International Journal of Engineering, Science and Information Technology

Journal Information
EISSN : 2775-2674
Published by: Master of Information Technology (10.52088)
Total articles ≅ 135

Latest articles in this journal

Marsa Mahasin, Irma Amelia Dewi
International Journal of Engineering, Science and Information Technology, Volume 2, pp 64-72;

YOLO v4 has a structure consisting of 3 parts: backbone, neck, and head. The backbone is a part of the YOLO v4 structure that serves as a feature extractor from the image; the backbone is also a convolutional neural network that can be replaced with another convolutional neural network. Many backbones are recommended by previous research, such as CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0. Therefore, research needs to be done to determine the effect of different backbones on the YOLO v4 model. One of the research objects that can be used is a microfossil. Research on the detection of microfossils is fundamental to assist paleontologists in knowing the species of microfossils as a determinant of rock age and distinguishing between similar microfossils. In this research, three backbones consisting of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 were used to train and detect image sets of 5 species of foraminiferal microfossils. The results were evaluated to determine the advantages of each backbone. There are a few metrics are that being used for evaluation, namely precision, recall, f1-score, average precision (AP), mean average precision (mAP), frames per second (FPS), and model size. As a result, the mean average precision (mAP) of the CSPDarkNet53 model reached 83.41%, the highest compared to CSPResNeXt-50 and EfficientNet-B0, which get a value of 81,00% and 81,76%. CSPResNeXt-50 model has a precision of 75.60%, recall of 81.10%, and f1-score of 78%. CSPDarkNet53 model also got the highest FPS value of 33.4FPS. However, the YOLO v4 model with the EfficientNet-B0 backbone is the lightest model, with only 156.8 MB.
International Journal of Engineering, Science and Information Technology, Volume 2, pp 48-51;

Smartphones have become more popular due to advances in high-speed Internet connectivity. Smartphones are popular among young people, including medical students, as virtual devices. As a result, excessive use of smartphones has expressed concerns about its addictive potential, a condition known as nomophobia. Nomophobia (No MObile PHone PhoBIA) is the worry or fear people feel when they do not have their mobile phone or are unable to use it. The term was introduced in 2008 and is considered a modern phobia. Nomophobia is also a general pathology among students, particularly those in medicine. This literature review examines the prevalence of nomophobia, symptoms, causes of nomophobia among medical students, and the impact of nomophobia on student achievement. Existing literature on nomophobia in the PUBMED and Google Scholar databases was examined using the search terms ‘nomophobia’ OR ‘mobile phone use’ OR ‘mobile phone addiction’ AND 'medical students.' Several studies have found that medical students have nomophobia. More than 50% of medical students in this review have moderate nomophobia, while 5-20% have severe nomophobia. The most common symptoms of nomophobia were anxiety, agitation, tachycardia, inability to turn off the mobile phone, constantly checking the phone, charging the battery even when the phone is nearly fully charged, fear of not being able to connect to a data network, concerns about being removed from online status or identity, and avoid activities to spend time on a mobile device. Students with severe nomophobia reported poor academic performance; students with a higher level of nomophobia performed poorly academically and vice versa. Medical students had a greater incidence of addiction to mobile phones, which affected their health and academic achievement. More emphasis should be placed on early detection and intervention to overcome nomophobia.
Chicha Rizka Gunawan, Nurdin Nurdin, Fajriana Fajriana
International Journal of Engineering, Science and Information Technology, Volume 2, pp 100-105;

Acehnese traditional clothing is one of the cultural heritages in Indonesia. In today's modern era, the problem faced is the lack of media to introduce cultural heritage in Aceh. Therefore, a media was formed that could introduce Aceh's traditional clothing, namely Southeast Aceh. The press utilizes Augmented Reality (AR) technology so that users can add virtual objects to the natural environment that are easy to use. In this study, a system design using Unified Modeling Language (UML) diagrams has been carried out, including use case diagrams, activity diagrams, and sequence diagrams. This system is built using the C++ language using the Unity application and the vuforiaSDK platform. Then the test results were obtained on the Southeast Aceh traditional clothing recognition application. Namely, the minimum distance that can display 3d objects is a distance of 5 cm, and the maximum distance that can be detected is 80 cm. Based on the test results in the distance test table, the best distance obtained, which results in the detection of markers that are still clear and bright, is at a distance between 5 cm to 70 cm. Meanwhile, at a distance of more than 80 cm, the marker cannot detect markers to display 3D objects because the distance between the camera and the marker is too far. Likewise, with the angular slope, the minimum angle of inclination detected is an angle of 0°, while the maximum angle of inclination detected is an angle of 75°. Based on the test results on the angle slope table, the best angle is obtained, which results in detecting markers that are still clear and bright at a distance between 0-60°. After that, testing is also carried out based on the lighting, where if the light is too bright or too dark, the camera cannot detect the marker.
Suhaili Sahibul Muna, Nurdin Nurdin, Taufiq Taufiq
International Journal of Engineering, Science and Information Technology, Volume 2, pp 106-110;

