Jurnal Techno Nusa Mandiri

DIAGNOSE OF MENTAL ILLNESS USING FORWARD CHAINING AND CERTAINTY FACTOR

2023-11-06T16:30:44+07:00

The prevalence of mental disorders in Indonesia is increasingly significant, as seen from the 2018 Riskesdas data. Riskesdas records mental, emotional health problems (depression and anxiety) as much as 9.8%. This shows an increase when compared to the 2013 Riskesdas data of 6%. Based on these data, it can be said that many people still suffer from mental disorders. Meanwhile, the number of medical personnel, medicines and public treatment facilities for people with mental disorders is still limited. In addition, the lack of public awareness, concern and knowledge about mental health causes a lack of public interest in consulting a psychologist, so people tend to self-diagnose. One solution for self-diagnosis is to use an expert system. This study developed an expert system using the forward chaining method and certainty factor. Based on the research conducted, the results are as follows. First, the expert-based system that has been developed can help provide the results of a diagnosis that is carried out before there are complaints and will be detected early by efforts to increase awareness of the prevention of mental illness and reduce the tendency to self-diagnose. Second, applying the forward chaining method and certainty factor to this expert system can produce an accuracy rate of 95.918%. An expert has also validated these results; in this study, the expert was a psychologist at a hospital in Yogyakarta.

ANALYSIS OF USABILITY USING HEURISTIC EVALUATION METHOD AND MEASUREMENT OF SUS ON PRICILIA APPLICATION

2023-10-04T09:53:19+07:00

The Presence Digital Application (PRICILIA) is a presence application owned by PT. BGR Logistics Indonesia. However, until now, there has never been an evaluation of usability testing. Complaints from users regarding the PRICILIA application include menu displays that are less interactive, long loading times, and the unavailability of other alternatives besides GPS. Of course, this affects the level of user satisfaction with the application. Therefore, usability testing is needed to be able to measure the level of user comfort, application feasibility, and the application interface. In this study, the system evaluation method used is Heuristic Evaluation with measurement using the System Usability Scale (SUS). The results of this study indicate that aspects that need to be improved with high priority are Error Prevention (H5) and Recognition rather than Recall (H6) because they have a seriousness rating on a scale of 3, while the average score of the final seriousness rating obtained from a total of 10 heuristic aspects is 1, 72 which is then rounded off to a scale of 2. The SUS test results obtained an average final SUS score of 55.13. The results of the calculation of the SUS method are that the Acceptance Ranges have low marginal status, the Grade Scale is on a D scale, and the Adjective Twigs are at the OK level. This shows that the PRICILIA application still needs improvement. Therefore, 30 recommendations for improvement are proposed for future application development.

PRE-ECLAMPSIA DIAGNOSIS EXPERT SYSTEM USING FUZZY INFERENCE SYSTEM MAMDANI

2023-10-23T16:50:56+07:00

Various institutions utilize computer information systems to analyze and process data. An expert system is an information system that is used to help analyze and determine decisions on a problem based on rules determined by experts. This research focuses on creating a prototype expert system for diagnosing pre-eclampsia or pregnancy poisoning in pregnant women based on measuring blood pressure and checking proteinuria. The existing data is then analyzed using the Mamdani system's fuzzy inference method. Supporting theory regarding the fuzzy inference system of Mamdani, pre-eclampsia and its examination indicators will be used as a basis for creating this expert system prototype. The data used were secondary data on preeclampsia patients in the form of medical records of blood pressure measurements, proteinuria examinations and doctor diagnoses of preeclampsia patients at two Regional General Hospitals (RSUD), namely Atambua and Kefamenanu, totaling 20 samples. The interface or user interface of this prototype system is made as simple as possible so that it can be operated by all ordinary people. The programming language used is Visual Basic (VB) with the Visual Studio 2010 developer application. The initial prototype of this system will continue to be developed until it can become a Information systems or real applications used in hospitals. The results of this research are that the expert system for diagnosing preclampsia can be used well and easily by hospital staff and show congruence between the system diagnosis results and the diagnosis results from obstetricians or experts in the 20 processed data.

