Claim Missing Document
Check
Articles

Topic Modeling in the News Document on Sustainable Development Goals Hidayatul Fitri; Widyawan Widyawan; Indah Soesanti
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 5, No 3 (2021): September 2021
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijitee.67467

Abstract

Indonesia is a developing country and supports the program of the Sustainable Development Goals (SDGs) which consist of 17 goals. SDGs is not only the government’s duty, but a shared duty from any elements. Online media has a crucial role in implementing goals of Indonesia’s SDG. Information published in online news related to the SDGs is an important consideration for the government, society, and all elements. Categorizing news manually to find out news topics is very time-consuming and done by the ability of news editors. News presented by online media on the news site can be used as topic modeling, where hidden topics can be found in the news on online media. Topic modeling will classify data based on a particular topic and determine the relationship between text. Latent Dirichlet allocation (LDA) is one of the methods on topic modeling to find out the trend of topics of SDGs news. Based on the result of this research, the implementation of LDA is the right choice for finding topics in a document. The result of topic modeling with k = 17 obtained the highest coherence score of 0.5405 on topic 8. Topic 8 discussed news related to the eighth SDGs goals, namely decent work and economic growth. This categorization was based on words formed after the LDA process. Then, topic 5 discussed the news on the 17th SDGs goals, namely partnerships for the goals. Topic 6 discussed the news of the first SDGs, namely no poverty.
Machine Learning Untuk Estimasi Posisi Objek Berbasis RSS Fingerprint Menggunakan IEEE 802.11g Pada Lantai 3 Gedung JTETI UGM Chairani Chairani; Widyawan Widyawan; Sri Suning Kusumawardani
JURNAL INFOTEL Vol 7 No 1 (2015): May 2015
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v7i1.23

Abstract

Penelitian ini membahas tentang estimasi posisi (localization) objek dalam gedung menggunakan jaringan wireless atau IEEE 802.11g dengan pendekatan Machine Learning. Metode pada pengukuran RSS menggunakan RSS-based fingerprint. Algoritma Machine Learning yang digunakan dalam memperkirakan lokasi dari pengukuran RSS-based menggunakan Naive Bayes. Localization dilakukan pada lantai 3 gedung Jurusan Teknik Elektro dan Teknologi Informasi (JTETI) dengan luas 1969,68 m2 dan memiliki 5 buah titik penempatan access point (AP). Untuk membentuk peta fingerprint digunakan dimensi 1 m x 1 m sehingga terbentuk grid sebanyak 1893 buah. Dengan menggunakan software Net Surveyor terkumpul data kekuatan sinyal yang diterima (RSS) dari jaringan wireless ke perangkat penerima (laptop) sebanyak 86.980 record. Hasil nilai rata-rata error jarak estimasi untuk localization seluruh ruangan di lantai 3 dengan menggunakan algoritma Naive Bayes pada fase offline tahap learning adalah 6,29 meter. Untuk fase online dan tahap post learning diperoleh rata-rata error jarak estimasi sebesar 7,82 meter.
OBSERVASI ALIRAN SUNGAI UNTUK PERINGATAN DINI BANJIR LAHAR DINGIN MEMANFAATKAN JARINGAN SENSOR NIRKABEL Agung Priyanto; Widyawan; Sujoko Sumaryono
Jurnal Teknomatika Vol 5 No 1 (2012): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

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

Abstract

Banjir lahar dingin merupakan bencana yang biasanya menyertai letusan atau erupsi gunung berapi. Ini terjadi ketika material vulkanik hasil erupsi yang menumpuk di lereng dan kaki gunung berapi terbawa air hujan melewati sungai- sungai yang berhulu di gunung tersebut. Air yang bercampur dengan material vulkanik ini memiliki massa jenis yang besar sehingga gelombang suara yang dihasilkan ketika mengalir berbeda dengan aliran yang terdiri dari air saja. Parameter inilah yang akan diteliti perbedaanya melalui percobaan yang akan dilakukan. Sinyal suara aliran sungai diperoleh menggunakan serangkaian sensor suara yang disusun secara array Masing-masing sensor terhubung dengan sebuah node jaringan sensor nirkabel IQRF. Data yang diperoleh masing-masing node dikumpulkan dan dikirimkan ke pusat pengolah data berupa sebuah PC. Pengolahan data suara ini dilakukan menggunakan signal processing MATLAB untuk memperoleh informasi apakah aliran air sungai tercampur material vulkanik seperti abu dan pasir hasil erupsi. Informasi yang diperoleh dapat membantu untuk pengembangan sistem peringatan dini banjir lahar dingin.
PENGEMBANGAN APLIKASI DOMOTIC BERBASIS ARSITEKTUR BERORIENTASI LAYANAN DENGAN ANDROID SDK SEBAGAI NILAI TAMBAH LAYANAN BERBASIS INTERNET Widy Agung Priasmoro; Widyawan; Bimo Sunarfri Hantono
Jurnal Teknomatika Vol 6 No 1 (2013): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

