Jurnal Teknologi dan Sistem Komputer
Not a member yet
364 research outputs found
Sort by
Maturity classification of cacao through spectrogram and convolutional neural network
Get PDFCacao pod's ideal harvesting time is when it is about to be ripe. Immature harvest would result in hard cacao beans not suitable for fermentation, while overripe cacao pods lead to fungal-infected, defective, and poor-quality yields. The demand for high-quality cacao products is expected to rise due to advancing technology in the present. Pre-harvesting needs to provide optimal identification of which amongst the pods are ripened enough and ready for the next stage of the cacao process. This paper recommends a technique to determine the ripeness of cacao. Nine hundred thirty-three cacao samples were used to collect thumping audio data at five different pod's exocarp locations. Each sound file is 1 second long, creating 4665 cacao sound file datasets at 16kHz sample rate and 16-bit audio bit depth. The process of the Mel-Frequency Cepstral Coefficient Spectrogram was then applied to extract recognizable features for the training process. The deep learning method integrated was a convolutional neural network (CNN) to classify the cacao sound successfully. The experimental design model's output exhibits an accuracy of 97.50 % for the training data and 97.13 % for the validation data. While the overall accuracy mean of the classification system is 97.46 %, whether the cacao is unripe or ripe
Deteksi Arteri Karotis pada Citra Ultrasound B-Mode Berbasis Convolution Neural Network Single Shot Multibox Detector
Get PDFDetection of vascular areas (blood vessels) using B-Mode ultrasound images is needed for automatic applications such as registration and navigation in medical operations. This study developed the detection of the carotid artery area using Convolution Neural Network Single Shot Network Multibox Detector (SSD) to determine the bounding box ROI of the carotid artery area in B-mode ultrasound images. The data used are B-Mode ultrasound images on the neck that contain the carotid artery area (primary data). SSD method result is 95% of accuracy which is higher than the Hough transformation method, Ellipse method, and Faster RCNN in detecting carotid artery area in the B-Mode ultrasound image. The use of image enhancement with Gaussian filter, histogram equalization, and Median filters in this method can increase detection accuracy. The best process time of the proposed method is 2.09 seconds so that it can be applied in a real-time system.Deteksi area vaskular (pembuluh darah) menggunakan citra ultrasound B-Mode diperlukan untuk aplikasi otomatis seperti registrasi dan navigasi dalam operasi medis. Penelitian ini melakukan kajian deteksi area arteri karotis menggunakan Convolution Neural Network Single Shot Multibox Detector (SSD) untuk menentukan RoI area arteri karotis dengan fitur bounding box pada citra ultrasound B-Mode. Data yang digunakan dalam penelitian adalah citra ultrasound B-Mode pada bagian leher yang mengandung area arteri karotis (data primer). Hasil metode SSD memiliki akurasi 95% dan akurasi yang lebih tinggi dari metode transformasi Hough, metode Ellipse dan Faster RCNN dalam mendeteksi area arteri karotis pada citra ultrasound B-Mode. Penerapan image enhancement dengan filter Gaussian, histogram equalization dan filter Median memberikan pengaruh dalam peningkatan akurasi deteksi. Waktu proses terbaik dari metode yang diusulkan adalah 2,09 detik sehingga dapat diterapkan dalam sistem yang bersifat real-time
Modifikasi Algoritme Bellman-Ford Untuk Pencarian Rute Terpendek Berdasarkan Kondisi Jalan
Get PDFThe application of the Bellman-ford algorithm for finding the shortest path both weighted and unweighted graph has a weakness in determining the shortest path based on road conditions. This study modified the Bellman-Ford algorithm by adding the Technique for Order of Preference by Similarity to the Ideal Solution method to provide alternative road assessments based on its condition criteria including road density, road width, travel time, and distance. This modified Bellman-Ford has better performance in finding the alternative shortest path by choosing a road with smoother conditions, even though distance and travel time increase.Penerapan algoritme Bellman-Ford untuk pencarian lintasan terpendek dalam suatu graf berbobot atau tidak berbobot mempunyai kelemahan dalam menentukan rute terpendek berdasarkan faktor-faktor kondisi jalan. Penelitian ini mengkaji modifikasi algoritme Bellman-Ford dengan menambahkan metode Technique for Order of Preference by Similarity to Ideal Solution untuk memberikan penilaian alternatif jalan berdasarkan kriteria kondisi jalan meliputi tingkat kepadatan jalan, lebar jalan, waktu tempuh, dan jarak. Bellman-Ford yang dimodifikasi ini mempunyai kinerja yang lebih baik dalam menemukan jalur terpendek alternatif dengan memilih jalan dengan kondisi lebih lancar, walaupun jarak dan waktu tempuh bertambah
