Articles
<![CDATA[Distance Correlation-Based Regression Tree Algorithm For Structural Damage Detection ]]>
<![CDATA[Jimmy Tjen]]>;
<![CDATA[Genrawan Hoendarto]]>;
<![CDATA[Tony Darmanto]]>;
<![CDATA[Thommy Willay]]>
<![CDATA[ JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 10 No 2 (2023): JATISI (Jurnal Teknik Informatika dan Sistem Informasi) ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35957/jatisi.v10i2.5402
<![CDATA[This paper proposes a novel idea of a fault detection algorithm based on the Regression Tree (RT) algorithm from the decision tree learning and the distance correlation, which is the nonlinear version of Pearson’s correlation, to reduce the number of sensors without significantly decreasing the model predictive accuracy and the fault diagnosis capability. A numerical validation on an experimental dataset provided by the Los Alamos National Laboratory (LANL) with MATLAB software shows that the proposed algorithm has a comparable model predictive accuracy to the classical RT while requiring a smaller number of sensors (5 instead of 24) and more robust in detecting faults with false negative and positive rates < 15%. Furthermore, we demonstrate that our proposed algorithm runs about 4 times faster than the classical RT on an experimental dataset with 4096 samples on an 8-core, 16 GB RAM machine. In a real-life setup, the proposed algorithm can be used to provide a sensor installment plan on a structure. Such that, the user can still monitor the presence of a fault inside a building precisely, but with a cheaper maintenance cost.]]>
<![CDATA[Algoritma Pendeteksi Kerusakan Struktur Bangunan Berbasis Korelasi Jarak dan Metode Kuadrat Terkecil Parsial ]]>
<![CDATA[Jimmy Tjen]]>
<![CDATA[ JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 8, No 3 (2022): Volume 8 No 3 ]]>
Publisher : <![CDATA[Program Studi Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26418/jp.v8i3.56011
<![CDATA[Sering kali, sebuah kerusakan struktur yang masif terjadi karena pengabaian terhadap kerusakan kecil. Kejadian malang ini kemudian menimbulkan berbagai kerugiaan, baik secara material maupun korban jiwa. Oleh karena itu, dirasa penting untuk dapat mendeteksi kerusakan dari sebuah struktur sedini mungkin untuk mencegah terjadinya hal yang tidak diinginkan. Penelitian ini menggagas sebuah algoritma pendektesi kerusakan struktur bangunan berbasiskan pada metode korelasi jarak dan kuadrat terkecil parsial. algoritma ini berfokuskan pada pemilihan sekelompok sensor yang dapat bekerja secara optimal berdasarkan pada perhitungan korelasi jarak. Berdasarkan pada percobaan pada data experimental dari sebuah struktur jembatan, algoritma yang digagas dapat mengurangi jumlah akselerometer yang diperlukan hingga 80% untuk menyusun model prediktif tanpa mengurangi atau bahkan meningkatkan akurasi dari model prediktif akselerometer sebesar 1 hingga 1,3%. Lebih lanjut, algoritma yang digagas dapat mendekteksi keberadaan kerusakan struktur dengan baik, serta mampu mengkarakterisasi tingkat kerusakan dari struktur berdasarkan pada perubahan standar deviasi dari residu kuadrat.]]>
<![CDATA[Penentuan Jalur Diagnostik Penyakit Berbasis Konsep Pembelajaran Mesin: Studi kasus Penyakit Hepatitis C ]]>
<![CDATA[Jimmy Tjen]]>;
<![CDATA[Valentino Pratama]]>
<![CDATA[ Journal of Applied Computer Science and Technology Vol 4 No 2 (2023): Desember 2023 ]]>
Publisher : <![CDATA[Indonesian Society of Applied Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52158/jacost.v4i2.556
<![CDATA[Hepatitis is considered to be one of the most dangerous diseases, which often leads to death if not handled properly. Thus, early detection via precise diagnosis is needed in order to prevent the unfortunate event. This research aims to provide a novel hepatitis C diagnosis based on the machine learning algorithm, which is the classification tree from the decision tree learning and the distance correlation, which measures the Euclidean distance between 2 vectors. In particular, the goal is to develop a low computational cost yet precise algorithm for diagnosing the possibility of whether a person is being infected with Hepatitis C or not. Based on the experiment, the distance correlation-based classification tree algorithm outperforms the classical classification tree algorithm by around 3% while using only 7 features instead of 12 as in the classical algorithm. Furthermore, the algorithm identified albumin (ALB), Creatinine (CREA), Bilirubin (BIL), Aspartate Transaminase (AST) and Cholesterol (CHOL) as significant risk factors in determining whether someone is potentially infected with hepatitis C or not, with Creatinine is identified as the most important parameter among all 5 parameters mentioned above.]]>
