Jurnal Informatika dan Teknologi Komputer ( J-ICOM)

Sistem Kontrol Dan Monitoring Budidaya Jamur Tiram Berbasis Iot Menggunakan Metode Fuzzy Logic Tsukamoto

Chicha Rizka Gunawan — 2026-10-01

Oyster mushroom cultivation requires stable temperature and air humidity to support growth. In the study location, environmental control was still performed manually, making consistent control difficult. This study developed an Internet of Things (IoT)-based control and monitoring system using the Tsukamoto fuzzy logic method. The system uses a DHT22 sensor to measure temperature and humidity, a Wemos D1 Mini as the controller, and a fan and humidifier as actuators. Sensor data are processed using fuzzy membership, rule inference, and defuzzification to determine actuator control, while monitoring data are delivered to a web interface. Testing was conducted using a prototype in Limau Mungkur Village, Pematang Jaya District, Langkat Regency, North Sumatra, with observations over 20 days. The system produced an average temperature of 25.1 °C and average humidity of 85.6%. Ten representative control tests were classified as appropriate, resulting in 100% agreement between the system decisions and the defined ideal cultivation conditions. The implementation demonstrates that the IoT and Tsukamoto fuzzy logic approach can automate environmental monitoring and control for oyster mushroom cultivation.

Analisis Kinerja Kendali Fuzzy PID pada Sistem Pengendalian Level Deaerator Menggunakan Matlab

arsy febrina dewi — 2026-10-01

A deaerator is a boiler component responsible for removing oxygen and other gases from the water used to generate steam. Steam is used to heat the water and strip away dissolved gases—such as oxygen (O2) and carbon dioxide (CO2)—that could otherwise cause corrosion within the boiler system. Deaerator control affects both water heating and liquid levels; therefore, it is necessary to develop a simulation system for deaerator level control using MATLAB. The process involves establishing a level setpoint and modeling the deaerator, followed by determining the PID parameters (Kp, Ki, and Kd) and designing the fuzzy controller. Subsequently, simulations are conducted in MATLAB to evaluate system responses, including rise time, settling time, overshoot, and steady-state error. Based on the test results, it can be concluded that both Fuzzy-PID and conventional fuzzy controllers are capable of tracking setpoint changes and maintaining the level at a steady state with near-zero steady-state error. The Fuzzy-PID controller demonstrates a faster response to setpoint changes compared to the conventional fuzzy controller, although it exhibits slightly higher overshoot and undershoot during these transitions. In contrast, the conventional fuzzy controller provides a smoother response with smaller transient deviations but requires more time to reach a steady state.

Penerapan Teknologi Digital di Bank Sampah

nia_78 Sumarni — 2026-10-01

Digital transformation has created new opportunities to improve community-based waste management through the use of information technology. In Indonesia, waste banks have begun adopting website-based systems to support administrative recording, information sharing, and digital management of waste transactions. However, the success of such technological innovations largely depends on how community members perceive and accept the technology. This study aims to analyze the factors influencing the acceptance of digital technology in community-based waste bank management using the Technology Acceptance Model (TAM). A quantitative approach was employed using a survey of 90 members of the Arga Tirta Waste Bank in North Bengkulu. It analyzed using descriptive statistics and multiple linear regression. The results show that attitude toward use (β = 0.355) and perceived usefulness (β = 0.250) have positive and significant effects on behavioral intention to use. In contrast, perceived ease of use (β = 0.0840) does not significantly influence users’ intention to adopt the technology. The model explains only 12.2% of the variance in behavioral intention, indicating limited explanatory power. These findings suggest that technology adoption in rural community contexts is not solely determined by technical aspects such as system usability. Social perceptions, collective attitudes, and institutional support may play more substantial roles in shaping users’ willingness to adopt digital systems. This study contributes to the literature by demonstrating the limited explanatory capacity of TAM in community-based environmental management and highlighting the importance of social and contextual factors in shaping digital technology adoption in rural waste management initiatives.