Prediction of Call Drops in GSM Network using Artificial Neural Network
Get PDFGlobal System for Mobile communication is a digital mobile system that is widely used in the world. Over the years, the number of subscribers has tremendously increased, the quality of service (Call Drop Rate) became an issue to consider as many subscribers were not satisfied with the services rendered. In this paper, we present the Artificial Neural Network approach to predict call drop during an initiated call. GSM parameters data for the prediction were acquired using TEMS Investigations software. The measurements were carried out over a period of three months. Post analysis and training of the parameters was done using the Artificial Neural Network to have an output of “0” for no-drop calls and “1” for drop calls. The developed model has an accuracy of 87.5% prediction of drop call. The developed model is both useful to operators and end users for optimizing the network
Performance of XMPP-Based Gateway for IoT Device Communication Services
Get PDFPenelitian ini mengkaji kinerja gateway komunikasi untuk perangkat-perangkat IoT dengan memanfaatkan protokol XMPP agar perangkat ini dapat saling terhubung dan berkomunikasi menggunakan jaringan Internet. Perangkat IoT berupa sensor node yang diimplementasikan menggunakan NodeMCU yang terhubung dengan modul sensor DHT11 dan lampu LED sebagai simulasi bahwa ada data yang masuk. Perangkat IoT telah dapat berkomunikasi menggunakan gateway protokol XMPP dan melakukan proses request-response. Hasil pengujian kinerja gateway saat transmisi data dengan variasi ukuran dari 10-100 MB mendapatkan waktu tunda rata-rata 9,3 ms, jitter rata-rata jitter 0,00178 ms, dan throughput rata-rata 161,4 kbps. Parameter penggunaan CPU memiliki kenaikan rata-rata 12% dan penggunaan memori cenderung konstan pada saat terjadi transmisi data.This study examines the performance of a communication gateway for IoT devices by utilizing the XMPP protocol so that these devices can be connected and communicate using the Internet. The sensor nodes, which are IoT devices, were implemented using NodeMCU connected to the DHT11 sensor module and LED lights to simulate the incoming data. Sensor nodes can communicate using the XMPP protocol gateway and process the request-response data. Gateway data transmission performance with size variations from 10-100 MB gets an average delay time of 9.3 ms, an average jitter of 0.00178 ms, and an average throughput of 161.4 kbps. The CPU usage parameter has an average increase of 12%, and memory usage tends to be constant when data transmission occurs
Studi komparatif empat model propagasi empiris dalam ruangan untuk jaringan nirkabel kampus
Get PDFPropagation is one of the important factors to understand in wireless communication systems. Prediction of the value of propagation, especially for closed areas, is very necessary to determine success in building wireless networks. Various kinds of propagation modeling were developed to find the best approach to calculate the value of signal losses. A comparative study of 4 types of empirical propagation modeling was made to provide the most suitable propagation modeling analysis for campus wireless networks. The ITU-R model (P.1238) provides predictive results that are closest to the actual data in the field, with a relative error rate of 16.381%.Propagasi menjadi salah satu faktor yang penting untuk dipahami dalam sistem komunikasi wireless. Prediksi terhadap nilai propagasi, khususnya untuk area tertutup, sangat diperlukan untuk menentukan keberhasilan dalam membangun jaringan wireless. Berbagai macam pemodelan propagasi dikembangkan untuk mencari pendekatan terbaik untuk menghitung nilai rugi-rugi sinyal yang terjadi. Sebuah studi komparatif terhadap 4 jenis pemodelan propagasi empiris dibuat guna memberikan analisis pemodelan propagasi yang paling sesuai untuk jaringan wireless kampus. Pemodelan ITU-R (P.1238) memberikan hasil prediksi yang paling mendekati data aktual di lapangan, dengan tingkat kesalahan relatif sebesar 16,381%
