Jurnal Teknologi dan Rekayasa Sistem Komputer (TEKNOKOM)
Not a member yet
85 research outputs found
Sort by
VEHICLE STARTER SYSTEM FOR SAFETY BASED MICROCONTROLLER USING INTERNET OF THINGS
Get PDFTechnology is currently growing very fast which affects and has a significant purpose in human life. In the current era, the technology of the security system is something that is very necessary. The high crime rate has now reached an alarming stage. Motorcycles currently only use conventional ignition keys to turn them on to improve the vehicle's security system, so a vehicle security system with a microcontroller connected to an Internet of Things-based fingerprint sensor is needed to improve the vehicle's security system. Research shows that a motorcycle security system with a microcontroller is connected to a fingerprint sensor based on the Internet of Things, namely turning on and turning off the vehicle with fingerprints owned or via the internet of things using the telegram application for remote and realtime systems. The way the results of this study work is when the first finger taps on the fingerprint sensor on the registered finger, the motor will turn on, then the second finger taps on the fingerprint sensor, the motor will die, for remote systems, namely using telegram bots, the prefix is to enter chat instructions on the telegram bot if the telegram bot replies to the instruction then the motor will follow according to the instruction on or off and if the instruction is wrong then the telegram bot will tell that the instruction is wrong. The results of this study show that when adding fingerprints it has a delay of 1.74s, removing fingerprints is 0.24s and the IoT system itself is 90% successful
SKIN CANCER IMAGE DETECTION SYSTEM USING THE CONVOLUTIONAL NEURAL NETWORK MODEL
Get PDFThe development of science and technology (IPTEK) in the current era is growing very rapidly in various fields such as industry, education, especially the health sector. Many technologies can be used, one of which is artificial intelligence technology. This study aims to detect skin cancer images using CNN so that they can be efficient and precise. This research method uses the convolutional neural network (CNN) method, namely image processing, the development of a multilayer perceptron (MLP), in which the neurons of the data are propagated in two dimensions. Because this method has very high accuracy compared to the fuzzy k-nearest neighbors. The results of this study are that there are 7 classes of skin cancer images including actinic keratosis, basal cell carcinoma, dermatofibroma, benign keratosis, melanocytic nevi, vascular lesions and melanoma. From the results of testing the 7 classes using the convolutional neural network (CNN) method with a very high accuracy rate of 99%, 96%, 98%, 99%, 100%, 99% and 96%, respectively. With the conclusion that using the convolutional neural network (CNN) method produces an average accuracy of 98% compared to the Mobilnetv2, Resnet50 and VGG16 models, which means that the CNN model is proven to be more accurate. So it is hoped that this detection system can be applied as a skin cancer detection system for the world of health
IMPLEMENTASI DIGITAL IMAGE PROCESSING SEBAGAI PENDETEKSI POSISI MATAHARI PADA PERANCANGAN DUAL AXIS SOLAR TRACKER
Get PDFOne of the uses of new renewable energy (EBT) in Indonesia which has great potential is solar panels. Solar panels are electrical devices that are used to convert solar energy into electrical energy. The limited surface area of the panels requires users to be able to pay attention to the work efficiency of solar panels. The aspect that has the most influence on optimizing the efficiency of solar panel performance is the placement of the surface of the solar panel against incoming solar radiation. Therefore, it is necessary to have a method to detect the position of the sun to provide input to the actuator so that the surface of the solar panel is positioned in the direction of the sun's rays. This study describes the accuracy of detecting the position of the sun using digital image processing methods. This process needs to be done as a reference in designing a dual axis solar tracker. Detection of the sun's position using this method gets 100% accurate results in cloudless sky conditions and gets 80% success results in cloudy sky conditions
IMPLEMENTASI METODE ADASYN DALAM DETEKSI URL BERBAHAYA MENGGUNAKAN MACHINE LEARNING: DEMI MENINGKATKAN KEAMANAN SIBER DI ERA DIGITAL
Get PDFCybercriminals exploit malicious URLs as a distribution channel to spread harmful software across the internet. They take advantage of vulnerabilities in browsers to install malicious software with the aim of gaining remote access to the victims' computers. Typically, this malicious software aims to gain access to networks, steal sensitive information, and silently monitor targeted computer systems. In this research, a data mining approach known as Classification Based on Association (CBA) is employed to detect malicious URLs using both the URL itself and the features of the presented web pages. The CBA algorithm utilizes a training dataset of URLs as historical data to discover association rules that can be used to create an accurate classifier. By detecting dangerous URLs and malicious software, this contribution can assist organizations and individual users in enhancing the security of their computer systems and networks, thereby protecting sensitive data and reducing the risk of security incidents. The experimental results demonstrate that CBA achieves performance on par with tested classification algorithms, achieving an accuracy of 99% and low rates of false positives and false negatives. Future research could expand its focus to detect malicious URLs and software on mobile devices and embedded systems, as they have become significant targets for cybercriminals
IMPLEMENTATION OF TWO LANGUAGE CHATBOT WEB TO FIND INFORMATION ON BATIK USING THE ARTIFICIAL NEURAL NETWORK MODEL
Get PDFInformation technology plays an important role in the progress of a country in order to disseminate information massively and make it easier for the public to obtain information. Currently, the development of information technology continues to innovate, such as with the existence of artificial intelligence (AI) technology. This research will discuss AI technology, namely the BatikInd chatbot with the artificial neural network (ANN) method, which aims to make it easier for people to find information about the types of batik that, exist in all regions of Indonesia. The design of the ANN method for making chatbots uses hundreds of sentences to be processed into a database of information about the types of batik and explanations about the batik you want to find. Database processing with epochs reaching 200 produces an accuracy rate of 1.0 (100%) which means the accuracy rate is very good and the error rate reaches 0.03 (0%) which means the error rate is very low. The results of a very good level of accuracy and a very low error rate indicate that this AI can function properly and is feasible to use. It is hoped that with information technology like this, it will make it easier for people to find information about batik and can increase people's literacy and knowledge about batik in all regions of Indonesia
