Search

Penyakit paru-paru, seperti pneumonia dan kanker paru-paru, menjadi masalah kesehatan global dengan tingkat kematian tinggi, terutama dipengaruhi oleh polusi udara, infeksi, dan kebiasaan merokok. Pencegahan dan deteksi dini sangat penting dalam mengurangi dampaknya. Algoritma yang digunakan dalam penelitian ini meliputi Random Forest, XGBoost, dan Logistic Regression. Tujuannya yaitu untuk membandingkan performa tiga algoritma machine learning dalam mengklasifikasikan penyakit paru-paru menggunakan metrik evaluasi seperti, akurasi, presisi, recall, dan F1-score. Setelah hyperparameter tuning, XGBoost menunjukkan hasil terbaik dengan akurasi 94,44%, presisi 94,98%, recall 94,44%, dan F1-score 94,41%, menunjukkan keseimbangan optimal antara presisi dan recall. Random Forest juga memberikan hasil yang sebanding dengan XGBoost dengan akurasi dan presisi yang tinggi. Sementara itu, Logistic Regression menunjukkan keterbatasan dalam menangani data yang kompleks, dengan performa yang lebih rendah pada seluruh metrik evaluasi. Penelitian ini menunjukkan bahwa algoritma berbasis pohon keputusan seperti XGBoost dan Random Forest lebih unggul untuk klasifikasi penyakit paru-paru, menjadikannya metode yang lebih andal untuk mendukung deteksi dini penyakit ini. Kata kunci: Hyperparameter Tuning, Logistic Regression, Penyakit Paru-paru, Random Forest, XGBoost.

Tata kelola Teknologi Informasi (TI) adalah kerangka kerja yang digunakan organisasi untuk mengelola dan mengendalikan sumber daya TI secara efektif, dengan tujuan memaksimalkan nilai bisnis. PT. Kobexindo Tractor TBK menghadapi tantangan dalam mengoptimalkan manajemen TI mereka, khususnya dalam pengelolaan data penting. Penelitian ini bertujuan untuk menerapkan kerangka COBIT 2019 guna meningkatkan tata kelola TI di PT. Kobexindo Tractor TBK, sehingga layanan data kritis dapat dikelola secara efisien. Temuan menunjukkan bahwa perusahaan belum melakukan penilaian menyeluruh terhadap tata kelola TI dan menghadapi tantangan dalam manajemen data pesanan dan informasi stok. PT. Kobexindo Tractor TBK memerlukan proses tata kelola TI yang lebih terstruktur untuk memastikan penggunaan teknologi yang efektif dan efisien dalam mencapai tujuan bisnis. Proses tinjauan pustaka mengidentifikasi kesenjangan dalam penelitian saat ini, memberikan dasar untuk penelitian yang lebih komprehensif. Setelah analisis tujuan BAI05 dan BAI11, ditemukan hasil yang berbeda. Pada BAI05, pertanyaan mencapai level 2 dengan 75%, di bawah 85%. Demikian juga, pada BAI11, pertanyaan mencapai level 2 dengan 66%. Dengan temuan ini, penelitian ini didukung landasan teoretis yang kuat, memastikan analisis yang mendalam terhadap masalah tata kelola TI. Kata kunci: Tata Kelola Teknologi Informasi, COBIT 2019, Manjemen Informasi

Kekurangan gizi menjadi masalah dalam tumbuh kembang anak yang dapat menyebabkan stunting, wasting, mudah terkena penyakit serta penurunan kecerdasan otak dan mental. Stunting di Kabupaten Sikka pada tahun 2022 sebesar 13,8% dari hasil e-PPGBM periode Bulan Agustus 2022. Untuk mengatasi masalah ini diperlukan klasifikasi status stunting yang sangat berpengaruh terhadap tumbuh kembang anak sehingga dapat memberikan perhatian lebih dari faktor stunting yang paling tinggi di suatu daerah. Dengan bertambahnya jumlah balita dan peningkatan kasus stunting, proses penyelesaian tidak bisa dilakukan dengan cepat. Selain itu, tidak semua petugas posyandu bisa menghitung status gizi balita secara manual. Oleh karena itu, agar orang tua dan kader posyandu dapat mengetahui kondisi anak lebih cepat, diperlukan sistem yang menggunakan model algoritma C4.5. Sistem ini mampu mengolah data numerik (kontinu) dan diskrit. Penelitian ini menggunakan 5 atribut, yaitu usia, inisiasi menyusui dini (Imd), tinggi badan, jenis kelamin, dan berat badan. Keistimewaan penelitian ini adalah penggunaan atribut Inisiasi Menyusui Dini (IMD) yang belum pernah digunakan dalam penelitian sebelumnya dengan data numerik. Penggunaan algoritma C4.5 untuk menganalisis hasil stunting dan menyajikannya dalam bentuk website menghasilkan tingkat akurasi yang tidak jauh berbeda dengan pembagian data latih dan data uji sebesar 92.68 dan 90.98% dengan Max Dept 10. Kata kunci: Algoritma C4.5, Stunting, Balita, Klasifikasi, Website

Pada perumahan padat penduduk, ruang terbatas menjadi salah satu tantangan utama bagi penghuni dalam melakukan aktivitas sehari-hari, termasuk dalam proses menjemur pakaian. Jemuran konvensional sering kali memakan ruang yang signifikan dan kurang efisien saat kondisi cuaca berubah tiba-tiba, seperti hujan atau kekurangan sinar matahari. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem jemuran pakaian otomatis berbasis Arduino Nano yang dapat dioperasikan secara mandiri untuk memaksimalkan penggunaan ruang dan meningkatkan efisiensi pengeringan pakaian. Sistem ini dilengkapi dengan sensor hujan dan sensor cahaya yang secara otomatis mengendalikan pergerakan jemuran. Ketika terdeteksi hujan, jemuran akan ditarik secara otomatis untuk melindungi pakaian, dan akan kembali terbuka saat kondisi cuaca kembali cerah. Metode penelitian melibatkan desain perangkat keras dan perangkat lunak yang terintegrasi dengan Arduino Nano, serta pengujian performa sistem dalam berbagai kondisi cuaca. Hasil penelitian menunjukkan bahwa sistem jemuran otomatis ini berhasil berfungsi secara optimal dalam merespons perubahan cuaca, dengan waktu respons cepat dan penghematan ruang yang signifikan di area perumahan padat penduduk. Implementasi teknologi ini diharapkan dapat menjadi solusi praktis untuk meningkatkan kenyamanan penghuni dan efisiensi penggunaan ruang di hunian urban yang terbatas. Kata kunci: Jemuran Otomatis, Arduino Nano, Sensor Cuaca, Hunian Padat, Efisiensi Ruang.

