. Through experimentation, it was found that employing the RMSprop optimizer with a learning rate of 0.001 yielded superior results compared to the Adam optimizer utilized in previous iterations. Additionally, increasing the number of epochs from 10 to 20 resulted in a significant enhancement in accuracy, highlighting the importance of iterative training for model refinement. Moreover, the implementation of Early Stopping proved to be a valuable technique, effectively conserving training time by halting the training process once optimal accuracy levels were reached. These findings underscore the efficacy of various optimization strategies in bolstering the performance of CNN models for rose leaf disease detection. The achieved accuracy rates signify a substantial advancement in disease detection technology, holding promise for enhancing agricultural productivity and ensuring plant quality. This research contributes valuable insights into the optimization of CNN parameters, paving the way for further advancements in automated disease detection systems in the field of agriculture.

Diseases in plants are often detrimental to agriculture, can be seen manually and require a very long time, which can lead to possible errors in disease detection. Detecting diseases in plants early can overcome these problems and reduce the risk of reduced crop production. The aim of this research is to make a comparison of quickly and accurately detecting tomato leaf diseases compared to previous researchers who used Deep Learning applications. Which can be applied effectively for image classification using the VGG19 method. The implementation of this model uses a dataset containing 2,694 images, including 3 different types of diseases. That the conclusion of this research is the fastest and most accurate way to detect tomato leaf diseases. To prove this research, results and necessary data will be presented in this paper. The accuracy obtained on the VGG-19 architecture was 91.85% with the best increase in accuracy compared to the previous journal which only produced 87% accuracy.

Adau Kapuas is a company operating in the transportation services sector. In processing income and costs, Adau Kapuas Limited liability companies still use bookkeeping as a data collection medium, such as recording payment and expenses, which are processed starting from recording ticket sales and goods delivery transactions, which process passenger data and goods delivery data. The income obtained from tickets and delivery of goods and the total costs are then entered back into the computer. This proves the difficulty faced by Adau Kapuas, namely having to do work twice daily. This research discusses the application of income and cost processing at Adau Kapuas Pontianak. This application was designed using Netbeans IDE 8.2. It can process admin data, types of goods, types of income, costs, bus classes, destinations, ticket sales transactions, delivery of goods, income transactions, and cost transactions. The reports produced by this application include ticket sales reports, goods delivery reports, income reports, and cost reports. With the income and expense processing application, it is hoped that it can support the performance of Adau Kapuas Pontianak in processing income and expense transactions and presenting reports more easily, quickly, and accurately.   

The turbine can be a component that plays an important role as an energy converter that produces power in a picohydro power plant (PLTPH). The turbine used in this study is the Kaplan Turbine. The Kaplan turbine is a type of reaction turbine with a head of 1.58 m. This research examines the effect of variations in the number of blades on turbine rotation and output power in pico-hydro power plants (PLTpH) using Kaplan turbines so that voltage, current, power can be generated which affect the torque value and the efficiency obtained in the PLTpH prototype. This study aims to obtain a turbine runner with the number of blades that can produce the highest efficiency, so a variation of the Kaplan turbine runner is made with a number of blade runner variations, namely 4 blades, 6 blades, and 8 blades. The results showed that the addition of the number of blades produced the highest output with the number of blades 6 which produced a turbine rotation of 218.1 Rpm, generator rotation of 2433 Rpm, generator voltage of 19 volts, generator power of 1900 watts, and torque of 17.5 Nm. Nilai efesiensi yang dihasilkan yaitu 26,62 %. The results of this research are expected to be a reference and help improve human resources to develop power plants in rural areas, and open up opportunities for the community to develop small-scale power plants, namely pico-hydro power plants.

Rapid Application Development (RAD) is one of the Software Development Cycle (SDLC) methodologies that are often used by development teams that prioritize time efficiency. The RAD methodology is considered as one of the methodologies that has the shortest completion time compared to other SDLC methodologies. This study aims to validate, update, and expand the previous discussion regarding the universal conditions of RAD model research in the world of software feature development. Objectives can be obtained using a narrative review procedure, which is applied to previously collected literature. This study aims to make conclusions about the model of the RAD methodology which is very effective, supports and constrains the RAD model, and is efficient compared to other development models. Not only that, this research also guides the universal stages in SDLC and the RAD methodology used to integrate these stages.

