Garuda - Garba Rujukan Digital

PENGUKURAN SSIM DAN ANALISIS KINERJA METODE INTERPOLASI UNTUK PENINGKATAN KUALITAS CITRA DIGITAL Wulandari, Meirista
Jurnal Muara Sains, Teknologi, Kedokteran dan Ilmu Kesehatan Vol 1, No 1 (2017): Jurnal Muara Sains, Teknologi, Kedokteran dan Ilmu Kesehatan
Publisher : Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/jmstkik.v1i1.429

Terdapat banyak aplikasi pengenalan pola yang membutuhkan input citra dengan ukuran tertentu. Ukuran dari citra mempengaruhi hasil dari pengenalan pola tersebut. Metode interpolasi seringkali digunakan untuk mengatur ukuran citra. Kualitas citra hasil interpolasi tergantung dari metode interpolasi yang diterapkan. Pengukuran kualitas citra hasil interpolasi dapat dilakukan dengan pendekatan kualitas indeks. Salah satu pendekatan indeks kualitas yang sering digunakan adalah SSIM. Selain kualitas citra, metode interpolasi juga berpengaruh terhadap perubahan tekstur citra. Tekstur citra adalah fitur utama yang sering digunakan pada pengolahan citra dan computer vision untuk mengklasifikasikan suatu objek. Salah satu metode untuk melihat karakteristik tekstur citra adalah dengan statistik citra tersebut. Metode statistik mengkarakteristikkan tekstur citra berdasarkan distribusi statistik citra. Penelitian ini membanding 4 metode interpolasi yaitu NNI, Bilinear Interpolation, Bicubic Interpolation dan NNV. Keempat metode interpolasi tersebut dianalisis dengan kuantitatif parameter dari tekstur citra. Parameter yang dimaksud adalah rerata, standar deviasi, skewness, energi, entropi dan kehalusan. Sepuluh buah citra uji digunakan pada penelitian ini. Berdasarkan keenam fitur yang dianalisis, nilai skewness suatu citra sangat terpengaruh proses interpolasi. Perubahan nilai skewness dari citra hasil interpolasi dengan citra asli mencapai 800%, Perubahan energi mencapai 90%, entropi 75%, kehalusan 18%, standar deviasi 10% dan rerata 0,9%. Pengukuran SSIM dengan metode Bicubic Interpolation menghasilkan nilai SSIM yang lebih tinggi dibandingkan dengan metode lainnya.Kata kunci: interpolasi, tekstur, kualitas, citra, SSIM

Perancangan Alat Presensi Berdasarkan Pengenalan Wajah Fawzi, Ahmad; Fat, Joni; Wulandari, Meirista
TESLA: Jurnal Teknik Elektro Vol 25 No 1 (2023): TESLA: Jurnal Teknik Elektro
Publisher : Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/tesla.v25i1.22527

: The attendance system is something that is commonly encountered every day by employees or students. A attendance that is neatly arranged certainly makes it easier when carrying out the data collection process. The attendance that is used to minimize abuse is by using a non-contact attendance. This attendance system utilizes one of the technologies from computer vision. Attendance system designed to apply digital image processing technology. Image processing is a method used to process or process from the original image so as to produce another image that suits your needs. The tool is designed to consist of several modules, namely the image acquisition module, processing module, information display module, and storage module. The image acquisition module used is a Logitech C920 webcam; a processing module is a Raspberry Pi 4B; an information display module is a 7-Inch Capacitive Touch Screen LCD, and a storage module is a 64GB SanDisk microSD. The attendance tool matches the facial image with the data that has been entered into the storage system. The algorithm for the face recognition method uses the Histogram of Oriented Gradients (HOG). Attendance data recording uses CSV format which consists of date, time of entry, time of exit, and subject name. Tests were carried out with several sample cases and tests with five different subjects. Each subject was subjected to a attendance experiment five times with a distance of ± 40 cm. The algorithm can recognize the subject accurately if the subject is facing right in the image acquisition module ABSTRAK: Sistem presensi merupakan hal yang biasa ditemui setiap harinya oleh pegawai ataupun pelajar/mahasiswa. Presensi yang tersusun secara rapi tentunya memudahkan saat dilakukan proses pendataan. Presensi yang digunakan untuk meminimalisir penyalahgunaan yaitu dengan menggunakan presensi non-kontak. Sistem presensi ini memanfaatkan salah satu teknologi dari computer vision. Sistem presensi yang dirancang menerapkan teknologi pengolahan citra digital. Pengolahan citra merupakan metode yang digunakan untuk mengolah ataupun memproses dari gambar asli sehingga menghasilkan gambar lain yang sesuai dengan kebutuhan. Alat yang dirancang terdiri beberapa modul yaitu modul akuisisi citra, modul pemroses, modul penampil informasi, dan modul penyimpanan. Modul akuisisi citra yang digunakan berupa webcam Logitech C920, modul pemroses berupa Raspberry Pi 4B, modul penampil informasi berupa LCD 7 Inch Capacitive Touch Screen, dan modul penyimpanan berupa microSD SanDisk 64 GB. Alat presensi mencocokkan gambar wajah dengan data yang telah dimasukkan ke dalam sistem penyimpanan. Algoritma untuk metode pengenalan wajah menggunakan Histogram of Oriented Gradients (HOG). Pencatatan data presensi menggunakan format CSV yang terdiri dari tanggal, waktu masuk, waktu keluar, dan nama subjek. Pengujian dilakukan dengan beberapa contoh kasus dan pengujian dengan lima subjek berbeda. Masing-masing subjek dilakukan percobaan presensi sebanyak lima kali dengan jarak ± 40 cm . Algoritma dapat mengenali subjek secara akurat jika subjek menghadap ke depan tepat pada modul akusisisi citra