Penelitian ini meningkatkan teknik backward chaining untuk diagnosis Demam Berdarah Dengue (DBD) dengan mengintegrasikan algoritma backtracking, dengan tujuan untuk meningkatkan efisiensi penelusuran gejala dan aturan dalam sistem pakar. Hasil eksperimen menunjukkan bahwa penggunaan backtracking secara signifikan mengurangi waktu pemrosesan dibandingkan dengan metode tanpa backtracking. Pada eksperimen yang melibatkan 3 aturan, waktu pemrosesan berkurang dari 168,50 ms menjadi 19,53 ms, sementara untuk 6 aturan, waktu pemrosesan turun dari 161,63 ms menjadi 20,88 ms. Demikian pula, dalam pengujian dengan 10 aturan, waktu pemrosesan menurun dari 161,68 ms menjadi 17,38 ms. Secara keseluruhan, integrasi algoritma backtracking meningkatkan efisiensi penelusuran rata-rata sebesar 88%, terbukti menjadi pendekatan yang sangat efektif, terutama dalam sistem pakar yang memiliki banyak aturan dan gejala. Kata kunci: Backward Chaining, Backtracking, Diagnosis DBD, Efisiensi

Kegagalan jantung (Heart Failure) merupakan salah satu penyebab utama kematian dan morbiditas secara global, dengan lebih dari 26 juta orang terdampak di seluruh dunia. Deteksi dini kegagalan jantung sangat penting untuk mencegah komplikasi yang lebih serius, namun diagnosis sering kali sulit dilakukan karena gejala yang tidak spesifik. Pembelajaran mesin (machine learning) telah banyak digunakan untuk membantu prediksi risiko kegagalan jantung melalui analisis data medis. Berbagai algoritma klasifikasi telah diimplementasikan dalam berbagai penelitian sebalumnya, namun belum ada konsensus mengenai algoritma terbaik. Penelitian ini bertujuan untuk melakukan komparasi performa beberapa algoritma klasifikasi dalam memprediksi gagal jantung, menggunakan dataset Heart Failure Prediction dari Kaggle. Algoritma yang diuji termasuk Logistic Regression, K-Nearest Neighbors (KNN), Decision Tree, Random Forest, GaussianNB, dan LightGBM. Hasil menunjukkan bahwa algoritma Random Forest memberikan performa terbaik dengan akurasi 95 persen, sedangkan algoritma KNN menunjukkan akurasi terendah sebesar 76 persen. Penelitian ini diharapkan dapat berkontribusi dalam pengembangan sistem pendukung keputusan klinis yang lebih baik untuk prediksi kegagalan jantung. Kata Kunci: Heart Failure, mesin pembelajaran algoritma klasifikasi

Peran E-Commerce dalam mendukung Program Digital Economi sangat dibutuhkan daerah kabupaten Gorontalo untuk membantu memperkuat ekonomi lokal dengan memfasilitasi akses ke pasar yang lebih luas, Urgensi Penelitian berdasarkan study literatur dan hasil observasi mengangakat permasalahan bahwa belum ada terdapat penelitian pengembangan aplikasi e-commerce khusunya hasil peternakan menggunakan Location Based serviced dengan metode havesine sehingga Penelitian ini bertujuan untuk membangun aplikasi E-Commerce Menggunakan integrasi Metode Location Based Service dengan Algoritma Haversisne berbasis Android pada pemasaran hasil Peternakan daerah kabupaten gorontalo sehingga dapat menawarkan solusi inovatif untuk menghubungkan peternak dengan konsumen melalui platform digital. Metode ini memanfaatkan layanan berbasis lokasi untuk menentukan jarak antara penjual dan pembeli secara akurat, memungkinkan optimalisasi distribusi hasil ternak dan pengiriman yang lebih efisien. Hasil pengembangan menunjukkan bahwa LBS dan algoritma Haversine mampu memberikan efisiensi dalam pengelolaan distribusi dan pemetaan pasar lokal dengan hasil perhitungan jarak tempuh mengunakan google Maps sejauh 23,3 km, sedangkan hasil menggunakan algoritma haversine lebih cepat yaitu 12,1 km, terdapat perbedaan jaarak tempuh sekitar 11 km. Platform ini juga meningkatkan akses pasar bagi peternak lokal, memberikan peluang pemasaran yang lebih baik, serta memperkuat ekosistem perdagangan hasil ternak berbasis digital. Kata kunci: E-Commerce; Peternakan; Location base Service; Haversine; Android

Pengamanan data dalam era digital menjadi semakin penting dengan meningkatnya kebutuhan untuk melindungi informasi sensitif. Penelitian ini mengimplementasikan algoritma Hill Cipher yang dimodifikasi dengan operasi modulo pada karakter ASCII untuk memperluas cakupan aplikasi metode kriptografi ini. Hill Cipher, yang secara klasik menggunakan alfabet dengan operasi modulo 26, dibatasi hanya pada huruf-huruf alfabet. Modifikasi yang diusulkan dalam penelitian ini menggunakan operasi modulo 256, yang mencakup seluruh karakter ASCII (0–255), termasuk huruf, angka, simbol, dan karakter khusus. Penelitian ini menggunakan matriks kunci berukuran 2 x 2 yang memastikan keamanan melalui perhitungan determinan yang tidak nol dan coprime dengan 256. Proses enkripsi dilakukan dengan mengalikan vektor yang mewakili nilai ASCII dari plaintext dengan matriks kunci, diikuti oleh operasi modulo 256 untuk memastikan hasilnya berada dalam rentang karakter ASCII yang valid. Hasil enkripsi berupa ciphertext kemudian dideskripsi dengan invers matriks kunci yang diperoleh melalui operasi invers modulo 256. Penelitian ini membuktikan bahwa Hill Cipher yang dimodifikasi dapat diterapkan secara efektif untuk pengamanan data modern berbasis teks, menghasilkan ciphertext yang aman dan plaintext yang dapat didekripsi dengan akurat. Kata kunci: Hill Cipher, ASCII, operasi modulo 256, enkripsi, dekripsi

Penelitian ini mengkaji penerapan Internet of Things (IoT) dalam sistem monitoring kesehatan melalui tinjauan literatur yang mendalam. Inovasi dalam perangkat wearable, platform cloud, dan algoritma analitik memungkinkan pengumpulan data fisiologis secara real-time, pemantauan jarak jauh, dan deteksi dini anomali kesehatan. Implementasi teknologi ini telah menunjukkan hasil yang menjanjikan, seperti akurasi tinggi dalam pengukuran parameter kesehatan, efektivitas dalam mendeteksi kondisi kritis, dan peningkatan akses terhadap perawatan kesehatan untuk populasi yang kurang terlayani. Namun, adopsi sistem monitoring kesehatan berbasis IoT menghadapi beberapa tantangan, termasuk keamanan data, interoperabilitas, dan validasi klinis. Untuk memaksimalkan potensi teknologi ini, penelitian masa depan perlu difokuskan pada penguatan keamanan dan privasi data pasien. Dengan memanfaatkan kemajuan teknologi seperti Artificial Intelligence (AI), Machine Learning (ML), dan integrasi Electronic Health Records (EHR), sistem monitoring ke6sehatan berbasis IoT dapat mencapai potensi penuh mereka dalam mentransformasi perawatan kesehatan dan memberdayakan individu untuk mengambil peran proaktif dalam mengelola kesehatan. Kata kunci: Catatan Kesehatan Elektronik, Internet of Things, Kecerdasan Buatan, Pembelajaran Mesin, Sistem Pemantauan Kesehatan.