<![CDATA[Uncovering Legendary Coffee Shops in Pontianak Through Sentiment Analysis ]]>
<![CDATA[Salim, Ilucky]]>;
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ bit-Tech Vol. 7 No. 3 (2025): bit-Tech ]]>
Publisher : <![CDATA[Komunitas Dosen Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32877/bt.v7i3.2240
<![CDATA[Nowadays, coffee shops are scattered everywhere offering a variety of unique experiences to attract customers. Despite the rapid emergence of modern coffee shops, certain long-established coffee shops (often referred to as “legendary coffee shops”) continue to thrive and maintain a loyal customer base. The success of legendary coffee shops can be attributed to factors such as signature beverages, distinctive ambiance, and a strong word-of-mouth reputation. Unlike newer establishments that rely heavily on digital marketing, these coffee shops build trust and popularity over time. To further understand their influence, sentiment analysis can be applied to customer reviews of the coffee shops. This study analyzes two legendary coffee shops in Pontianak, namely Aming Coffee Shop and Asiang Coffee Shop to understand the key factors behind their sustainability despite strong competition using Naïve Bayes Method. The best accuracy for testing data at a 50:50 ratio was 76.76%, while training data reached 96.16%. The resulting precision and recall values are 96.16% and 78.81%. This study employs N-gram 3 model to identify the top words of both coffee shops. The findings indicates that both coffee shops are well-known for their signature milk coffee and unique flavor beverages that resonate with the local community. Aming Coffee Shop attracts young customers with affordable prices, while Asiang Coffee Shop maintains its traditional coffee shop ambiance, appealing to customers seeking nostalgia. From these two case studies, it is evident the success of a coffee shop is highly influenced by taste, branding, and customer experience.]]>
<![CDATA[Perancangan Sistem Pakar Penyakit Demam Berdarah Menggunakan Metode Gradient Boosting Decision Tree ]]>
<![CDATA[Valentina, Cecilia]]>;
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ MDP Student Conference Vol 4 No 1 (2025): The 4th MDP Student Conference 2025 ]]>
Publisher : <![CDATA[Universitas Multi Data Palembang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35957/mdp-sc.v4i1.11200
<![CDATA[Dengue fever is a disease transmitted through mosquito bites and can cause high death rates in several countries . This disease is most commonly found in countries with a tropical climate. Therefore, technology utilization has been implemented to help people to predict dengue fever. This research design an expert system using the Gradient Boosting Decision Tree (GBDT) method to classification a symptoms of dengue fever. This research used a dataset from Kaggle website and this data was analyzed and resulted in accuracy of 89%, a recall of 88,79%, and a precision of 69,96%. So, it was able to provide an accurate prediction of dengue fever through the GBDT method. The classification result was then adapted into mobile based application with a UI/UX design so that it can directly interact with users.]]>
<![CDATA[Perancangan UIUX Aplikasi Pemantau Kelembaban Tanah dan Suhu Udara Pada Tanaman Buah Naga ]]>
<![CDATA[Sabila, Qolbi Sin]]>;
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ MDP Student Conference Vol 4 No 1 (2025): The 4th MDP Student Conference 2025 ]]>
Publisher : <![CDATA[Universitas Multi Data Palembang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35957/mdp-sc.v4i1.11201
