Garuda - Garba Rujukan Digital

A BACKTRACKING APPROACH FOR SOLVING PATH PUZZLES Sakti, Joshua Erlangga; Arzaki, Muhammad; Wulandari, Gia Septiana
Journal of Fundamental Mathematics and Applications (JFMA) Vol 6, No 2 (2023)
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jfma.v6i2.18155

We study algorithmic aspects of the Path puzzle--a logic puzzle created in 2013 and confirmed NP-complete (Non-deterministic Polynomial-time-complete) in 2020. We propose a polynomial time algorithm for verifying an arbitrary Path puzzle solution and a backtracking-based method for finding a solution to an arbitrary Path puzzle instance.To our knowledge, our study is the first rigorous investigation of an imperative algorithmic approach for solving Path puzzles. We prove that the asymptotic running time of our proposed method in solving an arbitrary Path puzzle instance of size $m \times n$ is $O(3^{mn})$. Despite this exponential upper bound, experimental results imply that a C++ implementation of our algorithm can quickly solve $6 \times 6$ Path puzzle instances in less than 30 milliseconds with an average of 3.02 milliseconds for 26 test cases. We finally prove that an $m \times n$ Path puzzle instance without row and column constraints is polynomially solvable in $O(\max\{m,n\})$ time.

Optimizing Emotion Recognition with Wearable Sensor Data: Unveiling Patterns in Body Movements and Heart Rate through Random Forest Hyperparameter Tuning Nur, Zikri Kholifah; Wijaya, Rifki; Wulandari, Gia Septiana
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7761

This research delves into the utilization of smartwatch sensor data and heart rate monitoring to discern individual emotions based on body movement and heart rate. Emotions play a pivotal role in human life, influencing mental well-being, quality of life, and even physical and physiological responses. The data were sourced from prior research by Juan C. Quiroz, PhD. The study enlisted 50 participants who donned smartwatches and heart rate monitors while completing a 250-meter walk. Emotions were induced through both audio-visual and audio stimuli, with participants' emotional states evaluated using the PANAS questionnaire. The study scrutinized three scenarios: viewing a movie before walking, listening to music before walking, and listening to music while walking. Personal baselines were established using DummyClassifier with the 'most_frequent' strategy from the sklearn library, and various models, including Logistic Regression and Random Forest, were employed to gauge the impacts of these activities. Notably, a novel approach was undertaken by incorporating hyperparameter tuning to the Random Forest model using RandomizedSearchCV. The outcomes showcased substantial enhancements with hyperparameter tuning in the Random Forest model, yielding mean accuracies of 86.63% for happy vs. sad and 76.33% for happy vs. neutral vs. sad.

Comparative Prediction of Physical Fatigue Patterns in Bandung, Indonesia Workers using CNN and ANN Ardiansyah, Muhammad Fikri Raihan; Wijaya, Rifki; Wulandari, Gia Septiana
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.7280

This research explores the impact of physical fatigue on task performance and evaluates the effectiveness of Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) in predicting fatigue levels. Physical fatigue, as a critical factor influencing performance and safety, serves as a signal for the body's need for rest. Utilizing a smartwatch with heart rate sensors, this study applies ANN for subjective fatigue assessments and CNN for time series analysis. With a structured approach encompassing data collection, preprocessing, and model training, a confusion matrix evaluates the model's performance. Results indicate an accuracy of 92.4% for the ANN model with an RMSE of 0.275, while the CNN model achieves an accuracy of 85.46% with an RMSE of 0.381. These findings affirm the effectiveness of both models in predicting fatigue, providing valuable insights for future research and emphasizing the importance of comprehensive data analysis for a nuanced understanding of individual performance (Number of data: 149,796 from 6 subjects).

Knowledge graph completion for scholarly knowledge graph Taufiqurrahman, Taufiqurrahman; Wiharja, Kemas Rahmat Saleh; Wulandari, Gia Septiana
Bulletin of Social Informatics Theory and Application Vol. 8 No. 2 (2024)
Publisher : Association for Scientific Computing Electrical and Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/businta.v8i2.657

Scholarly knowledge graph is a knowledge graph that is used to represent knowledge contained in scientific publication documents. The information we can find in a scientific publication document is as follows: author, institution, name of journal/conference, and research topic. A knowledge graph that has been built is usually still not perfect. Some incomplete information may be found. To add the missing information, we can use knowledge graph completion, which is a method for finding missing or incorrect relationships to improve the quality of a knowledge graph. Knowledge graph completion can be carried out on a scholarly knowledge graph by adding new entities and relationships to produce further information in the scholarly knowledge graph. The data added to the scholarly knowledge graph are only other papers of first author entity, the research field of first author entity, and a description of the conference/journal entity. The result shows that the scholarly knowledge graph was completed by adding 81% correct data for other papers of first author entity, 80.3% correct data for the research field of first author entity, and 53.9% correct data for the description of the conference/journal.