Konsep Orientasi Pelanggan sangat penting bagi perusahaan untuk berkembang di era saat ini, dengan memanfaatkan teknologi untuk mendapatkan wawasan yang mendalam tentang perilaku pelanggan mereka. Salah satu alat teknologi tersebut adalah pembelajaran mesin, khususnya yang menggunakan pendekatan pemrosesan bahasa alami (NLP). Penelitian ini menggunakan lima algoritma yang berbeda dan menggabungkan berbagai metode untuk meningkatkan kinerja model machine learning. Melalui penerapan teknik-teknik seperti random over-sampling (ROS) dan ensemble learning, akurasi prediksi keseluruhan untuk kelas minoritas meningkat secara signifikan. Model ensemble yang diintegrasikan dengan ROS mencapai akurasi 0,90 dan mean square error 0,91, mengungguli algoritma lain yang diuji dalam penelitian ini. Pendekatan yang dioptimalkan ini tidak hanya menunjukkan keefektifan pemanfaatan teknologi untuk sebuah perusahaan dapat menerapkan strategi yang berpusat pada pelanggan, tetapi juga menyoroti pentingnya peningkatan metodologi dalam pemodelan prediktif untuk keberlanjutan bisnis. Kata kunci: Klasifikasi Emosi, Pembelajaran Mesin, Pemrosesan Bahasa Alami, Hard Voting, Random Over Sampling.

K-Means dan K-Medoids digunakan untuk menilai indikator sosial ekonomi dan kesehatan di Provinsi Jawa Timur tahun 2023 melalui metode klasterisasi. Dengan menggunakan Principal Component Analysis (PCA) untuk mereduksi dimensi variabel, penelitian ini mengelompokkan wilayah berdasarkan karakteristik sosial ekonomi dan kesehatan. Data yang dianalisis termasuk angka harapan hidup, tingkat kemiskinan, pengangguran, dan akses ke layanan kesehatan. Kebaruan penelitian ini terletak pada kombinasi unik antara PCA dan K-Medoids untuk menghasilkan klaster yang lebih akurat dan robust terhadap outlier, dibandingkan metode yang biasanya hanya menggunakan satu teknik klasterisasi atau tidak melibatkan reduksi dimensi. Hasil penelitian menunjukkan bahwa K-Medoids dengan PCA menghasilkan klaster yang lebih koheren dan terpisah daripada K-Means, terutama dalam menangani outlier. Menurut metode Elbow dan Silhouette, empat hingga lima klaster adalah pilihan terbaik. PCA meningkatkan akurasi dan efisiensi klasterisasi dengan mengurangi kompleksitas data, yang menghasilkan klaster yang lebih baik Diharapkan temuan ini akan membantu pemerintah membuat kebijakan yang lebih baik untuk mengatasi ketimpangan kesehatan dan sosial ekonomi di Jawa Timur. Kata kunci: Klasterisasi, Outlier, Principal Component Analysis (PCA)

Penerapan teknologi baru dapat mendorong siswa untuk giat belajar dan tidak mudah menyerah jika menemui kesulitan dalam belajar. Fisika merupakan salah satu mata pelajaran di sekolah menengah pertama, dan siswa dituntut untuk menerapkan apa yang telah dipelajari secara praktis. Pembelajaran Fisika terdiri dari banyak materi, salah satunya adalah materi asam basa. Materi asam basa di pelajari oleh siswa kelas tujuh SMP Negeri Alok belum memiliki fasilitas laboratorium yang memadai untuk praktikum sehingga perlu dibuat media pembelajaran Virtual Lab yang interaktif . Metode yang digunakan dalam merancang aplikasi Virtual Lab Fisika Asam Basa yaitu MDLC (Multimedia Development Life Cycle). Aplikasi Virtual Lab ini kemudian diuji oleh guru dan ahli media, dimana aplikasi Virtual Lab Asam Basa yang dikembangkan tergolong kriteria “layak dan tanpa perlu revisi” dengan skor rata-rata keseluruhan 90% dengan pengujian blackbox sehingga media pembelajaran ini memenuhi aspek kevalidan. Aplikasi Virtual Lab Asam Basa yang menyajikan langkah-langkah yang dapat dipraktekkan oleh pengguna dengan cara mensimulasikan percobaan dan mengikuti petunjuk penggunaan dan aplikasi Virtual Lab dapat diakses melalui android. Kata Kunci: Fisika; Virtual Lab; Asam Basa; MDLC; Pembelajaran

Commuter Line ialah salah satu sektor pelayanan publik dibidang transportasi banyak dipergunakan oleh masyarakat saat ini. Sesuai perkembangan teknologi banyak opini masyarakat terhadap pelayanan Commuter Line beredar secara online, untuk menyampaikan opininya masyarakat menggunakan media sosial seperti Twitter. Media Twitter dapat dijadikan sebagai bahan evaluasi peningkatan kualitas layanan. Twitter memudahkan pelanggan untuk menyampaikan keluhan serta pendapat terkait layanan seperti PT KAI Commuter. Untuk memahami komentar pelanggan, persepsi layanan publik, dan mendapatkan opini baru maka perlu dilakukan analisis sentimen terhadap pelayanan Commuter Line. Analisis sentimen ini bertujuan untuk mengklasifikasikan tweets masyarakat terhadap layanan Commuter Line ke dalam sentimen complain dan not complain dengan menggunakan metode Naive Bayes. Metode ini mempunyai tingkat akurasi paling tinggi dalam pengklasifikasian analisis sentimen. Data yang diunduh dari Twitter menggunakan aplikasi RapidMiner sebanyak 1.010 tweet dan data validasi sebanyak 1.003 tweets. Pada akhir tahap penelitian diperoleh accuracy 78,11%, precision 81,76%, recall 72,51%, dan AUC yang didapat sebesar 0,814. Kata kunci: Analisis sentimen; Commuter Line; Twitter; Naive Bayes

