Dynamic Noise Reduction with Deep Residual Shrinkage Networks for Online Fault Classification

Fault signals in high-voltage (HV) power plant assets are captured using the electromagnetic interference (EMI) technique. The extracted EMI signals are taken under different conditions, introducing varying noise levels to the signals. The aim of this work is to address the varying noise levels found in captured EMI fault signals, using a deep-residual-shrinkage-network (DRSN) that implements shrinkage methods with learned thresholds to carry out de-noising for classification, along with a time-frequency signal decomposition method for feature engineering of raw time-series signals. The approach will be to train and validate several alternative DRSN architectures with previously expertly labeled EMI fault signals, with architectures then being tested on previously unseen data, the signals used will firstly be de-noised and a controlled amount of noise will be added to the signals at various levels. DRSN architectures are assessed based on their testing accuracy in the varying controlled noise levels. Results show DRSN architectures using the newly proposed residual-shrinkage-building-unit-2 (RSBU-2) to outperform the residual-shrinkage-building-unit-1 (RSBU-1) architectures in low signal-to-noise ratios. The findings show that implementing thresholding methods in noise environments provides attractive results and their methods prove to work well with real-world EMI fault signals, proving them to be sufficient for real-world EMI fault classification and condition monitoring.

Classification of Adulterated Particle Images in Coconut Oil Using Deep Learning Approaches

In the production of coconut oil for consumption, cleanliness and safety are the first priorities for meeting the standard in Thailand. The presence of color, sediment, or impurities is an important element that affects consumers’ or buyers’ decision to buy coconut oil. Coconut oil contains impurities that are revealed during the process of compressing the coconut pulp to extract the oil. Therefore, the oil must be filtered by centrifugation and passed through a fine filter. When the oil filtration process is finished, staff inspect the turbidity of coconut oil by examining the color with the naked eye and should detect only the color of the coconut oil. However, this method cannot detect small impurities, suspended particles that take time to settle and become sediment. Studies have shown that the turbidity of coconut oil can be measured by passing light through the oil and applying image processing techniques. This method makes it possible to detect impurities using a microscopic camera that photographs the coconut oil. This study proposes a method for detecting impurities that cause the turbidity in coconut oil using a deep learning approach called a convolutional neural network (CNN) to solve the problem of impurity identification and image analysis. In the experiments, this paper used two coconut oil impurity datasets, PiCO_V1 and PiCO_V2, containing 1000 and 6861 images, respectively. A total of 10 CNN architectures were tested on these two datasets to determine the accuracy of the best architecture. The experimental results indicated that the MobileNetV2 architecture had the best performance, with the highest training accuracy rate, 94.05%, and testing accuracy rate, 80.20%.

Strawberry Maturity Recognition Algorithm Combining Dark Channel Enhancement and YOLOv5

Aiming at the problems of low accuracy of strawberry fruit picking and large rate of mispicking or missed picking, YOLOv5 combined with dark channel enhancement is proposed. In “Fengxiang” strawberry, the criterion of “bad fruit” is added to the conventional three criteria of ripeness, near-ripeness, and immaturity, because some of the bad fruits are close to the color of ripe fruits, but the fruits are small and dry. The training accuracy of the four kinds of strawberries with different ripeness is above 85%, and the testing accuracy is above 90%. Then, to meet the demand of all-day picking and address the problem of low illumination of images collected at night, an enhancement algorithm is proposed to enhance the images, which are recognized. We compare the actual detection results of the five enhancement algorithms, i.e., histogram equalization, Laplace transform, gamma transform, logarithmic variation, and dark channel enhancement processing under the different numbers of fruits, periods, and video tests. The results show that combined with dark channel enhancement, YOLOv5 has the highest recognition rate. Finally, the experimental results demonstrate that YOLOv5 is better than SSD, DSSD, and EfficientDet in terms of recognition accuracy, and the correct rate can reach more than 90%. Meanwhile, the method has good robustness in complex environments such as partial occlusion and multiple fruits.

Effect of Data Augmentation in the Classification and Validation of Tomato Plant Disease with Deep Learning Methods

The paper discusses disease identification and classification in tomato plants, as well as the effect of data augmentation in deep learning models. The database used here is Tomato plant leaves (TPL) images from the PlantVillage Database in the healthy and disease classes. The disease categories have been chosen depending on their occurrence in the Indian States. The proposed ResNet50, ResNet18, and ResNet101 deep-learning model with transfer learning combined with the softmax classification are used to identify and categorize the tomato leaf images into the healthy or diseases classes in the dataset. The unique combination of including the noise and blur in the images and position and color data augmentation makes the dataset robust. Two different data augmentation methods are used for the classification problem, and significant improvement is seen in the classification accuracy with the proposed augmented dataset. The model’s success rate makes the model helpful in extending support in validating a model for identifying plant disease. The validation of models is done on PlantVillage and images taken at Krishi Vigyan Kendra Narayangaon, Pune, India. ResNet101 model trained with augmented dataset outperforms the testing accuracy of 99.99% and validation accuracy of 95.83%.