Netflix has produced many TV series, one of which is Money Heist. This series has four seasons with a total of 38 episodes. The fourth season was released on April 3, 2020, which has eight episodes. The fourth season of Money Heist is 31.73 times more demand than the average series around the world. However, despite the many requests for the fourth season of the Money Heist series, there are still some negative comments made by the connoisseurs of the Money Heist series. In the YouTube comments column on the Netflix channel, there are still many who comment neutral and provide positive comments on this series. Therefore, there needs to be a method in which viewers' comments or opinions can be analyzed in order to be able to classify the opinions they make about this series by conducting sentiment analysis using the Naïve Bayes algorithm. Based on the results of research conducted, Naive Bayes can be said to be successful in conducting sentiment analysis because it achieves results of 81%, 74.83%, and 75.22% for accuracy, precision, and recall, respectively.

Sudoku is a game that sharpens the brain and is very well known. But the problem faced in this condition is how we can find a solution for the completion of this game. Problems with the Sudoku game can be solved by using the concept of Artificial Intelligence (AI). Some of the algorithms that can be used are the Breadth First Search (BFS) and Depth Limited Search (DLS) algorithms. The purpose of this research is to find a solution for Sudoku and make a comparative analysis of the search results of the two algorithms. The results obtained are application design in the form of a simulation of the completion of the Sudoku game problem with two algorithms. And it has been proven from the two algorithms that DLS is more efficient and faster than BFS. While BFS itself has advantages, in terms of a more structured and systematic search system that is able to find all possible numbers in each box. In this case, if a Sudoku question has more than one answer, then BFS will find it.

The Department of Communication and Information (Diskominfo) of the Bandung City Government is an agency that has the responsibility of carrying out several parts of the Regional Government in the field of communication and informatics. Based on the composition of the regional service organization Bandung City Diskominfo has five fields and two UPTs which are part of the Bandung City Diskominfo. Bandung City Diskominfo in implementing work programs has IT as a supporter of business processes in government agencies. Based on the results of research conducted that IT management in Bandung City Government Diskominfo found several clauses that were still unfulfilled in this Diskominfo impact on the management of government information security institutions that can affect the performance of Bandung City Government. Therefore, there is a need for standardization that needs to be implemented as a guide that examines the direction in safeguarding information or assets that are considered sensitive to an organization. With the existence of these problems pushed to design information security recommendations based on ISO 27001: 2013 standards at Diskominfo. Also makes the design of IT information security systems that are focused on the control of Annex Information Security Policies, Human Resource Security, Operational Security, Communication Security and Asset Management so that business IT processes can run in accordance with the objectives of the organization. The results of this study are expected to help in securing IT information at the Bandung Diskominfo City and can also improve the goals of an organization.

At present, the use of ICT is growing very rapidly. This has led to changes in processes, functions, and policies in various sectors, including the public service sector managed by the government. e-Government is a new mechanism between the government and the community and stakeholders, which involves the implementation of information technology, and aims to improve the quality (quality) of public services. Bandung City is one of the cities that is very intensive in developing the use of ICT in implementing e-Government. The focus of the city government of Bandung is the Government to Citizen (G2C) application model. The application that is still lacking in use is the e-punten application. One important factor for the success of e-Government services is the acceptance and willingness of people to use e-Government services. E-punten application services provided by the Bandung city government will not run perfectly if no people are using it. To assess what factors influence the use of e-punten applications in the city of Bandung, the UTAUT model is used. To analyze the factors that influence the acceptance of e-punten applications SEM analysis is used. In this study, the PLS-SEM approach is used to solve multiple regression when specific problems occur in the data, such as the small sample size of the study. The PLS evaluation is carried out by evaluating the measurement model and the structural model that best suits the UTAUT model. Factors that influence the use of e-punten applications are effort expectancy for behavioral intention, facilitating conditions for use behavior, and behavioral intention for use behavior. The factors that have the most influence are performance expectancy and effort expectancy.

TCP SYN Flood as one kind of Denial of Service (DoS) attack, still popular to flood the server connection, by sending SYN packets to the target. Because of the risk caused by this attack, there is a need for a network security mechanism. In this paper, one of the security mechanisms proposed is using Stateful Packet Inspection (SPI) method on Configserver Security and Firewall (CSF). By using SPI method, CSF has capabilities to responsible for separating packets of data, that may be entered with data packets that should not be entered into the server. For example: port to be opened, port closed, and IP Address that may access the server for anywhere. This paper combines both of CSF and SPI method to prevent TCP SYN Flood (DoS) with Proof of Concept (PoC) at the Linux operating system. The security process is done in 3 ways: configuring a maximum connection from an IP Address to a server, securing an incoming SYN packet per second, and counting how many times an IP Address violates the minimum SYN packet rule per second before being blocked by a firewall.

