Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
Analisis konsumsi energi protokol routing reaktif dsr pada mobile ad hoc network
No full textMobile ad-hoc network is a connection between mobile devices that uses wireless media. Mobile devices on the network hereinafter referred to a nodes. This network does not have an administrative center so each node on the network in addition to functioning as a sender and receiver of data information also functions as a router that will look for route information from the sender to the receiver. The topology of an ad-hoc network is always changing because the nodes move dynamically. The topology changes resulted in the repetition of route information searches. The process of finding route information requires a routing protocol. The routing protocol-enabled nodes must maintain the energy usage in the route-finding mechanism. Choosing the right routing protocol can be a solution to make energy use by nodes more efficient, especially in ad-hoc networks. In this study, a routing protocol in the reactive category is used, namely DSR (Dynamic Source Routing). This study aims to determine the performance of energy consumption, remaining energy, and PDR with scenarios of increasing node movement speed and network area. Based on the research results, it is known that the DSR routing protocol can handle changes in the speed of node movement and network area related to energy consumption and remaining energy. This is evidenced by the results of research showing that with faster node movements and wider areas, less energy is required. Meanwhile, regarding the success of packet delivery, the DSR routing protocol cannot handle changes in the speed of node movement and network area. This is evidenced by the results of the packet delivery ratio measurement which shows that with faster node movements and wider areas, many packets are not successfully received.Jaringan mobile ad-hoc merupakan koneksi antar perangkat (mobile) yang menggunakan media wireless. Perangkat dalam jaringan disebut juga node. Jaringan ini tidak memiliki pusat administrasi sehingga setiap node pada jaringan selain berfungsi sebagai pengirim dan penerima informasi data juga berfungsi sebagai router yang akan mencari informasi rute dari pengirim ke penerima. Topologi pada jaringan ad-hoc selalu berubah karena node bergerak secara dinamis. Perubahan topologi tersebut berakibat terjadinya pengulangan pencarian informasi rute. Proses pencarian informasi rute membutuhkan protokol routing. Node yang diaktifkan protokol routing harus menjaga penggunaan energi dalam mekanisme pencarian rute. Pemilihan protokol routing yang tepat dapat menjadi solusi agar penggunaan energi oleh node menjadi lebih efisien, terlebih pada jaringan ad-hoc. Pada penelitian ini digunakan protokol routing dalam kategori reaktif yaitu DSR (Dynamic Source Routing). Penelitian ini bertujuan untuk mengetahui performansi konsumsi energi, energi yang tersisa, dan PDR dengan skenario penambahan kecepatan pergerakan node dan luas area jaringan. Berdasarkan hasil penelitian, diketahui bahwa protokol routing DSR dapat menangani perubahan kecepatan pergerakan node dan luas area jaringan terkait konsumsi energi dan energi yang tersisa. Hal ini dibuktikan dengan hasil penelitian yang menunjukkan bahwa dengan pergerakan node yang semakin cepat dan area yang semakin luas, membutuhkan energi yang kecil. Sedangkan terkait keberhasilan pengiriman paket, protokol routing DSR tidak dapat menangani perubahan kecepatan pergerakan node dan luas area jaringan. Hal ini dibuktikan dengan hasil pengukuran packet delivery ratio yang menunjukkan bahwa dengan pergerakan node yang semakin cepat dan area yang semakin luas, banyak paket yang tidak berhasil diterima
Fatigue Detection Using Decision Tree Method based on PPG signal
Full text linkFatigue is a complex psychophysiological condition marked by sleepiness or fatigue, poor performance, and a range of physiological changes. A decision tree may be used to categorize weariness based on the subject's heart rate data. To begin the experiment, a dataset of the heart rate signal was obtained. The signal has already undergone preprocessing. The feature obtained through preprocessing is then used to construct the decision model. Four traits were discovered. The HF power, LF power, normalized HF power, and normalized LF power are the characteristics. This research has a 75.94% accuracy rating. The precision, recall, and F-measure scores for this study were 0.736, 0.736, and 0.736, respectively
Model Prediksi Dengan Artificial Neural Network Untuk Kejadian Banjir Rob Di Wilayah Pesisir Kota Bandar Lampung
