Claim Missing Document
Check
Articles

Analisis Pergerakan Futsal Menggunakan Gyroscope Dan Accelerometer Dengan Metode Decision Tree Idzar Andalan Tunjang Serawai; Aji Gautama Putra; Maman Abdurohman
eProceedings of Engineering Vol 6, No 2 (2019): Agustus 2019
Publisher : eProceedings of Engineering

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

Abstract

AbstrakDewasa ini sepak bola menjadi olahraga primadona yang sedang disukai banyak orang baik tua maupun muda.Karena itu semakin banyaknya penggemar sepak bola, maka semakin bertambah juga orang yang inginbelajar mengenai sepak bola. Namun kurangnya informasi untuk mempelajari sepak bola menjadi masalahorang yang ingin mempelajari sepak bola. Penulis bertujuan ingin membuat suatu prototype yang dapatmembantu orang untuk belajar sepak bola tanpa harus mengikuti sekolah sepak bola ataupun mencari pelatihuntuk belajar sepak bola. Prototipe ini berupa alat yang menggunakan raspberry pi dan dipasangkan sensorgyroscope dan juga accelerometer yang di pasangkan di kaki dominan pengguna untuk membaca pergerakanpengguna. Hasil dari pengujian prototipe yang dibuat adalah mendapatkan akurasi sebesar 70%.Kata kunci : Sepak bola, Skil Sepak Bola, Analisis, Gyroscope, Accelerometer, Decision treeAbstractNowadays football become a famous sport which is loved by many old and young people. Because many peopleloved football it make some people want to learn about playing football. But the information of learn aboutfootball is tough. The writer aim to make a prototype to help people to learn about football easier without cometo football class and without coach of football. This prototype used a raspberry pi with the gyroscope andaccelerometer sensor that use on the dominant leg user to playing football to get the data of user movement.The result of testing for paper show that the accuracy of this prototype is around 70%.Keywords: : Football, Football skill, Analize, Gyroscope, Accelerometer, Decision tree
Simulasi Perbandingan Performa Multipath Tcp Dan Tcp Pada Jaringan Wired Krisna Kristiandi Hartono; Aji Gautama Putrada; Maman Abdurohman
eProceedings of Engineering Vol 6, No 2 (2019): Agustus 2019
Publisher : eProceedings of Engineering

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

Abstract

Abstrak TCP yang berjalan pada layer transport yang umumnya di gunakan untuk pengiriman paket data,akan tetapi TCP dalam kondisi Congestion yang membebani TCP, Throughput yang di hasilkan tidakoptimal. TCP hanya menerapkan satu jalur saat terjadi koneksi, sehingga sangat rentan saat terjadiCongestion yang menyebabkan Packet Loss , maka komunikasi transfer data akan berakhir. Untukmenanggulangi kondisi tersebut, diperlukan Multipath TCP dari pengembangan TCP. Multipath TCPdapat mengatasi hal tersebut dengan menggunakan metode redundant yaitu menggunakan antarmukaaktif dengan pengiriman secara sekaligus secara bersamaan, untuk jaringan Wired secara sekaligus yangharus di simulasikan terlebih dahulu sebelum di implementasikan. Uji coba menggunakan data hasilaktivitas (Througput dan Packet Loss). Dalam hasil simulasi NS-2 dan animasi Matlab dari data tersebutmenerapkan metode redundant untuk transfer data secara bersamaan. Hasil uji coba jaringan Wiredsimulasi NS 2 dan animasi Matlab di dapat bahwa penggunaan Multipath TCP meningkatkan akurasilebih besar dari TCP berdasarkan hasil percobaan beberapa Delay RTT, didapatkan hasil optimum padaDelay RTT 25 ms yaitu Throughput pada Multipath TCP sebesar 132.676 Kbps dan TCP 40.01 Kbps padatransfer data. Sedangkan pada Packet Loss pada Multipat TCP terendah pada Delay RTT 15 Ms yaitu5.60% dan tertinggi pada Delay RTT 15 Ms pada jaringan TCP yaitu 54%.Kata kunci : Multipath TCP, TCP, Wired, Throughput, Delay RTT, Packet Loss, NS 2, Matlab.Abstract TCP is running at the transport layer which is generally used for sending data packets, but TCP inCongestion conditions that burden TCP, throughput generated is not optimal. TCP only applies one pathwhen there is a connection, so it is very vulnerable when Congestion occurs which causes Packet Loss, thedata transfer communication will end. To overcome this condition, Multipath TCP is needed from thedevelopment of TCP. Multipath TCP can overcome this by using a redundant method that is using anactive interface with sending simultaneously at the same time, for the Wired network at the same timewhich must be simulated first before being implemented. The trial uses activity result data (Througputand Packet Loss). In the NS-2 simulation results and Matlab animation of the data apply the redundantmethod for simultaneous data transfer. Network test results NS 2 cable simulation and Matlab animationcan be used using Multipath TCP to increase verification greater than TCP based on the results of severalRTT Delay trials, obtained optimal results on the 25 ms RTT Delay according to the Multipath TCPthroughput of 132,676 Kbps and TCP 40.01 Kbps on data transfer. While the lowest packet loss on TCPMultipat Delay 15 RT RT Ms is 5.60% and the highest on the 15 Ms RTT Delay on the TCP network is54%.Keywords: Multipath TCP, TCP, Wired, Throughput, Delay RTT, Packet Loss, NS 2, Matlab.
Analisis Perbandingan Performansi Mqtt Dan Http Pada Platform Iot Node-red Elza Fitria Dwi Permatasari; Aji Gautama Putra; Maman Abdurohman
eProceedings of Engineering Vol 6, No 2 (2019): Agustus 2019
Publisher : eProceedings of Engineering