Web edukasi anti-bullying PT Atma Nirvana Indonesia meningkatkan kesadaran sosial mahasiswa

shendy — 2026-10-01

Perkembangan teknologi informasi telah mengubah paradigma penyebaran nilai edukasi melalui platform digital yang menghubungkan dokumen secara global. Penelitian ini bertujuan untuk mengembangkan sebuah website edukasi anti-bullying bagi PT. Atma Nirvana Indonesia sebagai instrumen untuk meningkatkan kesadaran sosial di kalangan mahasiswa. Latar belakang penelitian ini didasari oleh masih maraknya fenomena perundungan di lingkungan perguruan tinggi serta minimnya media literasi digital yang spesifik menangani masalah preventif tersebut. Untuk menghasilkan sistem yang berkualitas dan terstruktur, penelitian ini menerapkan metode pengembangan Waterfall yang mencakup tahapan analisis, desain, pengodean, hingga pengujian sistem secara berurutan. Metode ini menjamin setiap fitur edukatif dapat diimplementasikan sesuai dengan kebutuhan pengguna sasaran. Hasil penelitian menunjukkan bahwa website edukasi yang dikembangkan mampu berfungsi sebagai media interaktif yang efektif dalam menyajikan konten pencegahan perundungan. Melalui integrasi modul materi dan kanal informasi yang sistematis, platform ini terbukti dapat meningkatkan pemahaman dan empati sosial mahasiswa. Kesimpulannya, pengembangan web edukasi ini tidak hanya menjadi solusi teknologi bagi PT. Atma Nirvana Indonesia, tetapi juga menjadi sarana strategis dalam menciptakan ekosistem kampus yang lebih sehat, aman, dan bebas dari tindakan perundungan di era transformasi digital saat ini

Rancang Bangun Sistem Point of Sales Berbasis Web Terintegrasi Laporan Keuangan dan Pengeluaran Operasional

raju — 2026-10-01

Efisiensi operasional dan akurasi manajemen keuangan merupakan faktor krusial dalam keberlanjutan usaha retail, termasuk pada Toko Astea Lampung Utara. Namun, saat ini Toko Astea masih menghadapi kendala dalam pengelolaan administrasi yang belum terintegrasi, di mana pencatatan pengeluaran operasional dan perhitungan laba bersih masih dilakukan secara konvensional. Hal ini mengakibatkan risiko selisih data yang tinggi dan terhambatnya penyusunan laporan keuangan yang valid. Penelitian ini bertujuan untuk merancang dan mengimplementasikan Sistem Informasi Point of Sales (POS) berbasis web yang mampu mengintegrasikan data transaksi dengan laporan keuangan dan pengeluaran operasional secara otomatis. Metode pengembangan sistem yang digunakan adalah metode Waterfall, yang dipilih karena sifatnya yang sistematis dan terstruktur, mulai dari analisis kebutuhan hingga tahap implementasi. Pendekatan ini memastikan setiap logika perhitungan akuntansi dirancang dengan matang guna menjamin akurasi data finansial. Hasil penelitian ini berupa platform digital yang memudahkan proses transaksi kasir sekaligus menyediakan laporan laba rugi secara real-time. Dengan implementasi sistem ini, Toko Astea Lampung Utara dapat memantau arus kas secara transparan dan melakukan pengambilan keputusan manajerial dengan lebih cepat. Digitalisasi ini diharapkan mampu meningkatkan profesionalisme manajemen toko dan efisiensi kerja dalam jangka panjang

Website E-Katalog Tapis Lampung Terintegrasi QR Code Untuk Pemasaran Produk Craftina

ovi — 2026-10-01

Perkembangan teknologi informasi menuntut pelaku usaha untuk mengadopsi media pemasaran digital yang cepat dan efisien. Produk Tapis Lampung sebagai warisan budaya bernilai tinggi memerlukan platform modern agar tetap kompetitif di pasar global. Salah satu solusi inovatif adalah pemanfaatan website sebagai media e-katalog yang terintegrasi dengan teknologi QR Code untuk menjembatani informasi fisik dan digital secara instan. Permasalahan yang dihadapi Craftina adalah masih terbatasnya media promosi dan penyampaian informasi produk kepada konsumen sehingga jangkau pemasaran belum optimal. Proses pemasaran saat ini masih bersifat konvensional sehingga calon pembeli sulit mendapatkan detail produk dan informasi stok secara real-time. Untuk mengatasi permasalahan ini, dilakukan pengembangan sistem informasi e-katalog menggunakan metode Waterfall. Tahapan penelitian dimulai dari analisis kebutuhan, perancangan sistem, hingga implementasi menggunakan bahasa pemrograman PHP dan basis data MySQL guna memastikan sistem berjalan stabil dan terstruktur. Hasil pengujian black box testing menunjukan seluruh fungsi sistem berjalan sesuai dengan kebutuhan pengguna. Penelitian menunjukkan bahwa sistem informasi e-katalog berbasis website berhasil mempermudah proses pemasaran pada Craftina. Melalui fitur QR Code, konsumen dapat mengakses spesifikasi produk secara mandiri dan cepat melalui perangkat seluler. Implementasi ini tidak hanya meningkatkan profesionalisme manajemen Craftina dalam mengelola data produk, tetapi juga memberikan pengalaman berbelanja yang lebih informatif dan modern bagi pelanggan.

