Deep learning approach to improve the recognition of hand gesture with multi force variation using electromyography signal from amputees.

Variations in muscular contraction are known to significantly impact the quality of the generated EMG signal and the output decision of a proposed classifier. This is an issue when the classifier is further implemented in prosthetic hand design. Therefore, this study aims to develop a deep learning classifier to improve the classification of hand motion gestures and investigate the effect of force variations on their accuracy on amputees. The contribution of this study showed that the resulting deep learning architecture based on DNN (deep neural network) could recognize the six gestures and robust against different force levels (18 combinations). Additionally, this study recommended several channels that most contribute to the classifier's accuracy. Also, the selected time domain features were used for a classifier to recognize 18 combinations of EMG signal patterns (6 gestures and three forces). The average accuracy of the proposed method (DNN) was also observed at 92.0 ± 6.1 %. Moreover, several other classifiers were used as comparisons, such as support vector machine (SVM), decision tree (DT), K-nearest neighbors, and Linear Discriminant Analysis (LDA). The increase in the mean accuracy of the proposed method compared to other conventional classifiers (SVM, DT, KNN, and LDA), was 17.86 %. Also, the study's implication stated that the proposed method should be applied to developing prosthetic hands for amputees that recognize multi-force gestures.

An Embedded System Using Convolutional Neural Network Model for Online and Real-Time ECG Signal Classification and Prediction.

This paper presents an automatic ECG signal classification system that applied the Deep Learning (DL) model to classify four types of ECG signals. In the first part of our work, we present the model development. Four different classes of ECG signals from the PhysioNet open-source database were selected and used. This preliminary study used a Deep Learning (DL) technique namely Convolutional Neural Network (CNN) to classify and predict the ECG signals from four different classes: normal, sudden death, arrhythmia, and supraventricular arrhythmia. The classification and prediction process includes pulse extraction, image reshaping, training dataset, and testing process. In general, the training accuracy achieved up to 95% after 100 epochs. However, the prediction of each ECG single type shows a differentiation. Among the four classes, the results show that the predictions for sudden death ECG waveforms are the highest, i.e., 80 out of 80 samples are correct (100% accuracy). In contrast, the lowest is the prediction for normal sinus ECG waveforms, i.e., 74 out of 80 samples are correct (92.5% accuracy). This is due to the image features of normal sinus ECG waveforms being almost similar to the image features of supraventricular arrhythmia ECG waveforms. However, the model has been tuned to achieve an optimal prediction. In the second part, we presented the hardware implementation with the predictive model embedded in an NVIDIA Jetson Nanoprocessor for the online and real-time classification of ECG waveforms.

Automated Cobb Angle Measurement for Adolescent Idiopathic Scoliosis Using Convolutional Neural Network.

The Cobb angle measurement of the scoliotic spine is prone to inter- and intra-observer variations in the clinical setting. This paper proposes a deep learning architecture for detecting spine vertebrae from X-ray images to evaluate the Cobb angle automatically. The public AASCE MICCAI 2019 anterior-posterior X-ray image dataset and local images were used to train and test the proposed convolutional neural network architecture. Sixty-eight landmark features of the spine were detected from the input image to obtain seventeen vertebrae on the spine. The vertebrae locations obtained were processed to automatically measure the Cobb angle. The proposed method can measure the Cobb angle with accuracies up to 93.6% and has excellent reliability compared to clinicians' measurement (intraclass correlation coefficient > 0.95). The proposed deep learning architecture may be used as a tool to augment Cobb angle measurement in X-ray images of patients with adolescent idiopathic scoliosis in a real-world clinical setting.

Embedded Machine Learning Using a Multi-Thread Algorithm on a Raspberry Pi Platform to Improve Prosthetic Hand Performance.

High accuracy and a real-time system are priorities in the development of a prosthetic hand. This study aimed to develop and evaluate a real-time embedded time-domain feature extraction and machine learning on a system on chip (SoC) Raspberry platform using a multi-thread algorithm to operate a prosthetic hand device. The contribution of this study is that the implementation of the multi-thread in the pattern recognition improves the accuracy and decreases the computation time in the SoC. In this study, ten healthy volunteers were involved. The EMG signal was collected by using two dry electrodes placed on the wrist flexor and wrist extensor muscles. To reduce the complexity, four time-domain features were applied to extract the EMG signal. Furthermore, these features were used as the input of the machine learning. The machine learning evaluated in this study were k-nearest neighbor (k-NN), Naive Bayes (NB), decision tree (DT), and support vector machine (SVM). In the SoC implementation, the data acquisition, feature extraction, machine learning, and motor control process were implemented using a multi-thread algorithm. After the evaluation, the result showed that the pairing of the MAV feature and machine learning DT resulted in higher accuracy among other combinations (98.41%) with a computation time of ~1 ms. The implementation of the multi-thread algorithm in the pattern recognition system resulted in significant impact on the time processing.

