A5009517106- Multimedia Learning Systems
- Computer Science and Engineering
- Data Mining and Machine Learning Applications
- Edcuational Technology Systems
- Advanced MRI Techniques and Applications
- COVID-19 diagnosis using AI
- Blockchain Technology in Education and Learning
- Decision Support System Applications
- Digital Imaging for Blood Diseases
- Atomic and Subatomic Physics Research
- Information Retrieval and Data Mining
- Radiomics and Machine Learning in Medical Imaging
- Smart Agriculture and AI
- Vehicle License Plate Recognition
- Sparse and Compressive Sensing Techniques
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Currency Recognition and Detection
- Local Governance and Development
- Educational Games and Gamification
- Gaze Tracking and Assistive Technology
- IoT-based Smart Home Systems
- Plant Water Relations and Carbon Dynamics
- Diverse Scientific Research Studies
- Hand Gesture Recognition Systems
Universitas Ma Chung
2012-2024
Chiba University
2013-2015
The growth in the number of vehicles Indonesia causes traffic jam problems, including on toll roads. Traffic problem roads occurs because users must stop and make payments gate. Government built an Automatic Toll Gate Shelter (or Gardu Tol Otomatis/GTO) as effort to reduce this problem. However, GTO can only be used by certain type only. In study, we developed a system that classify so for various types cross road. will receive vehicle input classified. learning process do classification is...
The use of circulant matrix as the sensing in compressed (CS) scheme has recently been proposed to overcome limitation random or partial Fourier matrices. Aside from reducing computational complexity, for magnetic resonance (MR) image offers feasibility hardware implementations. This paper presents simulation thoracic MR imaging with matrix. comparisons reconstruction three different type images using are investigated term number samples, iteration and signal noise ratio (SNR). results...
Personal medicine is very important for those who have special health problems. Having several types of pills can make it hard people to remember every pill especially aged citizen easily forget his or her own medication. Another problem often encountered the difficulty recognizing drug whose labels packaging are damaged and read. This research, we developed a multi convolutional neural network (CNN) model identify using classification rules. The idea CNN that almost all type three main...
Abstract Malaria can be difficult to detect from thin blood smears. Image recognition methods such as convolutional neural network used malaria, but the training process takes a long time. Previous research created new architecture and compares it several other architectures VGG-16 ResNet. The effect of preprocessing is analyzed in this research. VGG-16, ResNet, custom by previous are being study. include gray-world normalization comprehensive normalization. highest accuracy improvement per...
COVID-19 menjadi salah satu masalah yang besar bagi banyak negara di dunia sejak tahun 2020. dan Pneumonia memiliki kemiripan dalam hal gejala seperti batuk sesak napas. Upaya diagnosis dilakukan dengan pemeriksaan laboratorium juga rontgen dada. Citra hasil x-ray dada pasien kesamaan tetapi ahli radiologi berhasil menemukan bahwa terdapat perbedaan antara citra penderita dimana pola kaca ditumbuk pada X-ray virus Corona.Diagnosis menggunakan model Deep Learning. Pada penelitian ini akan...
Indonesia has a lot of typical food which is rich in flavor. However, compared with countries such as China, Thailand or India, Indonesian not widely known by the international community. One factors that cause less popular information cannot be accessed easily foreign travelers during visit to Indonesia. Food name written on restaurant menu can read, but really showing about food, ingredients, how prepared picture itself. Hence, it required facilitate who want find out based menus. An...
Malaria is an infectious disease caused by peripheral blood parasites of the genus Plasmodium. The estimated global malaria cases reached 229 million in 2019, which 250,644 occurred Indonesia. large number makes early and accurate diagnosis very important because it can reduce severity prevent death. most widely used method far examining a thin smear under microscope looking for infected cells. This research examines effect regularization applied to several Convolutional Neural Network (CNN)...
Malaria is an infectious disease caused by the Plasmodium parasite. In 2019, there were 229 million cases of malaria with a death toll 400.900. increased in 2020 to 241 people reaching 627,000. diagnosis which carried out observing patient’s blood sample requires experts and if it not done correctly, misdiagnosis can occur. Deep Learning be used help diagnose classifying thin smear images. this study, transfer learning techniques on Convolutional Neural Network speed up model training...
Video conference merupakan aplikasi yang memungkinkan pengguna untuk berkomunikasi, melakukan rapat, belajar dan berbagi informasi. Hingga saat ini, sudah banyak video digunakan, seperti Zoom, Google Meet, Microsoft Teams. Tentunya disetiap terdapat ulasan mengenai digunakan. Dengan adanya ulasan, maka lain dapat mempertimbangkan mengetahui lebih jauh terkait Namun karena jumlah di internet sangat banyak, diperlukan analisis sentimen mengklasifikasikan ke dalam positif, netral, atau negatif....
Pada bulan Desember 2019, virus COVID-19 menyebar ke banyak negara, termasuk di Indonesia yang kemudian menjadi pandemi dan menimbulkan masalah serius karena masih belum adanya vaksin untuk mencegah penularan. Uji spesimen saluran nafas atas bawah saat ini merupakan salah satu metode efektif mengetahui apakah seseorang terinfeksi atau tidak. Salah indikasi dari infeksi adalah sesak pneumonia serta munculnya ground-glass opacity pada citra CT. Penelitian studi awal melihat CT organ thorax...
Kekerasan seksual merupakan salah satu masalah serius yang perlu diselesaikan. Setiap tahunnya terdapat lebih dari 2000 aduan kekerasan seksual. Di satuan Pendidikan, sebanyak 55% pelaku guru atau tenaga pendidik. Jumlah ada masih belum merepresentasikan jumlah sebenarnya karena 63% peserta survei DIKTI tidak melaporkan kasus diketahuinya dengan alasan menjaga nama baik kampus. Dengan begitu, Kementerian Kebudayaan, Riset, dan Teknologi (Kemendikbud) menerbitkan Peraturan Menteri...