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

Abstract

AbstrakAplikasi web saat ini berkembang pesat mulai dari front-end hingga back-end, dan teknologi Web ini mendukung perkembangan teknologi komputasi terdistribusi dimana teknologi ini memungkinkanmelakukan proses di banyak mesin, dan hasilnya dimanfaatkan oleh banyak mesin. Salah satu dukungan teknologi Web pada komputasi terdistribusi adalah pada pembangunan Web Service yang berfungsisebagai aplikasi transaksi data antar mesin yang terlibat di dalamnya. Konsep Web Service muncul untuk menjembatani sistem-sistem informasi yang digunakan oleh masing-masing sumber. Pada prinsipdasarnya, suatu komunikasi data merupakan proses mengirimkan data dari satu komputer ke komputeryang lain untuk terselenggaranya proses pengiriman paket data tersebut. Arsitektur yang digunakanpada tugas akhir ini adalah arsitektur publish/subscribe dan request/reply. Dalam tugas akhir ini telah diimplementasikan sistem monitoring suhu dan kelembaban udara yang berbasis MQTT dan HTTP yangterkoneksi dengan NodeMCU, dan sensor suhu DHT22 yang berfokus pada perbandingan performansi kedua protokol yang digunakan. Hasil dari analisis pada tugas akhir ini, yaitu rangakain alat NodeMCUdan Sensor DHT22 bekerja dengan baik dan mendapatkan data suhu ruangan. Parameter performansi throughput terbesar didapatkan pada protokol MQTT dengan nilai 110000 bits/s. Parameter performansidelay dan packet loss terkecil didapatkan pada protokol MQTT dengan nilai 0,00042 % packet loss dan 0,0086902 untuk delay. Kinerja sistem monitoring udara lebih baik menggunakan protokol MQTTdibandingkan dengan HTTP dilihat dari nilai performansi seperti throughput, delay, dan packet loss.Kata kunci: MQTT, HTTP, NodeMCU, DHT22, Web ServiceAbstract Web applications are currently developing rapidly from the front-end to the back-end, and this Webtechnology supports the development of distributed computing technology where this technology allows processes in many machines, and the results are used by many machines. One of the support of Webtechnology in distributed computing is the development of a Web Service that functions as a datatransaction application between machines involved in it. The concept of Web Service appears to bridge the information systems used by each source. Basically, a data communication is a process of sending datafrom one computer to another for the delivery of the data packet. The architecture used in this thesis isthe publish / subscribe and request / reply architecture. In this final project a MQTT and HTTP based temperature and humidity monitoring system has been implemented that is connected to NodeMCU, anda DHT22 temperature sensor that focuses on comparing the performance of the two protocols used. Theresults of the analysis in this thesis, namely the range of NodeMCU tools and DHT22 sensors work well and get room temperature data. The biggest throughput performance parameter is found in the MQTTprotocol with a value of 110000 bits / s. The smallest delay and packet l oss performance parameters areobtained in the MQTT protocol with a value of 0,00042% packet loss and 0.0086902 for delay. The performance of air monitoring systems is better using the MQTT protocol compared to HTTP in terms ofperformance values such as throughput, delay, and packet loss. Keywords: MQTT, HTTP, NodeMCU, DHT22, Web Service
Pengujian Smart Doorbell Menggunakan Kamera Dan Metode Haar-casscade Algi Fajardi; Aji Gautama Putrada; Maman Abdurohman
eProceedings of Engineering Vol 6, No 2 (2019): Agustus 2019
Publisher : eProceedings of Engineering