No full textThe fastest sea level rise began in 2013 and reached its highest level in 2021. This is part of the ongoing global warming impact, where polar ice continues to melt, glaciers also continue to melt, causing sea level rise. In the Bandar Lampung City area, there are several areas that are threatened with tidal flooding, namely Karang City Village and Kangkung Village, Bumi Waras Village, and Sukaraja Village. Bandar Lampung itself is the city center in the coastal area. Where the majority of the population is in the Coastal area so that the threat of tidal flooding is caused by rising sea levels. To study the occurrence of tidal floods in the past, this research uses an Artificial Neural Network which has the ability to study non-linear data which is then carried out by training and testing until the best configuration model is obtained. Based on the analysis and discussion that has been carried out, several important points can be drawn, including the results of training and dataset testing that has been carried out. , 80:20, and 90;10. This is evidenced by the results of the high accuracy of the model configuration and also the results of the prediction table which is able to describe the actual conditions, setting the model configuration experimentally is able to produce the best training accuracy value reaching 100% while for the best testing accuracy is 88%. The average correlation value of training with the 50:50 dataset is 0.975, the 60:40 dataset is 0.975, the 70:30 dataset is 0.951, the 80:20 dataset is 0.935, and the 90:10 dataset is 0.929. For the average value of the correlation test with the 50:50 dataset of 0.514, the 60:40 dataset is 0.362, the 70:30 dataset is 0.488, the 80:20 dataset is 0.284, and the 90:10 dataset is 0.402. Whereas the average error value for the 50:50 dataset is 0.006, the 60:40 dataset is 0.006, the 70:30 dataset is 0.010, the 80:20 dataset is 0.007, and the 90:10 dataset is 0.007, the flood prediction table is made based on 1 configuration the best with a training accuracy rate of 98% and a testing accuracy of 80% with an error value of 0.004, namely configuration model 14, this model is the best configuration model out of 3 dataset divisions out of a total of 5. The prediction table uses sea level tides of 1.5 meters. The prediction table is able to provide good tidal flood percentage values, especially when there are active astronomical phenomena. The results of this good flood prediction table illustrate that the backpropagation ANN is able to study datasets well and can be used by BMKG forecasters in making tidal flood early warnings.Kenaikan muka air laut paling cepat dimulai pada tahun 2013 dan mencapai titik tertinggi pada tahun 2021. Hal ini merupakan bagian dari dampak pemanasan global yang sedang berlangsung, dimana es di kutub terus mencair, gletser juga terus mencair sehingga menyebabkan kenaikan muka air laut. Di wilayah Kota Bandar Lampung terdapat beberapa wilayah yang terancam banjir rob yaitu Desa Kota Karang dan Desa Kangkung, Desa Bumi Waras, dan Desa Sukaraja. Bandar Lampung sendiri merupakan pusat kota di kawasan pesisir. Dimana mayoritas penduduknya berada di wilayah Pesisir sehingga ancaman banjir rob disebabkan oleh naiknya permukaan air laut. Untuk mempelajari kejadian banjir rob di masa lalu, penelitian ini menggunakan Artificial Neural Network yang memiliki kemampuan untuk mempelajari data non linier yang kemudian dilakukan pelatihan dan pengujian hingga diperoleh model konfigurasi yang terbaik. Berdasarkan analisis dan pembahasan yang telah dilakukan, dapat ditarik beberapa poin penting antara lain hasil pelatihan dan pengujian dataset yang telah dilakukan. , 80:20, dan 90;10. Hal ini dibuktikan dengan hasil akurasi konfigurasi model yang tinggi dan juga hasil tabel prediksi yang mampu menggambarkan kondisi sebenarnya, pengaturan konfigurasi model secara eksperimental mampu menghasilkan nilai akurasi training terbaik mencapai 100% sedangkan untuk akurasi pengujian terbaik adalah 88%. Rata-rata nilai korelasi training dengan dataset 50:50 adalah 0,975, dataset 60:40 adalah 0,975, dataset 70:30 adalah 0,951, dataset 80:20 adalah 0,935, dan dataset 90:10 adalah 0,929. Untuk nilai rata-rata uji korelasi dengan dataset 50:50 sebesar 0,514, dataset 60:40 adalah 0,362, dataset 70:30 adalah 0,488, dataset 80:20 adalah 0,284, dan dataset 90:10 adalah 0,402. Sedangkan rata-rata nilai error untuk dataset 50:50 adalah 0,006, dataset 60:40 adalah 0,006, dataset 70:30 adalah 0,010, dataset 80:20 adalah 0,007, dan dataset 90:10 adalah 0,007, prediksi banjir tabel dibuat berdasarkan 1 konfigurasi terbaik dengan tingkat akurasi pelatihan 98% dan akurasi pengujian 80% dengan nilai error 0,004 yaitu model konfigurasi 14, model ini merupakan model konfigurasi terbaik dari 3 divisi dataset dari total 5. Tabel prediksi menggunakan pasang surut air laut 1,5 meter. Tabel prediksi tersebut mampu memberikan nilai persentase banjir rob yang baik, terutama saat terjadi fenomena astronomi aktif. Hasil tabel prediksi banjir yang baik ini menggambarkan bahwa JST backpropagation mampu mempelajari dataset dengan baik dan dapat digunakan oleh peramal BMKG dalam membuat peringatan dini banjir rob