The development of the marketplace is growing very rapidly and has become familiar in the lives of Indonesian people. The term marketplace has also been imprinted in the general public as a place for buying and selling online without having to meet physically. In practice, the marketplace has also provided a lot of convenience and comfort in shopping, starting from transaction security and selection of varied shopping items, also equipped with estimates in shipping. It doesn't stop there; the development of the marketplace has also penetrated almost all products, including services, food, music, books, household products, airline tickets, and even investments that can be made in the marketplace. Google Lighthouse is a complex metric where the assessment includes in terms of Performance, Accessibility, Best Practices, and SEO, which is presented with a score of 0 to 100 in other words, Google will assess a website with a predetermined metric and then audit it to improve accessibility and SEO. a website. The results of this study are expected to be able to present actual analytical information based on the matrix determined by Google Lighthouse for future improvements where the Tokopedia marketplace gets a performance value with a yellow score of 85, which can be optimized by minimizing the speed index 3.7s, time to interactive 5.9s and total blocking time is 390s to be more optimal in terms of performance and Shopee has decreased in performance with a value of 13 red on first contently paint 2.8s, speed index 16.8s, time to interactive 26.5s, largest contently paint 16.3s, cumulative layout shift 0.484 and total blocking time of 1,710ms to be further assessed for optimal results. Based on this test, it can be concluded that Tokopedia is superior to Shopee from various aspects of the matrix tested.
Abdul Rahman, Syahbudin Hasibuan, Dwika Karima Wardani, Agus Ardi
International Journal of Engineering, Science and Information Technology, Volume 2, pp 15-20;

This study aims to determine the best storage media and storage time for cocoa seeds. The research was carried out at the Plant Physiology Laboratory, Faculty of Agriculture, Medan Area University. The analytical method used is Completely Randomized Design (CRD) with treatments, namely No Storage Media, Use of PE Plastic Storage Media + 1 Week Storage, PE Plastic + 2 Weeks Storage, PE Plastic + 3 Weeks Storage, Aluminum Foil Paper + 1 Week Storage, Aluminum Foil + 2 Weeks Storage, Aluminum Foil Paper + 3 Weeks Storage, Burlap Sack + 1 Week Storage, Burlap Sack + 2 Weeks Storage, Burlap Sack + 3 Weeks Storage, Glass Bottle + 1 Week Storage, Glass Bottle + 2 Weeks Storage , Glass Bottle + 3 Weeks of Storage, a total of 12 treatments with 3 replications. The data were analyzed statistically with the F test at a 5% significance level. If F Count is greater than F Table 5%, then it is continued with the Duncan' New Multiple Range Test (DNMRT) at a level of 5%. The results showed that the treatment on several storage media had a significant effect on the simultaneous growth of cocoa seeds. And the length of time for storing seeds for one week was significantly different, there were parameters for observing seed germination, seed growing simultaneously and seed growing speed.
Heri Purwanto, Aldi Novriadi, Fatah At Thariq
International Journal of Engineering, Science and Information Technology, Volume 2, pp 1-7;

Recipes are guides to making something together with notes on ingredients and their amount. To be able to make food, of course, the cook must prepare the ingredients in advance to be processed into ready-to-eat dishes. Often people have a lot of food ingredients but don't know how to process them. Cooking without seriousness, of course, some people fail when making a dish. Back then, people depends on recipe that was passed down from generation to generation. Now, the digital world is growing rapidly. Anything can be done with increasingly modern technology. Everything needed is accessible with today's technology. Everything is so easy, including the matter of food. Even so, in this digital era, people use smartphones but still cannot use them properly. Many of them use search engines so they need to sort out which are real recipes and which are just random recipes. The purpose of this study is to help people find recipes by taking photos of food ingredients and then finding out what can be made from these ingredients. This technique uses Artificial Intelligence (AI) with MobileNet and Tiny YOLOv2 SSD modules. The design uses the Unified Modeling Language (UML). The study used experimental methods to test the accuracy of the AI used. Data collection will be utilizing a literature study. This research uses agile for system development. Test results show that the SSD MobileNet model has a guessing accuracy of 77%, while Tiny YOLOv2 is 81%. The guessing accuracy might get higher if good camera quality is used
Agus Budi Purnomo, Asep Rohman Hidayat, Rita Walaretina
International Journal of Engineering, Science and Information Technology, Volume 2, pp 21-33;