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings.

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method.

Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method.

Heat rate of a combined cycle power plant (CCPP) is a parameter that is typically used to assess how efficient a power plant is. In this paper, the CCPP heat rate was predicted using an artificial neural network (ANN) method to support maintenance people in monitoring the efficiency of the CCPP. The ANN method used fuel gas heat input (P1), CO2 percentage (P2), and power output (P3) as input parameters. Approximately 4322 actual operation data are generated from the digital control system (DCS) in a year. These data were used for ANN training and prediction. Seven parameter variations were developed to find the best parameter variation to predict heat rate. The model with one input parameter predicted heat rate with regression R2 values of 0.925, 0.005, and 0.995 for P1, P2, and P3. Combining two parameters as inputs increased accuracy with regression R2 values of 0.970, 0.994, and 0.984 for P1 + P2, P1 + P3, and P2 + P3, respectively. The ANN model that utilized three parameters as input data had the best prediction heat rate data with a regression R2 value of 0.995.

Mechanical Pressure Characterization of CNT-Graphene Composite Material.

Carbon nanotubes (CNTs) and graphene are extensively studied materials in the field of sensing technology and other electronic devices due to their better functional and structural properties. Additionally, more attention is given to utilize these materials as a filler to reinforce the properties of other materials. However, the role of weight percentage of CNTs in the piezoresistive properties of these materials has not been reported yet. In this work, CNT-graphene composite-based piezoresistive pressure samples in the form of pellets with different weight percentages of CNTs were fabricated and characterized. All the samples exhibit a decrease in the direct current (DC) resistance with the increase in external uniaxial applied pressure from 0 to 74.8 kNm-2. However, under the same external uniaxial applied pressure, the DC resistance exhibit more decrease as the weight percentage of the CNTs increase in the composites.

Data on records of temperature and relative humidity in a building model with green facade systems.

Reducing cooling load is one of the important aspects to increase energy saving in the building. This paper presents the data record of temperatures (surface and space temperatures) and relative humidities in a building model integrated with green facade systems. The research was conducted in a tropical climate country. There were three types of green facade systems that act as the main parameter: 0%; 50%; and 90%. The preliminary studies were conducted at the Architecture Department of Diponegoro University in Semarang (Indonesia) and the data obtained is presented in this paper. The dataset was collected through field data measurement of green facade systems attached on the facade of the building model. The building model was observed during sunny days. The data presented in this article are related to the research article entitled Observation to building thermal characteristic of green façade model based on various leaves covered area [1].

Acacia Holosericea: An Invasive Species for Bio-char, Bio-oil, and Biogas Production.

To evaluate the possibilities for biofuel and bioenergy production Acacia Holosericea, which is an invasive plant available in Brunei Darussalam, was investigated. Proximate analysis of Acacia Holosericea shows that the moisture content, volatile matters, fixed carbon, and ash contents were 9.56%, 65.12%, 21.21%, and 3.91%, respectively. Ultimate analysis shows carbon, hydrogen, and nitrogen as 44.03%, 5.67%, and 0.25%, respectively. The thermogravimetric analysis (TGA) results have shown that maximum weight loss occurred for this biomass at 357 °C for pyrolysis and 287 °C for combustion conditions. Low moisture content (<10%), high hydrogen content, and higher heating value (about 18.13 MJ/kg) makes this species a potential biomass. The production of bio-char, bio-oil, and biogas from Acacia Holosericea was found 34.45%, 32.56%, 33.09% for 500 °C with a heating rate 5 °C/min and 25.81%, 37.61%, 36.58% with a heating rate 10 °C/min, respectively, in this research. From Fourier transform infrared (FTIR) spectroscopy it was shown that a strong C-H, C-O, and C=C bond exists in the bio-char of the sample.

Frequency Domain Analysis of Sensor Data for Event Classification in Real-Time Robot Assisted Deburring.

Process monitoring using indirect methods relies on the usage of sensors. Using sensors to acquire vital process related information also presents itself with the problem of big data management and analysis. Due to uncertainty in the frequency of events occurring, a higher sampling rate is often used in real-time monitoring applications to increase the chances of capturing and understanding all possible events related to the process. Advanced signal processing methods are used to further decipher meaningful information from the acquired data. In this research work, power spectrum density (PSD) of sensor data acquired at sampling rates between 40-51.2 kHz was calculated and the corelation between PSD and completed number of cycles/passes is presented. Here, the progress in number of cycles/passes is the event this research work intends to classify and the algorithm used to compute PSD is Welch's estimate method. A comparison between Welch's estimate method and statistical methods is also discussed. A clear co-relation was observed using Welch's estimate to classify the number of cycles/passes. The paper also succeeds in classifying vibration signal generated by the spindle from the vibration signal acquired during finishing process.