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

Abstract

Kebutuhan akses ke peralatan di rumah sangat dibutuhkan, terutama bagi mereka penghuni rumah yang menginginkan akses cepat mengetahui informasi keadaan rumahnya atau melakukan aktifitas mengatur beberapa peralatan di rumah. Namun, hal tersebut akan mempersulit penghuni rumah apabila sedang berpergian jauh. Untuk itu, diperlukan sebuah kendali jarak-jauh yang dapat memudahkan penghuni rumah agar dapat dengan mudah mematikan atau menyalakan lampu, mengatur suhu udara ruangan dan memantau keadaan rumah melalui kamera. Di dalam penelitian ini dipaparkan mengenai pengembangan Domestic Robotic dengan arsitektur berbasis layanan. Penelitian ini akan dilakukan pada pengembangan dan implementasi aplikasi client berbasis mobile Android sebagai remote control home automation dan web-service RESTful yang terpasang di home-gateway. Pemilihan smartphone Android sebagai remote control dikarenakan biaya yang terjangkau untuk berbagai kalangan konsumen, selain itu bagi para developer, pengembangan aplikasinya tidak membutuhkan banyak biaya. Penelitian ini dilakukan di tim JTETI UGM, dengan hasil keluaran berupa sistem rumah pintar (smart-home) yang dapat dikendalikan dan dipantau dengan menggunakan perangkat Android.
Rancang Bangun Sistem Rekomendasi Pariwisata Mobile dengan Menggunakan Metode Collaborative Filtering dan Location Based Filtering Assaf Arief; Widyawan; Bimo Sunafri Hantono
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 3: Agustus 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (876.779 KB)

Abstract

The innovations of electronic tourism (e-tourism) has gained attention in recent time, this result in the increased number of prototypes tourism applications web desktop based and mobile based. This research focuses on improving the quality of tourism service by building an automatic recommender system application that can run on mobile devices such as mobile phones, PDAs (Personal Digital Assistant), smartphone, iPad, etc. A tourism recommendation system is generally ask advice from officers with manually guide to help choose tourist spot will be visited, that were still deemed to be a subjective opinion. It becomes less precise in the use of informations, behavior, interests, tastes, and the rating to be conveyed to other tourists with similar preferences, which it’s the basis for providing content recommendations.This research objective are to build the mobile tourism recommendation system automation using the concept of personalization with collaborative filtering method and location based filtering for the alternate of manual systems (ask advice from officers of travel agency). The completion steps of this research are to make a mobile recommendation system with methods of collaborative filtering and location-based filtering, create a prototype mobile web-based applications, designing, manufacturing and the final process are improvement recommendations system.The results of this research is a mobile recommendation system application with platforms of JQuery Mobile, HTML 5, JavaScript, Ajax, PHP and MySQL. The test process are functionality testing, compatibility testing and system recommendations testing. It can be seen that the design of tourism recommendation system is able to provide tourist recommendation are suitable with the methods CF and LBF were applied.
Simulasi Deployment Jaringan Sensor Nirkabel Berdasarkan Algoritma Particle Swarm Optimization Zawiyah Saharuna; Widyawan; Sujoko Sumaryonjo
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 3: Agustus 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (493.193 KB)

Abstract

Deployment is one of several important issues in Wireless Sensor Network (WSN). During WSN deployment, the connectivity between each sensor nodes must be considered carefully to create reliable communication. In this research, we propose a WSN deployment tool based on Particle Swarm Optimization (PSO) algorithm with connectivity of the wireless to be our concern. Implementation of the PSO algorithm is focused to optimize received power of each sensor node based on its position in the 2D space. Therefore, every sensor node in the network will be able to reach its best position and improves the network connectivity. The deployment simulation results with various transmit power (e.g. -25 dB, -28 dB, -31 dB, -34 dB, -37 dB, -40 dB, -43 dB, and -46 dB) are successfully form a network with well maintained connectivity. After 100 times of simulation, the average of convergence is reached at iteration 29.
Estimasi Posisi Objek dalam Gedung Berdasarkan GSM Fingerprint Hani Rubiani; Widyawan; Lukito Edi Nugroho
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 3: Agustus 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1423.062 KB)

Abstract

Most research of indoor localization is based on the use of short-range signals, e.g. WiFi, Bluetooth, ultra sound, and infrared. This research discusses indoor localization using the Global System for Mobile Communication (GSM). The GSM has many advantages that is explained as follows. The system can be used in vast area coverage and worked even the electrical condition of the building is being extinguished. The estimation of object position uses Receive Signal Strength (RSS) GSM fingerprinting. The experiment is conducted with 2, 3, and 4 cell-ID. The localization phase uses Naive Bayes (NB) method. Afterwards, the results will be compared with Nearest Neighbour (NN) method. The results show a correlation between the number of cell ID with average minimum distance error. The accuracy is 7.89 m using NB with four cell ID. The error is better than the use of k-NN method which has accuracy of 12.19. For the all scenario, NB method has better accuracy than k-NN method.
INVys: Sistem Navigasi Dalam Ruangan untuk Penyandang Tunanetra Menggunakan Kamera RGB-D Widyawan; Muhamad Risqi Utama Saputra; Paulus Insap Santosa
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 4: November 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i4.6372