Penelitian ini bertujuan untuk mengembangkan dan menguji aplikasi Augmented Reality (AR) berbasis metode markerless dengan pendekatan mid air untuk meningkatkan efektivitas pembelajaran tata surya. Aplikasi ini dirancang untuk mengatasi keterbatasan pada aplikasi AR konvensional, yang sering kali bergantung pada deteksi permukaan datar, serta untuk meningkatkan realisme dan fleksibilitas interaksi antara objek virtual dan lingkungan fisik. Metodologi pengujian mencakup empat skenario berbeda yang mengevaluasi akurasi deteksi ruang 3D di bawah berbagai kondisi pencahayaan. Hasil pengujian menunjukkan bahwa sistem mampu mendeteksi ruang 3D dengan baik pada intensitas cahaya tinggi di luar ruangan (1007 LUX) dan rendah di dalam ruangan (20 LUX). Namun, ketika kamera diarahkan ke tembok polos dengan intensitas cahaya 100 LUX, deteksi ruang 3D gagal. Sebaliknya, pada kondisi malam hari dengan cahaya sangat rendah (di bawah 15 LUX), aplikasi tetap berhasil menempatkan objek 3D secara akurat. Penilaian usability dari 24 responden memberikan skor SUS rata-rata 92,4, menempatkan aplikasi dalam kategori "Acceptable" dengan Grade Scale "A" dan Adjective Rating "Excellent". Temuan ini menegaskan bahwa aplikasi AR yang dikembangkan memiliki potensi signifikan sebagai media pembelajaran interaktif, memberikan visualisasi yang mendalam dan mendukung pemahaman konsep tata surya secara efektif. Kata kunci: Mid Air, Markerless, Augmented Reality, Tata surya, Usability

Tuberkulosis (TB) merupakan jenis penyakit kronis yang disebabkan oleh bakteri Mycobacterium tuberculosis yang dapat menular dari 1 orang ke orang lainnya melalui udara atau yang disebut dengan airbone. Pendeteksian bakteri M.tuberculosis pada citra sputum penderita TB merupakan suatu tantangan dalam menentukan identifikasi untuk dapat membedakan bakteri tersebut dengan background dengan hasil pewarnaan sputum yang cendrung memiliki tingkat warna yang bervariasi, sehingga dapat menurunkan hasil akurasi pendeteksian. Oleh karena itu diperlukan suatu pendekatan yang lebih akurat dalam mendeteksi bakteri TB pada citra BTA. Untuk itu penelitian ini bertujuan melakukan pengolahan citra berupa segmentasi pada citra BTA dengan menerapkan preprocessing ruang warna CIE Lab, menentukan batas ambang yang maksimal dengan Multi Thresholding dan dilakukan segmentasi menggunakan K-Means Clustering. Hasil eksperimen didapatkan bahwa pengaplikasian metode Multi Thresholding dan K-Means memberikan tingkat akurasi sebesar 99.57% pada pendeteksian bakteri TB. Kata kunci: Tubekulosis, Ziehl Neelsen, Multi Thresholding, K-Means.

The annual evaluation carried out by LLDIKTI looked at the performance of lecturers in their regions, and it was revealed that some lecturers, especially lecturers at Jenderal Ahmad Yani University (UNJANI), still had difficulty fulfilling the tridharma duties of teaching, research and community service, which are important aspects of higher education. To consistently fulfill these obligations, lecturers are required to innovate. A study aimed at exploring how knowledge exchange and enrichment impact the innovative performance of UNJANI lecturers, collecting data through an online survey distributed to them. This research aims to understand the influence of knowledge sharing and enrichment on lecturer innovation, and its success is assessed through questionnaire analysis. These findings underscore the important positive correlation between knowledge sharing, enrichment, and increased innovative performance among UNJANI lecturers, indicating that encouraging these practices can increase the fulfillment of tri dharma obligations.

Checking the identity of motorcycle owners when leaving the college area is a mandatory activity for security officers to ensure that vehicles entering and exiting the college are the same driver. The conventional checking process often causes the impact of vehicle queues when the volume of vehicles increases. Therefore, an intelligent system is needed to detect multi-plate vehicles automatically. One approach in the world of image detection of an object is the use of the YOLO (You Only Look Once) algorithm. This algorithm predicts bounding boxes and possible classes in a single frame. This research divides objects into 3 classes, namely vehicles, driver's faces, and vehicle plates. The dataset used was 74 varied images consisting of 50 training data, 12 validation data and 12 testing data. The image was trained using 300 epochs and a batch size of 8 and resulted in an F1 score calculation for detecting objects reaching 92%.

The capital market plays a significant role in a country's economy, facilitating corporate financing and providing investment opportunities for the public. One popular investment instrument is stocks, yet many investors struggle to make profitable investment decisions due to a lack of understanding of stock investments. Therefore, predicting stock prices can be a way to determine the future value of a stock. This research aims to address this issue by applying the Long Short-Term Memory (LSTM) algorithm to predict stock prices on the IDX30 index. LSTM is capable of processing sequential data, such as stock price data, complexly because it can store information over long periods. The testing is conducted using various parameters in layers, epochs, and time steps to obtain the best prediction model. The LSTM architecture used consists of four layers: the LSTM layer with 128 neurons, dropout and dense layers with 64 neurons, and an additional dense layer that converts the output from the previous layer into prediction results. This study demonstrates that the LSTM algorithm can accurately predict stock prices based on evaluation metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The best results for PT Bank Central Asia Tbk show a MAPE of 1.14% and RMSE of 137.71, PT Bank Rakyat Indonesia Tbk shows a MAPE of 1.58% and RMSE of 87.4, and PT Bank Mandiri Tbk shows a MAPE of 1.64% and RMSE of 88.26.

Social media is currently an alternative medium in conveying messages in the form of news and can be used as a tool to exchange news from different places. Many people use social media to express opinions, express feelings, as well as experiences and things that can be of concern. In this study, the data processing used was the K-Nearest Neighbor Algorithm with the classification method as a media for comparing the functions of the two bots, namely the WhatsApp and Telegram bots. Using SPSS (Statistical Product and Serive Solutions) and Rapidminer as a place to perform calculations and analysis. Based on the results of testing data mining with Rapid Miner, the calculation results are obtained which will be used as information to support user satisfaction in using Social Media Bots. User satisfaction is found in WhatsApp Bot users 72.22% and Telegram Bot users 28.57%. Calculations are carried out with a data mining process obtained from the K-Nearest Neighbor algorithm to make it easier to find Bot user satisfaction on both WhatsApp and Telegram social media. The WhatsApp bot is the best choice and has several useful functions as a digital communication media tool on the Internet of Things.

Sentiment analysis is a technique to decipher textual views and feelings. This study assesses a model's performance in sentiment analysis of Google Play Store reviews for the Amikom One app. With more unfavorable ratings, the primary problem is the imbalance in classes. It was done using the Synthetic Minority Over-sampling Technique (SMOTE) to remedy this. The techniques used are preprocessing the data, using SMOTE, and classifying sentiment using an artificial neural network (ANN). F1-score, recall, accuracy, and precision are used in the model evaluation process. The outcomes demonstrate a great degree of accuracy improvement in the ANN model's performance following the use of SMOTE. On training data, the model successfully classified sentiment reviews with 100% accuracy, while on test data, it achieved 93.44% accuracy. Sentiment research shows that 54.10 percent of the evaluations are favorable to the application, with 45.90% being critical. This study Artificial Neural Networks' (ANN) potential in sentiment analysis of mobile application reviews, offering developers with useful insights into how to enhance program quality using user feedback.

