Jurnal LPPM iSTTS
Not a member yet
189 research outputs found
Sort by
Comparative Analysis of Large Red Chili Price Forecasting Models in Malang Regency Using Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA)
Full text linkLarge red chili is a strategic food commodity with high demand, yet its price often fluctuates due to factors such as weather, harvest seasons, and market dynamics. In Malang Regency, these fluctuations impact inflation and economic stability, necessitating an accurate forecasting model to support decision-making. This study aims to develop a price forecasting model using Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA) methods and compare their performance using daily time series data on large red chili prices from January 2022 to August 2024, obtained from the Representative Office of Bank Indonesia in Malang. The data underwent preprocessing, where LSTM data was transformed using MinMaxScaler, while ARIMA data was differenced to meet stationarity assumptions, then split into 80% training and 20% testing data, with optimal parameters obtained through Grid Search for both models. The results show that the LSTM model with three layers (150, 150, 150 units) and a dropout of 0.2 achieved an RMSE of 2.326 and MAPE of 3.65%, whereas the best ARIMA configuration (4,1,3) achieved an RMSE of 2.455 and MAPE of 3.80%. Although both models performed competitively and yielded promising results, LSTM demonstrated superior accuracy in forecasting large red chili prices in dynamic market conditions
Multi View Natural Network for Cross-Project Software Defect Prediction
Full text linkSoftware Defect Prediction (SDP) plays a critical role in software engineering by enabling early identification of potentially defective modules, to assist developers and testers in prioritizing testing and inspection efforts to improve software quality and reliability. Driven by rapidly changing business requirements, defect prediction models have become increasingly essential in quality assurance workflows. Traditional approaches to SDP focused on Within-Project Defect Prediction (WPDP), where models are trained on historical data from the same project and effective under sufficient data conditions. This challenge motivates the adoption of Cross-Project Defect Prediction (CPDP), which leverages data from different projects. However, CPDP faces notable challenges including datasets distributional differences and class imbalance, which can degrade prediction performance and bias. To address these issues, recent studies have proposed data transformation, resampling, and domain adaptation techniques. In this study, we explore a multi-view learning approach using Neural Networks (NN) to enhance generalization and performance in CPDP scenarios. By leveraging multiple views of the same dataset—generated through concatenation of heterogeneous software metrics, imputation for missing values, normalization using Box-Cox transformation, and embedding-based feature transformation—we aim to construct a robust Multi-View Neural Network (MVNN). This architecture enables the integration of diverse information while mitigating the limitations of single-view learning in CPDP. Our method preserves more in-formation compared to conventional approaches that rely only on shared features. Experimental validation using benchmark SDP repositories demonstrates the competitiveness of our approach, offering improved performance over existing CPDP models and highlighting the potential of multi-view learning in defect prediction tasks
A Cascading Evaluation of Digital Population Identity in Palembang: Insights from ILPE and IPA
Full text linkSince 2022, the Indonesian government has implemented the Digital Population Identity (IKD) application, introduced by the Palembang City Population and Civil Registration Office (Disdukcapil). However, user satisfaction with IKD remains low. This study evaluates IKD user satisfaction using a cascading method combining the Electronic Public Service Index (ILPE) and Importance Performance Analysis (IPA). The ILPE calculation yields a total score of 2.682. The Information Availability (I) dimension scores highest at 0.570, reflecting strong user satisfaction with data accuracy and relevance. In contrast, the Interaction (SI) dimension scores the lowest at 0.325, highlighting the need for better communication and interaction. The IPA analysis categorizes dimensions into quadrants: Quadrant 1 (Keep Up the Good Work) includes T1 (Password Security), T4 (Reputation Recognition), T5 (Clarity of Authentication Criteria), I1 (Data Accuracy), I2 (Timely Updates), R2 (Access Availability), and R3 (Response Speed), showing excellent performance. Quadrant 2 (Concentrate Here) includes E4 (Accuracy of Data Entry Instructions) and U3 (Intuitive Navigation), requiring significant improvement. Quadrant 3 (Low Priority) includes E1 (Intuitive Navigation), E3 (Personalized Experience), T2 (Authentication Clarity), U1 (Intuitive Interface), U2 (Instruction Clarity), SI1 (Social Interaction), and SI2 (Communication Ease), with lower improvement priorities. Quadrant 4 (Possibly Overrated) contains R1 (Form Download Speed), which may be overemphasized. These findings aim to guide policy refinement, enhance public service efficiency, and improve user satisfaction