Analisis dan Perancangan Sistem Informasi Manajemen Pet Grooming Berbasis Web

yuyun — 2026-10-01

Industri perawatan hewan peliharaan saat ini mengalami pertumbuhan pesat, namun manajemen operasional pada Bondi Pet Shop masih menghadapi kendala akibat penggunaan sistem manual. Permasalahan utama meliputi ketidakteraturan penjadwalan grooming yang memicu terjadinya double booking, serta risiko kesalahan pada rekapitulasi laporan keuangan. Penelitian ini bertujuan untuk menghasilkan sistem informasi manajemen pet grooming berbasis web yang terintegrasi sebagai solusi digital bagi Bondi Pet Shop. Metode pengembangan sistem yang digunakan adalah Waterfall, yang mencakup tahapan analisis kebutuhan, perancangan sistem, implementasi melalui pengkodean, pengujian, serta pemeliharaan. Tahap analisis dilakukan untuk memetakan kebutuhan fungsional seperti manajemen data pelanggan, fitur booking layanan, dan pengolahan grooming digital. Perancangan sistem dimodelkan menggunakan Unified Modeling Language (UML) untuk memberikan struktur aplikasi yang jelas. Hasil penelitian menunjukkan bahwa sistem informasi ini mampu mengotomatisasi proses bisnis, meminimalisir kesalahan manusia dalam pencatatan data, serta memudahkan pemilik dalam memantau laporan pendapatan secara real-time. Dengan implementasi sistem ini, Bondi Pet Shop dapat meningkatkan efisiensi operasional dan kualitas pelayanan kepada pelanggan secara signifikan

Pengembangan Sistem Informasi Rencana Kerja Pembangunan Infrastruktur Desa Batu Raja

krisna — 2026-10-01

Penyusunan Rencana Kerja Pemerintah Desa (RKPDesa) merupakan agenda tahunan krusial dalam menentukan arah pembangunan desa, khususnya pada bidang infrastruktur. Namun, Desa Baturaja masih menghadapi kendala dalam pengelolaan data usulan yang konvensional, sehingga memicu risiko kehilangan berkas, redudansi data, dan lambatnya proses verifikasi kelayakan proyek. Penelitian ini bertujuan untuk mengembangkan Sistem Informasi Penyusunan RKPDesa berbasis web yang dikhususkan pada bidang pembangunan infrastruktur guna meningkatkan efisiensi dan transparansi administrasi. Metode pengembangan perangkat lunak yang digunakan adalah metode Waterfall, Pemilihan metode ini didasarkan pada karakteristik kebutuhan sistem yang telah terdefinisi secara jelas sejak awal berdasarkan regulasi pemerintah. Pengujian sistem dilakukan menggunakan metode Black-Box Testing untuk memastikan seluruh fungsi penyerapan usulan, validasi, anggaran, hingga cetak dokumen berjalan dengan baik. Hasil penelitian menunjukkan bahwa sistem informasi ini berhasil memangkas waktu birokrasi, meminimalkan kesalahan rekapitulasi data, serta mempermudah aparatur desa dalam menyusun laporan perencanaan secara akurat dan real-time. Penerapan teknologi ini terbukti mampu mengoptimalkan tata kelola pemerintahan Desa Baturaja menuju digitalisasi administrasi yang lebih akuntabel