PEMANTAUAN TEMPERATUR PADA INKUBATOR EUBLEPHARIS MACULARIUS (LEOPARD GECKO) BERBASIS ZIGBEE Wulandari, Meirista; Adrianto, Christopher Calvin; Hugeng; Suraidi
TESLA: Jurnal Teknik Elektro Vol 25 No 2 (2023): TESLA: Jurnal Teknik Elektro
Publisher : Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/tesla.v25i2.27371

One type of reptile that is currently developing is the Eublepharis Macularius or better known as the Leopard Gecko. Leopard Gecko is a tame reptile class animal that has a unique pattern on the outer skin of its body. The size of this animal is also not too big but also not too small, around 24 - 27 cm. The breeding of this animal is one of the interesting things to study because the sex of the Leopard Gecko can be influenced through the temperature setting of the egg incubator. Engineering the Leopard Gecko incubator for temperature is one of the interesting implementations of electrical engineering to enliven the Leopard Gecko industry. A simple plastic container can be engineered as a means of monitoring and controlling the temperature of the Leopard Gecko incubator by wireless Xbee. By controlling the temperature of the incubator, the sex of the Leopard Gecko eggs can be monitored. A certain temperature can determine the sex tendency of the Leopard Gecko. A temperature of 26°C can hatch female Leopard Gecko eggs, while a temperature of 32°C can hatch male Leopard Gecko eggs. Some electronic equipment that can be used are such as temperature sensors, microcontrollers, ZigBee, relays, incandescent lamps, and monitors. With this set of electronic equipment, the temperature in the incubator can be monitored and controlled wirelessly. Translated with DeepL.com (free version) ABSTRAK Salah satu hewan jenis reptil yang sedang berkembang saat ini adalah Eublepharis Macularius atau yang lebih dikenal dengan Leopard Gecko. Leopard Gecko merupakan hewan berkelas reptil yang jinak dan mempunyai corak yang unik pada kulit luar tubuhnya. Ukuran hewan ini juga tidak terlalu besar namun juga tidak terlalu kecil, sekitar 24 – 27 cm. Perkembangbiakan hewan ini merupakan salah satu hal yang menarik untuk diteliti karena jenis kelamin dari Leopard Gecko dapat dipengaruhi melalui pengaturan temperatur dari inkubator telurnya. Rekayasa inkubator Leopard Gecko terhadap temperatur merupakan salah satu implementasi bidang teknik elektro yang menarik untuk menyemarakan perindustrian Leopard Gecko. Kontainer plastik sederhana pun dapat direkayasa sebagai alat pemantauan dan pengendalian temperatur inkubator Leopard Gecko secara nirkabel Xbee. Dengan dikendalikannya temperatur pada inkubator, jenis kelamin hasil penetasan telur Leopard Gecko dapat dipantau. Temperatur tertentu dapat menentukan kecenderungan jenis kelamin dari Leopard Gecko tersebut. Temperatur 26oC dapat menetaskan telur Leopard Gecko berjenis kelamin betina, sedangkan pada temperatur 32oC dapat menetaskan telur Leopard Gecko berjenis kelamin jantan. Beberapa peralatan elektronika yang dapat digunakan adalah seperti sensor suhu, mikrokontroler, ZigBee, relay, lampu pijar, dan monitor. Dengan rangkaian peralatan elektronika tersebut, temperatur pada inkubator dapat dipantau dan dikendalikan secara nirkabel pada rentang suhu 32,00oC - 32,50oC. Hal ini dilakukan untuk mengupayakan didapatkannya hasil penetasan telur Leopard Gecko berjenis kelamin jantan.

Microscopic Sand Image Classification Using Convolutional Neural Networks Redja, Christie; Pranoto, Wati Asriningsih; Wulandari, Meirista
Ultima Computing : Jurnal Sistem Komputer Vol 16 No 2 (2024): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v16i2.3907

Abstract— This research paper reviews the use of Convolutional Neural Networks (CNNs) to categorize diverse sand type using microscopic images, with an objective of improving quality control in construction materials. The paper compares three CNN architectures—LeNet-5, Inception v3, and ResNet50—for discriminating between specific sand categories, such as two river sands (Cipongkor and Citarum) and three types of silica sand (brown, cream, and white). Each model was trained and tested on different dataset splits, with images pre-processed to highlight specific microscopic properties. To achieve a thorough comparison, each model's performance was measured using a variety of measures such as F1-score, accuracy, recall, and precision. These measurements enabled a comprehensive evaluation of how accurately and reliably each CNN model categorized the various sand types. ResNet50 consistently delivered the highest accuracy, achieving perfect classification in some instances, showcasing its effectiveness in capturing fine details in sand textures. These results highlight the potential of CNN-based approaches for precise and automated sand classification, which supports increased quality assurance in construction and related areas. Index Terms— Convolutional Neural Network (CNN); sand classification; LeNet-5; Inception v3; ResNet50