Comparison of Premium Rice Price Prediction in East Java with ARIMA and LSTM (Case Study: National Food Agency Data)
Full text linkRice price prediction plays a crucial role in maintaining economic stability and food security, especially in East Java, one of Indonesia's major rice production centers. This study aims to forecast premium rice prices in East Java using the ARIMA (AutoRegressive Integrated Moving Average) method. The data utilized in this research comprises premium rice prices obtained from the National Food Agency over the period from March 15, 2021, to October 17, 2024. The analysis process begins with data exploration to identify trends and seasonal patterns in the rice price data. Subsequently, the data is analyzed using ARIMA and LSTM methods, both recognized for their effectiveness in time-series forecasting. The ARIMA(1,1,1) model was selected due to its capability to capture price dynamics through its autoregressive, integrated, and moving average components, making it well-suited for linear data with minimal seasonal variation. LSTM was employed as a comparative model because it is a subset of Machine Learning that integrates computational models and neural network algorithms, offering potential improvements in prediction accuracy. The LSTM model used for prediction consists of four layers, each with 50 neurons, dropout rates of 20% and 30%, and a single output layer representing the predicted price. The results indicate the ARIMA model provides highly accurate price estimates with a Mean Absolute Percentage Error (MAPE) of 0.485%, whereas the LSTM model achieves a MAPE of 1.95%. These findings serve as a reference for policymakers and food industry stakeholders in formulating strategic measures to stabilize rice prices in East Java
Penggunaan Value Stream Analysis Tools (VALSAT) dan Waste Assessment Model (WAM) untuk Mereduksi Waste Pada Pabrik Timah di Pasuruan
No full textPT. XYZ merupakan pabrik penghasil lead alloy dengan menggunakan bahan baku berupa aki bekas. Produksi dilakukan melalui 3 proses yaitu, proses battery breaker, proses furnace, proses refining. Penelitian ini akan mengamati proses produksi secara menyeluruh untuk mengetahui pemborosan yang terjadi. Metode yang diterapkan adalah Waste Assessment Model (WAM) dan metode Value Stream Analysis Tools (VALSAT). Hasil dari pengamatan ini menemukan rata-rata tingkat pelayanan sebesar 87% yang berarti tingkat efektifitas pelayanan masih kurang karena masih dibawah 100% sehingga masih dapat dilakukan perbaikan. Dan untuk memperbaiki tingkat pelayanan, maka perusahaan dapat menggunakan metode WAM yaitu dengan melakukan analisis atau pengamatan terhadap pemborosan yang terjadi terlebih dahulu. Usulan perbaikan yang direkomendasikan meliputi pengeliminasian pemborosan pada battery breaker untuk permasalahan pengeringan menggunakan energi matahari dapat digantikan dengan menggunakan mesin filter press dan untuk permasalahan pengumpulan hasil crushing dari aki bekas dapat diganti dengan langsung meletakkan hasil crushing pada wadah supaya dapat lebih cepat. Sedangkan pada proses refining dapat dilakukan penambahan jumlah operator dan untuk permasalahan produk menunggu sesuai lot untuk di kemas dapat dilakukan penambahan kapasitas mesin untuk menghindari penyimpanan berlebih
Perancangan Purwarupa Mobile App Pemanfaatan Food Waste untuk Mendorong Ekonomi Sirkular sebagai Solusi Pangan
Full text linkPenumpukan food waste di Indonesia menjadi masalah krusial dengan dampak negatif yang signifikan. Fenomena food waste ini disebabkan oleh pemborosan makanan dan pengelolaan sampah yang tidak optimal. Dampaknya meliputi degradasi lingkungan, kerugian ekonomi, memperparah kelaparan, dan mengancam ketahanan pangan. Oleh karena itu, dalam penelitian ini akan dirancang model bisnis dan purwarupa mobile app pemanfaatan food waste sebagai solusi pengelolaan food waste yang terintegrasi dan efektif. Aplikasi ini diharapkan dapat mempermudah akses masyarakat terhadap makanan berlebih dan daur ulang food waste, sehingga meningkatkan pengelolaan food waste dan menciptakan ekonomi sirkular di Indonesia.
Terdapat 4 tahapan proses dasar untuk mencapai kesuksesan perancangan purwarupa ini. Tahapan tersebut meliputi identifikasi masalah, pengumpulan data dengan metode studi literatur, perancangan User Interface (UI) untuk menentukan aplikasi referensi dan konsep purwarupa, dan hasil perancangan yang merupakan hasil final dari purwarupa yang telah dibuat.