Sistem pendukung keputusan berbasis web dengan metode MOORA untuk pemilihan pestisida tanaman singkong

hadi — 2026-10-01

Tanaman singkong merupakan komoditas utama di Gapoktan Mulang Maya yang sering menghadapi kendala serangan hama dan penyakit. Keterbatasan pengetahuan petani dalam memilih pestisida yang tepat, efektif, dan ekonomis sering kali memicu kerugian finansial akibat pemilihan produk yang masih bersifat intuitif dan subjektif. Penelitian ini bertujuan untuk membangun Sistem Pendukung Keputusan (SPK) pemilihan pestisida tanaman singkong berbasis web guna memberikan rekomendasi yang objektif. Metode yang digunakan dalam komputasi SPK ini adalah Multi-Objective Optimization on the basis of Ratio Analysis (MOORA), yang mampu mengoptimalkan multikriteria yang saling bertentangan, seperti efektivitas obat (benefit) dan harga (cost). Pengembangan sistem dirancang menggunakan metode Waterfall, yang meliputi tahapan analisis kebutuhan, desain sistem, pengkodean, hingga pengujian. Sistem berbasis web ini diimplementasikan menggunakan bahasa pemrograman PHP dan basis data MySQL. Hasil penelitian menunjukkan bahwa penerapan metode MOORA dalam sistem ini berhasil menyaring dan mengurutkan alternatif pestisida terbaik berdasarkan bobot kriteria yang telah ditentukan. Berdasarkan pengujian sistem, aplikasi ini dinilai fungsional, adaptif, serta layak digunakan sebagai alat bantu bagi pengurus dan petani di Gapoktan Mulang Maya dalam mengambil keputusan pemilihan pestisida secara cepat, akurat, dan efisien

Deteksi Pencurian Listrik pada Data Smart Meter Menggunakan Pembelajaran Mesin

Rafli Alfian — 2026-10-01

Electricity theft is a primary source of non-technical losses (NTL) in power distribution systems, causing substantial economic damage to utilities. This study develops a machine learning approach to detect electricity theft using real smart meter data from the State Grid Corporation of China (SGCC), comprising 42,372 consumers over 1,034 days with an 8.53% theft rate. Nineteen statistical features were engineered from the daily consumption profiles after handling 25.64% missing values through linear interpolation and outliers through the three-sigma rule. Four classifiers, namely Logistic Regression, Decision Tree, Random Forest, and histogram-based Gradient Boosting, were trained with the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance and evaluated on a stratified hold-out set. The Gradient Boosting model achieved the best performance with an ROC-AUC of 0.750, an F1-score of 0.323, and a recall of 0.416, outperforming the other classifiers, while cross-validation confirmed the stability of the results. Feature importance analysis revealed that the missing-data ratio, the low-consumption ratio, and the longest zero-consumption run are the most discriminative indicators of theft. The results show that statistical feature engineering combined with ensemble learning provides an effective and computationally efficient method for electricity theft detection in smart grids.

Klasifikasi Kepuasan Pelanggan pada Layanan Servis Otomotif Menggunakan Naive Bayes: Studi Kasus di PT AUTO2000 Sukun Malang

Vanesa Putri Maya Hasyim — 2026-10-01

Customer satisfaction serves as a crucial indicator for assessing the quality of after sales services. PT AUTO2000 Sukun routinely gathers customer feedback through satisfaction surveys. However, the manual evaluation process is both time consuming and susceptible to subjective judgment. This study seeks to classify customer satisfaction based on customer comments using the Multinomial Naive Bayes algorithm. The dataset comprises 108 customer reviews accompanied by manually assigned positive and negative sentiment labels. The research procedure consisted of text preprocessing, including case folding, tokenization, stopword removal, and stemming, followed by feature extraction using Term Frequency Inverse Document Frequency (TF IDF). The dataset was then divided into 70% training data and 30% testing data. Synthetic Minority Over sampling Technique (SMOTE) was applied exclusively to the training data to alleviate class imbalance. Model performance was assessed using accuracy, precision, recall, F1 score, and a confusion matrix. The findings reveal that the Multinomial Naive Bayes algorithm attained an accuracy of 76 percent. For the negative class, the model achieved a precision of 79%, a recall of 86%, and an F1 score of 83%. For the positive class, it obtained a precision of 67%, a recall of 55%, and an F1 score of 60%. These findings suggest that the Multinomial Naive Bayes algorithm exhibits satisfactory capability in classifying customer satisfaction. Nevertheless, the model still encounters challenges in accurately recognizing all instances belonging to the positive class.

