Jurnal Teknologi dan Sistem Komputer
Not a member yet
364 research outputs found
Sort by
Algoritme deteksi kedatangan tsunami otomatis untuk sistem observasi tinggi muka air laut
Full text linkThe automatic tsunami detection algorithm needs to be put in the sea level observation system to give society a quick warning when a tsunami happens. This study designs an automatic tsunami detection algorithm consisting of three sub-algorithm: spike elimination, gap data filling, and tsunami detection. Spike elimination and gap data filling are used to improve the sea level data, which is often disturbed by spikes and gap data due to electronic factors. This algorithm was tested using time-series tide gauge data that contain tsunami waveforms in Indonesia from 2007 to 2019. About 54.52 % of 409 spikes have been eliminated while the gap data were successfully filled. Furthermore, tsunami detection, which uses DART (Deep-ocean Assessment and Reporting of Tsunamis) and TEDA (Tsunami Early Detection Algorithm) methods, can detect 7 of 10 tsunami waveforms. However, there are three undetected tsunamis and one false detection. This algorithm has an average delay of 7.7 minutes in detection time.Agar dapat menginformasikan kedatangan tsunami dengan cepat kepada masyarakat, sistem observasi muka air laut perlu dilengkapi dengan algoritme deteksi tsunami otomatis. Penelitian ini bertujuan merancang algoritme deteksi tsunami yang terdiri dari 3 subalgoritme, yaitu eliminasi spike, pengisian data kosong, dan pendeteksi tsunami. Subalgoritme eliminasi spike dan pengisian data kosong digunakan untuk memperbaiki data observasi tinggi muka air laut yang sering terganggu oleh spike dan data kosong akibat faktor elektronik peralatan. Hasil perancangan diuji dengan data historis tide gauge saat terjadi tsunami antara tahun 2007-2019. Hasilnya, spike telah tereliminasi sebanyak 54,52 % dari 409 kemunculan, sedangkan data kosong berhasil diisi 100%. Pendeteksian tsunami yang menggunakan metode DART (Deep-ocean Assessment and Reporting of Tsunamis) dan TEDA (Tsunami Early Detection Algorithm) mampu mendeteksi 7 dari 10 sinyal tsunami, namun masih ada 3 sinyal yang tidak terdeteksi dan 1 kesalahan deteksi. Selain itu, rata-rata waktu pendeteksian tsunami sekitar 7,7 menit setelah tiba di lokasi tide gauge
Peramalan kekuatan gerak tangan menggunakan Extreme Learning Machine untuk terapi pasca-stroke
Full text linkStroke or Cerebrovascular accident (CVA) can cause weakness in one side of the body, including the upper limbs such as the hand. Rehabilitation is needed to restore the function of the hand. Rehabilitation should also measure the strength of the movements carried out. This article aims to forecast the strength of movement based on Electromyography (EMG) signals using the Extreme Learning Machine (ELM). This study collected EMG signal data and movement strength, carried out data pre-processing and data extraction using various extraction features, applied ELM for forecasting strength based on EMG signals, and applied created models in stroke therapy robots. The forecasting model is evaluated by measuring the Mean Squared Error (MSE). The average value of the best MSE in offline testing is 1.77, while the real-time testing is 0.79. A small MSE value indicates that the model is good enough. The resulted value of strength can be applied to make the stroke therapy robots actuating properly.Stroke atau Cerebrovascular Accident (CVA) dapat menyebabkan kelemahan pada salah satu bagian sisi tubuh termasuk anggota gerak atas, seperti tangan, sehingga diperlukan rehabilitasi untuk mengembalikan fungsi dari tangan. Rehabilitasi yang dilakukan sebaiknya juga dapat mengukur kekuatan dari gerakan yang dilakukan. Artikel ini bertujuan untuk melakukan peramalan kekuatan gerakan berdasarkan sinyal Electromyography (EMG) menggunakan metode Extreme Learning Machine (ELM). Tahapan yang dilakukan meliputi pengumpulan data sinyal EMG dan kekuatan gerakan, pre-processing data dan ekstraksi fitur data menggunakan berbagai fitur ekstraksi, penerapan ELM untuk peramalan kekuatan berdasarkan sinyal EMG, dan penerapan model yang dibuat pada robot terapi stroke. Evaluasi model peramalan dilakukan dengan mengukur Mean Squared Error (MSE). Nilai rata-rata MSE terbaik pada pengujian offline adalah 1,77, sedangkan pada pengujian real-time sebesar 0,79. Nilai MSE yang kecil menunjukkan bahwa model yang dibuat sudah cukup baik. Pergerakan robot berdasarkan nilai kekuatan yang dilakukan sudah dapat bergerak dengan baik
