Teknika

The Implementation of A* Algorithm for Developing Non-Player Characteristics of Enemy in A Video Game Adopted from Javanese Folklore "Golden Orange"

Subari, Nira Radita, Bimo Prakoso — Fri, 07 Jun 2024 09:18:48 +0700

Video games are a means of entertainment for everyone, from children to adults. The genre of games now is also very diverse, ranging from adventure, puzzles to storytelling, and even many folk stories have been made into video games by several developers in Indonesia. Starting from folk tales with horror themes such as kuntilanak, legends such as cucumber mas, to folk tales that rarely sound like golden oranges. The folklore video game of buah jeruk emas is a video game that tells of a king who gets a whisper from the gods to get golden oranges. The king then held a competition to get the golden orange fruit. The player must be able to take the golden orange fruit from the enemy in the form of a Non Playable Character (NPC) who will chase the player. In making NPCs, algorithms are used to help play video games. Therefore, the author wants to apply the A * algorithm in the game of golden oranges so that npc can catch up to players according to the planned system. The main method used is A * and then the addition of the FSM method for other methods. The golden orange fruit is a video game using the A * algorithm and the FSM method after testing it can be concluded that it is enough to make the game run. With the results according to the planned system.

Rancang Bangun Website Mempawah Mangrove Park Menggunakan Metode Rational Unified Process (RUP)

Yudi, Ilhamsyah, Renny Puspita Sari — Fri, 07 Jun 2024 09:05:39 +0700

Mempawah Mangrove Park (MMP) adalah taman hutan bakau di Desa Pasir, Kecamatan Mempawah Hilir, Kabupaten Mempawah. Namun objek wisata tersebut belum memiliki situs web. Meskipun informasi tentang tempat wisata masih dapat diakses melalui media sosial, keberadaan situs web dapat memperluas jangkauan informasi kepada calon pengunjung yang lebih luas. calon pengunjung juga akan mendapatkan kemudahan untuk mengetahui detail, jam operasional, dan fasilitas yang tersedia. Oleh sebab itu, penelitian ini membangun sebuah situs web yang mendukung Mempawah Mangrove Conservation (MMC) dalam memperkenalkan dan menyajikan informasi mengenai MMP. Situs web dibangun dengan menerapkan metode pengembangan perangkat lunak Rational Unified Process (RUP). RUP merupakan metode pengembangan perangkat lunak inkremental yang meningkatkan efisiensi dan efektivitas pengembangan. Sehingga jika perubahan kebutuhan fungsional, RUP mampu untuk beradaptasi dengan perubahan tersebut. Situs web yang dibangun diuji menggunakan metode Black-Box untuk menguji fungsionalitasnya. Penilaian aspek tampilan aplikasi dilakukan dengan menggunakan skala Likert yang melibatkan partisipasi dari 30 responden. Berdasarkan hasil pengujian, diperoleh persentase sebesar 75.21%, berdasarkan skala likert hasil ini termasuk dalam kategori “Baik”.

Optimisasi Monitoring Tugas Akhir Mahasiswa Dengan Integrasi Formasi Metode Agile Framework Scrum dan Notifikasi WhatsApp di Institut Teknologi Garut