Automatic temperature detector to mitigate the spread of COVID-19
No full textThe COVID-19 causes wide impact in business operation. The enterprise must mitigate the risk of COVID-19 spread in its environment. The monitoring of body temperature for employees can be applied as a method to prevent COVID-19 spread. However, the monitoring system must consider several factors such as contactless system, accountable, and simple. The integration between IR temperature sensor and attendance system based on ESP32 is able to provide those need. The use of proximity, IR, and RFID sensor is affordable to detect body temperature properly within 10 cm. The proposed system provides notification if user gets fever or suspect of COVID-19 by detecting the body temperature. The accuracy of sensor is adequate. It is based on the comparison testing between proposed system with body thermometer where the testing is performed 30 times for each condition. In order to deduce the comparison result, this study uses analysis of variance method. The analysis produces F-critical (4,006) greater than F-value (0,022) where it means that the proposed system and body thermometer have similar testing result. It is shown good accuracy for the proposed system
Internet of things for monitoring parking system using optical character recognition
No full textThis research is in the form of an IoT-based parking system, which can help the transportation department. Currently, there are several obstacles experienced in collecting parking levies in the field, the absence of automatic and real-time information on four-wheeled and two-wheeled vehicles and the processing of vehicle parking tax levies is not transparent. One of the components of local revenue is the motor vehicle tax, in Bandar Lampung City, the implementation is still not optimal. This type of On Street Parking parking service uses the curb to park motor vehicles, generally guarded by a parking attendant with a parking location that has been determined by the parking manager. At each On Street Parking parking point, parking attendants are facilitated with a tool in the form of "Monitor Parking", with detection cameras that take pictures of motor vehicle license plates and store them in a database. OCR (Optical Character Recognition) technique of annotated plate data, and generates data again. The design results are in the form of a vehicle parking monitoring tool that can be run through portable gadgets. The "Monitor Parking" tool is easy to use and can help make it easier for parking attendants and the Transportation Agency to monitor parking in the field.Penelitian ini berupa sistem parkir berbasis IoT yang dapat membantu dinas perhubungan. Saat ini terdapat beberapa kendala yang dialami dalam memungut retribusi parkir di lapangan, tidak adanya informasi otomatis dan real time pada kendaraan roda empat dan roda dua serta proses retribusi pajak parkir kendaraan yang tidak transparan. Salah satu komponen pendapatan asli daerah adalah pajak kendaraan bermotor, di Kota Bandar Lampung pelaksanaannya masih belum optimal. Jenis layanan parkir On Street Parking ini menggunakan trotoar untuk memarkir kendaraan bermotor, umumnya dijaga oleh juru parkir dengan lokasi parkir yang telah ditentukan oleh pengelola parkir. Pada setiap titik parkir On Street Parking, petugas parkir difasilitasi dengan alat berupa “Monitor Parking”, dengan kamera pendeteksi yang mengambil gambar plat nomor kendaraan bermotor dan menyimpannya dalam database. Teknik OCR (Pengenalan Karakter Optik) dari data pelat beranotasi, dan menghasilkan data lagi. Hasil perancangan berupa alat pemantau parkir kendaraan yang dapat dijalankan melalui gadget portable. Alat “Monitor Parkir” mudah digunakan dan dapat membantu memudahkan petugas parkir dan Dishub dalam memantau parkir di lapangan
Monitoring of three-phase distribution power transformer based on the Internet of Things (IoT) and SCADA