Optimizing Emotion Recognition with Wearable Sensor Data: Unveiling Patterns in Body Movements and Heart Rate through Random Forest Hyperparameter Tuning Nur, Zikri Kholifah; Wijaya, Rifki; Wulandari, Gia Septiana
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7761

This research delves into the utilization of smartwatch sensor data and heart rate monitoring to discern individual emotions based on body movement and heart rate. Emotions play a pivotal role in human life, influencing mental well-being, quality of life, and even physical and physiological responses. The data were sourced from prior research by Juan C. Quiroz, PhD. The study enlisted 50 participants who donned smartwatches and heart rate monitors while completing a 250-meter walk. Emotions were induced through both audio-visual and audio stimuli, with participants' emotional states evaluated using the PANAS questionnaire. The study scrutinized three scenarios: viewing a movie before walking, listening to music before walking, and listening to music while walking. Personal baselines were established using DummyClassifier with the 'most_frequent' strategy from the sklearn library, and various models, including Logistic Regression and Random Forest, were employed to gauge the impacts of these activities. Notably, a novel approach was undertaken by incorporating hyperparameter tuning to the Random Forest model using RandomizedSearchCV. The outcomes showcased substantial enhancements with hyperparameter tuning in the Random Forest model, yielding mean accuracies of 86.63% for happy vs. sad and 76.33% for happy vs. neutral vs. sad.

Pemutakhiran Website Jurnal Digital Sebagai Media Komunikasi dan Dokumentasi Kegiatan Siswa Pada SD Ar Rafi’ Bandung Sulistiyo, Mahmud Dwi; Sthevanie, Febryanti; Wulandari, Gia Septiana
Jurnal Pengabdian Masyarakat Bhinneka Vol. 3 No. 4 (2025): Bulan Juli
Publisher : Bhinneka Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58266/jpmb.v3i4.334

Program pengabdian kepada masyarakat ini dilaksanakan di SD Ar Rafi’ Bandung dengan tujuan memutakhirkan website jurnal digital sebagai media komunikasi dan dokumentasi kegiatan siswa. Program ini merupakan kelanjutan dari inisiatif digitalisasi buku jurnal siswa yang telah diimplementasikan sebelumnya. Berdasarkan evaluasi dan masukan dari pihak sekolah, dilakukan pengembangan sistem secara menyeluruh guna mencakup aspek afektif dan psikomotorik siswa secara lebih komprehensif. Pemutakhiran mencakup penambahan fitur pencatatan kegiatan ekstrakurikuler, data prestasi, dan data pelanggaran siswa. Dari segi antarmuka (UI/UX), dilakukan sejumlah penyempurnaan. Fungsionalitas sistem juga ditingkatkan melalui penambahan beberapa menu. Selain itu, ditambahkan fitur ekspor laporan PDF berdasarkan rentang waktu tertentu. Melalui pengembangan ini, website jurnal digital SD Ar Rafi’ kini mampu mendukung proses dokumentasi dan pemantauan perkembangan siswa secara lebih menyeluruh, efisien, dan adaptif terhadap kebutuhan sekolah. Program ini diharapkan berkontribusi dalam mendorong transformasi digital di jenjang pendidikan dasar serta meningkatkan kolaborasi antara sekolah, guru, siswa, dan orang tua.

Pengembangan Chatbot dan Pengoptimalan Mesin Pencarian untuk Meningkatkan Pemasaran dan Layanan Bisnis Lumina Indonesia Sulistiyo, Mahmud Dwi; Sthevanie, Febryanti; Wulandari, Gia Septiana
Jurnal Pengabdian Masyarakat Bhinneka Vol. 4 No. 1 (2025): Bulan September
Publisher : Bhinneka Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58266/jpmb.v4i1.416

Pemanfaatan media sosial dan website merupakan strategi pemasaran daring yang diterapkan oleh UMKM Lumina Indonesia, yang bergerak di bidang konsultan bisnis dan kesehatan mental. Namun, strategi ini masih menghadapi kendala, terutama dalam penyampaian informasi kepada pelanggan. Banyak pelanggan mengalami kesulitan menemukan informasi terkait layanan yang diinginkan, sehingga kerap menghubungi admin secara langsung. Kondisi ini membuat admin harus menyediakan waktu dan energi ekstra untuk menjawab pertanyaan, meskipun informasi tersebut telah tersedia di website. Untuk mengatasi permasalahan tersebut, kegiatan pengabdian masyarakat ini mengusulkan dan mengimplementasikan dua solusi utama: (1) pengembangan aplikasi chatbot yang mampu memberikan respons cepat dan relevan terhadap pertanyaan pelanggan, serta (2) penerapan teknologi Search Engine Optimization (SEO) untuk meningkatkan keterlihatan dan jangkauan website di mesin pencari. Hasil kegiatan menunjukkan bahwa penerapan chatbot membantu mengurangi beban kerja admin dan mempercepat pelayanan informasi, sementara optimalisasi SEO meningkatkan jumlah kunjungan dan visibilitas website. Dengan demikian, kedua solusi ini dinilai mulai meningkatkan efektivitas pemasaran daring dan kualitas layanan Lumina Indonesia.