<![CDATA[The increase in the number of dragon fruit commodities is greatly influenced by the growth and quality of the plant itself. Soil moisture and air temperature are the main factors that must be considered by farmers in the cultivation of dragon fruit plants. There is a need for regular monitoring of dragon fruit plants to maximize the growth of these plants. This research aims to design a User Interface (UI) display for the application of monitoring soil moisture and air temperature in dragon fruit plants. This application is based on Android to be more flexible when used. This monitoring application is supported by the use of IoT technology sensor devices connected to a microcontroller, this application can present real-time data about plant conditions, such as soil moisture levels and air temperature in a visual form that is easy to understand for users. The result of this research is a UI design with ease of providing information to users so that it can enable users to improve decision-making accuracy in monitoring soil moisture and air temperature in dragon fruit plants. This is expected to have a positive impact on the productivity of users in caring for dragon fruit plants and can maintain the quality of the harvest.]]>
<![CDATA[Beauty Product Recommendation from Customer Reviews Based on Multinomial Naïve Bayes Algorithm ]]>
<![CDATA[Therence, Claretty]]>;
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ Informatics and Digital Expert (INDEX) Vol. 7 No. 1 (2025): INDEX, Mei 2025 ]]>
Publisher : <![CDATA[LPPM Universitas Perjuangan Tasikmalaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.36423/index.v7i1.2208
<![CDATA[The cosmetic industry’s increasing dependence on online platforms makes understanding customer sentiment essential for brand success. The study addresses the challenge of understanding customer sentiment regarding concealer brands on the Shopee platform, a critical aspect for brand managers and consumers alike. The problem stems from the vast amount of reviews that can be overwhelming for stakeholders looking to extract actionable insights. To solve this, we applied a Naïve Bayes classification approach with a Bag of Words (BoW) model to analyze a dataset containing 3,920 customer reviews. This dataset was divided into 1,120 training samples and 280 testing samples of each of 10 brands, following an 80:20 ratio. The analysis yields recurring positive and negative sentiment themes, achieving test accuracy of 87.95% and a training accuracy of 94.31%. Findings reveal key consumer preferences and lead to specific product recommendations, such as Mad For Makeup and Luxcrime for high coverage, Guele for lightweight formulas. Additionally, tailored marketing strategies like enhancing packaging and engaging with consumers through social media are suggested. This research provides actionable insights for brand managers, contributing to sentiment analysis literature in the cosmetics sector.]]>
<![CDATA[Pengaruh Jenis Stopwords terhadap Akurasi Model Multinomial Naïve Bayes dalam Proses Sentimen Analisis ]]>
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ Jurnal Buana Informatika Vol. 16 No. 01 (2025): Jurnal Buana Informatika, Volume 16, Nomor 01, April 2025 ]]>
Publisher : <![CDATA[Universitas Atma Jaya Yogyakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Implementing machine learning in business has enabled producers and sellers to assess product quality by analyzing customer reviews through Sentiment Analysis (SA). This study investigates the impact of different stopword categories on the accuracy of the Multinomial Naïve Bayes (MNB) model for SA. This research considered ten stopword categories: general, conjunctions, slang, temporal terms, nouns, pronouns, interjections, adverbs, and single-letter words. A Friedman test conducted on commentary from three shoe products revealed that removing conjunction stopwords (MNB-conjunction) could potentially improve the predictive accuracy of the MNB model for SA by approximately 1%. A T-test further validated this result, showing that two out of three datasets provided evidence that MNB-conjunction outperformed the MNB model without removing stopwords.]]>
<![CDATA[Prediksi Safety Stock Penjualan Produk Pakaian Berbasis Model DR-ARIMA (Studi Kasus: Veruby Store) ]]>
<![CDATA[Verita, Nengsy]]>;
<![CDATA[Tjen, Jimmy]]>