Sistem Pakar Deteksi Gangguan Konsentrasi Belajar Siswa Menggunakan Metode Certainty Factor

Efri Gresinta — 2026-10-01

This study aims to develop a web-based expert system to detect learning concentration disorders in students using the Certainty Factor method. The research was conducted at SDN Baru 06 Pagi Pasar Rebo, focusing on 62 third-grade students. The absence of a counseling teacher or child psychologist at the school makes the identification process rely heavily on the teachers subjective intuition. The system uses 15 behavioral symptoms categorized into three dimensions: inattention, hyperactivity, and impulsivity. The expert knowledge base (CFpakar) was formulated through a Focus Group Discussion (FGD) with third-grade teachers. The Certainty Factor algorithm combines expert confidence and user input to calculate the CF value per dimension and the final combined CF, classifying the severity into five categories: Not Indicated, Mild, Moderate, Severe, and Very Severe. The results show that the system successfully calculates the confidence level of the disorder, provides dimension-specific diagnostic profiles, and generates printable reports via DomPDF. This system assists teachers in identifying students concentration issues systematically and designing appropriate learning interventions.

Implementasi Data Mining Dengan Metode Apriori Dalam Menentukan Pola Pembelian Obat

akbar hulalata — 2026-10-01

This research was conducted based on the large amount of pharmacy drug sales transaction data that has not been optimally utilized as a source of information to support decision-making. The study aims to implement the Apriori algorithm on drug purchase transaction data at Seruni Pharmacy to identify consumer purchasing patterns and support decision-making processes. The data used consisted of 13,068 drug sales transactions from 2021–2025, with 12,700 transactions analyzed after the preprocessing stage. The analysis process was carried out using RapidMiner with a minimum support value of 10% and a minimum confidence value of 60%. The results of the study produced 140 association rules indicating relationships between drug purchase products. One of the rules with the highest confidence value of 99% showed that consumers who purchased herbal products, medical devices, and wound care products also tended to purchase topical ointment cream simultaneously. In addition, associations were found between generic prescription drugs and limited over-the-counter drugs with confidence values of 71% and 78%, respectively. Based on these results, the Apriori algorithm was proven effective in identifying drug purchasing patterns and can be utilized to support inventory management, product arrangement, and promotional and marketing strategies at Seruni Pharmacy.

Analisis Pemanfaatan Tools Forensik dalam Investigasi Credential Phishing pada Discord Web Menggunakan Metode OSCAR

ZULKI RIVAI — 2026-10-01

Credential phishing on Discord Web can generate digital traces across browser storage and network traffic, requiring appropriate forensic tools according to the characteristics of each evidence source. This study analyzes the utilization of forensic tools in investigating credential phishing on Discord Web using the OSCAR method, consisting of Obtain, Strategize, Collect, Analyze, and Report. A controlled experimental scenario was conducted using a phishing domain represented in browser and network artifacts as xn--dscord-waa.online. FTK Imager was used to acquire the browser profile, while DB Browser for SQLite, Autopsy, and Wireshark were used for artifact examination. The results show that DB Browser for SQLite identified the phishing URL in browser History, Discord-related cookies, email, and username, while no phishing-domain cookie or saved login data was found. Autopsy identified the phishing domain, login.html, email, and username in browser storage artifacts. Wireshark identified DNS resolution, the phishing server IP address, and TLS SNI associated with the phishing domain and official Discord services. The findings demonstrate that each tool contributes different evidence according to the source and characteristics of the artifacts. The OSCAR method provides a structured workflow for positioning and utilizing forensic tools throughout the investigation.

Performance Analysis of the Apriori Algorithm in Identifying Product Purchase Patterns in Transaction Data

Sri Hartati Hartati — 2026-10-01

Republik Computer Slawi frequently faces inventory imbalances, characterized by stockouts for some products and overstocking for others. This study aims to analyze the performance of the Apriori algorithm in identifying product purchasing patterns to serve as a basis for data-driven decision-making. The analysis was conducted on 1,399 sales transaction records using RapidMiner, with a minimum support of 5% and a minimum confidence of 60%. The results demonstrate that the Apriori algorithm successfully generated frequent itemsets—up to 3-itemsets—and produced 10 association rules with confidence values ranging from 0.855 to 0.981. The "Mouse" product exhibited the highest support value at 0.773, while the combination of "Mouse" and "Laptop Bag" showed the highest support among 2-itemsets at 0.662. Performance metrics yielded an RMSE of 0.060 and a Squared Error of 0.004, indicating a low level of prediction error for the model. Consequently, the Apriori algorithm proves effective in identifying purchasing patterns and can be utilized to support more optimal inventory management at Republik Computer Slawi.