No full textThe three-phase distribution transfomer, equipment for stepping down the voltage from medium (20/11,5 kV) to low voltage network (400/231 V) with a constant power, is a type of the PT. PLN (Persero) assets which has a direct relationship with customers. The condition and the performance of transformer are affecting on how the continuity of the electricity distributed. Hence, the monitoring process of three-phase distribution transfomer condition and performance should be done. Some elements which have to be monitored such as voltage (ZMPT101B sensor), current (ACS712 30 A sensor), power, and transfomer load. Those elements could be included as an electrical indicator.And then the transfomer’s temperature (DS18B20 sensor) and the oil transfomer level (HC SR04 sensor) could be included as a mechanical indicator. All of the sensors are processed and programmed with Arduino Mega 2560 which has been connected directly into an additional modul called Ethernet shield and router. The results then emitted by WiFi into SCADA to be shown. The results shown by SCADA is the information whether transformer need to be maintened or no
A virtual cage for monitoring system semi-intensive livestock’s using wireless sensor network and Haversine method
No full textIndonesia has great livestock potential. The semi-intensive grazing system is one of the efforts to increase the production of healthy and superior dairy or beef livestock. This grazing system has many advantages. However, it has several weaknesses that can prejudice farmers, including lost or stolen livestock due to a lack of control and monitoring. Therefore, tracking livestock’s position in the WSN-based grasslands monitoring will be implemented to overcome these weaknesses. Thus, it will provide benefits as a support for a modern and controlled livestock system. The built WSN consists of several nodes installed on livestock consisting of Arduino nano, GPS Neo Module, LoRa S-1278, DS3231 clock module, and MCU node. Tracking is visible through the application by displaying the map and livestock’s GPS position. In addition, the system is notified if the livestock’s position is located more than in the permitted radius of the farm. The system was examined and analyzed using the Haversine method with various scenarios to find the maximum range transmission and perform system toughness. The results stated that the system could track the livestock’s position up to 11 Km and the location error calculation obtained by Haversine is only 11.7% of the actual location.Indonesia memiliki potensi ternak yang besar. Sistem penggembalaan semi intensif merupakan salah satu upaya untuk meningkatkan produksi ternak sapi perah atau sapi potong yang sehat dan unggul. Sistem penggembalaan ini memiliki banyak keuntungan. Namun, ada beberapa kelemahan yang dapat merugikan petani, antara lain ternak hilang atau dicuri karena kurangnya kontrol dan pengawasan. Oleh karena itu, pelacakan posisi ternak dalam pemantauan padang rumput berbasis WSN akan diterapkan untuk mengatasi kelemahan tersebut. Dengan demikian akan memberikan manfaat sebagai penunjang sistem peternakan yang modern dan terkendali. WSN yang dibangun terdiri dari beberapa node yang dipasang pada ternak yang terdiri dari Arduino nano, Modul GPS Neo, LoRa S-1278, modul clock DS3231, dan node MCU. Pelacakan dapat dilihat melalui aplikasi dengan menampilkan peta dan posisi GPS ternak. Selain itu, sistem akan diberi tahu jika posisi ternak berada lebih dari radius peternakan yang diizinkan. Sistem diperiksa dan dianalisa menggunakan metode Haversine dengan berbagai skenario untuk mencari jangkauan maksimum transmisi dan melakukan ketangguhan sistem. Hasilnya menyatakan bahwa sistem dapat melacak posisi ternak hingga 11 Km dan perhitungan kesalahan lokasi yang diperoleh Haversine hanya 11,7% dari lokasi sebenarnya
Static and dynamic human activity recognition with VGG-16 pre-trained CNN model
No full textHuman Activity Recognition has been widely studied using the Convolutional Neural Network (CNN) algorithm to classify a person's movements by utilizing data from devices that record movements such as cameras. The benefits generated by this technology are useful for modern devices such as Virtual Reality and Smart Home technology with CCTV cameras. The VGG-16 (Visual Geometric Group with 16 Layers) pre-trained model is one of the models used for transfer learning and has won the Image Net competition. In this study, the authors tested the performance of the VGG-16 model to identify two types of human activity, namely Static and Dynamic. This study uses 1,680 public datasets which are divided into 80% Data Train, 10% Data Validation, and 10% Data Test I. In addition, there are also 100 local datasets as Data Test II. There is no overfitting issue in the training and testing process. The accuracy of the Testing process with public and local images dataset produces a high accuracy of 98.8% and 97% respectively