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

Abstract

AbstrakPada umumnya kedatangan seorang tamu, pemilik rumah mengetahui dari suara bel listrik konvensionalyang ditekan oleh tamu namun ketika pemilik rumah sedang tidak berada didalam rumah, pemilikrumah tidak mengetahui keberadaan tamu yang datang. Berdasarkan permasalahan tersebut, SmartDoorbell berbasis Internet of Things (IoT) dirancang untuk mengetahui datangnya tamu melalui deteksiOpenCV dengan metode Haar-cascade yang memberikan notifikasi pada smartphone melalui email dannotifikasi suara modul buzzer didalam rumah. Dengan adanya Smart Doorbell berbasis IoT pemilikrumah dapat mengetahui informasi kedatangan tamu walaupun pemilik rumah tidak berada di rumah.Hasil dari penelitian ini menunjukan bahwa klasifikasi menggunakan upperbody recognition lebih baikdibandingkan dengan face recognition dengan nilai rata-rata selisih waktu terdeteksi 6,05 detik pada delay30 detik dan 6,31 detik pada delay 60 detik dan akurasi sebesar 95%.Kata kunci : Smart Doorbell, Internet of Things, smartphone, OpenCV, Haar-cascadeAbstractIn general, when a guest arrives, homeowners know from the sound of a conventional electric bell pressedby guests, but when the homeowner is not in the house, the homeowner does not know the whereabouts ofguests who come. Based on these problems, the Internet-based Smart Doorbell of IoT (IoT) is designed todetermine the arrival of guests through OpenCV detection with the Haar-cascade method and notifyingsmartphones on e-mail and sound notification by buzzer module inside the house. With the IoT-basedSmart Doorbell, homeowners can find out guest arrival information even though the homeowner is not athome. The results of this study indicate that classification using upperbody recognition is better than facerecognition with an average value of the detected time difference of 6.05 seconds at a delay of 30 secondsand 6.31 seconds at a delay of 60 seconds and 95% accuracy.Keywords: Smart Doorbell, Internet of Things, smartphone, OpenCV, Haar-cascade
Failover for Multiple-Controller with Failure Detection Method in Software Defined Network on Distributed Switch Decision Ryan Lingga Wicaksono; Maman Abdurohman; Hilal Hudan Nuha
eProceedings of Engineering Vol 10, No 3 (2023): Juni 2023
Publisher : eProceedings of Engineering

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

Abstract

Abstract-Hardware is important for the system to be used, with the increase in a lot of hardware such as switches and connected hosts can cause a decrease in quality on the network. Systems that have more than one core device can use two scenarios namely, load balancing and failover. Software Defined network allows the separation of the control plane and the data plane in the network. Based on it, it provides scalability and centralized control. In addition, by using these properties, clustering controllers consisting of 3 controllers are also applied. The clustering controller system uses ONOS with the aim of stabilizing and improving network performance. Communication between the data plane and the control plane is necessary to detect, calculate, and insert rules that create new paths. The system used to be able to achieve connectivity is scattered everywhere. System by utilizing a centralized controller, one can anticipate one point of failure. Service interruptions due to the failure of the communication network link that occurs are unavoidable circumstances. This study proposes a failover mechanism on the controller. Moving from a failed master controller to a slave controller results in a delay time from the average of each switch connected in the failed master controller. The average delay time in each different traffic background results in a different value from each traffic background. In the background traffic of 500mb/s has an average delay time of 0.159ms, the background traffic of 750mb/s has an average delay time of 0.194ms, and background traffic of 900mb/s has an average delay time of 0.309ms. The delay time value occurs in 1 master controller failure. Different results occurred in 2 controller failures, when using a background traffic of 500mb/s, the average delay time value was 0.203ms, the background traffic was 750mb/s the average delay time was 0.265ms and the background traffic was 900mb/s, the average delay time was 0.346ms. The failure handling mechanism on the master controller is intended to overcome delay time when the backup controller takes over the tasks of the new master controller. Keywords-software defined network; failover; controller; delay time
TICKER SYMBOL IDENTIFICATION WITH CIMA ON NON-STATIONARY STOCK PRICE DATASET Aji Gautama Putrada; Maman Abdurohman; Doan Perdana; Hilal Hudan Nuha
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 1 (2024): JITK Issue August 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i1.5349

