Claim Missing Document
Check
Articles

Extending Hybrid GRG-NS With LSTM-Based Demand Forecasting for Dynamic Multi-Depot Routing in Disaster Logistics Dedy Hartama; Poningsih Poningsih; Lili Tanti
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1444

Abstract

Disaster logistics management requires accurate demand forecasting and efficient routing optimization to ensure timely distribution of emergency supplies under dynamic and uncertain conditions. Conventional routing approaches often experience limitations in handling fluctuating disaster demand, resulting in inefficient distribution performance and increased operational costs. This study proposes an integrated LSTM–Hybrid Generalized Reduced Gradient and Neighborhood Search (LSTM–Hybrid GRG–NS) framework for disaster-demand forecasting and routing optimization. The proposed approach combines Long Short-Term Memory (LSTM) for sequential demand prediction with a hybrid GRG–NS optimization mechanism to improve routing efficiency and solution convergence. Experimental evaluation was conducted using disaster-demand scenarios and routing datasets to assess forecasting and optimization performance. The forecasting results demonstrated strong predictive capability with low MAE, RMSE, and MAPE values, indicating that the LSTM model effectively captured temporal demand patterns. Furthermore, the routing optimization results showed that the proposed framework successfully generated stable and near-optimal routing solutions while maintaining full demand fulfillment and efficient vehicle utilization. The convergence analysis also confirmed that the optimization process converged consistently within a limited number of iterations. Overall, the proposed LSTM–Hybrid GRG–NS framework provides an effective and reliable decision-support approach for proactive humanitarian logistics and disaster-routing management.
Performance Comparison of Decision Tree, KNN, and Naive Bayes for Air Quality Classification Yan Yang Thanri; Juli Iriani Iriani; Lili Tanti Tanti; Luthfi Zaidi Zaidi
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i2.5121

Abstract

Air quality degradation has become a critical environmental and public health issue, necessitating accurateand reliable classification models to support effective monitoring systems. This study aims toconduct a comparative analysis of four machine learning algorithms-Decision Tree, k-Nearest Neighbor (kNN), Naive Bayes, and Stochastic Gradient Descent (SGD)-for classifying air quality using environmental parameters, including particulate matter ≤ 2.5 μm (PM2.5), carbon monoxide (CO), temperature, humidity, nitrogen dioxide (NO2), and sulfur dioxide (SO2). The methodology employssupervised learning, where each model is trained and evaluated using classification accuracy, area under the receiver operating characteristic curve (AUC), F1-Score, precision, recall, and Matthews Correlation Coefficient (MCC), supported by ROC curve and confusion matrix analyses. The results show that the Decision Tree algorithm achieves the best overall performance, attaining a classification accuracy of 93.8% with a balanced precision, recall, and F1-Score, indicating strong and consistent predictive capability. The kNN and Naive Bayes models record the highest AUC values (0.980 and 0.982, respectively), demonstrating excellent class separability, although their accuracy and F1-Score are lower than those of the Decision Tree. In addition, the SGD model, implemented with a modified Huber loss function and L2 regularization, provides interpretable feature-weight analysis, identifyingPM2.5 and CO as dominant indicators of the Hazardous air quality class, while temperature and humidity significantly influence the Fair and Good classes. Based on the comprehensive evaluation, the Decision Tree algorithm is recommended as the most reliable model for accurate air quality classification, whereas the SGD model is particularly suitable for feature contribution analysis to enhance interpretability. These findings offer practical insights for selecting appropriate machine learning models in air quality monitoring and decision-support systems.
Perbandingan Kinerja Metode Random Forest dan Logistic Regression Dalam Konteks Prediksi Penerima Beasiswa Bagi Mahasiswa Baru Muhammad Suhada; Roslina Roslina; Lili Tanti
Jurnal Minfo Polgan Vol. 15 No. 2 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i2.16473