CLASSIFICATION OF POTATO LEAF DISEASES USING CONVOLUTIONAL NEURAL NETWORK

2023-10-23T16:50:48+07:00

Potatoes are an agricultural product that has the fourth highest content of wheat flour after corn, wheat, and rice. Although potatoes play a critical role in agriculture, this crop is susceptible to various diseases and pests. There are several potato leaf diseases that are not yet known to farmers. Dry spot potato leaf disease (late blight) and late blight. If not treated, this disease on potato leaves will spread to the stem and reduce crop yields, causing crop failure. By using technology in the form of digital image processing, this problem can be overcome. This research proposes an appropriate method for detecting disease in potato leaves. Classification will be carried out in three classes, namel, Early Blight, Healthy and Late Blight using the Deep Learning method of Convolutional Neural Network (CNN). The data used comes from an online dataset via the kaggle.com page with the file name Potato Disease Leaf Dataset (PLD) totaling 3251 training datasets which are then divided into training, testing, and validation. The processes carried out are image pre-processing, image augmentation, then image processing using a Convolutional Neural Network (CNN). In the classification process using the CNN method with RMSprop optimizer, the accuracy was 97.53% with a loss value of 0.1096.

ELECTRICITY MANAGEMENT SYSTEM WITH TECHNOLOGY INTERNET OF THINGS

2023-10-30T09:37:58+07:00

The increasing global demand for electricity has put a strain on energy resources and raised concerns about environmental sustainability. To address these challenges, the integration of modern technologies is crucial. This research presents a study on the implementation of an Electrical Energy Management System (EMS) using Internet of Things (IoT) technology. The proposed system aims to optimize electrical energy usage, enhance efficiency, and reduce the environmental impact. The EMS employs IoT devices and sensors to monitor and collect real-time data on electricity consumption in office buildings. Through data, the system can identify patterns and anomalies in energy consumption, allowing for informed decision-making and proactive energy management strategies.

CLASSIFICATION OF RICE TEXTURE BASED ON RICE IMAGE USED THE CONVOLUTIONAL NEURAL NETWORK METHOD

2023-10-31T14:43:12+07:00

There are several types of rice that are commonly sold in rice stores. Many people, especially millennials, are not familiar with the different types of rice such as IR42 rice, Pera rice, sticky rice, and Pandan Wangi rice. Therefore, digital image processing techniques are needed to help analyze the types of rice to help people know what kind of rice they are going to buy at the market. The method commonly used in image processing for image classification is the convolutional neural network (CNN) method. Currently, CNN has shown the most significant results in image classification. This research used a dataset of 1560 rice images. The data was divided into two sets (training data and validation data) with an 80:20 ratio. The accuracy obtained by the CNN model using InceptionV3 for the rice data was 95.7% with a loss of 0.123. The Android application developed in this research achieved an accuracy of 83,4% based on the testing results calculated using the confusion matrix.

REAL TIME DETECTION OF CHICKEN EGG QUANTITY

2023-11-06T07:51:51+07:00

A common problem currently being faced in the chicken egg production home industry is difficulty in counting the number of eggs. Currently, calculating the number of eggs is still done manually, which is less than optimal and prone to errors, so many entrepreneurs often experience losses. The manual system currently used also has the potential for this to happen. The use of technology on an MSME scale among laying hen breeders has not been widely adopted, this is due to limited access and understanding of technology. One alternative solution to deal with this problem is to build a real-time computerized system. The system that will currently be built in this research uses GLCM feature extraction and the SVM classification method. This system will detect egg production via CCTV cameras and will be stored in a database to be displayed on the website. The advantage of this system is that egg entrepreneurs can monitor chicken egg yields in real time. The results of trials that have been carried out using GLCM feature extraction and the SVM classification method in calculating the number of eggs using the SVM method with a polynomial kernel are highly recommended for use in this research because it can achieve 95% accuracy.

COMPARISON OF KNN, NAIVE BAYES, DECISION TREE, ENSEMBLE, REGRESSION METHODS FOR INCOME PREDICTION

2023-11-06T16:24:03+07:00

Using the income classification dataset, we performed data analysis with the help of data mining to gather interesting information from the available data. Currently, data processing can be done using many tools. One of the tools that we use for data processing is the orange application. By using the dataset we looked at the welfare level ranging from marital status, school, gender, and from all fields related to income ranging from sales, to daily life to find out the income earned by employees or workers from several countries such as the United States, Cambodia, United Kingdom, Puerto-Rico, Canada, Germany, Outer US (Guam-USVI-etc). The purpose of this analysis is to determine the hourly income in one week that can affect the income classification. The classification technique uses various classification models, namely the K-Nearest Neighbor (KNN) algorithm model, Naïve Bayes, Decision Tree, Esemble Method and Linear Regression algorithm. The results of the analysis based on the test results of various algorithm models can be concluded that the best algorithm model for measuring workers' income is to use the Naive Bayes Decision. Analysis of variables based on Hours-per-Week and Capital-Gain affects Income Classification which determines whether the income earned is more than 50 thousand/50 K and the analysis results in a prediction of a person's income level.