The transformation of existing buildings at the National Gallery of Indonesia has undergone several transitions, ranging from colonial residences and educational spaces to exhibition spaces. This transitional need became an important consideration in terms of the function and identity of the word ‘National’ contained in it until finally, a proposal for the development of the National Gallery of Indonesia in 2013 was initiated, which focuses on exploring the mass of new buildings that support exhibition spaces with conservation considerations in mind. The form of the mass becomes visually unimportant because it can give a provocative and inviting impression. References are based on mass transformation, new mass response to sustainable buildings, and visual response to the front area. This research aims to explore new building forms of the National Gallery, which can be considered in the subsequent development process and the discourse on architectural forms in development buildings with elongated tread characters and sustainable buildings in the middle. The research method uses literature research and case studies. The data collection technique was carried out by literature observation. It was concluded that the eight study samples did not simultaneously have the second criterion (contrast - symmetric or dynamic - proactive) but rather the configuration form of the four criteria. Consideration of balanced form is dominant rather than different balance. While the application of rhythm is found in the principle of height difference resulting from the mass transformation process.
Syarifah Akmal, M Sayuti, Muhariani Hasibuan
International Journal of Engineering, Science and Information Technology, Volume 2, pp 40-47;

Coffee is one type of plant that has a harvest season in certain months, while the amount of coffee export demand is always there even though it is not in the coffee season. So that the company is often unable to meet the demand for coffee exports. This study aims to find out how the use of the decomposition method in forecasting the demand for Arabica coffee exports and also to find out the results of forecasting the demand obtained. This study uses a quantitative approach, which was conducted at CV. Oro Kopi Gayo is located in the Gayo highlands, precisely in the Mongal Village, Bebesen District, Central Aceh Regency. The data used in this study is secondary data, namely data on Arabica coffee export demand from 2017 to 2021. The results of forecasting coffee export demand using the decomposition method in 2022, which is 1754216 kg, have increased when compared to demand in 2021, which is equal to 1536000 kg with a percentage increase of 14%. Demand for coffee exports in January was 160192 kg, February was 172445 kg, March was 146829 kg, April was 76822 kg, May was 88583 kg, June was 106127 kg, July was 129510 kg, August was 45472 kg, September was 45472 kg 269457 kg, October 225509 kg, November 239090 kg, and December 94090 kg. The highest demand for Arabica coffee exports occurred in September, amounting to 269457 kg, in November at 239090 kg, and in October at 225509 kg. Then it decreased again in December, which was 94090 kg. The increase and decrease in the repetitive data pattern indicate that the data has a seasonal pattern.
Rosy Febriani Daud, Khairunnisa Khairunnisa
International Journal of Engineering, Science and Information Technology, Volume 2, pp 52-57;

Currently, hoax news is easily spread on social media in seconds. Various kinds of Social Media that exist in cyberspace today, namely Facebook, Instagram, Line, Whatsaap, Telegram, Mechat, Hago, and others, can make it very easy for us to access news or get information compared to us getting information from print media such as newspapers, magazines, Tabloids and so on. The impact on society is very harmful, even severe. Hoax thrives on Social Media, sometimes, we can't prevent it. Fighting deceptions is part of the effort to provide education during the current Covid-19 outbreak. The younger generation can carry out simple socialization through education about hoaxes and start from the surrounding environment, namely family, colleagues, and neighbors. Especially now that almost all people in Indonesia use social media in the form of Whatsapp to facilitate the spread of hoax news. The hoax phenomenon is no longer a strange thing in Indonesia. The danger of hoax news makes people restless and anxious because the information received is not known for its truth or accuracy. Due to the rapid growth of communication technology, it can make hoaxes circulate quickly in seconds in the community through social media.
Chichi Rizka Gunawan, Nurdin Nurdin, Fajriana Fajriana
International Journal of Engineering, Science and Information Technology, Volume 2, pp 96-99;

Object detection is an activity that aims to gain an understanding of the classification, concept estimation, and location of objects in an image. As one of the fundamental computer vision problems, object detection can provide valuable information for the semantic understanding of images and videos and is associated with many applications, including image classification. Object detection has recently become one of the most exciting fields in computer vision. Detection of objects on this system using YOLOv3. The You Only Look Once (YOLO) method is one of the fastest and most accurate methods for object detection and is even capable of exceeding two times the capabilities of other algorithms. You Only Look Once, an object detection method, is very fast because a single neural network predicts bounded box and class probabilities directly from the whole image in an evaluation. In this study, the object under study is an object that is around the researcher (a random thing). System design using Unified Modeling Language (UML) diagrams, including use case diagrams, activity diagrams, and class diagrams. This system will be built using the python language. Python is a high-level programming language that can execute some multi-use instructions directly (interpretively) with the Object Oriented Programming method and also uses dynamic semantics to provide a level of syntax readability. As a high-level programming language, python can be learned easily because it has been equipped with automatic memory management, where the user must run through the Anaconda prompt and then continue using Jupyter Notebook. The purpose of this study was to determine the accuracy and performance of detecting random objects on YOLOv3. The result of object detection will display the name and bounding box with the percentage of accuracy. In this study, the system is also able to recognize objects when they object is stationary or moving.
Back to Top Top