Ridwan Setiawan, Deni Heryanto, Faizal Rifaldy — Thu, 06 Jun 2024 10:56:39 +0700

Lama waktu penyelesaian tugas akhir atau skripsi menjadi salah satu hal yang penting dalam proses penyelesaian studi mahasiswa, di mana beberapa penyebab keterlambatan penyelesaian skripsi dipengaruhi beberapa hal yang di antaranya proses pengerjaan oleh mahasiswa diakhirkan, kurangnya intensitas bimbingan, kurangnya motivasi penyelesaian, dan aktivitas monitoring. Tujuan penelitian ini adalah mengembangkan sistem monitoring tugas akhir dengan menerapkan API WhastApp sebagai notifikasi kepada mahasiswa untuk memberikan peringatan kepada mahasiswa yang memiliki progres lambat. Metode yang digunakan dalam perancangan perangkat lunak menggunakan Agile dengan framework Scrum dengan pemodelan sistem menggunakan Use Case Diagram dan skenario Use Case dengan bahasa pemrograman menggunakan PHP dan MySQL sebagai DBMS. Hasil penelitian menunjukkan mahasiswa, dosen, dan koordinator skripsi dapat melihat progres melalui dashboard dan notifikasi melalui WhatsApp. Penelitian ini dilaksanakan pada Institut Teknologi Garut dengan studi kasus yang diambil pada salah satu jurusan yaitu Ilmu Komputer. Sistem yang dibangun dapat memantau progres tugas akhir mahasiswa, memberikan notifikasi kepada mahasiswa yang tidak melakukan bimbingan dalam waktu tertentu, memberikan peringatan, dan motivasi kepada mahasiswa sehingga mendorong komunikasi dan keterlibatan yang lebih baik di antara mahasiswa dan pembimbing dalam penyelesaian tugas akhir, sedangkan penerapan Framework Scrum pada pembangunan sistem terjadi keterlambatan penyelesaian dari estimasi meski masih dalam status wajar.

Pengelompokan UMKM Batik Madura Menggunakan Metode K-Means dan Sillhoutte Coefficient

Yeni Kustiyahningsih, Achmad Khozaimi, Jaka Purnama — Wed, 12 Jun 2024 16:08:50 +0700

UMKM merupakan salah satu sektor pendukung perekonomian di Indonesia. UMKM Batik Madura memberikan kontribusi yang cukup tinggi terhadap penyerapan tanaga kerja dan peningkatan ekonomi masyarakat daerah. Hal ini terbukti pada penyerapan tenaga kerja UMKM di Kabupaten Bangkalan Madura sebesar 210.003 dan Sampang sebesar 264.569. Permasalahan penelitian ini berkaitan dengan banyaknya UMKM Madura, sehingga menyulitkan Dinas Koperasi dalam menjalankan kebijakan pemerintah dalam memberikan pelatihan, bantuan pengembangan UMKM dan pendampingan. Tujuan penelitian adalah mengelompokan UMKM Batik Madura menjadi beberapa kluster menggunakan metode K-Means dan Sillhoutte Coefficient. Metode K-Means dapat melakukan pengelompokan berdasarkan data yang sama atau mempunyai similarity yang tinggi. Data UMKM akan dilakukan preprosesing terlebih dahulu untuk mengatasi data yang kosong dan normalisasi. Metode Sillhoutte Coefficient (SC) digunakan untuk menentukan jumlah kluster yang paling optimal. Pengelompokan UMKM Batik ini berdasarkan perpektif balance scorecard yaitu bisnis internal, keuangan, learning and growth dan pelanggan. Hasil cluster yang paling optimal adalah K=3. Nilai SC adalah sebesar 0,275, dengan 9 fitur dan SC = 0,403 dengan 5 fitur, artinya dengan metode seleksi fitur information gain terjadi peningkatan snilai SC sebesar 0,128. Prosentase hasil pengelompokan adalah cluster 1 sebesar 15 %, cluster 2: 25 % dan cluster 3 : 60 %. Kategori pemetaan cluster 1 adalah sangat baik, cluster 2 baik dan cluster 3 sedang.

The Smart Door Lock Using Face Recognition Access Based on Internet Of Things (IoT)

Wed, 12 Jun 2024 16:22:04 +0700

Security is one of the basic things that humans need. In relation to a house or room, the focus of security is on the door lock. Various types of door locks have been created, ranging from conventional ones with physical keys, to modern types. This modern type of door lock is also made with various ways to open it. Some use a series of codes (keypad), some use card sensors, fingerprint sensors, to the use of face recognition technology. Several door lock technologies with face recognition have also been created, but they are still expensive. The other problem is that those devices are not equipped with some fail-safe mechanisms, in case there are troubles with the device. This smart door lock is made using face recognition technology based on the Internet of Things. This lock is equipped with an ESP32cam camera integrated in the ESP8266MOD module that can recognize faces that have been registered in the database on the website. In addition, the door is also equipped with a push button to open the door from the inside, and a button as a backup if there is a malfunction of the face recognition feature. The device test indicates no apparent issues and operates smoothly. The accuracy test for the camera yields positive outcomes, reaching up to 100% in normal lighting conditions, and dropping to around 60-80% in blur condition. Accuracy is further compromised, potentially dropping in dim light that the images are only reached 40-60% for clear images and 20% in blurry images.