The Knowledge Management System Application is an application that users can use to store and manage knowledge from the Community Of Practice (CoP) Marine Information Systems Study Program (SIK). CoP, known as the Expertise Group or KBK, consists of students and lecturers. The problem that exists based on the results of observations is that the Knowledge Management System Application called Asmape.Com application has not been utilized optimally; this can be seen from the use of the application, which is only used by three courses in the Marine Information Systems study program, namely knowledge management, business intelligence, and biodiversity. The successful implementation of an application depends on technological aspects and requires comprehensive attention to the existing dimensions of the information system. Therefore, it is necessary to model the utilization of knowledge management system applications (Asmape.com), which can be used as a systematic guide to understanding, analyzing, and improving performance. The methodology used is the information systems methodology from Hevner. One of the stages in the method is to determine the components using the Kitchenham systematic literature review. The study results show four layers in the model of utilizing knowledge management system applications: Infrastructure, Technology, Process, and Performance. The infrastructure consists of learning outcomes and technical skills components, and processes consist of Organization, People, Asmape Services, and Artifact Knowledge components. The performance consists of Pedagogic excellence, Digitalization Knowledge Management, and Openness Excellence.

Fulfilling nutritional needs with the Recommended Dietary Allowances (RDA) shows the average value of the number of vitamins, protein and other nutrients the body needs to function properly. Each person's nutritional needs are different, so the RDA can be calculated based on different age groups and gender. In general, there are still many people who do not know the nutritional value of food and consume food without considering whether it meets the body's needs. This usually happens because calculating the RDA value is not yet familiar to do. Efforts are needed to increase awareness about the importance of a balanced diet through RDA calculations. Calculation and determination of nutritional status using the RDA number serves as a measuring tool to monitor whether a person's nutritional intake is in accordance with daily needs. This research developed a web-based application to calculate RDA numbers and group RDA numbers into nutritional status of less, enough, or more. Determination of nutritional status is carried out using the fuzzy tahani method, by displaying the results in percentage form, so that users can easily see the proportion or percentage of nutritional status obtained. This application not only calculates nutritional values, but provides a food record feature to help users manage healthy eating patterns.

Breast cancer is one of the most common causes of death worldwide. Data mining can be utilized to detect breast cancer, where information is extracted from data to provide valuable insights. Clustering of breast cancer is conducted to assist medical professionals in grouping the characteristics of each cancer type. However, multicollinearity in breast cancer data can impact clustering results. To address this issue, dimensionality reduction through Principal Component Analysis (PCA) is employed. PCA can effectively handle multicollinearity issues and enhance computational efficiency. Additionally, the K-Means method has limitations in determining the optimal number of clusters. Therefore, the Gap Statistic method is employed to find the optimal K value suitable for breast cancer data. This study compares the evaluation results of the K-Means clustering model, the combined PCA-KMeans clustering model, and the combined PCA-GapStatistic-KMeans clustering model. The findings indicate that the evaluation results for the K-Means model with PCA dimensionality reduction and optimal Gap Statistic K are superior to the K-Means model without dimensionality reduction. The Gap Statistic suggests 2 clusters as the optimal number, with an evaluation result of 1.195513.

This study explores the use of Convolutional Neural Network to identify and classify regional batik motifs, a significant aspect of Indonesian cultural heritage. The CNN model was optimized with Adam optimizer and used to extract distinctive features from the batik patterns. Subsequently, a hierarchical clustering method was employed to construct a relationship tree depicting the link between batik motifs based on their region. The research findings demonstrate that the CNN model effectively classifies batik motifs with an accuracy of up to 88%. The study provides insights into the intricate connections between regional batik designs and contributes to the preservation and understanding of Indonesia's cultural heritage.

Magelang Regency, with a wealth of tourist destinations with a variety of things, such as Borobudur Temple and Nepal Van Java, has extraordinary tourism potential. With this diversity, it is a challenge for tourists to determine the best tourist objects that suit their preferences. This study aims to develop an intelligent system for recommending the selection of the best tourist attractions in Magelang Regency by integrating the Weighted Product and K-Means Clustering Methods. The system is designed to provide accurate recommendations based on tourist criteria such as location, facilities, tickets, and security, as well as group attractions based on their level of potential. The Weighted Product method is used to determine the best tourist attractions, while K-Means Clustering groups tourist destinations into high, medium, and low potential categories. In this study, several stages were carried out: literature study, data collection, system design, data analysis, implementation, and system testing to produce an effective and efficient recommendation system for tourists in Magelang Regency. The results of this research obtained the best tourism, namely at Borobudur Temple.

Game is a form of entertainment that is often used to refresh the mind from the fatigue of daily activities and routines. Honkai: Star Rail is a popular turn-based game from Hoyoverse available on Google Play Store. Several studies have proposed Sentiment Analysis with Naïve Bayes classification method. However, not many have identified the reviews of a game to the extent of identifying on its aspects. In aspect-based sentiment analysis, text is analyzed to identify various attributes or components, then the relevant sentiment (positive, negative, or neutral) for each of these attributes is determined. This research aims to analyze aspect-based sentiment using the Naïve Bayes Classifier method, as well as categorize sentiment into positive and negative, and classify reviews into certain aspects. The results obtained after 5-fold iteration obtained the best average accuracy of 79%, The evaluation results show that it is necessary to tune the model using Grid Search Hyperparameter Tuning. Optimization of smoothing parameters with alpha = 0.1 proved effective in improving model performance with the highest weighted average accuracy of 93%. The evaluation results show that Grid Search Hyperparameter Tuning optimization gives better performance to the Naive Bayes algorithm model in multi-label classification.

One of the topics that has been discussed on twitter is the rules regarding the removal of masks. However, there's a chance that the data from Twitter contains unequal data classes. An unequal amount of data can cause the classification process to malfunction. Combining under- and oversampling techniques is known as combine sampling, and it is a data-balancing strategy. The research's data consists of Indonesian tweets using the hashtag "The Policy of Removing Masks." In this study, the classification approach was K-Nearest Neighbor, while the oversampling and undersampling techniques were SMOTE and Tomek Links. The purpose of this research is to classify sentiment using the K-Nearest Neighbor algorithm and to use combine sampling to balance the amount of training data in the two classes that are not yet balanced. 234 training data with a positive sentiment and 652 training data with a negative sentiment were obtained after the data was divided. Due to an imbalance in the quantity of training data between the two classes, the positive class's data is minor and the negative class's data is major. The quantity of training data are 613 in the positive class and 613 in the negative class obtained following the combine sampling. Following the balancing of data between the two classes, sentiment classification was performed, yielding accuracy of 60.4%, precision of 78.5%, and recall of 65%. The reason for the accuracy number of 60.4% is because machine learning misinterpreted a tweet regarding Indonesia's mask removal policy, leading to incorrect classification.