IMPLEMENTATION OF THE EDAS METHOD IN SELECTING INVESTMENT IN THE AGRICULTURAL SECTOR
Get PDFCapital is one of the most important things in any business activity that will be carried out. Capital includes capital before planting, planting period until harvest time arrives and post-harvest. Because of the large number of farmers in Kuningan district, the Kuningan district Food Security and Agriculture Agency needs investors to help the farmers. In this study designing and building applications for selecting investments in the agricultural sector using a decision support system with the EDAS method. EDAS is a multi-criteria decision-making method based on the AS score. The data used is data from direct interviews with farmers to determine criteria, sub criteria and alternatives. The criteria include land area, capital, harvest period, yields, and selling price. The alternatives include the names of the farmers, namely Tati, Niryo, Odah, Umin, and Tarwa, as well as types of farming, such as chili, shallots, rice, corn, and peanuts. From the results of the overall calculation of this study, it shows that the EDAS method produces the best choice for Tati farming with the type of chili farming. This research produces a web-based application that can be used by farmers and investors and furthermore, it can be developed into an Android or mobile-based application. The goal is to make it easier for investors to find and choose the best farms to invest in
PRIORITIZING TASKS IN INFORMATION SYSTEM PROJECTS: A NOVEL APPROACH USING VIKOR METHOD
Get PDFInformation Systems (IS) projects often face significant challenges, with many failing to meet their objectives. One of the key factors contributing to these failures is the improper prioritization of tasks. This article addresses this issue by proposing a comprehensive approach to task prioritization in IS projects using the VIKOR method. The approach takes into account four key criteria - cost, time, risk, and complexity - and uses the VIKOR method to rank tasks based on these criteria. The VIKOR method provides a systematic and objective way of prioritizing tasks, ensuring effective resource allocation, appropriate risk management, and the achievement of strategic objectives. The application of the VIKOR method in the context of IS projects is a novel contribution of this article. However, it is also recognized that the proposed approach has its limitations and that further research is needed to consider additional criteria, explore other decision-making methods, and examine the dynamic nature of IS projects. Overall, this article contributes to the growing body of knowledge on project management in IS and provides a practical tool for project managers to improve their decision-making processes
IMPROVING EXAMPLE-PROBLEM-BASED-LEARNING (EPBL) WITH GROW COACHING MODEL AND DESIGN SPRINT TO OPTIMIZE PRE-INCUBATION CURRICULUM: CASE STUDY OF USER INTERFACE DESIGN
Get PDFLearning to develop user interfaces is one of the subject matter in startup business pre-incubation activities in PT. Tunas Inkubator Creative Startup. The Example-Problem Based Learning (EPBL) learning method is proven to be able to improve students' cognitive abilities (hard skills). However, hard skill competence alone is not enough to measure one's ability. This research aims to improve the hard skill competencies, as well as the soft skills of the tenants. The contribution to this research is that researchers apply the GROW coaching model method to measure tenant motivation and insert design sprints into the Example-Problem-Based Learning method. Where the function of the design sprint is to improve the attitude of cooperation between teams. The improvisation of learning methods in this study aims to measure students' speed in mastering user interface design subjects. From the trial results it is known that tenants can complete the user interface design within 2 weeks
MUZAKI BEHAVIOR IN PAYING ZAKAT THROUGH THE APPLICATION OF THE UNIFIED THEORY MODEL ACCEPTANCE AND USE OF TECHNOLOGY IN JAKARTA PROVINCE
Get PDFThis paper investigated the intents and behavior of muzakki who pay zakat through e-zakat using the Unified Theory of Acceptance and Use of Technology (UTAUT). In DKI Jakarta, the study was done. This article utilizes sampling convenience. The research data were collected using a questionnaire-based survey. Using SmartPLS 3.0, route analysis serves as a statistical instrument for evaluating hypotheses. . The findings indicated that neither the performance expectation variable nor the social influence variable substantially affected the desire to use e-zakat. The variable business expectation had a substantial beneficial impact on both the willingness to use e-zakat and the conditions that allow for a substantial beneficial impact on e-zakat use behavior
DESIGNING A WORK PERMIT REPORTING INFORMATION SYSTEM ON HIBA GROUP
Get PDFIn 1949 the HIBA Group was here to meet the transportation needs of the community. The company's commitment is to provide increased customer satisfaction through professional management and operational team support to the demands of the changing times. HIBA Group offers complete, professional, modern, and integrated transportation services. In addition to providing comprehensive, professional, current, and integrated transportation services, the HIBA Group also provides work comfort to employees, especially for maintenance, construction, and bus bodybuilding. In the construction or maintenance process, each activity must report a work permit or Permit to Work (PTW), whose function is to monitor and analyze the work to be carried out. The analysis is carried out from the workers' health, difficulty, the environment, and work tools (PPE). The reporting process is still manual form or conventional system to slow down the work being done if the work is essential for a tender. The PTW must also be analyzed and reported on the related circumstances so that PTW work tends to be slow. An online-based PTW information system Website design was made to simplify and speed up the PTW reporting to solve this problem. The method used for developing information systems uses the Prototype Model with an object-oriented system approach modeled using the Unified Modeling Language (UML). This research is the design of the PTW information system Website used in the HIBA Group