Abstract

Penerimaan beasiswa bagi mahasiswa baru merupakan salah satu upaya perguruan tinggi dalam meningkatkan kualitas sumber daya manusia serta memberikan kesempatan pendidikan yang merata. Namun, proses seleksi penerima beasiswa sering menghadapi kendala dalam hal efektivitas dan akurasi, terutama ketika harus mempertimbangkan berbagai faktor seperti prestasi akademik, kondisi ekonomi, serta aktivitas non-akademik mahasiswa. Oleh karena itu, diperlukan pendekatan berbasis machine learning untuk mendukung pengambilan keputusan yang lebih objektif dan tepat sasaran. Penelitian ini bertujuan untuk membandingkan kinerja dua metode machine learning, yaitu Random Forest dan Logistic Regression, dalam memprediksi calon penerima beasiswa bagi mahasiswa baru. Dataset yang digunakan berasal dari data historis mahasiswa dengan variabel penentu yang meliputi aspek akademik, ekonomi, dan demografis. Proses penelitian mencakup tahap pra-pemrosesan data, pembagian dataset, pembangunan model, serta evaluasi performa menggunakan metrik akurasi, presisi, recall, dan F1-score. Diharapkan hasil penelitian ini dapat menunjukkan metode mana yang lebih unggul dalam hal kinerja prediksi, sekaligus memberikan kontribusi praktis bagi perguruan tinggi dalam menyusun sistem pendukung keputusan penerimaan beasiswa yang lebih transparan, akurat, dan efisien. Selain itu, penelitian ini juga memberikan nilai tambah dalam pengembangan penerapan machine learning di bidang pendidikan, khususnya pada aspek manajemen beasiswa.
Track Record Model in Employee Performance Optimization Using Weight Product Method Safrizal; Lili Tanti; Dio Febrian Surbakti; Nurainun
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.721

Abstract

Employee performance improvement is a crucial aspect for the growth and success of a company, especially in the agricultural sector that relies on the quality and competence of human resources. However, subjective and manual employee assessments often face challenges, such as high levels of subjectivity and the time required to complete the process. To overcome these obstacles, this study proposes the use of the Weighted Product (WP) method as an approach to building a track record model in employee performance assessment. This study involves several methodological stages, first by studying the literature related to decision support systems, WP methods, track records, and employee performance assessments. Furthermore, data collection is carried out from a dataset that includes monthly assessments of employee performance based on several criteria such as attendance, cooperation, work quantity, responsibility, and others. The next process involves modeling, where the WP model is designed to produce the maximum total value of the existing assessment criteria. Model validation is carried out through two approaches, namely the Criterion-related Validity Test and the Internal Consistency Test. The test results show that the WP model has a Criterion-related Validity of 0.9851, indicating a strong relationship between the employee scores generated and the assessments given by the supervisor. In addition, Cronbach's alpha reached a value of 1.0, indicating excellent internal reliability of the model. Thus, the use of the WP method in the employee performance tracking system can be considered effective and can improve objectivity and efficiency in employee performance assessment in the context of agricultural companies. This method not only helps in identifying high-performing employees, but also in motivating them to achieve the highest performance standards, which in turn can improve the overall operational quality and reputation of the company
Implementasi Model LKS Berbasis Teknologi untuk Pembelajaran Efektif di SMA Swasta Medan Lili Tanti; Safrizal; Deni Adhar; Clarensia Mende Simalango
ORAHUA : Jurnal Pengabdian Kepada Masyarakat Vol. 2 No. 02 (2025): Januari
Publisher : Faatuatua Media Karya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70404/orahua.v2i02.126

Abstract

Penggunaan Model Lembar Kerja Siswa (LKS) berbasis teknologi melalui platform Wizer.me telah menjadi solusi inovatif dalam meningkatkan efektivitas pembelajaran di SMA Swasta Nurani Medan. Penelitian ini bertujuan untuk mengkaji implementasi dan dampak penggunaan teknologi ini terhadap keterlibatan dan hasil belajar siswa. Studi pendahuluan dilakukan untuk memahami masalah yang dihadapi dalam pembelajaran, sementara pelatihan diberikan kepada guru untuk menguasai penggunaan Wizer.me. Guru-guru dibimbing dalam pengembangan LKS yang sesuai dengan kurikulum dan kebutuhan pembelajaran siswa. Implementasi LKS dalam pembelajaran menghasilkan peningkatan keterlibatan siswa dan motivasi belajar mereka. Evaluasi dilakukan melalui observasi, wawancara, dan kuesioner untuk mengevaluasi persepsi guru dan siswa. Hasil menunjukkan bahwa penggunaan LKS berbasis teknologi telah meningkatkan interaksi antara guru dan siswa serta antarsiswa, sementara hasil belajar siswa juga meningkat. Guru dan siswa menilai positifpenggunaan teknologi ini dalam pembelajaran. Kesimpulannya, penggunaan LKSberbasis teknologi melalui Wizer.me adalah solusi yang efektif dalam meningkatkanefektivitas pembelajaran di SMA Swasta Nurani Medan, memberikan kontribusi positif bagi keterlibatan dan hasil belajar siswa. Dengan adopsi teknologi ini, diharapkan pembelajaran di SMA Swasta Nurani Medan dapat menjadi lebih dinamis dan relevan dengan tuntutan zaman, menciptakan lingkungan pembelajaran yang inklusif dan berdaya guna bagi siswa.
Membangun Kecakapan Digital Siswa Kejuruan melalui Eksplorasi Computer-Based Test (CBT) dalam Evaluasi Pembelajaran Safrizal; Andrian Syahputra; Lili Tanti; Rabiana Saragih; M. Haidil Umam
ORAHUA : Jurnal Pengabdian Kepada Masyarakat Vol. 3 No. 01 (2025): Juli
Publisher : Faatuatua Media Karya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70404/orahua.v3i01.183