Packaged food and beverages often pose a risk of increasing diabetes when consumed regularly. This study aims to classify these products based on their nutritional content listed on the labels, with a focus on identifying diabetes risk. The methods employed include K-Means and Fuzzy C-Means, K-Means is used to determine initial center of cluster, while Fuzzy C-Means enhances the clustering by assigning probabilistic memberships to each data point. These methods are applied to products sold in stores in Banyumas Regency, Central Java, Indonesia. This research is the first to combine these two methods in the context of product clustering based on nutritional labels. The results indicate that packaged food and beverage products can be classified into high-risk and low-risk clusters for diabetes. Consequently, this study provides important guidance for consumers in choosing healthier.

Weather is the atmospheric condition at a specific location and time that is variable and constantly changing. Many factors influence weather conditions, one of which is rainfall. Rainfall is a climatic parameter characterized by high variability due to climate anomalies. These anomalies make rainfall prediction very challenging. Specific factors can cause uneven distribution patterns of rainfall between different regions. The exact amount of rainfall that will occur cannot be determined precisely, but predictions or estimations can be made for future rainfall amounts. This study predicts rainfall in Tegal Regency using ETSFormer. Its aim is to provide useful information about future rainfall patterns for the community, especially in Tegal Regency, to facilitate daily activities. The results show that the ETSFormer model effectively predicts rainfall, achieving optimal results with an 8:2 data composition using univariate analysis, yielding the best MSE evaluation metric of 0.002925439039245248 and MAE of 0.036676984280347824.

In particular, stunting and being under the Red Line (BGM) are significant issues for society and the healthcare system. This research utilizes machine learning, particularly the K-Nearest Neighbor (KNN) and Naïve Bayes algorithms, for classifying the health of children experiencing stunting or BGM. The training data used comes from the Indonesian Posyandu website, serving as the foundation for classifying new data. This research not only identifies patterns in the data through KNN but also compares the prediction results between KNN and Naïve Bayes in assessing the probability of stunting or BGM in children. This issue reflects nutritional deficiencies and has the potential to cause developmental delays and long-term health impacts. This approach allows for the comparison of predictive outcomes, enhancing the accuracy of children's health assessments. By using the RapidMiner application, the accuracy result for KNN is 70.62% and for Naïve Bayes is 99.47%, providing a deeper understanding of the effectiveness of each algorithm in addressing child health challenges. The aim of this research is to classify new toddler data using the KNN and Naïve Bayes methods, implemented in the form of a Visual Basic application. It is hoped that this will help monitor children's health more effectively and be more easily accessible to interested parties.

Every year, the library must be buying books in order to increase the collection of books that are in the libraries. When purchasing books, it is necessary to make various considerations so that the books that will be used are relevant to the needs of students and lecturers in academic activities. The procurement of books in the library is still done manually with book selection carried out by the librarians is still one-on-one of the list of submissions of books that have been made by the lecturer. Therefore, there is a need to have a renewal of the system of book acquisition in the libraries one of which uses the decision support system in the process of the book acquisitions. In this study the decision support system used is the MOORA method in determining the rating of the recommendation book to be held. The alternative submission data will be obtained from the library's proposal with the book data from the publisher's book collection. The study uses five criteria for book acquisition, including book price, year of publication, book stock, number of book proposals, and availability of books. This decision support system will provide a recommendation for purchase of books from the alternative data for book submission that will be calculated using the MOORA method to obtain any book recommendation that matches the criteria and budget of the book procurement. Accuracy level testing using the Confusion Matrix by comparing the results of manual calculations with the system to obtain 100% accuracy.

The user interface (UI) design of software in the early stages of development is crucial to ensure the future success of the product and is key to creating an effective user experience (UX). This study aims to produce a UI design for software, namely an e-repository, and conduct a usability evaluation based on user satisfaction with the UX of the design. The resulting e-repository design is a prototype, where the research process implemented the design thinking method consisting of five main phases: empathize, define, ideate, prototype, and test. The evaluation is conducted in the test phase, where the evaluation uses the usability testing method by assigning a number of task scenarios, totaling 8 tasks, to respondents. Furthermore, to measure user satisfaction levels, a questionnaire based on the System Usability Scale (SUS) is used, consisting of 10 statements with both positive and negative orientations. The research results indicate that the UI design has addressed the issues and met the needs of users. Meanwhile, the analysis results from the usability evaluation show that the Adjective Ratings are categorized as Good. Additionally, in terms of Acceptability Ranges, the prototype is deemed Acceptable by users, with a Grade Scale obtained being B, where the evaluation results indicate that the scores obtained are above the average SUS score standard.

In today's rapidly evolving technological landscape, the successful implementation of IT projects is increasingly contingent upon effective organizational change management (OCM). This research paper explores the intersection of OCM and IT project delivery, proposing a comprehensive framework that integrates these two critical domains. Through a review of existing literature and analysis of case studies, we identify key challenges and best practices for synchronizing OCM strategies with IT project management processes. Our findings reveal that the alignment of OCM with IT project delivery not only enhances project success rates but also promotes sustainable organizational transformation. This integrated approach ensures that technological advancements are supported by a well-prepared workforce, thereby minimizing resistance and maximizing adoption. The paper concludes with practical recommendations for practitioners aiming to bridge the gap between OCM and IT project delivery, ultimately fostering a more agile and resilient organizational environment.

This Systematic Literature Review study discusses the factors that influence the adoption of e-government services with varsiability in the influence of these factors in various countries. The research confirms the importance of trust, performance expectancy, effort expectancy, social influence, and facilitating conditions in the acceptance and adoption of e-government services. Trust factors, especially related to information security and government transparency, were found to be key elements in driving e-government adoption. In addition, the expectation of benefits obtained, ease of use, and influence from the social environment also play an important role in people's decision to use the service. Suggested recommendations to increase e-government adoption involve improving technology infrastructure, supportive policies, technology training for government personnel, as well as an approach that considers local community conditions and factors. This study provides important insights for governments and agencies in improving e-government services and increasing the adoption of these technologies across various social and cultural environments.

At present, clove cultivation is increasingly in demand, especially by farmers because it is easy to maintain and the selling price is high. Researchers conducted observations in Tana Toa Village on how the processing of cloves after harvesting is drying them in the sun until they turn brown and shrink. After that, farmers select dried cloves and distinguish between good and bad quality. One way for farmers and traders to determine the quality of cloves is by visually inspecting the size and color. One of the disadvantages of this manual classification process is that each person can look at the same material in bulk in different ways depending on the situation or individual weak points. The aim of this research is to help farmers produce high quality cloves that will ultimately produce favorable results on their economy. With digital image-based methods and Naive Bayes, this process can be done quickly and efficiently, reducing operational costs and labor time. The Naive Bayes algorithm is able to process data more thoroughly than humans, especially if the image quality and features used for classification are optimized. This reduces human errors that may occur during manual processing. The results of this study are, Gaussian Naive Bayes testing has an accuracy of 0.82. Bernoulli naïve bayes has an accuracy of 0.69, Complement naïve bayes and multinomial naïve bayes each have an accuracy of 0.89. This shows that they affect the accuracy rate of clove quality effectively