<![CDATA[ Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 14, No 2: Agustus 2025 ]]>
Publisher : <![CDATA[STMIK Banjarbaru ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35889/jutisi.v14i2.2854
<![CDATA[Effective inventory management has become a crucial aspect in the fashion retail industry, especially in responding to fluctuating demand. This study aimed to predict safety stock needs using the DR-ARIMA (3,0,6) model, an enhancement of ARIMA that considers demand response and error analysis. Predictions were validated with Root Mean Square Error and used to establish lower and upper sales projection limits for safety stock calculation. The model demonstrated good accuracy for product categories with stable sales patterns such as tops, while showing limitations in categories with more volatile demand like bottoms. These findings highlight the imporantance of integrating trend analysis and customer behavior data to develop more adaptive and responsive stock management strategies amid market dynamics. Key Words: Safety Stock; ARIMA; Demand Response; Fashion Retail AbstrakPengelolaan persediaan yang efektif menjadi aspek penting dalam industri riteal fashion, terutama dalam menghadapi permintaan yang fluktuatif, penelitian ini bertujuan memprediksi kebutuhan safety stock menggunakan model DR-ARIMA (3,0,6), yang merupakan pengembanagn dari ARIMA yang memperhitungkan respon permintaan dan analisis kesalahan. Hasil prediksi divalidasi dengan Root Mean Square Error dan digunakan untuk menentukan batas bawah dan atas proyeksi penjualan sebagai dasar penentuan safety stock. Model menunjukkan tingkat akurasi yang baik untuk kategori produk dengan pola penjualan stabil seperti atasan, namun memiliki keterbatasan dalam kategori dengan pola permintaan fluktuatif seperti bawahan. Temuan ini menegaskan pentingnya integrase analisis tren dan data perilaku pelanggan demi pengelolaan stok yang lebih adaptif dan responsif terhadap dinamika pasar. ]]>
<![CDATA[Prediksi Safety Stock Produk Filter Oli Sepeda Motor Berbasis Demand Response (DR) - ARMA ]]>
<![CDATA[Tendean, Sandi]]>;
<![CDATA[Tjen, Jimmy]]>;
<![CDATA[Iskandar, Riyadi Jimmy]]>
<![CDATA[ bit-Tech Vol. 8 No. 1 (2025): bit-Tech ]]>
Publisher : <![CDATA[Komunitas Dosen Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32877/bt.v8i1.2282
<![CDATA[Manajemen rantai pasokan merupakan hal krusial yang dibutuhkan dalam menjaga persediaan suatu produk supaya tetap tersedia selama masa tunggu. Hal ini bertujuan untuk menjaga keberlanjutan suatu bisnis sehingga penjualan produk tersebut tidak terganggu dengan permasalahan kurangnya persediaan. Namun, metode prediksi konvensional seperti ARMA-klasik dan ARMA-GARCH seringkali kurang akurat pada data riil yang bersifat sparse yang didominasi nilai nol dan fluktuatif. Penelitian ini bertujuan untuk menggagas sebuah metode Auto Regressive Moving Average (ARMA) baru yang menggabungkan konsep demand response dengan analisis galat yang bernama Demand Response-ARMA (DR-ARMA). Metode ini dikembangkan melalui tiga tahap, yaitu penurunan matematis berbasis RMSE dan analisis tren, adaptasi model untuk data sparse, dan validasi menggunakan data primer penjualan sparepart filter oli dari CV di Kalimantan Barat selama 60 hari. DR-ARMA mengoptimasi prediksi ARMA berdasarkan pada tren penjualan serta mengontrol ketidakpastian prediksi dengan memanfaatkan analisis galat, supaya kesalahan prediksi dapat berkurang selama perhitungan safety stock. Simulasi numerik dilakukan pada data penjualan filter oli dari sebuah perusahaan yang ada di Kalimantan Barat. Hasil simulasi menunjukkan bahwa metode DR-ARMA dapat memprediksi penjualan filter oli dengan akurasi 80%, lebih tinggi dibandingkan metode prediksi lainnya seperti ARMA-Generalized Auto Regressive Conditional Heteroskedasticity (GARCH) (74%) dan ARMA-klasik (57%). Metode DR-ARMA juga dapat digunakan untuk memprediksikan safety stock untuk 60 hari kedepan dengan tingkat kesalahan prediksi sekitar 17%. Hal ini menunjukkan bahwa metode DR-ARMA cocok digunakan untuk memprediksikan safety stock dari data yang bersifat sparse. Metode DR-ARMA dapat membantu pengguna dalam mengatur jumlah persediaan barang yang dibutuhkan tanpa perlu melakukan pengisian gudang secara berlebihan.]]>