Abstract

Revolusi digital dalam dunia pendidikan menuntut transformasi paradigma evaluasi pembelajaran, khususnya di tingkat pendidikan kejuruan. Penelitian ini mengeksplorasi implementasi Computer-Based Test (CBT) sebagai instrumen strategis untuk membangun kecakapan digital siswa di tingkat sekolah menengah kejuruan. Metodologi penelitian mengadopsi pendekatan kualitatif-kuantitatif dengan desain action research yang melibatkan 180 siswa dari berbagai program keahlian. Implementasi CBT dilakukan melalui tahapan analisis kebutuhan, pengembangan platform, pelatihan pengguna, dan evaluasi efektivitas. Hasil penelitian menunjukkan peningkatan signifikan dalam kecakapan digital siswa, dengan rata-rata persentase respons positif meningkat sebesar 52,7% berdasarkan hasil angket pre-post kegiatan. Partisipasi aktif siswa dalam mengoperasikan platform CBT mencapai 92,3%, sementara tingkat kepuasan terhadap sistem evaluasi digital mencapai 87,5%. Inovasi ini berhasil mengintegrasikan teknologi evaluasi dengan pengembangan kompetensi digital, menciptakan ekosistem pembelajaran yang adaptif dan relevan dengan tuntutan industri 4.0. Implementasi CBT tidak hanya meningkatkan efisiensi proses evaluasi, tetapi juga mengembangkan literasi teknologi siswa sebagai bekal menghadapi dunia kerja yang semakin tergantung pada teknologi digital.
Extending Hybrid GRG-NS With LSTM-Based Demand Forecasting for Dynamic Multi-Depot Routing in Disaster Logistics Dedy Hartama; Poningsih Poningsih; Lili Tanti
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1444

Abstract

Disaster logistics management requires accurate demand forecasting and efficient routing optimization to ensure timely distribution of emergency supplies under dynamic and uncertain conditions. Conventional routing approaches often experience limitations in handling fluctuating disaster demand, resulting in inefficient distribution performance and increased operational costs. This study proposes an integrated LSTM–Hybrid Generalized Reduced Gradient and Neighborhood Search (LSTM–Hybrid GRG–NS) framework for disaster-demand forecasting and routing optimization. The proposed approach combines Long Short-Term Memory (LSTM) for sequential demand prediction with a hybrid GRG–NS optimization mechanism to improve routing efficiency and solution convergence. Experimental evaluation was conducted using disaster-demand scenarios and routing datasets to assess forecasting and optimization performance. The forecasting results demonstrated strong predictive capability with low MAE, RMSE, and MAPE values, indicating that the LSTM model effectively captured temporal demand patterns. Furthermore, the routing optimization results showed that the proposed framework successfully generated stable and near-optimal routing solutions while maintaining full demand fulfillment and efficient vehicle utilization. The convergence analysis also confirmed that the optimization process converged consistently within a limited number of iterations. Overall, the proposed LSTM–Hybrid GRG–NS framework provides an effective and reliable decision-support approach for proactive humanitarian logistics and disaster-routing management.
EkspediGo Implementation for Transparent Shipment Tracking and Efficient Expedition Operations Lili Tanti; Mas Ayoe Elhias Nasution; Fhery Agustin; Yan Yang Thanri; Zulfa Khairunnisa; Romi Antoni; Khairun Dini
Jurnal IPTEK Bagi Masyarakat Vol 6 No 2 (2026)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/j-ibm.v6i2.1809