A Novel Maximum Mean Discrepancy-Based Semi-Supervised Learning Algorithm

To provide more external knowledge for training self-supervised learning (SSL) algorithms, this paper proposes a maximum mean discrepancy-based SSL (MMD-SSL) algorithm, which trains a well-performing classifier by iteratively refining the classifier using highly confident unlabeled samples. The MMD-SSL algorithm performs three main steps. First, a multilayer perceptron (MLP) is trained based on the labeled samples and is then used to assign labels to unlabeled samples. Second, the unlabeled samples are divided into multiple groups with the k-means clustering algorithm. Third, the maximum mean discrepancy (MMD) criterion is used to measure the distribution consistency between k-means-clustered samples and MLP-classified samples. The samples having a consistent distribution are labeled as highly confident samples and used to retrain the MLP. The MMD-SSL algorithm performs an iterative training until all unlabeled samples are consistently labeled. We conducted extensive experiments on 29 benchmark data sets to validate the rationality and effectiveness of the MMD-SSL algorithm. Experimental results show that the generalization capability of the MLP algorithm can gradually improve with the increase of labeled samples and the statistical analysis demonstrates that the MMD-SSL algorithm can provide better testing accuracy and kappa values than 10 other self-training and co-training SSL algorithms.

PENGENALAN HURUF LATIN PADA ANAK USIA DINI DENGAN PENERAPAN METODE BACKPROPAGATION

Early childhood has difficulty remembering Latin letters or Roman characters than adults. Some of the factors that cause it are cognitive development, motivation, interest in learning, emotions and environmental factors. To overcome this, an innovative media is needed so that children can easily remember Latin letters. One of the innovative media applies digital image processing techniques and artificial intelligence. The fonts used are 10 types of letter models with image processing techniques such as preprocessing, binaryization, pixel mapping and creating vector as feature extraction. While the artificial intelligence used is the backpropagation method. The total data is 208 letter images with 625 input features with 500 epochs, the best learning rate used by the system is 0.025 so that the best training accuracy is 93.96% and testing accuracy is 92.31%.

Development of a Longitudinal Diagnosis and Prognosis in Patients with Chronic Kidney Disease: Intelligent Clinical Decision-Making Scheme

Previous studies on CKD patients have mostly been retrospective, cross-sectional studies. Few studies have assessed the longitudinal assessment of patients over an extended period. In consideration of the heterogeneity of CKD progression. It’s critical to develop a longitudinal diagnosis and prognosis for CKD patients. We proposed an auto Machine Learning (ML) scheme in this study. It consists of four main parts: classification pipeline, cross-validation (CV), Taguchi method and improve strategies. This study includes datasets from 50,174 patients, data were collected from 32 chain clinics and three special physical examination centers, between 2015 and 2019. The proposed auto-ML scheme can auto-select the level of each strategy to associate with a classifier which finally shows an acceptable testing accuracy of 86.17%, balanced accuracy of 84.08%, sensitivity of 90.90% and specificity of 77.26%, precision of 88.27%, and F1 score of 89.57%. In addition, the experimental results showed that age, creatinine, high blood pressure, smoking are important risk factors, and has been proven in previous studies. Our auto-ML scheme light on the possibility of evaluation for the effectiveness of one or a combination of those risk factors. This methodology may provide essential information and longitudinal change for personalized treatment in the future.

Analisis dan Penerapan Algoritma Convolutional Neural Network untuk Klasifikasi Kendaraan Prioritas

Jumlah kendaraan bermotor di Indonesia terus menerus meningkat di setiap tahunnya. Hal ini dapat menimbulkan masalah lalu lintas, salah satunya yaitu kemacetan. Dampak yang ditimbulkan dari kemacetan salah satunya yaitu terganggunya arus lalu lintas. Sedangkan menurut UU RI Nomor 22 Tahun 2009 tentang lalu lintas dan angkutan jalan pada pasal 134 terdapat 7 kendaraan yang harus mendapatkan prioritas di jalan raya. Karena itu, dalam penelitian ini dilakukan analisis model klasifikasi untuk jenis kendaraan pemadam kebakaran, ambulans / mobil jenazah, dan kendaraan non-prioritas dengan menerapkan algoritma CNN menggunakan data video dari CCTV yang dikelola oleh ATCS Kota Bandung. Pada penelitian ini terdapat 5 skenario berbeda dimana skenario tersebut dibedakan dengan menggunakan metode holdout dalam pembagian data dan evaluasi model. Hasil penelitian ini menunjukan bahwa skenario terbaik terdapat pada skenario 2 dengan data training sebesar 60%, data validation sebesar 20%, dan data testing sebesar 20% berhasil mendapatkan validation accuracy sebesar 66,15% dan testing accuracy sebesar 69,231%.

The Development of an Intelligent Zinc Oxide Lighting Arrester Tester

Zinc oxide arrester is often used as lightning protection device in 10KV distribution network. In order to check the reliable operation of the zinc oxide arrester, preventive tests are often carried out. In this project, the intelligent tester adopts high-precision clamp current mutual inductance technology as the front-end acquisition mode of current signals; Magnetic isolation technology is used to ensure the accuracy of current and voltage sampling and the anti-interference ability and testing accuracy of the instrument are improved by using fast Fourier transform for data processing. The integrated application of several technologies provides a basis for judging the operating state of the 10kV zinc oxide arrester. The charged measurement of operating parameters of 10kV zinc oxide arrester is realized and the measurement efficiency is improved.