Peningkatan Wawasan Kecerdasan Artifisial di SMK Telkom Bandung Melalui Kegiatan Workshop Sulistiyo, Mahmud Dwi; Sthevanie, Febryanti; Wulandari, Gia Septiana
Charity : Jurnal Pengabdian Masyarakat Vol. 6 No. 1 (2023): Special Issue
Publisher : PPM Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/charity.v6i1a.5918

Wawasan kecerdasan artifisial (AI) merupakan pengetahuan tentang teknologi dan cara kerja kecerdasan artifisial, termasuk bagaimana mesin dan sistem dapat diprogram untuk melakukan tugas-tugas yang biasanya dilakukan oleh manusia. Dengan meningkatnya penggunaan AI di berbagai bidang, termasuk industri, teknologi, dan bisnis, penting bagi siswa di SMK Telkom Bandung untuk memahami dan memiliki wawasan tentang AI. Sayangnya, sampai saat ini, SMK Telkom Bandung masih belum menerapkan materi terkait AI di dalam kurikulumnya. Salah satu cara untuk meningkatkan wawasan tentang AI di kalangan siswa SMK adalah melalui kegiatan workshop. Workshop merupakan forum yang memungkinkan siswa untuk belajar secara langsung dari para ahli, akademisi, atau praktisi di bidang terkait, dan memiliki kesempatan untuk bertanya dan berdiskusi tentang topik yang dibahas. Memahami permasalahan dan kebutuhan SMK Telkom Bandung tersebut, tim Pengabdian Masyarakat dari kelompok keahlian Intelligent System, Fakultas Informatika, Universitas Telkom mengadakan kegiatan workshop tentang wawasan AI. Kegiatan ini bertujuan untuk membantu siswa SMK Telkom Bandung dalam mempersiapkan diri menghadapi tantangan di masa depan dan berkarir di bidang yang terkait dengan AI. Serangkaian workshop diselenggarakan selama tiga hari dengan materi meliputi pengenalan dunia AI, penerapan metode AI, dan aplikasi AI yang kekinian. Materi disampaikan secara interaktif dengan selalu melibatkan peserta melalui quiz online dan penugasan di tempat. Kegiatan workshop ini mendapatkan respon yang positif, baik dari siswa-siswi maupun para guru, serta antusiasme yang tinggi untuk diadakannya workshop lanjutan tentang wawasan AI ini.

Solving Tatamibari Puzzle Using Exhaustive Search Approach Reinhard, Enrico Christopher; Arzaki, Muhammad; Wulandari, Gia Septiana
Indonesian Journal on Computing (Indo-JC) Vol. 7 No. 3 (2022): December, 2022
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2022.7.3.675

Tatamibari is a puzzle that was first published in 2004 and was proven to be NP-complete in 2020. However, to the best of our knowledge, algorithmic investigation of the Tatamibari puzzle is relatively new and limited. There are discussions about an approach for solving the Tatamibari puzzle using the Z3 SMT solver, but there are no details regarding the steps of the algorithm as well as its explicit asymptotic upper bound. In addition, this solver requires an additional library that cannot be directly executed using standard libraries in an arbitrary imperative programming language. Hence, this paper discusses an exhaustive search approach for solving an arbitrary Tatamibari puzzle. We show that this algorithm can find all solutions to an $m \times n$ Tatamibari instance with $h$ hints in $O(\max\{m^2 n^2, h^{mn-h} \cdot hmn\})$ time. We also use this algorithm to find the number of possible Tatamibari solutions in an $m \times n$ grid for some small values of $m$ and $n$.

Elementary Search-based Algorithms for Solving Tilepaint Puzzles Fridolin, Vincentius Arnold; Arzaki, Muhammad; Wulandari, Gia Septiana
Indonesian Journal on Computing (Indo-JC) Vol. 8 No. 2 (2023): August, 2023
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2023.8.2.750

This paper discusses the elementary computational aspects of Tilepaint puzzles, single-player logic puzzles introduced in 1995 and confirmed NP-complete in 2022. Two elementary search-based algorithms are proposed: the complete search technique with a bitmasking approach and the prune-and-search technique with a backtracking approach and pruning optimization. This paper shows that the asymptotic running time of these algorithms for solving an $m \times n$ Tilepaint instance containing $p$ tiles are respectively $O(2^{p} \cdot p \cdot mn)$ and $O(2^{p} \cdot mn)$, implying that the latter method is asymptotically faster by a factor of $p$. This paper also discusses tractable and intractable variants of Tilepaint puzzles. This paper shows that an $m \times n$ Tilepaint instance containing $mn$ tiles of size $1 \times 1$ is solvable in polynomial time. In contrast, this paper shows that solving general $m \times 1$ and $1 \times n$ Tilepaint puzzles remains intractable by reducing such problems from the subset-sum problem.

Title

Found 36 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 36 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 36 Documents
Search