Abstract

Ticker symbol identification based on stock price data in investor decisions has been proven to be pivotal. Though research exists on stock price forecasting, ticker symbol identification is still a research opportunity. Meanwhile, some temporal-sequential classification methods are available, such as classification-integrated moving average (CIMA) and recurrent neural network (RNN)-based deep learning such as long short-term memory (LSTM), and gated recurrent unit (GRU). Our research aim is to prove that CIMA can perform ticker symbol identification on non-stationary stock price datasets. This research collects ten most well-known stock price dataset from Kaggle and performs pre-processing. Then it designs CIMA with non-stationary data and the benchmark deep learning methods. Both methods are optimized with hyperparameter tuning and model selection between adaptive boosting (AdaBoost) and legacy k-nearest neighbors (KNN). The test results show five non-stationary features in the stock price dataset must go through a differentiation process. Then, AdaBoost has an accuracy of 0.9967 ± 0.001, while KNN has an accuracy of 0.9971 ± 0.001, with no significant difference based on t-test. Meanwhile, AdaBoost has a significantly smaller model size and testing and prediction time than KNN. In benchmarking, CIMA+AdaBoost is superior to the three other methods for accuracy, precision, recall, and f1-score, all of which have a value of 0.996. Our research contribution is ticker symbol identification based on stock price using CIMA on multiple-class sequential classification with non-stationary data. For future research, we advice to perform this method on other stock price data.
Badan Usaha Milik Desa (BUMDes) Berbasis Teknologi Informasi dan Komunikasi (TIK) – Menuju Ekosistem Smart Village Maman Abdurohman
Bandung Conference Series: Economics Studies Vol. 4 No. 2 (2024): Special Issue: Perguruan Tinggi Mandiri Gotong Royong Membangun Desa (PTMGRMD)
Publisher : UNISBA Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/bcses.v4i2.12570

Abstract

Abstract. This article discusses the conceptual development of BUMDes based on information and communication technology, to support the smart village ecosystem. The research location is Cinanjung Village, Tanjungsari District, Sumedang Regency, West Java Province. Cinanjung Village currently has a Badan Usaha Milik Desa (BUMDes), namely BUMDes Mandiri Cinanjung. BUMDes Mandiri Cinanjung has a diverse business focus in supporting local economic development and also utilizing digital technology. With various limitations, BUMDes Mandiri Cinanjung has been running for several years with the main basis of developing the potential of the village community. There are various potentials that can be developed with BUMDes Mandiri Cinanjung, including strengthening the digital economy with its flagship Payment Point Online Bank (PPOB), stock-taking management, bookkeeping, and human resource capabilities in digital technology. ICT-based BUMDes is one of the strategic steps in developing the potential of village communities by developing a digital technology-based village economy. This is the first step towards a smart village ecosystem that can improve the welfare of rural communities. Abstrak. Artikel ini membahas mengenai konseptual pengembangan BUMDes berbasis teknologi informasi dan komunikasi, guna mendukung ekosistem smart village. Lokasi penelitian di Desa Cinanjung, Kecamatan Tanjungsari, Kabupaten Sumedang, Provinsi Jawa Barat. Saat ini Desa Cinanjung telah memiliki Badan Usaha Milik Desa (BUMDes) yaitu Bumdes Mandiri Cinanjung. BUMDes Mandiri Cinanjung memiliki fokus usaha yang beragam dalam mendukung pengembangan ekonomi lokal dan juga memanfaatkan teknologi digital. Dengan berbagai keterbatasan, BUMDes Mandiri Cinanjung telah berjalan dalam beberapa tahun dengan basis utama pengembangan potensi masyarakat desa. Terdapat berbagai potensi yang dapat dikembangkan dengan adanya BUMDes Mandiri Cinanjung, diantaranya adalah penguatan ekonomi digital dengan unggulannya mengenai Payment Point Online Bank (PPOB), pengelolaan stock opname, pembukuan, dan kemampuan sumber daya manusia dalam teknologi digital. BUMDes berbasis TIK merupakan salah satu langkah strategis dalam pengembangan potensi masyarakat desa dengan mengembangkan perekonomian desa berbasis teknologi digital. Hal ini merupakan langkah awal menuju ekosistem smart village yang dapat meningkatkan kesejahteraan masyarakat desa.
HUMAN ACTIVITY RECOGNITION IMPROVEMENT ON SMARTPHONE ACCELEROMETERS USING CIMA Putrada, Aji Gautama; Abdurohman, Maman; Perdana, Doan; Nuha, Hilal Hudan
TEKTRIKA Vol 8 No 2 (2023): TEKTRIKA Vol.8 No.2 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i2.6973