Implementation of Classification Algorithm for Sentiment Analysis: Measuring App User Satisfaction

Rizki Aulia Putra, Rice Novita, Tengku Khairil Ahsyar, Zarnelly — Tue, 11 Jun 2024 13:14:48 +0700

Google Play Store is the official app store for Android devices from Google that offers rating and review features. This feature on the platform is a source of data for sentiment analysis in research on app user satisfaction. The purpose of this study is to provide an overview of app user satisfaction and evaluate the accuracy of the algorithms used. The algorithms compared include Support Vector Machine (SVM), namely linear, rbf, sigmoid, and polynomial kernels with Naïve Bayes Classifier (NBC). The key variables analyzed include perceived usefulness, perceived ease of use, relia-bility, responsiveness, and website design. The results showed that the SVM algorithm with a linear kernel achieved the highest accuracy of 95.23% compared to the NBC algorithm of 91.43%. For other accuracy results, rbf kernel 94.35%, sigmoid kernel 95.19% and polynomial kernel 93.31%. In addition, the results of sentiment analysis on application user satis-faction revealed that 75% of users were dissatisfied, with the service indicator having the highest number of negative sen-timents. These findings suggest that sentiment analysis can be an effective tool for companies to measure and improve user satisfaction. In addition, these results can also be a useful reference for new users in assessing apps before using them.

Perbandingan Algoritma Naïve Bayes dan TextBlob Untuk Mendapatkan Analisis Sentimen Masyarakat Pada Sosial Media

Giesta Rahguna Putri, Muhammad Akbar Maulana, Samsul Bahri — Wed, 26 Jun 2024 11:23:53 +0700

Media sosial Twitter adalah platform yang populer di Indonesia untuk berkomunikasi dan mendapatkan informasi dengan cepat. Hal ini memungkinkan masyarakat dengan mudah mengungkapkan opini dan sentimen mereka. Penelitian ini berfokus pada perbandingan algoritma TextBlob dan Naïve Bayes dalam menganalisis sentimen masyarakat. Temuan menunjukkan bahwa TextBlob mengklasifikasikan sebagian besar tweet sebagai positif, sementara Naïve Bayes menunjukkan kecenderungan yang serupa dengan akurasi sebesar 78,18%. Dari analisis TextBlob, sekitar 50,98% komentar menunjukkan sentimen positif, 16,01% negatif, dan 33,33% netral. Dengan menggunakan kedua algoritma ini, penelitian berhasil mengidentifikasi sentimen masyarakat dengan akurasi yang baik, menunjukkan distribusi yang jelas antara sentimen positif, netral, dan negatif.

Comparison of Extreme Learning Machine Methods and Support Vector Regression for Predicting Bank Share Prices in Indonesia

Williem Kevin Setiadi, Vincentius Riandaru Prasetyo, Fitri Dwi Kartikasari — Thu, 20 Jun 2024 09:20:22 +0700

Investing is the practice of postponing current consumption to obtain more significant value in the future. One profitable form of investment is stock investment, where investors buy company shares to benefit from appreciation in share value or dividend payments. Before investing in shares, investors need to pay attention to movements in the Composite Stock Price Index (IHSG), which reflects the performance of the Indonesian stock market. The Indonesian Stock Exchange (BEI) recorded around 740 companies listed in 2021. The BEI also compiled the LQ45 list of 45 stocks with the largest market capitalization, including the four largest banks in Indonesia. However, investing in bank shares only sometimes produces profits due to share price fluctuations. Stock price analysis and price movement predictions are important steps before investing. Extreme Learning Machine (ELM) and Support Vector Regression (SVR) methods are techniques used to predict time series data. This research compares the performance of the two methods in predicting stock prices of the big 4 Indonesian banks. The dataset used in this research comes from the Yahoo Finance site, which was taken since the market crash recovery period due to the Covid-19 pandemic. Based on the evaluation conducted, both the ELM and SVR methods are effective for predicting the share prices of the big four Indonesian banks. In terms of accuracy, the SVR method outperforms the ELM method due to its superior MAPE value. However, when considering computing time, the ELM method is more efficient than the SVR method.