Rapid Application Development (RAD) is one of the Software Development Cycle (SDLC) methodologies that are often used by development teams that prioritize time efficiency. The RAD methodology is considered as one of the methodologies that has the shortest completion time compared to other SDLC methodologies. This study aims to validate, update, and expand the previous discussion regarding the universal conditions of RAD model research in the world of software feature development. Objectives can be obtained using a narrative review procedure, which is applied to previously collected literature. This study aims to make conclusions about the model of the RAD methodology which is very effective, supports and constrains the RAD model, and is efficient compared to other development models. Not only that, this research also guides the universal stages in SDLC and the RAD methodology used to integrate these stages.

The Sompak Awe Jaya Cooperative currently manages conventional data, namely recording every savings and loan transaction in a ledger, which is then summarized in Microsoft Excel. Calculations for financial transactions use a calculator, so it takes a long time to process them. So the authors are interested in designing a savings and loan information system at the Sompak Awe Jaya cooperative. The idea of this design is that the finance department can efficiently process savings and loan data, automatic financial calculations are carried out by the system, and membership registration through the application will increase work efficiency. Meanwhile, cooperative managers can track savings and loan activities, view financial transaction data, receive reports, and print existing reports and this system is accessed by two actors, namely admin and finance. Therefore the author aims to create an accounting information system for processing savings and loans so that data management is carried out efficiently and effectively and helps secure existing data because the data is stored in the database. This design uses entity relationship diagram modeling and logical record structure for database design while modeling system flow using user case diagrams, deployment diagrams, activity diagrams, and sequence diagrams.

Sudoku is a game that sharpens the brain and is very well known. But the problem faced in this condition is how we can find a solution for the completion of this game. Problems with the Sudoku game can be solved by using the concept of Artificial Intelligence (AI). Some of the algorithms that can be used are the Breadth First Search (BFS) and Depth Limited Search (DLS) algorithms. The purpose of this research is to find a solution for Sudoku and make a comparative analysis of the search results of the two algorithms. The results obtained are application design in the form of a simulation of the completion of the Sudoku game problem with two algorithms. And it has been proven from the two algorithms that DLS is more efficient and faster than BFS. While BFS itself has advantages, in terms of a more structured and systematic search system that is able to find all possible numbers in each box. In this case, if a Sudoku question has more than one answer, then BFS will find it.

Online learning system or better known as tutoring "bimbel" online is one of the learning methods that are delivered electronically using a computer device or smartphone and connected to the internet. Online tutoring is designed to enable distance learning through the internet without having to come face-to-face with the teacher. Rumah Belajar is a learning portal prepared by the Ministry of Education and Culture containing more than 12,934 learning materials. This portal can be utilized by students as an alternative to getting learning materials, be it inside or outside school hours. This research uses DeLone and McLean success model which only uses variable information quality, system quality, service quality, and user satisfaction. From the results of questionnaire collection, as many as 100 respondents provided th e data information needed in this study. The data is processed with Structural Equation Modeling (SEM) application using AMOS22 application. It is expected that with this research can be obtained recommendations about the learning system or online learning guidance that is good and liked by many users.

A phenomenon known as a short circuit occurs when the input terminals of a power source come into direct electrical contact with one another, which results in a very high flow of current. This results in the production of a significant amount of heat, which poses a risk to the system itself and those located nearby. So, it is vital to identify a short circuit problem and rapidly respond to it once it is identified. When connected, the Short Circuit Indicator automatically detects a short circuit in a circuit to which it is attached. We were able to show the short circuit in our circuit board by inserting a piece of wire that has a resistance value that is very low, almost equal to zero, and which, as a result, created a short circuit at the source connection. Three single-phase currents imply high voltage power line short faults. Zero sequence currents imply grounding failure. Line patrollers may see or hear short circuits or grounding issues on 3kV-40.5kV power distribution networks, switchgear, cable branching units, etc. Answer "What is a short circuit?" to study them. It's how? What time? and why? Short-circuit prevention. Short circuit (fault current) studies must be done to ensure that electrical system equipment can tolerate short circuit energy. Grounding shipboard equipment is difficult. Grounding the power transformer's return to the chassis eliminates direct wiring. Power supply load connects to transformer return. Overcapacity may damage equipment and endanger lives. Short circuits triggered many fires. Short circuits safeguard structures.

