Alfred Yulius Arthadi Putra
Universitas Widya Dharma Pontianak

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

MENINGKATKAN KEMAMPUAN SISWA SMA DALAM PEMBUATAN JARINGAN LOCAL AREA NETWORK Fredrikus Suarezsaga; Alfred Yulius Arthadi Putra; Amok Darmianto; Kristina Kristina
JMM (Jurnal Masyarakat Mandiri) Vol 7, No 2 (2023): April
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v7i2.13462

Abstract

Abstrak: Jaringan komputer merupakan suatu cabang ilmu pengetahuan di bidang komputer dan dianggap sebagai pengimplementasian yang sangat penting mengingat jaringan komputer banyak diterapkan di berbagai bidang. Jaringan komputer memiliki beberapa klasifikasi berdasarkan lokasi, salah satunya adalah jaringan local area network (LAN). Pembuatan jaringan LAN sangat sederhana. Pelatihan pembuatan jaringan LAN dilaksanakan di SMA Widya Pratama Kubu Raya pada tanggal 12 November 2022. Tujuan dari kegiatan ini adalah mengenalkan kepada siswa bagaimana membuat sebuah kabel jaringan komputer lokal dan berbagi berkas di area lokal. Metode yang dilaksanakan berupa penyuluhan dan praktikum. Kegiatan ini diikuti oleh 27 siswa kelas XII. Hasil dari kegiatan ini dievaluasi dengan dua instrumen, yaitu tes dan survey kualitas PKM. Dari pelatihan yang sudah dilaksanakan, berdasarkan hasil pre-test dan post-test siswa mendapatkan peningkatan pengetahuan mengenai jaringan komputer sebesar 70,1 % dan untuk tingkat kualitas kegiatan ini sebanyak 91,36 % menyatakan setuju bahwa kegiatan ini bermanfaat. Abstract: Computer network is a dicipline of science in the computers science and is considered a very important implementation considering that computer networks are widely applied in various fields. Computer networks have several classifications based on location/geography, one of which is a local area network (LAN). In order to make a LAN network is very simple. LAN network creation training was held at SMA Widya Pratama Kubu Raya on November 12, 2022. The purpose of this activity is to introduce students to how to make a local computer network cable and share files in the local area. The method implemented is in the form of tutorial and practicum. This activity was attended by 27 students of class XII. The results were evaluated with two instruments, the test and the survey to measure of quality. From the test that has been carried out, based on the results of the pre-test and post-test students get an increase in knowledge about computer networks by 70.1% and for the quality level of this activity as much as 91.36% agree that this activity is useful.  
Short-Term Electricity Load Forecasting Using Hybrid CNN–LSTM Models on the UCI Electricity Load Dataset Ricky Imanuel Ndaumanu; Alfred Yulius Arthadi Putra
Technema: Journal of Intelligent Engineering and Computing Vol. 1 No. 1 (2026): March: Technema: Journal of Intelligent Engineering and Computing
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Accurate short-term electricity load forecasting (STLF) is critical for efficient energy management, demand response, and grid stability in modern residential environments. This study presents an empirical investigation of a hybrid convolutional neural network–long short-term memory (CNN–LSTM) model applied to the UCI Electricity Load dataset, integrating convolutional layers to extract localized temporal features and stacked LSTM layers to model long-term dependencies across households. The model is trained using Python and TensorFlow on a GPU-enabled workstation, with preprocessing including normalization, sliding-window sequence generation, and train-validation-test splitting. Performance is evaluated through mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and k-fold cross-validation. Comparative benchmarking against LSTM, CNN-GRU, and multi-scale CNN-LSTM architectures demonstrates superior accuracy, stability, and generalizability of the proposed hybrid model. Sensitivity and interpretability analyses further reveal critical temporal patterns, feature contributions, and operational insights, facilitating actionable energy management decisions. These results substantiate the hybrid CNN–LSTM approach as a robust, interpretable, and operationally relevant solution for STLF applications.
PENGARUH LEARNING RATE TERHADAP KINERJA DAN KONVERGENSI MODEL INDOBERT-BILSTM-CRF PADA NAMED ENTITY RECOGNITION BAHASA INDONESIA: IMPACT OF LEARNING RATE ON INDOBERT-BILSTM-CRF PERFORMANCE AND CONVERGENCE FOR INDONESIAN NAMED ENTITY RECOGNITION Alfred Yulius Arthadi Putra; Fredrikus Suarezsaga; Kristina
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p271-280