Facial Expression Recognition to Detect Student Engagement in Online Lectures

Joko Siswantoro, Januar Rahmadiarto, Mohammad Farid Naufal — Mon, 24 Jun 2024 08:46:11 +0700

In synchronous online lectures, the lecturers often provide the lecture material directly through video conference technology. On the other hand, there are many students who do not pay attention to the lecturers when they are participating in online lectures. As a consequence, in this research, an application was developed to assist lecturers in gathering data regarding the degree to which students who participate in online lectures pay attention to the presented information. The application employed a convolutional neural network (CNN) model to recognize each student's facial expressions and place them into one of two classes: either engaged or disengaged. The captured student facial image was preprocessed to facilitate the classification process. The preprocessing stage consisted of image conversion to gray scale, face detection using the Haar-Cascade Classifier model, and a median filter to reduce noise. In the process of designing a CNN model, three different hyperparameter tuning scenarios were implemented. These tuning scenarios aimed to obtain the best possible CNN model by determining which CNN model hyperparameters were the most optimal. The results of the experiments indicate that the CNN model from the second scenario has the highest level of accuracy in terms of recognizing facial expressions, coming in at 86%. The results of this research have been tested to measure the level of student participation in online lectures. The trial results show that the proposed application can help lecturers evaluate student engagement during online lectures.

Innovative Approach of 2D Platformer Mobile Game Development “Super Journey”

Kelvin Ferdinand, Kevin Jonathan JM, Darius Andana Haris — Sat, 06 Jul 2024 08:51:52 +0700

This study investigates the design and development process of “Super Journey”, a 2D platformer mobile game aimed at enhancing user engagement and satisfaction through innovative game mechanics and design. Utilizing the Agile methodology, the development stages included conceptualization, design, implementation using the Unity game engine, and iterative testing and evaluation based on user feedback. This development process involved crafting a detailed game design document, creating initial sketches and prototypes, and integrating graphical elements, animations, and game mechanics. The game features 3 levels with simple controls, visually appealing pixel art, and progressively challenging levels. A survey conducted with 20 participants revealed high overall satisfaction (4.15 out of 5), with particular praise for level design (4.25) and game mechanics (4.2). Feedback indicated areas for improvement, such as balancing difficulty levels and incorporating more diverse obstacles and enemies. The findings underscore the importance of agile, user-centered design in game development and provide insights for future iterations to further enhance the gaming experience. “Super Journey” exemplifies the effective integration of classic platformer elements with modern innovations, highlighting its potential in the competitive mobile gaming market. The results of this research are expected to serve as a reference and inspiration for other game developers to create superior products by combining innovative technology and thoughtful design.

Forecasting Model of Export and Import Value of Oil and Gas Using Gated Recurrent Unit Method

Tue, 25 Jun 2024 16:07:43 +0700

Indonesia’s natural resources are abundant, including oil and gas. It is one of the countries active in international trade, including exports and imports. Oil and gas exports are a significant source of income for the country, encouraging economic growth. Oil and gas imports are very important to meet domestic energy needs, which continue to increase in demand. Increasing oil and gas imports can increase the trade balance, which can affect the country’s economic stability if the value of imports exceeds the value of exports. Forecasting is a solution to overcome these problems by forecasting the value of oil and gas exports and imports. The gated recurrent unit (GRU) method is used for forecasting in this study because it has a simple computation and fairly high accuracy. The dataset used is monthly time series data from 1993 to 2023 from the website of the Badan Pusat Statistik (BPS). The MAPE results on the GRU model forecast the value of oil and gas exports and imports at 12.19% and 14.30%, respectively. The best average forecasting of export and import values obtained a MAPE of 13.38%.