Real-time currency recognition on video using AKAZE algorithm
Full text linkCurrency recognition is one of the essential things since everyone in any country must know money. Therefore, computer vision has been developed to recognize currency. One of the currency recognition uses the SIFT algorithm. The recognition results are very accurate, but the processing takes a considerable amount of time, making it impossible to run for real-time data such as video. AKAZE algorithm has been developed for real-time data processing because of its fast computation time to process video data frames. This study proposes the faster real-time currency recognition system on video using the AKAZE algorithm. The purpose of this study is to compare the SIFT and AKAZE algorithms related to a real-time video data processing to determine the value of F1 and its speed. Based on the experimental results, the AKAZE algorithm is resulting F1 value of 0.97, and the processing speed on each video frame is 0.251 seconds. Then at the same video resolution, the SIFT algorithm results in an F1 value of 0.65 and a speed of 0.305 seconds to process one frame. These results show that the AKAZE algorithm is faster and more accurate in processing video data
Sistem sensor untuk pemantauan kadar oksigen terlarut berbasis galvanik pada kolam budidaya ikan air tawar
Full text linkThis study aims to develop low-cost and environmentally friendly material galvanic-based dissolved oxygen sensors. A Dissolved oxygen (DO) sensor has been designed and fabricated on an 85 x 205 mm galvanic-based. The sensor structure device consists of Al-Zn reference layer electrode, Ag/AgCl active electrode, 120ml KCl electrolyte solvent 0,1 M, and closed by TiO2 membrane (PTFE). The Al-Zn formation reference electrode was done by Ag layer chlorination using FeCl3, and the TiO2 membrane was formed by TiO2 paste screen printing. The test was done to measure the sensor’s performance based on the current-voltage characteristics between 1.0 and 1.8 V. The results showed that a stable diffusion current was obtained when the input voltage was 1.5 V, resulting in the best sensor performance with a sensitivity of 0.7866 μA L/mg and a stable step response time of 3 mins. This prototype sensor showed high potential for prototyping for a low-cost water quality monitoring system.Penelitian ini bertujuan mengembangkan sensor oksigen terlarut berbasis galvanik yang ramah lingkungan dan terjangkau oleh masyarakat. Struktur desain sensor ini terdiri dari lapisan elektroda referensi Al-Zn, elektroda aktif Ag / AgCl, pelarut elektrolit KCl 120 ml 0,1 M, dan ditutup dengan membran TiO2 (PTFE). Pembentukan elektroda referensi Al-Zn dilakukan dengan klorinasi lapisan Ag menggunakan FeCl3 dan membran TiO2 dibentuk dengan sablon pasta TiO2. Pengujian dilakukan untuk mengukur kinerja sensor berdasarkan karakteristik tegangan arus antara 1,0 sampai 1,8 V. Hasil penelitian menunjukkan bahwa arus difusi yang stabil diperoleh pada saat tegangan input 1,5 V dan menghasilkan kinerja sensor terbaik dengan sensitivitas 0,7866 μA L/mg dan waktu respons langkah stabil 3 menit. Prototipe sensor ini menunjukkan potensi yang sangat tinggi untuk digunakan dalam sistem pemantauan kualitas air online berbiaya rendah
Segmentation and analysis of Pap smear microscopic images using the K-means and J48 algorithms
Full text linkPap smear merupakan salah satu metode untuk melakukan deteksi dini dari kanker leher rahim. Kajian ini membahas metode segmentasi dan analisis citra sel Pap smear menggunakan algoritme K-means agar sel sitoplasma, sel nukleus, dan sel radang dapat tersegmentasi secara otomatis. Hasil analisis fitur dari citra sel sitoplasma, nukleus, dan radang tersebut diklasifikasikan menggunakan algoritme J48 dengan data latih sebanyak 37 citra dan menghasilkan akurasi sebesar 94,594 %, presisi 95 %, dan sensitivitas sebesar 94,6 %. Pengujian klasifikasi pada data uji sebanyak 24 citra menghasilkan akurasi sebesar 91,6 %, presisi sebesar 92,5 % dan sensitivitas sebesar 91,7 %.A Pap smear is used to early detection cervical cancer. This study proposes the segmentation and analysis method of Pap smear cells images using the K-means algorithm so that cytoplasmic cells, nuclear cells, and inflammatory cells can be segmented automatically. The results of the feature analysis from the cytoplasmic, nuclear, and inflammatory cell images were classified using the J48 algorithm with 37 training data. The training resulted in an accuracy of 94.594 %, precision of 95 %, and sensitivity of 94.6 %. The classification of 24 testing images resulted in an accuracy of 91.6%, a precision of 92.5 %, and a sensitivity of 91.7 %