Abstract

Named Entity Recognition (NER) merupakan salah satu tugas penting dalam Natural Language Processing yang digunakan untuk mengidentifikasi dan mengklasifikasikan entitas dalam teks. Kinerja model NER berbasis pre-trained language model tidak hanya dipengaruhi oleh arsitektur, tetapi juga oleh konfigurasi hiperparameter, khususnya learning rate. Penelitian ini bertujuan menganalisis pengaruh learning rate terhadap kinerja dan konvergensi model IndoBERT-BiLSTM-CRF pada NER Bahasa Indonesia. Empat nilai learning rate diuji, yaitu 1×10-5, 2×10-5, 3×10-5, dan 5×10-5, dengan konfigurasi model lainnya dipertahankan tetap. Setiap konfigurasi dijalankan menggunakan tiga random seed untuk mengevaluasi kestabilan hasil. Kinerja model diukur menggunakan Token Macro-F1 dan Entity F1, sedangkan konvergensi dianalisis berdasarkan perubahan training loss dan Validation Entity F1 pada setiap epoch. Hasil menunjukkan bahwa peningkatan learning rate memberikan peningkatan kinerja hingga rentang tertentu. Entity F1 meningkat dari 0,8951 pada 1×10-5 menjadi 0,9392 pada 5×10-5, sedangkan Token Macro-F1 meningkat dari 0,5848 menjadi 0,7902. Dari sisi konvergensi, 5×10-5 mencapai Validation Entity F1 sebesar 0,90 pada epoch ke-5, lebih cepat dibandingkan 3×10-5 pada epoch ke-6 dan 2×10-5 pada epoch ke-9. Meskipun 5×10-5 memberikan rata-rata kinerja tertinggi, perbedaan Entity F1 dengan 3×10-5 sangat kecil. Temuan ini menunjukkan bahwa learning rate memberikan pengaruh yang lebih kuat terhadap kecepatan konvergensi, sementara peningkatan kinerja akhir mulai mengalami saturasi pada rentang 3×10-5 hingga 5×10-5.   Named Entity Recognition (NER) is an important Natural Language Processing task for identifying and classifying entities in text. The performance of NER models based on pre-trained language models is influenced not only by the model architecture but also by hyperparameter configuration, particularly the learning rate. This study investigates the effect of learning rate on the performance and convergence of an IndoBERT-BiLSTM-CRF model for Indonesian NER. Four learning rates were evaluated, namely 1×10-5, 2×10-5, 3×10-5, dan 5×10-5, while keeping the remaining model configurations unchanged. Each configuration was evaluated using three random seeds to assess performance stability. Model performance was measured using Token Macro-F1 and Entity F1, while convergence was analyzed based on training loss and Validation Entity F1 across epochs. The results show that increasing the learning rate improves model performance up to a certain range. Entity F1 increased from 0.8951 at 1×10-5 to 0.9392 at 5×10-5, while Token Macro-F1 increased from 0.5848 to 0.7902. In terms of convergence, the 5×10-5 configuration reached a Validation Entity F1 of 0.90 at epoch 5, earlier than 3×10-5 at epoch 6 and 2×10-5, at epoch 9. Although 5×10^(-5) achieved the highest average performance, its Entity F1 was only marginally higher than that of 3×10-5. These findings indicate that learning rate has a stronger effect on convergence speed, while final performance begins to saturate within the range of 3×10-5, to 5×10-5.
SISTEM REKOMENDASI LEMBAGA KURSUS KETERAMPILAN DAN BIMBINGAN BELAJAR DI KOYA PONTIANAK BERBASIS INTEGRASI PAIRWISE COMPARISON DAN CASE-BASED REASONING: A RECOMMENDATION SYSTEM FOR SKILLS TRAINING INSTITUTIONS AND TUTORING CENTERS IN PONTIANAK CITY USING AN INTEGRATION OF PAIRWISE COMPARISON AND CASE-BASED REASONING Kristina Kristina; Fredrikus Suarezsaga; Ricky Imanuel Ndaumanu; Alfred Yulius Arthadi Putra
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p231-240