Conventional power plants are generally designed on a large scale, centralized, and built far from the load center so that they require transmission and distribution networks to distribute electric power. The condition of the distribution channel's length, the high load supplied, and the increasing number of requests for electrical energy each year affect the quality of distribution of electrical energy. From the above problems, simulation and analysis of the installation of distributed generation are carried out. In installing Distributed Generation, three scenarios are used based on the most significant voltage drop point. The installation of Distributed Generation scenario 1 has an average voltage value of 95.16% or 19.81 kV and an average voltage drop of 9.82% or 1.965 kV, and power losses of 946.69 Kw, where losses power loss was reduced by 17.8% or 733.7 kW. The installation of Distributed Generation scenario 2 has an average voltage value of 95.84% or 19.17 kV and an average voltage drop of 4.16% or 0.833 kV, and power losses of 1062.4 Kw, where losses power loss was reduced by 15.8% or 618 kW. The installation of Distributed Generation scenario three does not experience a voltage drop, the average voltage value is 102.4% or 20.38 kV, and power losses are 1062.4 KW, where power losses are reduced by 29.7% or 1114, 6 kW.

Rapid Application Development (RAD) is one of the Software Development Cycle (SDLC) methodologies that are often used by development teams that prioritize time efficiency. The RAD methodology is considered as one of the methodologies that has the shortest completion time compared to other SDLC methodologies. This study aims to validate, update, and expand the previous discussion regarding the universal conditions of RAD model research in the world of software feature development. Objectives can be obtained using a narrative review procedure, which is applied to previously collected literature. This study aims to make conclusions about the model of the RAD methodology which is very effective, supports and constrains the RAD model, and is efficient compared to other development models. Not only that, this research also guides the universal stages in SDLC and the RAD methodology used to integrate these stages.

This study discusses about temperature monitoring system in the goat pen via smartphone. In addition to monitoring, temperature control is also needed to maintain temperature conditions in the goat pen. This system is useful so that goat cultivation produces well by getting a healthy temperature during its growing period. Manual monitoring is time-consuming, so a more practical monitoring application is required. This monitoring application is built using Internet of Things (IoT) technology so that it can be monitored remotely. The temperature data is taken from the DHT22 temperature sensor which is collected on a microcontroller which is then sent to the internet wirelessly. To control the temperature in the goat pen using an SSR relay. Based on the results of this study, the application of temperature monitoring in the goat pen via smartphone with the Internet of Things (IoT) is able to read the temperature value in the goat pen and can adjust the SSR to turn on and turn off the heating element remotely using a smartphone.

Adau Kapuas is a company operating in the transportation services sector. In processing income and costs, Adau Kapuas Limited liability companies still use bookkeeping as a data collection medium, such as recording payment and expenses, which are processed starting from recording ticket sales and goods delivery transactions, which process passenger data and goods delivery data. The income obtained from tickets and delivery of goods and the total costs are then entered back into the computer. This proves the difficulty faced by Adau Kapuas, namely having to do work twice daily. This research discusses the application of income and cost processing at Adau Kapuas Pontianak. This application was designed using Netbeans IDE 8.2. It can process admin data, types of goods, types of income, costs, bus classes, destinations, ticket sales transactions, delivery of goods, income transactions, and cost transactions. The reports produced by this application include ticket sales reports, goods delivery reports, income reports, and cost reports. With the income and expense processing application, it is hoped that it can support the performance of Adau Kapuas Pontianak in processing income and expense transactions and presenting reports more easily, quickly, and accurately.   

Simera Coffee is a small and medium-sized business that focuses on selling typical Indonesian coffee products in the form of coffee powder, where each type of coffee is obtained from specific and trusted suppliers to maintain coffee quality and consumer confidence. The problem is that business people must be able to set patterns in knowing item items, maximize data utilization, and store expenditure data without being analyzed in detail; moreover, difficulties in restocking, so product expenditure data do not know the pattern of the data. Sales transaction data is continuously increasing every day, causing the need for ample data storage. The apriori algorithm can be applied to a sales data management application or cashier application, which has the function of recording coffee powder sales transactions and, at the same time, providing the function of analyzing sales data contained in the database using the a priori algorithm.