Optimizer Comparison In Convolutional Neural Network For Real Time Face Recognition Elbert, Elbert; Wulandari, Meirista; Fat, Joni
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 1 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i1.12058

Face recognition is one of the computer vision technologies that's used in many industries. Face recognition always used in various sector that require the verification of an individual identity. There are many ways that can be used to develop face recognition, one of them is convolutional neural network. Convolutional neural network (CNN) is a deep learning neural network that is created specifically to process and analyze visual data, such as images and videos. CNN have the ability to learn many features from visual data, making them highly effective for tasks like face recognition. There are many factors that can affect CNN performance including the optimizers that are used in the neural network. Optimizers are the algorithm that adjust weights of the neural network to minimize error between the predicted output and actual target. This study used 10 different subjects for face recognition. In this study, the CNN model uses a training algorithm called backpropagation then will compare 3 different types of optimizers. The optimizers that used in this study are Adaptive Momentum (Adam), Root Mean Square Propagation (RMSProp), and Stochastic Gradient Descent (SGD). The results of the comparison will be shown in the form of performance metrics. The performance metrics include correct classification rate (CCR) as well as the confusion matrix of each model. CNN model with SGD optimizers has the highest CCR of 97.07%.

Design of A Braille Printer Based on ESP32 Microcontroller with Voice Input Beatrix, Maria; Wahab, Wahidin; Wulandari, Meirista
Green Intelligent Systems and Applications Volume 5 - Issue 1 - 2025
Publisher : Tecno Scientifica Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53623/gisa.v5i1.592

Braille is a tactile phonetic alphabet system invented by Louis Braille, a blind teacher from France, in the 1800s. The Braille system was recognized as "a vital language of communication, as valid as all other languages in the world" in 2005. There are other alternatives, such as touch-based methods, to convey information that is generally obtained through sight. One of them is the use of Braille letters for reading, writing, and improving welfare by increasing insight. However, only 52 special schools in Indonesia have printers for Braille books. Limited access to Braille printing facilities in Indonesia is due to high costs. The cost of a printer machine, approximately 50 million per school, poses a challenge in providing learning facilities. This research proposes a compact and cost-effective Braille printer using an ESP32 microcontroller with both speech and mechanical switch inputs. The mechanical switch is used for typing text to be printed, while the microphone captures sound input in the form of audio, as it is easier to use. Audio input is processed using speech-to-text technology. The speech-to-text process is carried out with speech recognition, which listens to the words spoken by the user and matches them with the data in the module to execute specific commands. This Braille printer is designed to print Braille letters based on data received directly from individuals with and without disabilities. The printer accepts input in the form of speech or text, which is then sent to the processing module, the ESP32 microcontroller. Once all data is processed, the Braille printer module controls axis movements using a stepper motor. Braille prints are embossed to create raised dots on paper. Experimental results demonstrate 100% accuracy for both speech and typing inputs, along with reliable printing performance on standard HVS paper. Compared to previous solutions, the proposed design is more versatile, affordable, and portable. This study presents a practical solution for increasing access to Braille education and information.

Computer Resource Utilization Analysis for Microsoft Excel and Python in Data Processing Kelvin, Kelvin; Wahab, Wahidin; Wulandari, Meirista
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 6 No. 2 (2024): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v6i2.11736

Data analysis is essential for gaining insights and making informed decisions. A crutial step in data analysis is data processing, which involves preparing and filtering raw data to ensure accuracy, consistency, and structure. While Microsoft Excel is commonly used for data processing, it is susceptible to human errors and has limitations in handling large datasets. Python provides an alternative by automating data processing through scripts executed by the interpreter. The superior software for data processing is obtained by comparing the computer resource utilization based on statistical theory approach, Wilcoxon signed-rank test. This test is appropriate because it does not require the assumption of a normal distribution, providing flexibility in comparing computer resource utilization between Microsoft Excel and Python. Microsoft Excel and Python proceed *.csv and *.xlsx files, then Task Manager recorded the data of computer resource utilization for each processing step. The Wilcoxon signed-rank test analyzes the data and evaluating two hypotheses. H0 (there is no any significant differences in computer resource utilization between Microsoft Excel and Python are calculated for each data processing) and H1 (there is significant differences in computer resource utilization between Microsoft Excel and Python are calculated for each data processing). The sum of ranks in Wilcoxon test are compared to the critical value from the Wilcoxon distribution table to determine the accepted hypothesis. Based on the Wilcoxon test results, hypothesis H1 is accepted, indicating a significant difference in computer resource utilization between Microsoft Excel and Python.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search