Adopsi Gamifikasi Pada Mobile Learning Menggunakan Extended Technology Acceptance Model (TAM)

Febriane Devi Rahmawati, Edwin Pramana, Hartarto Junaedi — Tue, 25 Jun 2024 16:11:43 +0700

Pembelajaran konvensional saat ini mulai bergeser dengan pembelajaran digital atau mobile learning karena dianggap lebih efektif dan interaktif. Gamification memiliki potensi yang besar dalam pembelajaran sebagai pembelajaran yang mengadaptasi permainan (game based learning). Tujuan penelitian ini adalah untuk mengidentifikasi dan mengetahui faktor-faktor yang mempengaruhi seseorang untuk mengadopsi gamifikasi pada mobile learning. Selain itu analisis pada faktor moderasi juga diteliti. Penelitian ini dilakukan pada mahasiswa di perguruan tinggi yang pernah menggunakan gamification pada mobile learning dengan rentang usia 17-25 tahun dengan jumlah responden pada penelitian ini adalah 402 responden. Pada tahap awal penelitian dilakukan pengembangan model teoritis dan penyusunan kuisioner, kemudian prosedur selanjutnya melakukan pemrosesan data dimulai dengan faktor analisis, uji validitas, dan uji reliabilitas. Selanjutnya dilakukan penggambaran model penelitian dengan AMOS dan dilakukan analisis SEM dari model TAM yang diberikan sehingga mendapatkan nilai standardize dan nilai magnitude of effect. Hasil dari penelitian ini terdapat 9 hipotesis yang diterima dan 1 hipotesis yang ditolak. Hipotesis yang ditolak adalah Social Influence terhadap Perceived Usefulness. Dalam pengujian efek moderasi, hasil nilai Pairwise Parameter Comparisons menunjukkan bahwa usia memberikan efek moderasi Perceived Ease of Use, Social Influence dan Perceived Usefulness terhadap hubungannya dengan Intention to Use.

The Design of 3D Virtual Reality Animation of Javan Rhino for Educational Media of Endangered Animals in Indonesia

Kent Vin Lievianto, Yana Erlyana — Thu, 04 Jul 2024 10:37:05 +0700

Indonesia is one of the largest archipelagic countries in the world. Indonesia has very rich biodiversity but is facing serious threats. Many endemic species are threatened with extinction due to factors such as climate change, habitat loss, illegal trade and poaching. This research highlights the urgent need for education about endangered animals, with a focus on the Javan Rhinoceros (Rhinoceros Sondaicus) which is categorized as Critically Endangered by the International Union for Conservation of Nature (IUCN). This research was created for Animalium, a research facility under the National Research and Innovation Agency (BRIN), which still lacks interactive Virtual Reality media for education. The main aim of this research is to design a 3D VR animation about the Javan Rhino to increase education and awareness about its conservation. Interviews with educators at Animalium revealed the need for such a medium to prevent damage to physical replicas and to engage visitors, especially children, in a more immersive and interactive learning experience. Observations showed that there were no 3D VR-based educational tools in the facility. The implementation of VR technology has the potential to significantly increase visitor engagement and experiences regarding the conservation of endangered species, in line with Sustainable Development Goals (SDGs) related to terrestrial ecosystems. This research highlights the potential of VR to provide immersive and interactive educational experiences, increase public awareness, and support wildlife conservation efforts, especially the Javan Rhino. The result of this design is an Unreal Engine project file that can be used in Animalium to create an immersive and interactive educational experience, increase public awareness, and support wildlife conservation efforts, especially the Javan Rhino.

Perbaikan Akurasi Random Forest Dengan ANOVA Dan SMOTE Pada Klasifikasi Data Stunting

Ari Ahmad Dhani, Taghfirul Azhima Yoga Siswa, Wawan Joko Pranoto — Mon, 01 Jul 2024 13:40:00 +0700