Abstract

Micro, small, and medium-sized expedition enterprises often rely on manual records, limiting operational efficiency and shipment transparency. This community service program implemented EkspediGo, a web-based expedition management system, at a partner logistics business. The participatory implementation comprised needs analysis, system configuration, role-based training for administrators, management, couriers, and customers, on-the-job mentoring, and evaluation. A descriptive before-after comparison showed that transaction recording time decreased from about 15 to 3 minutes, recording errors from 12-15 to 1-2 cases per month, monthly reporting time from about 2 working days to 15 minutes, and shipment-status complaints from 18 to 4 per month. Customers also gained independent tracking through waybill numbers. The findings indicate improved operational transparency and efficiency during the observed period, although replication at additional partners is required.
Implementing a Web-Based Digital Service System with User Assistance for Service Administration Mas Ayoe Elhias Nst; Lili Tanti; Budi Triandi; Rehan Nurli Pramudita Ginting
Jurnal IPTEK Bagi Masyarakat Vol 6 No 2 (2026)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/j-ibm.v6i2.1823

Abstract

This community service program implemented and disseminated a web-based digital service system at PT XXX to integrate catalog management, service requests, status monitoring, communication, document submission, and reporting. A participatory, descriptive-evaluative approach was used through needs assessment, system review, preparation of role-based manuals, demonstrations, guided simulations, and observation. Activities involved four partner personnel over two days. Evaluation covered seven core activities and classified 28 task-participant observations as completed independently, completed with assistance, or not completed. Results showed that 21 observations (75%) were completed independently, seven (25%) with assistance, and none were incomplete. The system and manuals therefore supported the initial implementation of a structured service workflow during the assisted simulation. These findings do not demonstrate improvements in efficiency, satisfaction, or operational performance because no baseline, processing-time, error-rate, or longitudinal usage data were collected. Further evaluation using usage logs, usability measures, and follow-up monitoring is required.
Co-Authors adhar, Deni Adhar, Deni Adhar Agung RM Alam Ahmad, Ahmad Syah Lubis Ahsanul Huda Albert Putra Nias Manao Alim Murtani Alvian Julianto Hutajulu alya, Alya Rahmadani Andra Alfira Andra Alfitra Andrian Syahputra Anggi, Anggi Canita Simanjuntak Ayu Nadya Ayuni Syahputri Aziz Ritonga, Mirwan Bob Subahan Riza Bob Subhan Riza Bob Subhan Riza Bob Subhan Riza Bob Subhan Riza, Bob Subhan Budi Triandi Budi Triandi Budi Triandi, Budi Clarensia Mende Simalango Daifiria Daifiria Dedy Hartama Deni Adhar Deni Adhar Deni Adhar Adhar Deni Anggara Devi Pratiwi Putri Dewi Kartika Dhooni, Dhoni Briliant Dio Febrian Surbakti Efendi, Syahril Erica Rian Safitri Evri Ekadiansyah fachrie, Fachrie Ditya Faisal Tanjung Fauzan Arif Feberianus Zai Fhery Agustin Fretty S Siahaan Gilang Dwi Fahri Harahap Handoko, Muhammad Yan Handoko Putra F Hartama, Dedy Hartati Tammamah Lubis Herman Mawengkang Indah Widiastuti Iwan Fitrianto Rahmad Jasri, Jasri Ramadhan Juli Iriani Juli Iriani Juli Iriani Juli Iriani Iriani Juli Iriani, Juli Juni Ismail Khairul Fajri Khairul Ummi Khairun Dini Lahmudin Sipahutar Lubis, Hartati Tammamah Luthfi Zaidi Zaidi M Rizky M Zendi Lubis M. Aidil Fitra Wahyudi M. Haidil Umam Mangunsong, Puja Mas Ayoe Elhias Nasution Mas Ayoe Elhias Nst Mawardah Azzahra Maya Silvi Lydia Muhammad Daud Muhammad Faris Muhammad Suhada Nanda Setiawan Nety Juwita Lubis Nurainun Nurhayati Nurhayati Pairin, Yusfrizal Bin Patuan Putra Wijaya Sitorus Poningsih Poningsih Poningsih Poningsih, Poningsih Rabiana Saragih Ratih Puspasari Ratih Puspasari Ratih, Ratih Puspasari Rehan Nurli Pramudita Ginting Ridho, Irdian Riza, Bob Subahan Rofiqoh Dewi Romi Antoni Roslina Roslina Roslina Roslina Roslina Roslina, Roslina Safitri, Erica Rian Safrizal Safrizal Safrizal Safrizal Safrizal Safrizal Safrizal Safrizal Salwani D, Zuki Salwani D Susianto Susianto Syefira Arrafah Tasya Ardilah Thanri, Yan Yang Wanayumini Windy, Micky Alviansyah Wirhan Fahrozi Yanyang Thanri Yudhi Andrian Yulika Ababil Zulfa Khairunnisa _, Safrizal