Abstract

This research presents the INVys system aiming to solve the problem of indoor navigation for persons with visual impairment by leveraging the capabilities of an RGB-D camera. The system utilizes the depth information provided by the camera for micronavigation, which involves sensing and avoiding obstacles in the immediate environment. The INVys system proposes a novel auto-adaptive double thresholding (AADT) method to detect obstacles, calculate their distance, and provide feedback to the user to avoid them. AADT has been evaluated and compared to baseline and auto-adaptive thresholding (AAT) methods using four criteria: accuracy, precision, robustness, and execution time. The results indicate that AADT excels in accuracy, precision, and robustness, making it a suitable method for obstacle detection and avoidance in the context of indoor navigation for persons with visual impairment. In addition to micronavigation, the INVys system utilizes the color information provided by the camera for macro-navigation, which involves recognizing and following navigational markers called optical glyphs. The system uses an automatic glyph binarization method to recognize the glyphs and evaluates them using two criteria: accuracy and execution time. The results indicate that the proposed method is accurate and efficient in recognizing the optical glyphs, making it suitable for use as a navigational marker in indoor environments. Furthermore, the study also provides a correlation between the size of the glyphs, the distance of the recognized glyphs, the tilt condition of the recognized glyphs, and the accuracy of glyph recognition. These correlations define the minimum glyph size that can be practically used for indoor navigation for persons with visual impairment. Overall, this research presents a promising solution for indoor navigation for persons with visual impairment by leveraging the capabilities of an RGB-D camera and proposing novel methods for obstacle detection and avoidance and for recognizing navigational markers.
Socio-user Context Aware-Based Recommender System: Context Suggestions for A Better Tourism Recommendation Kusuma Adi Achmad; Lukito Edi Nugroho; Achmad Djunaedi; Widyawan
International Journal on Information and Communication Technology (IJoICT) Vol. 9 No. 2 (2023): Vol.9 No. 2 Dec 2023
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v9i2.858

Abstract

The existing tourism recommender system model is mostly predictive analytics for destination recommendations (item recommendation). Limited research has been conducted in the discussion of a recommender system model, particularly context suggestion. Thus, it is necessary to develop a recommender system model not only to predict tourism destinations but also to suggest contexts appropriate for tourist preferences (context suggestions). A deep learning method was used to create a model of the socio-user context aware-based recommender system for context suggestions. The attribute used as a label to suggest context was uHijos, uCuisine, uAmbience, and uTransport. The accuracy of the socio-user context aware-based recommender system in suggesting the context of uHijos, uAmbience, and uTransport was 100% with an error rate of 0%. It was found that only the level of recognition of the model in suggesting uCuisine was less accurate (below 30%) with a classification error for more than 70%. Performance evaluation of the socio-user model context-based recommender system was considered efficient, particularly for the evaluation of the level of accuracy, completeness (recall/sensitivity), precision, and a harmonic average of precision and recall (F-score), mainly for label/context of uHijos, uAmbience, and uTransport.
QS-Trust: An IoT ecosystem security model incorporating quality of service and social factors for trust assessment Najib, Warsun; Sulistyo, Selo; Widyawan
Communications in Science and Technology Vol 9 No 1 (2024)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.9.1.2024.1419

Abstract

In the rapidly growing and increasingly complex Internet of Things (IoT) ecosystem, securing communication and data exchanges between devices is a major concern. To address this, we proposed QS-Trust, a trust-based security model considering both Quality of Service (QoS) and social parameters. QS-Trust uses a trust value to determine the trust level between devices and employs a QoS-aware trust-based algorithm to improve the security of data transmissions. Additionally, the model incorporates intelligence parameters such as computing power, memory capacity, device behavior and context information to enhance the accuracy of trust evaluation. Our simulation results demonstrated that QS-Trust effectively improved the security of the IoT ecosystem while maintaining the high level of QoS. The execution time of QS-Trust was in the range of 21 to 128 milliseconds, which is efficient for real-time IoT applications. QS-Trust offers a promising solution for securing the IoT ecosystem. The QS-Trust model effectively addresses the challenges of maintaining accurate and up-to-date trust levels in dynamic IoT environments through its decentralized approach, multi-factor evaluations, and adaptive algorithms. By continuously monitoring device performance and interactions and dynamically adjusting trust scores, QS-Trust ensures that the IoT network remains secure and reliable.