Front Matter - JTSiskom Volume 7 Issue 1 Year 2019
No full textThis article contains front-matter of JTSiskom Volume 7 Number 1 Year 2019, which includes a cover page, title page, editorial team, acknowledgment, editorial policy and table of contents. JTSiskom's editorial policies include focus and scope, review process statement, publication frequency, open access policy, archiving policy and statement of article processing fee
Sistem Penegakan Speed Bump Berdasarkan Kecepatan Kendaraan yang Diklasifikasikan Haar Cascade Classifier
Get PDFDriving at high speed is among the frequent causes of accidents. In this research, a warning system was developed to warn drivers when their speed beyond the safety limit. Haar cascade classifier was proposed for the detection system which comprises Haar features, integral image, AdaBoost learning, and cascade classifier. The system was implemented using Python OpenCV library and evaluated on road traffic video collected in one way traffic. As a result, the proposed method yields 97.92% of car detection accuracy in daylight and MSE of 2.88 in speed measurement.Berkendara dengan kecepatan tinggi merupakan salah satu penyebab terjadinya kecelakaan. Dalam penelitian ini, sistem peringatan dikembangkan untuk memperingatkan pengemudi ketika kecepatan mereka melanggar batas keamanan. Haar cascade classifier diusulkan untuk sistem deteksi yang terdiri dari Haar features, integral image, AdaBoost learning, dan cascade classifier. Sistem ini diimplementasikan menggunakan pustaka OpenCV Python dan dievaluasi pada video lalu lintas yang dikumpulkan dalam lalu lintas satu arah. Metode yang diusulkan menghasilkan akurasi deteksi mobil sebesar 97,92% di siang hari dan MSE 2,88 dalam pengukuran kecepatan kendaraan
Performance analysis of gray code number system in image security
Get PDFThe encryption of digital images has become essential since it is vulnerable to interception while being transmitted or stored. A new image encryption algorithm to address the security challenges of traditional image encryption algorithms is presented in this research. The proposed scheme transforms the pixel information of an original image by taking into consideration the pixel location such that two neighboring pixels are processed via two separate algorithms. The proposed scheme utilized the Gray code number system. The experimental results and comparison shows the encrypted images were different from the original images. Also, pixel histogram revealed that the distribution of the plain images and their decrypted images have the same pixel histogram distributions, which means that there is a high correlation between the original images and decrypted images. The scheme also offers strong resistance to statistical attacks
Metode SURF dan FLANN untuk Identifikasi Nominal Uang Kertas Rupiah Tahun Emisi 2016 pada Variasi Rotasi
Get PDFIn December 2016, Bank Indonesia (BI) officially launched the 2016 Year Emission Rupiah. With the development of technology, the process of buying and selling are not only possible between humans and humans, but humans with a machine. In addition, the machine must also be able to read and recognize the nominal banknotes in various variations of face and rotation. This is because humans can put money in machines with various variations of face and rotation. This study aims to apply and analyze the level of accuracy of nominal rupiah banknotes identification with the SURF and FLANN methods for rotation variation. Testing for identification of nominal rupiah banknotes is carried out with different rotation variations, namely 0o, 90o, 180o, and 270o. The proposed identification method provides 100% of accuracy.Pada bulan Desember 2016, Bank Indonesia (BI) secara resemi meluncurkan uang rupiah Emisi 2016. Semakin berkembangnya teknologi, saat ini proses jual beli tidak hanya dapat dilakukan antara manusia dengan manusia, akan tetapi manusia dengan mesin. Selain itu mesin juga harus dapat membaca dan mengenali nominal uang kertas dalam berbagai variasi muka dan rotasi. Hal ini dikarenakan manusia dapat memasukkan uang pada mesin dengan berbagai variasi muka dan rotasi. Penelitian ini bertujuan untuk menerapkan dan menganalisis tingkat akurasi identifikasi nominal uang kertas rupiah dengan metode SURF dan FLANN terhadap variasi rotasi. Pengujian identifikasi uang nominal uang kertas rupiah dilakukan dengan variasi rotasi yang berbeda yaitu 0o, 90o, 180o, dan 270o. Metode identifikasi yang diajukan memberikan hasil akurasi sebesar 100%