Optimasi proses penjadwalan mata kuliah menggunakan algoritme genetika dan pencarian tabu
Full text linkScheduling courses in higher education often face problems, such as the clashes of teachers' schedules, rooms, and students' schedules. This study proposes course scheduling optimization using genetic algorithms and taboo search. The genetic algorithm produces the best generation of chromosomes composed of lecturer, day, and hour genes. The Tabu search method is used for the lecture rooms division. Scheduling is carried out for the Informatics faculty with four study programs, 65 lecturers, 93 courses, 265 lecturer assignments, and 65 classes. The process of generating 265 schedules took 561 seconds without any scheduling clashes. The genetic algorithms and taboo searches can process quite many course schedules faster than the manual method.Penjadwalan mata kuliah merupakan permasalahan yang sering terjadi pada perguruan tinggi, di antaranya adalah bentrok waktu mengajar dosen, ruangan dan kelas mahasiswa. Kajian ini mengusulkan optimasi penjadwalan mata kuliah menggunakan algoritme genetika dan pencarian tabu. Algoritme genetika berfungsi untuk menghasilkan generasi terbaik kromosom yang tersusun atas gen dosen, hari, dan jam. Pencarian tabu digunakan untuk pembagian ruang perkuliahan. Penjadwalan dilakukan di fakultas Informatika yang mempunyai empat program studi dengan 65 dosen, 93 mata kuliah, 265 penugasan dosen, dan 65 kelas. Proses pembangkitan 265 jadwal membutuhkan waktu selama 561 detik dan tidak ada bentrok yang terjadi. Kombinasi algoritme genetika dan pencarian tabu dapat memproses jadwal mata kuliah yang cukup banyak dengan lebih cepat daripada cara manual
Prediksi dinamika pandemi di Pulau Jawa menggunakan metode Moving Average dan Knowledge Growing System
Full text linkThis study aims to analyze the comparative performance of pandemic dynamics prediction methods on the island of Java, based on data from March to May 2020 covering the provinces of DKI Jakarta, West Java, Central Java, DI Yogyakarta, and East Java. The prediction uses Knowledge Growing System (KGS) and time series models, namely Single Moving Average (SMA) and Exponential Moving Average (EMA). Based on the Mean Absolute Percentage Error (MAPE) computational results, the EMA method produces a lower error rate than the SMA method with 47.94 % on average. The KGS prediction with a Degree of Certainty (DoC) produced a trend analysis that the pandemic dynamics in DKI Jakarta province will decrease gradually if the current policy is still implemented. Whereas in the other provinces, the KGS predicted the pandemic dynamics trends will still increase.Penelitian ini bertujuan untuk menganalisis perbandingan kinerja metode-metode komputasi untuk memprediksi dinamika pandemi di Pulau Jawa berdasarkan data-data antara bulan Maret-Mei 2020 yang mencakup Provinsi DKI Jakarta, Jawa Barat, Jawa Tengah, DI Yogyakarta, dan Jawa Timur. Prediksi dilakukan menggunakan tiga metode, yaitu Knowledge Growing System (KGS) dan model deret waktu, yaitu Single Moving Average (SMA), dan Exponential Moving Average (EMA). Berdasarkan dari hasil-hasil komputasi Mean Absolute Percentage Error (MAPE) disimpulkan bahwa metode EMA menghasilkan tingkat kesalahan yang lebih kecil daripada metode SMA dengan rerata sebesar 47,94 %. KGS menghasilkan kompurasi Degree of Certainty (DoC) dan menganalisis tren dinamika pandemi di Provinsi DKI Jakarta akan turun, jika kebijakan yang saat ini diterapkan tetap dilanjutkan. Pada provinsi-provinsi lainnya, KGS memprediksi bahwa dinamika pandemi masih akan terus meningkat
Three combination value of extraction features on GLCM for detecting pothole and asphalt road