The Surabaya City Government launched an application based on an internet site or web page in the form of a data collection system carried out by the local Kader Surabaya Hebat (KSH) to record various problems in the community related to poverty and health problems, the application was named the Sayang Warga Application (ASW). The application that was launched does not mean it has shortcomings because until now the application has never been maintained, causing ASW to be considered less than optimal and this clearly hinders the performance of users in conducting data collection. This study uses the right method to achieve a goal. From what can be traced and studied, the appropriate method is to use a quantitative method. This study uses the Partial Least Square-Structural Equation Model (PLS SEM) method. The results of 12 variable relationship paths, 4 variable path relationships were declared insignificant and rejected because the T-test and P-value values were below 1.96 and 0.05, while 8 variable path relationships were declared significant and accepted because the T-test and P-Value values were above the threshold, namely 1.96 and 0.05. Furthermore, the results of the analysis of factors that influence the success of use in ASW can be concluded, the results of the hypothesis test indicate that perceived ease of use has a positive and significant effect on perceived usefulness. Because the hypothesis path has the highest value with a T-test of 6,560 with a P-Value of 0.000

In order to handle student discipline infractions at school, this project intends to design a decision support system (DSS) based on the Simple Multi-Attribute Rating Technique (SMART) technique integrated with a graphical dashboard. A variety of visual tools, such as scatter plots, heatmaps, pie charts, bar charts, and line charts, are used to evaluate and display violation data. This integration's primary goals are to make monitoring and analysis faster and more efficient and to support decision-making with regard to student infractions. The findings demonstrate how the SMART approach and visualization dashboard can be used to manage violation data more effectively, provide a better knowledge, and speed up reactions to infractions. This technique makes it easier for schools to spot trends in infractions, choose the best course of action for corrective measures, and enhance overall student discipline. It is anticipated that this system will enable discipline management in a learning environment in an efficient manner.

Diabetic retinopathy is a serious complication of diabetes that can lead to blindness if not detected and treated early. Automated detection of diabetic retinopathy requires effective feature extraction techniques to enhance diagnostic accuracy. This study aims to develop a method for detecting diabetic retinopathy by utilizing Local Binary Pattern (LBP) combined with wavelet transform, and then classifying the extracted features using Support Vector Machine (SVM). The approach includes feature extraction from retinal images using LBP and wavelet transform. The extracted features are subsequently classified with SVM to evaluate performance in detecting diabetic retinopathy. Analysis results show that the dominant feature is found in the fifth row with a value of 0.57006, indicating the effectiveness of the LBP method in feature extraction. The developed model demonstrates high performance with an accuracy of 95.59%, precision of 96%, recall of 97.96%, and F1-score of 96.97%. The combination of feature extraction methods with SVM proves to be effective and reliable in detecting diabetic retinopathy, offering low error rates and high accuracy, thus potentially serving as a valuable tool in clinical diagnosis

Along with advances in digital technology, the ease of carrying out payment transaction processes via digital wallet applications is increasing. OVO is one of the leading digital wallet applications in Indonesia. However, there are several users who complain and report problems such as difficulties in upgrading, login problems, transaction failures, and applications that respond slowly. These reviews can be seen through the comments column in the OVO application on Google Playstore. Application representation can influence user perceptions of an application. This research aims to assess the user experience of the OVO application using the User Experience Questionnaire (UEQ) method, which involves six aspects of assessment: attractiveness, clarity, efficiency, stimulation and innovation. The research results obtained show that the overall user assessment of the evaluation that has been carried out on the OVO application is positive. This research is expected to be able to provide important insights and information regarding user satisfaction with digital wallet applications. Apart from that, it is also hoped that this research can become a reference for subsequent research and further development related to the OVO application, with the aim of improving the user experience.

PT. Telkom Akses (PTTA) has constraints in the employee leave application management system, this is because the employee leave application process is still done manually and difficulties in determining the level of importance for employees who apply for leave. Therefore, a web-based application was built using FMCDM and the SAW Method. This study aims to improve efficiency and effectiveness in managing the employee leave application system by utilizing the Fuzzy Multi-Criteria Decision Making (FMCDM) approach using the Simple Additive Weighting (SAW) method at PT. Telkom Akses (PTTA). In order to make it easier for employees to carry out the deduction process and obtain complete and detailed information and rules related to deductions, the personnel department is expected to be able to create an online information system. To help with this, one of the fields of technology that can be utilized is soft computing technology. There are various methods that can be used to solve problems, one of which is the Fuzzy Multi Criteria Decision Making (FMCDM) method and the Simple Additive Weighting (SAW) method. The results of the study indicate that the web-based application that has been designed can help solve the problems faced by PT. Telkom Akses Medan STO Simpang Limun in terms of managing the employee leave application system and helping to determine the level of importance and ranking for employees who apply for leave accurately and efficiently, and the results of the application of FMCDM and the SAW Method in determining employee leave permits are that out of 7 employees who apply for leave, 2 employees get the highest rating results. The conclusion of this study is to help decision makers in determining employees who get leave permits based on relevant and transparent assessments of each employee who applies for leave.

This research was conducted to analyze user satisfaction with the Netflix application using the UX Honeycomb method. The UX Honeycomb method is used to evaluate various aspects of user experience, such as usability, aesthetic value, sustainability, accessibility, satisfaction, and diversity. This study involved data collection through online surveys and interviews with active Netflix users. Data analysis was conducted using statistical techniques and qualitative interpretation. The UX Honeycomb method was employed to understand the essential aspects of user experience within the application. The results of this study are expected to provide valuable insights for other streaming service providers to enhance their service quality and create a better user experience. Additionally, the contribution of the UX Honeycomb methodology in assessing user satisfaction can serve as a foundation for further research in the context of digital entertainment applications.

BAPPEDA-LITBANG Tambrauw, a regional technical institution in Tambrauw Regency, Southwest Papua, faces challenges in data management related to data integration and access. This condition hampers the planning and decision-making process there. This research aims to design a web-based data management system that can integrate various types of data from multiple sources, making it easier to access and analyze data in the agency. The prototype method was used in developing this system through problem identification, needs analysis, system design, implementation, testing, and improvement and evaluation. The research results show that the proposed web-based data management information system can overcome the challenges of limited data access and lack of data integration and support regional development that is more structured and responsive to community needs. In addition, this system can be a reference for developing systems in other government institutions with similar characteristics and challenges.

Artificial ripening methods use calcium carbide (carbide) which often leaves harmful residues on the mango fruit. This research designs a classification tool for carbite and non-carbite mango fruit using the Android-based InceptionV3 Convolutional Neural Network method. The mango fruit image dataset consists of 1622 images (881 images of carbite mangoes and 811 images of non-carbite mangoes) used to train and test the model. The testing process is done by implementing the model on a Raspberry Pi B+ connected to a camera pi to take pictures of mangoes at a distance of 30 cm. The results showed that the CNN model developed achieved an average accuracy of 94.4% in classifying carbitan and non-carbitan mangoes. This result shows that the classification tool designed can provide significant benefits for farmers, traders, and consumers in ensuring marketed quality.

