Article Per Year (5 Year)
p-Index From 2020 - 2025
1.431
P-Index
This Author published in this journals
All Journal Jurnal Penelitian Komunikasi dan Opini Publik Sisforma: Journal of Information Systems Jurnal Ilmiah KOMPUTASI Jurnal Dimensi Pendidikan dan Pembelajaran JITTER (Jurnal Ilmiah Teknologi Informasi Terapan) Jurnal Tekno Kompak Jurnal Pengabdian Masyarakat Teknik Jurnal Teknik Informatika (JUTIF) Brilliance: Research of Artificial Intelligence Jurnal Algoritma
Eka Angga Laksana
Universitas Widyatama
Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mathematics Mechanical Engineering Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Evaluation of E-learning Activity Effectiveness in Higher Education Through Sentiment Analysis by Using Naïve Bayes Classifier Eka Angga Laksana; Ase Suryana; Heri Heryono
SISFORMA Vol 5, No 1 (2018): May 2018
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (263.469 KB) | DOI: 10.24167/sisforma.v5i1.1450

Abstract

Sentiment analysis as part of text mining research domain has been being recognized due to the successful implementation in social media analysis. Sentiment analysis methods had intelligent ability to classify texts into negative or positive. Classified texts concluded whole users respond and described opinion polarity about particular topic. Based on this idea, this research took e-learning’s users opinion as object to be measured through sentiment analysis. The results can be used to evaluate the e-learning activity. This research had been implemented in Widyatama University which had been running e-learning activity for several years. Qualitative method by given questioner to users and gather the feedback is commonly used as evaluation of e-learning system previously. Still, questioner doesn’t represent the conclusion about the whole opinion. Hence, it needs the method to identify opinion polarity from e-learning member. The e-learning opinion data sets were gathered from questioner filled by e-learning member included both student and lecturer as participants. The participants gave review about learning outcome after their participation in e-learning activity. Their opinion was needed to describe current situation about e-learning activity. Therefore, the conclusion could be used to make improvement and described few achievements about the e-learning system. The data sets trained by Naïve Bayes classifier to group each user respond into negative or positive. The classification results were also evaluated by a number of particular evaluation metric used in data mining to show the classifier performance such as accuracy, precision, and recall.
Implementasi Metode Action Research untuk Peningkatan Daya Saing Umkm Melalui E-Commerce Azizah Zakiah; Ardhian Ekawijana; Eka Angga Laksana
Jurnal Penelitian Komunikasi dan Opini Publik Vol 23, No 1 (2019): JURNAL PENELITIAN KOMUNIKASI DAN OPINI PUBLIK - Juli 2019
Publisher : BPSDMP Kominfo Manado

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33299/jpkop.23.1.1727

Abstract

Bandung city has Binong Jati knitting textile center established since 1965. This region is famous to neighboring countries because its knitted products are exported to Singapore, Brunei Darussalam, and Malaysia. Wanina Store and Karimake Store is a production house located in Binong Knitting Village. Production capacity has decreased significantly due to decreased sales volume so that it affects the level of business profits and impact on the low level of production. These SMEs are still using conventional ways in marketing their products and their knowledge in innovating technology is still low. Both partners are still using traditional marketing methods. They have not taken advantage of the existing marketplace or social media, due to the level of skills in the mastery and utilization of information technology is very low. So, the solution to the problem is (1) create an e-Commerce-based website to increase market share expansion and sales management. (2) provide training on the use of e-commerce that has been made. (3) provide training on the utilization of top 5 popular. The research method used in this research is the action research method and to measure the success of the system that has been implemented using the DeLone & Mc lean framework.Keywords : Action Research, SMEs, e-commerce, Improving, DeLone &Mc Lean.
COLLABORATIVE FILTERING DAN APLIKASINYA Eka Angga Laksana
Jurnal Ilmiah Teknologi Infomasi Terapan Vol. 1 No. 1 (2014)
Publisher : Universitas Widyatama

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (246.658 KB) | DOI: 10.33197/jitter.vol1.iss1.2014.44