Full text linkThe rate of vehicle accidents in various regions is still high accidents caused by many factors, such as driver negligence, vehicle damage, and road damage. However, transportation technology developed very rapidly, for example, a smart car. The smart car is land transportation that does not use humans as drivers but uses machines automatically. However, vehicle accidents are still possible because automatic machines do not have the intelligence like humans to see all the vehicle's obstacles. Obstacles can take many forms, one of them is road potholes. We propose a method for detecting road potholes using the Gray-Level Cooccurrence Matrix with three features and using the Support Vector Machine as a classification method. We analyze the combination of GLCM Contrast, Correlation, and Dissimilarity features. The results showed that the combination of Contrast and Dissimilarity features had the best accuracy of 92.033 %, with a computing time of 0.0704 seconds per frame
Sistem rekomendasi peminatan peserta didik baru pada kurikulum K-13 menggunakan metode profile matching, simple additive weighting, dan kombinasi keduanya
Full text linkThe selection of students' interests based on the 2013 curriculum (K-13) is carried out before students start learning in class X. Accuracy in its determination is required to ensure that students learn according to their interests and talents. This study applies three DSS methods, namely profile matching, SAW, and a combination of both, to provide accurate recommendations for determining these students' interests. The three methods are compared using the same alternatives and criteria to find the most dominant method. The results of this study indicate that the application of SPK can assist PPDB activities with an accuracy of 79.2 %. In determining interest for students, the combination method is the most dominant, with an accuracy of 78 %. The application of DSS not only helps the specialization process to be faster but also accurate. This is indicated by only 6 out of 122 students who chose specialization based on the DSS recommendation getting a score below the KKM.Peminatan peserta didik dalam kurikulum 2013 dilakukan sebelum peserta didik memulai belajar di kelas X. Ketepatan dalam penentuannya diperlukan untuk memastikan peserta didik belajar sesuai dengan minat dan bakat yang dimiliki. Penelitian ini menerapkan tiga metode SPK, yaitu profile matching, SAW dan kombinasi keduanya, untuk memberikan rekomendasi peminatan siswa didik ini. Ketiga metode tersebut dikomparasikan menggunakan alternatif dan kriteria yang sama untuk mengetahui metode yang paling dominan. Hasil penelitian ini menunjukkan bahwa penerapan SPK dapat membantu kegiatan PPDB dengan akurasi 79,2 %. Dalam proses penentuan minat bagi peserta didik, metode kombinasi menjadi yang paling dominan dengan persentase sebesar 78 %. Penerapan SPK tidak hanya membantu proses peminatan menjadi lebih cepat, tetapi juga akurat. Hal ini dibuktikan dengan hanya terdapat 6 dari total 122 peserta didik yang memilih peminatan berdasarkan rekomendasi SPK mendapatkan nilai di bawah KKM
Malicious URLs detection using data streaming algorithms
Full text linkAs a result of advancements in technology and technological devices, data is now spawned at an infinite rate, emanating from a vast array of networks, devices, and daily operations like credit card transactions and mobile phones. Datastream entails sequential and real-time continuous data in the inform of evolving stream. However, the traditional machine learning approach is characterized by a batch learning model. Labeled training data are given apriori to train a model based on some machine learning algorithms. This technique necessitates the entire training sample to be readily accessible before the learning process. The training procedure is mainly done offline in this setting due to the high training cost. Consequently, the traditional batch learning technique suffers severe drawbacks, such as poor scalability for real-time phishing websites detection. The model mostly requires re-training from scratch using new training samples. This paper presents the application of streaming algorithms for detecting malicious URLs based on selected online learners: Hoeffding Tree (HT), Naïve Bayes (NB), and Ozabag. Ozabag produced promising results in terms of accuracy, Kappa and Kappa Temp on the dataset with large samples while HT and NB have the least prediction time with comparable accuracy and Kappa with Ozabag algorithm for the real-time detection of phishing websites