This research employs social media (Twitter) to apply sentiment analysis ascertain the degree of public satisfaction with the Bulukumba tourist attraction. Unstructured text data is a major challenge in sentiment analysis. For this reason, implementing the Naïve Bayes algorithm is an effective approach for conquering this challenge because of its ability to handle text data well. This study aims to evaluate the performance of multinomial Naïve Bayes by testing a combination of minimum document frequency (min-df) and maximum document frequency (max-df) parameter values in determining the level of accuracy. This analysis stage includes collecting data from Twitter related to the Bulukumba tourist attraction. Preprocessing carried out includes data cleaning, casefolding, text normalization, tokenization, stopword removal, and stemming. Feature extraction using Count Vectorizer and TF-IDF weighting. The process ends with 10-Fold Cross-Validation by separating the data into training data and test data for sentiment analysis classification, as well as evaluation using the Confusion Matrix. In this research, there are 10 test scenarios with various combinations of min-df and max-df. The values of employed min-df consists of 0.001, 0.002, 0.005, 0.01, 0.02 and max-df consists of 0.5 and 0.8. The results of implementing Multinomial Naïve Bayes in this test show that classification accuracy increases with effective min-df and max-df parameter settings. The greatest accuracy was 0.7910 in testing a combination of min-df parameter values of 0.001 and max-df 0.8. Meanwhile, the average accuracy for each test was obtained the highest value of 0.7272 with min-df of 0.002 and max-df of 0.5 and 0.8 respectively.

The school management information system (SIAHDU) is an application managed by the IT department of a Vocational High School in Salatiga City. This application is an application of SI/IT in the education sector which was created with the aim of making school business processes more effective and efficient, such as administrative activities for paying tuition fees, managing grades and report cards, violation points, attendance and student biodata that can be accessed by teachers and students. With the convenience provided, it cannot be denied that risks will always arise both internally and externally. Based on this, risk management activities need to be carried out to minimize risks that might hamper and stop the system's business processes. In this research, the ISO 31000:2018 framework is used as a risk analysis assessment guide. The stages used are divided into risk assessment and mitigation stages so that it is hoped that they can minimize and overcome existing risks. The aim of this research is to carry out risk assessments and risk mitigation in school management information system applications using ISO 31000:2018. The results of the day of research that was carried out contained 25 risk opportunities, three of which were at a high level, fourteen were at a medium level, eight were at a low level. It is hoped that the results of this risk management documentation will become a reference for schools to implement new policies to minimize risk opportunities Keywords: risk management, ISO 31000:2018, risk analysis

Health centers as health service providers have an important role in ensuring adequate drug availability for the community. However, drug management in health centers often faces obstacles, including the use of manual methods in stock monitoring, which can lead to unavailability or accumulation of unused drugs. This study aims to improve the efficiency of drug management in health centers through the application of the K-Means Clustering method. This method is used to group drug stocks into three main clusters: heavy drugs, moderate drugs, and light drugs. With this grouping, it is expected that pharmacists can more easily determine the type of drug, monitor drug availability in a timely manner, and manage drug procurement according to patient needs. Research methods include literature studies, data collection and analysis, system modeling design, and system testing and evaluation. The results of this study are expected to improve the efficiency of drug management in health centers, so that health services to the community can be more optimal. The results of testing using the Silhouette Coefficient (SC) method produced an average SC of 0.97 which means strong structure, so it can be concluded that it has a strong structure.

One of the activities that is routinely held during the learning process is filling out questionnaires by parents to determine the quality of Tadika CERIA education and services. The results of this questionnaire were then analyzed using the Spearman Rank Correlation method. This study aims to apply correlation analysis using Python to evaluate student satisfaction with the learning location at Tadika CERIA. Utilizing a dataset of survey responses that includes variables such as cleanliness, quality of teaching, and communication, analysis was conducted to identify key factors influencing student satisfaction. This approach not only shows the practical application of Python in data processing and statistical analysis, but also provides valuable insights for school administrators in improving the quality of the learning environment. The results show a positive correlation between certain aspects and student satisfaction, underscoring the importance of a deep understanding of student preferences and needs in the development of a conducive learning environment. This research makes an important contribution in the context of early childhood education, offering a foundation for further research in an effort to improve the holistic educational experience.

Technology that continues to develop indirectly forces people to adapt to these developments. The vital role of technology is becoming increasingly felt during the COVID-19 pandemic when all world activities are paralyzed and only allowed to communicate online. However, the enormous benefits of technology are also directly proportional to the risks that may occur. Therefore, IT Risk Management is needed to mitigate potential sources of threat. This research aims to analyze IT risk management by measuring the level of capability, gap analysis, and providing recommendations for improvement using the COBIT 2019 framework to support PT XYZ's work performance and IT security. Researchers used qualitative methods with data collection techniques through observation, interviews, and questionnaires. The results showed that the risk management domain that was the research focus EDM03, APO12, APO13, and DSS05 had a gap between the expected capabilities and what was happening in the company. Therefore, improvement recommendations are needed, such as determining the level of IT risk and socializing it with stakeholders, recording IT risk events, building an Information Security Management System (ISMS), implementing a network filtering mechanism, and regularly evaluating information about potential new threats by reviewing product security and vendor or third-party services.

Tsunamis have the potential to have a large impact on the environment, therefore early detection and preparation for tsunami need to be carried out to reduce the impact of casualties and losses incurred. This research aims to predict tsunami events due to large earthquakes in Indonesia as a form of early detection. The optimized neural network method is used in research to classify tsunami events in Indonesia in 2000-2023 for large earthquakes with strength more than 5 magnitudes. The research results show that the neural network structure formed consists of an input layer, a hidden layer, and an output layer. The results of the evaluation of the neural network model with SMOTE obtained an accuracy value of 99.43%, precision of 96.31%, and an F1 score of 97.86%, which means the resulting model is good. Therefore, an optimized neural networks can be applied as a warning system in various regions to detect potential tsunami events in the future.

The Wild Brain Workshop (TWBW) is a custom culture community in Medan that was founded in 2011. This community started from a custom workshop which then developed into a wider community with a focus on custom motorbikes, music and lifestyle. TWBW, as one of the well-known custom motorbike workshops in the city of Medan, of course gets lots of orders from various custom motorbike lovers. This research was created to create a mobile application for ordering custom motorbike packages by implementing CRM (Customer Relationship Management). The problem formulation in this research is designing an effective mobile application for ordering custom motorbike packages and implementing CRM to improve relationships with customers. The aim of creating this application is so that you can easily view the various custom motorbike packages available, see detailed specifications and prices, and place orders directly through the application. The implementation of CRM in this application is found in the chat feature and customer service menu. By implementing CRM (Customer Relationship Management), it is hoped that TWBW can manage relationships with customers, by utilizing technology to maximize communication and marketing. Through the development of this application, it is hoped that the use of this technology can effectively improve the ordering process.