Stunting terus menjadi isu kesehatan masyarakat yang kritis di Indonesia, khususnya di Kota Samarinda yang mencatat prevalensi sebesar 25,3% pada tahun 2022, menjadi yang tertinggi kedua di Provinsi Kalimantan Timur. Di tengah prioritas nasional untuk riset 2020-2024, penggunaan data mining untuk klasifikasi stunting memperlihatkan potensi yang signifikan namun tetap menghadapi tantangan dalam menangani data berdimensi tinggi dan ketidakseimbangan kelas. Penelitian ini bertujuan untuk meningkatkan akurasi klasifikasi stunting menggunakan metode Random Forest (RF) yang diintegrasikan dengan seleksi fitur ANOVA dan teknik SMOTE untuk menyeimbangkan kelas. Data yang digunakan dalam penelitian ini bersumber dari Dinas Kesehatan Kota Samarinda, meliputi 26 Puskesmas dengan 21 atribut dan total 150.466 record. Teknik validasi yang dipakai adalah cross-validation k =10. Hasil menunjukkan peningkatan akurasi dari 98,83% menjadi 99,77% naik sebesar 0,94% setelah penerapan seleksi fitur ANOVA. Fitur ZS TB/U, ZS BB/U, dan BB/U diidentifikasi sebagai yang paling berpengaruh. Peningkatan ini menunjukkan efektivitas integrasi metode dalam mengatasi masalah stunting pada dataset yang kompleks dan tidak seimbang, ini diharapkan dapat mendukung kebijakan dan intervensi kesehatan lebih lanjut di kawasan tersebut.

Model Optimasi SVM Dengan PSO-GA dan SMOTE Dalam Menangani High Dimensional dan Imbalance Data Banjir

Raenald Syaputra, Taghfirul Azhima Yoga Siswa, Wawan Joko Pranoto — Mon, 01 Jul 2024 16:41:47 +0700

Banjir merupakan salah satu bencana alam yang sering terjadi di Indonesia, termasuk di Kota Samarinda dengan 18-33 titik desa terdampak dari tahun 2018-2021. Penggunaan machine learning dalam mengklasifikasi bencana banjir sangat penting untuk memprediksi kejadian di masa mendatang. Beberapa penelitian sebelumnya terkait klasifikasi data banjir dalam 3 tahun terakhir telah dilakukan. Namun, dari beberapa penelitian tersebut memunculkan masalah terkait dengan dataset high dimensional yang dapat menurunkan performa model klasifikasi dan menyebabkan overfitting. Selain itu, masalah lain juga muncul dalam hal imbalance data yang menyebabkan bias terhadap kelas mayoritas dan representasi yang tidak akurat. Oleh karena itu, permasalahan dataset high dimensional dan imbalance data merupakan tantangan spesifik yang harus diatas dalam klasifkasi data banjir Kota Samarinda. Penelitian ini bertujuan mengidentifkasi fitur-fitur yang diperoleh dari seleksi fitur Genetic Algorithm (GA) yang memiliki pengaruh terhadap akurasi klasifikasi data banjir Kota Samarinda menggunakan algoritma Support Vector Machine (SVM), serta meningkatkan akurasi klasifikasi data banjir di Kota Samarinda dengan mengimplementasikan algoritma SVM yang dikombinasikan dengan metode Synthetic Minority Oversampling Technique (SMOTE) untuk oversampling, seleksi fitur dengan GA dan optimasi menggunakan Particle Swarm Optimization (PSO). Teknik validasi yang digunakan adalah 10-fold cross validation dan evaluasi performa menggunakan confusion matrix. Data yang digunakan berasal dari BPBD (Badan Penanggulangan Bencana Daerah) dan BMKG (Badan Meteorologi, Klimatologi, dan Geofisika) Kota Samarinda pada tahun 2021-2023 terdiri dari 11 fitur dan 1.095 record. Hasil penelitian menunjukkan bahwa fitur-fitur penting yang terpilih melalui GA adalah temperatur maksimum, kecepatan angin maksimum, arah angin maksimum, arah angin terbanyak, lamanya penyinaran matahari dan kecepatan angin rata-rata. Dengan kombinasi metode SVM, SMOTE, GA dan PSO, akurasi klasifikasi data banjir mencapai 82,28%. Namun, penelitian ini juga menghadapi tantangan seperti kontradiksi hasil dengan penelitian lain terkait penggunaan SMOTE dan variasi hasil akibat karakteristik dataset serta metode pembagian data yang berbeda. Hasil penelitian ini dapat digunakan oleh pemerintah daerah dan badan penanggulangan bencana daerah Kota Samarinda untuk memprediksi kejadian banjir dengan lebih akurat, serta memungkinkan tindakan pencegahan yang lebih efektif. Penerapan hasil penelitian ini dapat meningkatkan efektivitas dalam mitigasi bencana banjir Kota Samarinda.