Abstract

Pemilihan lembaga kursus keterampilan dan bimbingan belajar non-formal yang sesuai dengan kebutuhan individu di Kota Pontianak sering kali terkendala oleh keterbatasan akses informasi terstruktur dan kompleksitas multi-kriteria. Sebagian besar sistem rekomendasi yang ada saat ini berfokus pada platform pembelajaran daring (online-course) dan tidak mempertimbangkan batas-batas spasial serta karakteristik fasilitas fisik secara objektif. Penelitian ini bertujuan membangun sistem rekomendasi lembaga kursus keterampilan dan bimbingan belajar non-formal berbasis web di Kota Pontianak dengan mengintegrasikan metode Pairwise Comparison (PWC) dan Case-Based Reasoning (CBR). PWC digunakan untuk pembobotan kriteria secara terstruktur berdasarkan preferensi pengguna, sedangkan CBR digunakan untuk menghitung tingkat kemiripan (similarity score) antara kasus baru dan basis pengetahuan. Hasil pengujian bobot kriteria menghasilkan nilai pembobotan yang konsisten dengan Consistency Ratio (CR) sebesar 0,0206 (<0,1). Adapun kriteria program/jnis Kursus (C1) memiliki bobot tertinggi (0,3608),  biaya kursus (C2) berbobot 0,2284, fasilitas (C3) berbobot 0,1543 , lokasi/jarak (C4) berbobot 0,0807, kualitas pengajar (C5) berbobot 0,1241, dan jadwal kursus (C6) berbobot 0,0516. Pengujian sistem meliputi pengujian fungsional Black Box Testing dengan tingkat keberhasilan 100%, dan pengujian System Usability Scale (SUS) kepada 20 responden yang menghasilkan skor rata-rata 78,25 (kategori Good/ Grade B). Integrasi PWC dan CBR terbukti mampu memberikan rekomendasi lembagakursus fisik yang presisi dan fleksibel sesuai dengan kebutuhan calon peserta didik.   The selection of non-formal skills courses and tutoring institutions that suit individual needs in Pontianak City is often hampered by limited access to structured information and the complexity of the criteria used. Most existing recommendation systems focus on online learning platforms and do not objectively consider spatial boundaries and physical facility characteristics. This study aims to build a web-based recommendation system for non-formal skills courses and tutoring in Pontianak City by integrating the Pairwise Comparison (PWC) method from the Analytic Hierarchy Process (AHP) and Case-Based Reasoning (CBR). PWC is used to weight the criteria in a structured manner based on user preferences, while CBR is used to calculate the similarity score between new cases and the knowledge base. The results of the criteria weighting test produce a consistent weighting value with a Consistency Ratio (CR) of 0.0206 (<0.1). The criteria for program/course type (C1) have the highest weight (0.3608), course fee (C2) has a weight of 0.2284, facilities (C3) have a weight of 0.1543, location/distance (C4) have a weight of 0.0807, instructor quality (C5) have a weight of 0.1241, and courses schedule (C6) have a weight of 0.0516. System testing includes functional black-box testing with a success rate of 100% and usability testing using the System Usability Scale (SUS) with 20 respondents, which resulted in an average score of 78.25 (Good/Grade B category). The integration of PWC and CBR has been shown to provide precise and flexible recommendations for physical course locations based on the needs of prospective students.