Abstract

Abstract—Collaborative  filtering  merupakan  salah  satu dari teknik di dalam Recommender System yang paling sering digunakan saat ini karena kehandalannya. Recomender system banyak dipakai  di  dalam  dunia e-Commerce untuk  membuat personalisasi  di  dalam  sebuah  website.  Customer  website  eCommerce  datang  untuk  mencari  produk  tertentu,  di  sinilah peran recommender system dalam menampilkan produk yang berkaitan  yang  disukai  oleh  customer.  Biasanya  customer memberikan rating kepada produk yang mereka sukai dalam skala  tertentu.  Ada  berbagai  macam  algoritma  yang  bisa dipakai  dalam  mengitung similarity  antar item  maupun user. Algoritma ini sangat berhubungan dengan teknik yang dipakai di  dalam  machine  learning  dan  information  retrieval.  Begitu banyak  riset  di  bidang  recommender  ini  membuat  aplikasi  rekomender  berkembang  menjadi  semakin  luas  demi  tujuan riset  maupun  bisnis.  Penelitian  ini  memberikan  pemahaman singkat mengenai Collaborative filtering dan aplikasinya yang bersifat open source sehingga memberikan kesempatan untuk para peneliti agar mengembangkan hasil penelitiannya di atas salah satu platform aplikasi ini. Salah satu komponen penting di  dalam  aplikasi  adalah  validasi,  dan  inilah  yang  membuat aplikasi-aplikasi  ini  menjadi  begitu  diandalkan  dalam Recommender System.
TRAFFIC FLOW AND CONGESTION DETECTION WITH YOLOV8 AND BYTETRACK-BASED MULTI OBJECT TRACKING Marchel Maulana Fahrezi; Eka Angga Laksana
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2063

Abstract

The rapid urbanization witnessed in cities like Bandung, Indonesia, has emerged as a pressing issue, precipitating severe traffic congestion that poses challenges to economic growth and diminishes overall quality of life. This study endeavors to confront these multifaceted challenges through the development of a sophisticated real-time traffic surveillance and control system. The proposed system utilizes the current CCTV infrastructure in the city and incorporates advanced technologies like YOLOv8 for accurate vehicle detection and ByteTrack for dynamic real-time vehicle tracking. This system utilizes a comprehensive strategy, including multi-object tracking techniques to improve the precision of congestion detection. The system was thoroughly assessed in several places in Bandung, and it showed remarkable performance metrics. Specifically, YOLOv8 achieved an impressive 80% accuracy rate in vehicle detection, showcasing its efficacy in discerning vehicles within complex urban environments. Simultaneously, ByteTrack exhibited an average error rate of 17% in vehicle counting, further Strengthening the system's capabilities in accurately quantifying vehicular traffic. Furthermore, the combination of YOLOv8 and ByteTrack in a multi-object tracking paradigm yielded an 80% accuracy rate in congestion detection, emphasizing the system's robustness in real-time traffic management scenarios. These findings underscore the immense potential of the integrated YOLOv8 and ByteTrack system in traffic management strategies and alleviating congestion in smart cities like Bandung. This research has produced precise outcomes in identifying and quantifying the traffic congestion in various scenarios.
Perancangan Dokumen Repository Berbasis Private Cloud untuk Membantu Administrasi Sekolah SMKN 2 Cimahi Laksana, Eka Angga; -, Sunjana; Mardiansyah, Viddi; Madsu, Yosi Malatta; Herlistiono, Iwa Ovyawan
Jurnal Pengabdian Masyarakat Teknik Vol 6, No 1 (2023): Jurnal Pengabdian Masyrakat Teknik (JPMT)
Publisher : Fakultas Teknik Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/jpmt.6.1.43-48

Abstract

Sekolah menengah sebagai tempat dilaksanakannya kegiatan belajar mengajar senantiasa dituntut untuk menjaga kualitas pendidikannya. Kompetensi merupakan salah satu tolak ukur capaian yang diraih oleh peserta didik. Teknologi informasi semakin berkembang dan menggeser cara acara tradisional termasuk di dunia Pendidikan. Penggunaan teknologi terkini dapat menunjang kegiatan akademik dan dapat berperan serta dalam meningkatkan mutu sekolah sebagai institusi pendidikan. Proses kegiatan administrasi untuk mendukung kegiatan di sekolah juga memerlukan pemanfaatan teknologi informasi. Dokumen sebagai salah satu komponen penting dalam bisnis proses yang terjadi seperti surat menyurat, materi bahan ajar dan dokumen penting lainnya perlu untuk dilakukan manajemen agar memudahkan dalam proses pencarian dan untuk memenuhi standar mutu sesuai Standar Nasional Pendidikan (SNP) di Indonesia. Penyimpanan dokumen berbasis kertas perlahan-lahan mulai ditinggalkan sebab kurang efektif sebab faktor usia, daya tahan dan lainnya. Selain itu media penyimpanan digital berbasis public cloud yang bersifat free seperti google drive dan dropbox juga memiliki keterbatasan, di antaranya adalah ketersediaan sumber daya dan adaptasi pengembangan. Oleh karena itu kami memberikan saran dan solusi berupa penyimpanan berbasis private cloud dengan memanfaatkan teknologi open-source yang bernama Nextcloud sebagai solusi penyimpanan dokumen berbasis cloud untuk diimplementasikan di SMKN 2 Cimahi.
Rancang Bangun Teknologi Edukasi Berbasis Moodle dan Private Cloud di SMAN 26 Bandung Nafysah, Mutiara; Laksana, Eka Angga
JURNAL DIMENSI PENDIDIKAN DAN PEMBELAJARAN Vol 11, No 2 (2023): July 2023
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/dpp.v11i2.7151