Redesigning User Interface of Datascripmall Mobile Apps Using User Centered Design Method

Nicholas Hiu, Yana Erlyana — Sat, 06 Jul 2024 08:35:37 +0700

The rapid growth of the e-commerce industry, driven by technological advancements and increased internet access, has intensified competition for attracting and retaining customers. In Indonesia, the shift from desktop computers to smartphones has made mobile commerce (m-commerce) increasingly dominant. PT Datascrip, a leading Indonesian company, launched Datascripmall, a B2C and B2B e-commerce marketplace, in August 2020. Despite initial success, a decline in mobile app users indicated a need for an improved user interface (UI) and user experience (UX). This research underscores the urgent need to redesign the Datascripmall mobile app's UI using the User-Centered Design (UCD) methodology, focusing on user needs and preferences. The study employed questionnaires to identify the need for clearer explanations and a more consistent interface. Adding smart features and shortcuts for experienced users was found to boost efficiency and satisfaction. Interviews with the Datascripmall manager confirmed the necessity of a UI/UX redesign to enhance mobile app user numbers. The UCD process involved understanding the context of use, specifying user requirements, designing solutions, and evaluating them against these requirements. The study highlights the benefits of a redesigned UI/UX, enhancing the user experience with greater intuitiveness and engagement. Both qualitative and quantitative data support recommendations for creating a user-friendly interface and increasing overall user engagement. The result of this redesign is a prototype framework developed using Figma, which encompasses page structure, features, and content, providing a comprehensive view of the Datascripmall application UI design. This redesign aims to enhance user satisfaction and increase user numbers, leading to a more comfortable and engaging shopping experience.

Klasifikasi Penyakit Paru-Paru Berdasarkan Peningkatan Kualitas Kontras dan EfficientNet Menggunakan Gambar X-Ray

Asfa Dhevi Azzumzumi, Muhammad Hanafi, Windha Mega Pradnya Dhuhita — Sat, 06 Jul 2024 08:40:06 +0700

COVID-19 dan penyakit paru-paru telah menjadi faktor utama penyebab kematian manusia di seluruh dunia. Kematian pasien dipengaruhi oleh keterlambatan deteksi dini. Sebagian besar profesional medis menggunakan gambar untuk mengidentifikasi kondisi paru-paru. Namun, para ahli yang dapat me-diagnosis dengan gambar sangat terbatas. Diagnosis gambar mendiagnosa menggunakan penglihatan manusia secara konvensional. Klasifikasi penyakit paru-paru sangat bervariasi. Masalah yang disebutkan di atas menunjukkan bahwa deteksi penyakit paru-paru dengan Artificial Intelligence (AI) yang efektif telah ditetapkan. Namun, sebagian besar hasil penyakit paru-paru salah didiagnosis. Bagi pasien, masalah ini menjadi masalah besar. Bertujuan untuk menangani klasifikasi penyakit paru-paru dengan deteksi kesalahan yang tinggi, kami menggunakan beberapa teknik pre-processing gambar dan menerapkan model pembelajaran mendalam dalam EfficientNet. Model Pre-processing termasuk augmentasi, peningkatan white balance, dan peningkatan kontras. Berdasarkan penelitian sebelumnya, mayoritas proses analisa gambar medis mengalami kualitas gambar yang rendah. Berdasarkan laporan eksperimen, model yang kami usulkan mencapai hasil yang signifikan dalam mengurangi kesalahan deteksi pada klasifikasi penyakit paru-paru. Dimana hasil F1 score-nya 0,97, recallnya 0,98, presisinya 0,96, dan akurasinya 0,97. Kami mempertimbangkan untuk menggunakan model yang kami usulkan dalam klasifikasi multi-class. Kami mengevaluasi model yang kami usulkan menggunakan evaluation metric dan AUC Curve.

