Telkom Institute of Technology

About: Telkom Institute of Technology is a based out in . It is known for research contribution in the topics: Computer science & Network packet. The organization has 570 authors who have published 470 publications receiving 1390 citations.

Performance Analysis of SM-MISO with Q-CSIT in Wireless Sensor Network

Abstract: In this paper, we investigate the role of Q-CSIT in SM-MISO for wireless sensor networks system. The SN are connected to the CH, it is modeled as a MISO system. Spatial modulation has an advantage over a conventional MIMO system which does not require multiple radio frequency chains as many as the number of transmit antennas. The Q-CSIT is aimed to estimate the faded wireless channel with a limited/finite number of bits. The finite number of feedback bits trigger the SN adapt automatically its AMC modes. Adaptation of the AMC modes causes a changing of transmit power and transmission rate, these changes will make a better probability of error. The numerical results show that bigger the number of feedback bits yields better SER. Furthermore, lower spatial correlation generates a better probability of error. The last, quality of wireless channel that is stated in SNR also dominantly influences the performance of SM - MISO system.

Analysis of Community Response to Disasters through Twitter Social Media

Abstract: Disasters that occur in a place can give a variety of reactions in the community. Social media users, the dissemination of Twitter with followers, makes it easy and fast to share emergency information like a disaster. Some disasters often occur in Indonesia, such as earthquakes, volcanic eruptions, weather anomaly, and flooding. To find out the public response to an accident, researchers conducted twitter data crawling on July 26, 2019, to July 29, 2019, using the keyword "gunung tangkuban parahu erupsi", crawling data produced a dataset of 14,045 records. This study calculates the number of tweets before the disaster, to several days after the accident. The results of the survey indicate the response of the community to disasters relatively increased on the first day of the crash and decreased after two or three days after the disaster.

Object Detection for Using Mask in COVID-19 Pandemic with Faster R_CNN Inception V2 Algorithm

Abstract: When this research was done, based on data from https://covid19.go.id/, the number of positive patients reached 127,083, the increasing number of COVID-19 patients in Indonesia, and the new normal period had been imposed, making people more concerned about the health and the danger of spreading COVID-19 virus. New normal means were starting a new habit that is the habit of washing your hands and use a mask. Everyday activities in normal times require us to work as usual, in an atmosphere with other people. Everyone is required to use a mask to support the policy of using a mask, a system that can detect whether someone is wearing a mask or not. This research aims to be able to identify the use of masks in public areas. The dataset used is 5000 images of people wearing masks. This research uses the Faster R_CNN Inception V2 Algorithm. And then the results were evaluated using COCO mAP Score yielding in 0.58 mAP, with 0.78 mAP for large objects, 0.65 mAP for medium objects, and 0.48 mAP shows this research can contribute to the community to care in the use of masks. The model that has created in this study is used to detect the use of masks in public areas by using an image captured by a camera mounted in a particular place.

Word Embeddings Evaluation on Indonesian Translation of AI-Quran and Hadiths

Abstract: Word vectors are an important part of machine learning. Word vectors are a numerical representation of text data. One of the methods that can be used to convert text into numerics is word embeddings. The word embeddings algorithm that researchers often use is Continuous Bag of Word, Skip-Gram, and FastText. This paper will discuss the transformation of textual data from Islamic knowledge domain documents into numerical forms using these three algorithms, then evaluate the word vector results using intrinsic and extrinsic evaluation techniques. We conduct intrinsic evaluations by determining the words to be evaluated, then checking for the existence of synonyms, antonyms, related words, and derived words from the nearest set of words based on vector values. We also tried to use vector words to solve word analogy problems. The best word vector in extrinsic evaluation is the result of the CBOW algorithm which is integrated with Binary Relevance and Multilayer Perceptron, with an accuracy value of 77.56% and a hamming loss value of 8.14%.

Sistem Pengaman Kunci Kontak Sepeda Motor Melalui Android Berbasis NodeMCU ESP8266

Abstract: Pada penelitian ini telah dikembangkan mengenai sistem pengaman kunci kontak pada sepeda motor secara nirkabel untuk mencegah kasus pencurian. Modul atau perangkat nirkabel menggunakan sistem minimum berupa NodeMCU ESP8266 yang terhubung pada perangkat smartphone milik pengguna. Terdapat dua buah sensor getaran SW420 yang diletakkan pada titik-titik tertentu pada rangka (chasis) sepeda motor. Secara keseluruhan sistem pengiriman data terdekat dengan jarak 1 meter dari NodeMCU menuju perangkat android user membutuhkan RTT (round trip time) sebesar 8.37 ms dan throughput sebesar 3192 bps. Kemudian jarak terjauh yang dapat diukur sejauh 28 meter dengan RTT sebesar 9,3 ms dan memiliki throughput 3400 bps. Proses pengiriman data dilakukan secara satu arah. Parameter yang diukur yaitu jarak, throughput, dan RTT.