Abstract

Teknologi informasi dan komunikasi berkembang dengan pesat dan telah menyentuh banyak bidang dalam membantu pekerjaan manusia. Salah satu bidang yang telah disentuh oleh teknologi informasi dan komunikasi adalah bidang pendidikan dengan penggunaan tekonologi e-learning dalam membantu kegiatan belajar mengajar. E-learning digunakan oleh banyak sekolah maupun universitas dalam melaksanakan kegiatan belajar mengajar terutama di masa pandemi. Meskipun sekarang kebanyakan kegiatan belajar mengajar telah dilakukan secara offline, website e-learning masih bisa digunakan untuk melaksanakan ujian maupun ulangan harian. Moodle adalah salah satu framework LMS (Learning Management System) open-source yang dapat diperoleh secara gratis dengan portal e-learning yang bisa dimodifikasi agar dapat disesuaikan sebagaimana kebutuhan penggunanya. Moodle yang telah dimodifikasi tentu baru dapat digunakan jika sudah diisi dengan data-data tertentu mulai dari pengguna aplikasi sampai pembagian kelas dan mata pelajaran. Setelah data primer didapat, data tersebut perlu diolah terlebih dahulu sesuai format sistem sebelum bisa di input ke dalam Moodle.
Peer-Assisted Bulk-Synchronous Content Distribution Service: Sistem Cerdas Pendukung Akreditasi Perguruan Tinggi IAPS 4.0 Berbasis Nextcloud dan Python Laksana, Eka Angga; Sukenda
Jurnal Ilmiah Komputasi Vol. 23 No. 3 (2024): Jurnal Ilmiah Komputasi : Vol. 23 No 3, September 2024
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32409/jikstik.23.3.3611

Abstract

Peer-assisted Bulk-Synchronous Content Distribution Service merupakan sebuah aplikasi cerdas yang dibangun untuk mendukung proses akreditasi program studi perguruan tinggi. Aplikasi ini dibuat tidak untuk menggantikan system ataupun kebiasaan-kebiasaan yang telah ada namun lebih kepada melengkapi atau bahkan meningkatkan proses yang telah terjadi. Ada dua komponen fundamental Peer-assisted Bulk-Synchronous Content Distribution Service yaitu dokumen borang akreditasi dan Cloud Repository. Keduanya akan disatukan dalam sebuah service cerdas yang mampu men-sinkronkan kalimat di dalam dokumen borang dengan file-file bukti pendukungnya di dalam Cloud Repository. Hal ini terinspirasi dari proses akreditasi perguruan tinggi yang selalu melibatkan bukti-bukti pendukung terkait dengan kalimat-kalimat atau data yang tertulis di dokumen. Penelitian ini dikembangkan dengan memanfaatkan Bahasa pemrograman Python dan Nextcloud API. Python sebagai alat untuk membangun otomasi beberapa proses terkait sinkronisasi dan Nexcloud API sebagai kunci utama dalam manajemen file yang lebih leluasa di Nexctloud file repository. Oleh sebab itu sistem cerdas ini diharapkan dapat melakukan pengecekan kelengkapan sekaligus mempermudah pengguna dalam merelasikan antara kalimat maupun poin-poin dalam dokumen dengan file pendukungya. Dengan demikian diharapkan bahwa dengan adanya sistem ini akan dapat membantu pihak-pihak penyusun akreditasi agar dapat memastikan bahwa kelengkapan dokumen-dokumen pendukung menjadi terjamin dengan adanya sistem yang sederhana, informatif dan selalu update ketika ada tambahan dokumen baru.
Pendekatan Transfer Learning dengan InceptionResNetV2 dan Augmentasi MixUp untuk Peningkatan Klasifikasi Tumor Otak Mahendra, Randa; Laksana, Eka Angga; Sukenda, Sukenda
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2194