Hasil penelitian membahas tentang pembuatan ide bisnis aplikasi bernama FOODCYCLE. Perancangan purwarupa ini didasarkan pada penelitian terdahulu yang menganalisis kelayakan aplikasi food waste yang cukup serupa. Di mana penelitian tersebut menunjukkan adanya hasil yang positif dari aplikasi food waste dalam meningkatkan behavioral intention pengguna melalui model TAM (Technology Acceptance Model). Hal ini dipengaruhi oleh perceived ease of use dan perceived usefulness. Penyusunan konsep pada bagian ini juga mengacu pada aplikasi referensi. Hasil akhir dari penelitian ini terbagi menjadi karya utama yang merupakan purwarupa mobile app dalam bentuk UI dan karya pendukung berupa rancangan desain media sosial, banner, dan brosur mobile ap
Hand Sign Virtual Reality Data Processing Using Padding Technique
Full text linkThis study focuses on addressing the challenges of processing hand sign data in Virtual Reality environments, particularly the variability in data length during gesture recording. To optimize machine learning models for gesture recognition, various padding techniques were implemented. The data was gathered using the Meta Quest 2 device, consisting of 1,000 samples representing 10 American Sign Language hand sign movements. The research applied different padding techniques, including pre- and post-zero padding as well as replication padding, to standardize sequence lengths. Long Short-Term Memory networks were utilized for modeling, with the data split into 80% for training and 20% for validation. An additional 100 unseen samples were used for testing. Among the techniques, pre-replication padding produced the best results in terms of accuracy, precision, recall, and F1 score on the test dataset. Both pre- and post-zero padding also demonstrated strong performance but were outperformed by replication padding. This study highlights the importance of padding techniques in optimizing the accuracy and generalizability of machine learning models for hand sign recognition in Virtual Reality. The findings offer valuable insights for developing more robust and efficient gesture recognition systems in interactive Virtual Reality environments, enhancing user experiences and system reliability. Future work could explore extending these techniques to other Virtual Reality interactions
Metode Agile Scrum pada Rancang Bangun Sistem Informasi Manajemen Pelatihan Pegawai Perusahaan
Full text linkDalam penelitian ini, metode Agile Scrum diterapkan untuk mengembangkan Sistem Informasi Manajemen Pelatihan Pegawai berbasis web di PT Kliring Berjangka Indonesia. Sebagai Badan Usaha Milik Negara yang bergerak di bidang kliring penjaminan dan penyelesaian transaksi berjangka, PT Kliring Berjangka Indonesia memiliki tanggung jawab besar dalam mengembangkan kompetensi pegawainya guna memberikan layanan yang berkualitas. Namun, pengelolaan pelatihan pegawai dengan berbagai divisi dan jenis kompetensi menjadi tantangan, terutama karena belum adanya sistem yang terpusat. Hal ini menghambat perencanaan, evaluasi pelatihan, serta rekapitulasi data untuk keperluan audit.
Metode Agile Scrum dipilih karena mampu memfasilitasi interaksi intens antara product owner dan stakeholder, serta memberikan transparansi melalui sprint review dan retrospective. Metode ini juga memungkinkan fleksibilitas terhadap perubahan requirement, yang dalam penelitian ini menyebabkan penambahan sprint dari 5 menjadi 6. Sistem yang dikembangkan kemudian diuji menggunakan blackbox testing dan dievaluasi melalui User Acceptance Testing (UAT) oleh 12 calon pengguna. Hasil pengujian menunjukkan bahwa seluruh fungsi sistem berjalan dengan baik, sementara kuesioner UAT memperoleh nilai 80%, menandakan tingkat penerimaan yang baik dan kesuksesan sistem dalam mengatasi masalah yang dihadapi oleh staf SDM dan pegawai PT Kliring Berjangka Indonesia
Analisis Pengaruh Kinerja Mitra Kerja Terhadap Suplai Raskin Menggunakan Regresi Berganda-Path Analysis, Studi Kasus: Pengadaan Gabah dan Beras
Full text linkHasil monitoring dan evaluasi pelaksanaan Program Raskin menyatakan lemahnya pengawasan dan kontrol membuat kinerja mitra kerja Bulog ikut melemah sehingga berakibat terhadap proses penyaluran raskin. Keterlambatan pengiriman barang dan kuantitas kontrak yang tidak terpenuhi oleh mitra kerja diduga berpengaruh pada proses bisnis yang ada di Bulog, dimana penyaluran raskin merupakan salah satu proses bisnis utamanya. Analisis diperlukan untuk mengetahui bagaimana pengaruh faktor kinerja mitra kerja terhadap suplai raskin sehingga mampu memberikan rekomendasi tindakan yang tepat pada level manajerial Bulog. Analisis yang dilakukan pada penelitian ini menggunakan metode regresi berganda yang dikembangkan dengan metode path analysis dengan lima variabel bebas dan satu variabel terikat. Variabel bebas merepresentasikan kinerja mitra kerja yang mencakup faktor pemenuhan kuantitas beras berdasarkan kualitas atau LHPK, kuantitas realisasi tahun sebelumnya, kontribusi mitra kerja terhadap target, kapasitas produksi, dan pemenuhan hari kontrak oleh mitra kerja. Sedangkan variabel terikat dari penelitian ini ialah suplai raskin. Hasil analisis menunjukkan bahwa kinerja mitra kerja secara keseluruhan memiliki pengaruh positif terhadap kontribusi mitra kerja dalam memenuhi target Raskin. Pengaruh terbesar terdapat pada saat jumlah realisasi mitra kerja sama dengan target. LHPK yang diterima juga memiliki pengaruh terbesar terhadap kinerja mitra kerja, jumlah realisasi dan penetapan target mitra kerja