Two-wheeled motorized vehicles provide a separate role in shortening travel time and can also save costs compared to using public transportation (city transportation). With the availability of vehicle facilities for students, parents do not have bother with their child's business going school, so children go own school. However, presence brought by students school resulted decrease parental supervision children. Therefore, this study aims create monitoring control system website-based motor...
Desa Tegalweru terletak di kecamatan Dau, Kabupaten Malang. Dalam hal pengelolaan data administratif, dibantu oleh beberapa perangkat desa. Salah satu rutin administratif yang berkaitan langsung dengan layanan masyarakat adalah kegiatan surat menyurat. Berdasarkan analisa tahap awal ditemukan potensi masalah, seperti kurang efektifnya proses karena kependudukan menjadi pendukung utama harus diakses secara manual. Permasalahan ini perlu untuk mendapatkan perhatian khusus sehingga dapat...
Dunia periklanan di Indonesia saat ini memiliki perkembangan yang sangat pesat. Hal dibuktikan dengan semakin bertambah banyaknya media diciptakan, salah satunya adalah iklan billboard pada jalan raya. Iklan kelemahan, yaitu materi atau konten dari ditampilkan tidak dapat berubah-ubah, demikian maka target bisa tertuju konsumen tepat. Untuk mengatasi masalah tersebut dibutuhkan pemanfaatan teknologi untuk mendukung keefektifan kinerja billboard. Pada penelitian dibuat sebuah sistem...
Pemantauan atau monitoring adalah salah satu kegiatan untuk memantau setiap gerakan dari waktu ke waktu. memiliki berbagai tujuan termasuk menganalisis, mengumpulkan data mengamati pola pergerakan. juga dapat diartikan, yaitu melakukan pengamatan terhadap situasi di sekitarnya. Dalam penelitian ini, dibuat sebuah sistem ruangan yang mendeteksi objek manusia dengan menggunakan perangkat Raspberry Pi 3 dan akan mengirimkan push notification ketika dalam video. Untuk deteksi berbasis...
Low-resolution images can be reconstructed into high-resolution using the Super-resolution Convolution Neural Network (SRCNN) algorithm. This study aims to improve vehicle license plate number's recognition accuracy by generating a image SRCNN. The is carried out two types of character methods: Tesseract OCR and SPNet. training data for SRCNN uses DIV2K dataset consisting 900 images, while Chars74 dataset. constructed increase average number 16.9 % 13.8 with
Penelitian ini bertujuan untuk membandingkan akurasi pengenalan emosi melalui suara dengan menggunakan beberapa jenis classifier. Emosi dasar yang akan dikenali ada 4, yaitu senang, sedih, neutral dan marah. Metodologi penelitian dimulai memperoleh dataset dari database RAVDESS, terdiri 24 aktor jumlah sebanyak 60 per aktor. Namun, hanya 28 dipilih setiap aktor, sehingga total 672 digunakan dalam ini. Untuk mengekstraksi fitur suara, tiga teknik mel frequency cepstral coefficient (MFCC),...
Tujuan pengabdian ini untuk meningkatkan pengetahuan relawan paliatif tentang terapi primer dan alternatif kanker payudara. Metode pertama pada ini, tim pengabdi Universitas Ma Chung melaksanakan kegiatan homecare bersama dengan dokter RS Baptis Batu. Kegiatan dilaksanakan per hari-nya sekitar 2-3 jumlah pasien payudara sebanyak 4-5 pasien. kedua, hasil disampaikan kembali melalui seminar workshop yang dihadiri 51 relawan. Tes menggunakan kuesioner diberikan saat sebelum setelah acara. Uji...
Background: Diabetes Mellitus is a non-contagious disease characterized by hyperglycemia. mellitus occurs when the body cannot receive or use insulin properly. If you already have diabetes, then patient must take medication continuously because diabetes lifelong disease. Because medicines are quite expensive, alternative ways to cure needed consuming traditional medicines, one of which bitter melon (Momordica charantia). Objectives: This research aims predict secondary metabolite compounds...
<p>Sertifikat merupakan sebuah bentuk penghargaan yang didapat seseorang setelah menyelesaikan suatu uji kompetensi atau pembelajaran tertentu. Sertifikat harus dibuat dan disimpan dengan metode keamanan baik untuk mencegah terjadinya perubahan isi bahkan pemalsuan. Teknologi blockchain teknologi memungkinkan proses penyimpanan aman ongkos rendah. Keamanan terjamin karena semua orang bisa mengambil bagian menyimpan data ledger terdistribusi. Berdasarkan hasil penelitian perancangan...
We have developed a method called intersection profile to construct 4D-MRI (3D+time) from time-series of 2D-MRI. The basic idea is find the best matching time series 2D-MRI in sagittal plane (navigator slice) and coronal (data slice). In this study, we use semiautomatically extract right diaphragm motion 16 subjects (8 healthy 8 COPD patients). then evaluated quantitatively by calculating displacement each normalized it. also generate phase-length map view locate paradoxical patients....
We analyzed a statistical model of diaphragm motion using regular principal component analysis (PCA) and generalized N-dimensional PCA (GND-PCA). First, we generate 4D MRI respiratory from 2D an intersection profile method. then extract semiautomatically the boundary 4D-MRI to get subject-specific motion. In order build general motion, normalize in time spatial domains evaluate 10 healthy subjects by applying GND-PCA. also validate results leave-one-out The show that first three components...