Abstract

Diagnosis of brain tumors such as Glioma, Meningioma, and Pituitary using MRI still faces challenges, including reliance on manual interpretation, long evaluation times, and the potential for human error. To address these issues, deep learning-based approaches offer efficient and accurate solutions. This study aims to develop a brain tumor classification model based on deep learning using the InceptionResNetV2 architecture with MixUp augmentation to improve model accuracy and generalization. The model was trained on 7,023 MRI images (Glioma: 1,621; Meningioma: 1,645; Pituitary: 1,757; No-tumor: 2,000), with MixUp proven effective in reducing overfitting and handling data imbalance. The proposed model achieved a highest accuracy of 99.70%, surpassing other models such as CNN with Image Enhancement (97.84%) \[1], Xception (98.00%) \[2], EfficientNet (98.00%) \[3], and ResNet50 (98.47%) \[4]. Evaluation was conducted using metrics including precision, recall, F1-score, as well as MSE, RMSE, and MAE, showing strong performance. These results support the use of transfer learning for medical image classification with limited datasets. This research demonstrates clinical application potential, particularly in improving diagnostic accuracy, speeding up evaluation processes, and reducing human error. Future recommendations include using more diverse datasets, real-world evaluation, and integration into Clinical Decision Support Systems (CDSS).
Optimalisasi Parameter Support Vector Machine dengan Algoritma PSO untuk Tugas Klasifikasi Sentimen Ulasan IMDb Adrian, Mochammad Ilham; Laksana, Eka Angga
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2306

Abstract

Dalam penelitian ini, digunakan algoritma LinearSVC dari metode Support Vector Machine (SVM) untuk analisis sentimen terhadap data ulasan IMDb. Proses ekstraksi fitur dilakukan dengan TF-IDF Vectorizer. Tantangan utama terletak pada penentuan nilai hyperparameter, khususnya parameter regulasi (C), yang sangat menentukan kualitas hasil prediksi. Untuk mengatasi hal ini, penelitian ini menerapkan algoritma Particle Swarm Optimization (PSO) guna menemukan nilai C terbaik. Eksperimen menunjukkan bahwa tanpa optimasi, model SVM hanya mencapai akurasi 89,48%, tetapi setelah PSO diterapkan, nilai optimal C ditemukan sebesar 0,1612, yang meningkatkan akurasi model hingga 92,03% pada data uji. Selain itu, metrik evaluasi lainnya juga mengalami peningkatan signifikan, dengan Precision sebesar 91,29%, Recall 92,92%, dan F1-Score 92,10%. Signifikansi peningkatan ini menunjukkan bahwa metode PSO secara konsisten mengungguli pendekatan konvensional yang mengandalkan pemilihan hyperparameter secara manual atau grid search, yang sering kali lebih lambat dan kurang akurat dalam menemukan nilai optimal. Hasil penelitian ini membuktikan bahwa optimasi hyperparameter menggunakan PSO dapat meningkatkan performa SVM secara signifikan dalam klasifikasi sentimen. Pendekatan ini tidak hanya relevan untuk analisis ulasan IMDb tetapi juga dapat diterapkan pada berbagai tugas NLP lainnya, seperti analisis opini publik dan ulasan produk, menjadikannya solusi yang efisien dalam meningkatkan akurasi klasifikasi teks.
Making Learning Module Using Google Spaces for Kindergarten Teachers in Pangandaran Based on LMS (Learning Management System) Wahyu Wibowo, Ari Purno; Laksana, Eka Angga; Sukenda, Sukenda; Yustim, Benny
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5770

Abstract

Learning process Children of kindergarten age tend to get bored easily and must use a different approach, because at an early age children will get tired easily if taught something tire Computers with attractive visual displays, animations, and sounds can make the learning process feel like playing, so that they are more enthusiastic and motivated. to overcome this, it is necessary to create a more innovative multimedia-based teaching system on the material taught must have parameters that are visual, audio and interactive material, so that the material delivered can be easily measured according to learning outcomes, in this study the author tried to use the help of open source applications based on Google Spacess and LMS (Learning Management System) which can be used by kindergarten teachers in the Pangandaran area, by using this Google Spaces assistance, it turns out that teachers can create the same and more interactive teaching material, in the end with the help of digital media, the material can be adjusted to the individual abilities of each child's speed and can be evaluated directly because for example children who have mastered the material can proceed to the next stage, while on the contrary students who are left behind in learning can repeat more relaxedly repeating the learning, then with the help of teachers and the student learning process can be done independently and not limited by time, because the LMS module can be accessed at any time by students. From the results of the training held for 65 kindergarten teachers, 85% agreed that this LMS application was very helpful in teaching and easy to configure and re-develop.
Co-Authors -, Sunjana Adrian, Mochammad Ilham Ardhian Ekawijana Ase Suryana Azizah Zakiah Benny Yustim Heri Heryono Herlistiono, Iwa Ovyawan Madsu, Yosi Malatta Mahendra, Randa Marchel Maulana Fahrezi Maulana, Rafli Iqbal Nafysah, Mutiara Sukenda . Viddi Mardiansyah