Abstract

Human activity recognition (HAR) is a research field that focuses on detecting user activities and has wide applications. However, the problems that need to be solved are real-time constraints and imbalanced datasets due to different activity frequencies. Our research aims to apply classification integrated moving averages (CIMA) to HAR by evaluating its performance regarding real-time constraints and imbalanced datasets. We achieved the smartphone accelerometer dataset from Kaggle, which consists of several activities: walking, jogging, climbing, and descending stairs. We develop a general CIMA windowing algorithm with hyperparameters J and W. We benchmark CIMA with two state-of-the-art HAR methods: distributed online activity recognition system (DOLARS) and convolutional neural network (CNN). We conducted some imbalance and model size analysis. The test results show that, with J = 10 and W = 240, CIMA performs better than DOLARS and CIMA with recall, precision, and f1-score of 0.996, 0.993, and 0.994. We also prove that CIMA, assisted by quantization, has the smallest model size compared to the CNN and DOLARS model sizes. Finally, we demonstrate that CIMA performs well for imbalanced datasets, where CIMA’s recall on upstairs and downstairs activities is better than DOLARS and CNN, with values of 1.00 and 0.98, respectively. Key Words: classification integrated moving average, human activity recognition, smartphone, accelerometer, imbalanced dataset
Forecasting Model for Lighting Electricity Load with a Limited Dataset using XGBoost Abdurohman, Maman; Putrada, Aji Gautama
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 8, No. 2, May 2023
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v8i2.1687

Abstract

Energy forecasting is an important application of machine learning in renewable energy because it is used for operational, management, and planning purposes. However, using the electricity load dataset during COVID-19 is a research challenge in the forecasting model due to the limited dataset and non-stationarity. This paper proposes an extreme gradient boosting (XGBoost) forecasting model for a limited dataset. Forecasting models require large amounts of data to create high-accuracy models. We conduct research using the PT Biofarma office electricity usage dataset for eight months during the COVID-19 period. Because office activities were limited during the pandemic, the datasets obtained were few. Several methods are used for modeling limited datasets, namely XGBoost, multi-layer perceptron (MLP), autoregressive integrated moving average (ARIMA), and long short-term memory (LSTM). We have conducted several experiments using a limited dataset with these four methods. The test results with the t-test show that the electricity load data for work-from-office (WFO) and work-from-home (WFH) periods have a significant average difference. Then the test results with the augmented Dickey–Fuller (ADF) test show that our data is non-stationary. Compared to the benchmark method, the XGBoost method shows the best forecasting performance with mean absolute percentage error (MAPE), root mean squared error (RMSE), mean absolute error (MAE), and R2 of 0.48, 5.00, 3.09, and 0.61 respectively.
Performance Comparison of YOLOv8 and DETR in White Blood Cell Detection Rakhmatsyah, Andrian; Abdurohman, Maman; Erfianto, Bayu; Prihatni, Delita
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 4 (2025): August 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i4.6864

Abstract

Automated detection and classification of white blood cells (WBCs) from microscopic images play a vital role in supporting the diagnosis of hematological diseases. Accurate and robust object detection algorithms are essential for handling interclass similarities and imbalanced datasets. This study aims to evaluate and compare the performance of two modern object detection algorithms—Detection Transformer (DeTR) and YOLOv8—in performing multiclass WBC classification using public datasets from various sources with diverse visual characteristics. Five experimental scenarios were designed based on varying class distributions and data augmentation techniques, including horizontal/vertical flipping and random rotation. Both methods were trained and evaluated on the same dataset partitions, and their performances were assessed using the following standard metrics: precision, recall, and F1-score for each WBC class. The results show that YOLOv8 consistently achieved superior and more stable performance across all scenarios, with average F1-scores close to 1.00 even in augmented and imbalanced conditions. In contrast, DeTR performed competitively in balanced scenarios but showed lower consistency, particularly in classes such as Neutrophil and Monocyte. Data augmentation positively affected both models, although the gains were more prominent in YOLOv8. This study highlights the strong potential of YOLOv8 in real-time WBC classification tasks and presents DeTR as a viable yet less-optimized approach for this application. These findings contribute to the advancement of medical image-based object detection and offer valuable insights into the selection of appropriate algorithms for hematological image analysis