Algoritma Machine Learning Dalam Melakukan Prediksi Pemilihan Konfigurasi Kapal Tunda di Pelabuhan Tanjung Priok

Budi Tri Yulianto, Raden Muhammad Atok — Tue, 09 Jul 2024 11:39:24 +0700

Pengoperasian pelabuhan secara dasar meliputi berbagai kegiatan pelayanan, salah satu proses pelayanan kegiatan di pelabuhan yaitu pelayanan pemanduan dan penundaan kapal. Salah satu langkah yang dibutuhkan dalam proses penetapan kapal tunda dalam pelayanan pemanduan dan penundaan kapal yaitu pemilihan konfigurasi Kapal Tunda. Penelitian ini menguji performa klasifikasi Support Vector Machine (SVM) dan Naïve Bayes Classifier (NBC) pada data Laporan Harian Gerakan Kapal (LHGK) di Pelabuhan Tanjung Priok selama periode 2021 untuk proses pemodelan dan evaluasi. Penelitian ini bertujuan untuk membuat modelan prediksi dalam penentuan konfigurasi Kapal Tunda, evaluasi hasil model prediksi untuk memilih konfigurasi kapal tunda di Pelabuhan Tanjung Priok. Dengan menerapkan model klasifikasi NBC dan SVM yang ditingkatkan dengan kernel Linier dan RBF, termasuk juga pemilihan fitur baik untuk SVM dan Naïve Bayes. Hasil uji perbandingan model prediksi antara SVM dan NBC menujukan bahwa klasifikasi SVM memberikan hasil yang paling optimal, yaitu menggunakan kernel linier pada nilai C=10, diperoleh akurasi sebesar 84,7%, recall sebesar 84,7%, F1-score sebesar 88,7%, dan akurasi sebesar 88,7%. Penelitian ini dimasa yang akan datang dapat dimanfaatkan dalam proses pengambilan keputusan dalam menentukan susunan konfigurasi Kapal Tunda oleh petugas pelabuhan.

Exploration of Software as a Service (SaaS) as a Project Management Tools

Liliana, Daniel Soesanto, Bambang Prijambodo, Jasti Ohanna — Tue, 09 Jul 2024 11:40:26 +0700

Companies increasingly adopt software as a Service (SaaS) as a project management tool. SaaS offers greater flexibility, availability, and accessibility than traditional information system software. In this study, SaaS is used as the basis for creating project management applications, including recording work plans, the progress of each user's performance, and meeting documentation. The stages of the literature study are carried out by looking at journals and books. The trial was carried out using black-box testing. Verification trials are carried out by involving a team of programmers to see the flow of the system algorithm. Validation trials are carried out by asking various users involved in project implementation to try the system and asking users to fill out questionnaires related to the ease of use of project management features. The two stages of the trial showed good results, as evidenced by 77.8% of users stating that the SaaS concept really helped them with the flexibility of system installation with a short waiting time. Meanwhile, 76.16% of users stated that the features provided and their configuration could help them in project management. The research results show that SaaS has great potential to help companies to manage projects effectively. In future research, various factors in different project management can be explored deeper, so that SaaS becomes more configurable and used by a wider variety of users.

Classification of Lung Cancer with Convolutional Neural Network Method Using ResNet Architecture

Tue, 09 Jul 2024 11:41:31 +0700

Lung cancer has become one of the most frightening specters in the world of health, leading many people to death each year. Therefore, the classification of lung cancer types is very important to determine the appropriate treatment steps. Considering that lung cancer treatment in the early stages is far more effective and efficient, accurate classification is the key to improving survival rates. This research focuses on the classification of three common lung cancer types: Adenocarcinoma, Large Cell Carcinoma, and Squamous Cell Carcinoma. To achieve optimal results, this study utilizes the ResNet architecture, a deep neural network model that has demonstrated its capabilities in various fields. Before being used on the model, the dataset containing lung X-ray images of patients undergoes preprocessing. At this stage, each image is resized to 256x256 pixels to ensure uniformity and compatibility with the model. Furthermore, this research trains various ResNet models, ranging from ResNet50, ResNet101, to ResNet152, which is the model with the most parameters. By comparing the performance of each model, this study finds that all trained ResNet models are capable of producing good accuracy in classifying lung cancer types. Among these models, ResNet152 demonstrates the most superior performance with an accuracy of 89%. This result suggests that the ResNet architecture has great potential to be used as an aid in classifying lung cancer types with a high level of accuracy. This research makes a significant contribution to the effort to improve the diagnosis and treatment of lung cancer, paving the way for a brighter future for lung cancer patients.