Low-Cost Multimodal Physiological Telemonitoring System through Internet of Things

The objective of this study is to develop and test a patient telemonitoring system. This study was encouraged by the high number of health workers fatalities in Indonesia due to physical contact without proper protection. Based on the symptoms of COVID-19 it consists of electrocardiogram (ECG) sensors, body temperature sensors, respiratory rate sensors, and pulse oximeter. The physiological data were captured by the sensors and collected by a microcontroller then it sends the data to a cloud system so that health workers can access the data. The experiments were performed to test both the offline and online protocol to compare data sent via a direct connection and data sent via Wi-Fi. In the offline testing, there were several limitations observed such as the low sampling frequency of the ECG signals that reduce the fidelity of the signals. Such problems were also observed on respiratory rate data. Furthermore, the system is also very prone to subjects’ movement-related noise. The measurements of peripheral oxygen saturation (SpO2) and body temperature, on the other hand, have been detected the slight change up to 0.1% and 0.5oC respectively. In the online testing, the data transmission to the cloud is sent per 30 seconds so that morphologically the ECG signal data are not representative. The system requires a lot of improvements and future study should be directed to improve signals acquisition and processing while maintaining the concept of low-cost. Design improvement should also include a better attachment design to the human body as well as greater data transmission for the online system.

Implementasi Pengolahan Citra Untuk Identifikasi Daun Tanaman Obat Menggunakan Levenberg-Marquardt Backpropagation

Digital Image processing implementation can be applied to identify medicinal leaves, because it can help the elderly and people with color-blindness in identifying medicinal leave to be consumed and in avoiding reading errors, since some leaves have similar shape and color . In this discussion, the feature-extractions are using color and shape features, and using Levenberg-Marquardt for pattern recognition algorithm. The success of this medicinal plant identification system resulted in fairly good accuracy. The backpropagation network architecture used two hidden layers with 10 and 5 neurons. Data training is using 60 training leaf images with 15 images each of 5 types: green betel leaf, red betel, soursop, castor and aloe vera. Then, offline testing is using 20 test images for each of 4 images from 5 types with the accuracy of 85%. Meanwhile the online (realtime) test is using 20 times for each leaf types so the accuracy is 88%.

Model of Process Synchronization in Through Analysis

Synchronization of parallel processes of distributed information systems (DIS) has been largely determined by decisions taken at the stages of their design. Having already been in structural and functional models, when determining cause- and-effect relationships for events and actions in DIS components, it becomes necessary to coordinate them. In the proposed multilevel systemic, structural and functional synchronization model, a hierarchy of such causal relationships with interlevel mappings, inheritance and encapsulation of events and actions have been formed. The model has been also based on hierarchical extended Petri nets, which make it possible to represent various aspects of a special analysis of technical diagnostics, in particular, analysis of correctness, verification, testing, for the adopted display of the asynchronous-behavioral nature of the multilevel interaction of DIS processes. Features of the synchronization model include mapping operations for cross- level inheritance and encapsulations that synchronize events and actions, as well as end-to-end synchronized quasi-order relationships and compatibility for them. The synchronization model is also distinguished by the possibility of specializing its objects, operations and relations for the tasks of check and recognition of behavioral properties set for analysis and verification, basic in technical diagnostics, including in online and offline testing. The synchronization model has allowed one to determine the formal conditions for methods of end-to-end asynchronous coordination of events and actions of multi-level models, that represent design solutions for DIS, in particular, for technical diagnostics methods, and also to reduce the computational complexity of a special synchronization analysis due to an end-to-end decomposition approach. The dimension of the synchronization model has been estimated using the representation of Petri net graphs and special graphs of reachable states using list structures. The above estimates determine the limits of applicability of the formal synchronization model.

Laboratory stand for development of method and system for continuous non-contact non-destructive testing of technical condition of insulation equipment

Measurement of partial discharges (PD) is a generally accepted method of diagnosing the insulation of electrical equipment worldwide. Today, the trend is to move from conventional offline testing to online monitoring to predict the service life of insulation. For testing and calibration of the developed new methods with the contact method, a laboratory stand has been developed in accordance with GOST R 55191-2012 (IEC 60270:2000). The article suggests the use of acoustic and electromagnetic methods for a system of continuous non-contact non-destructive testing of the technical condition of insulation equipment, which will allow monitoring insulation equipment online and predicting its residual life. On their basis, a system of «on-line» diagnostics of high-voltage insulators has been developed.

Lw-CNN-Based Myoelectric Signal Recognition and Real-Time Control of Robotic Arm for Upper-Limb Rehabilitation

Deep-learning models can realize the feature extraction and advanced abstraction of raw myoelectric signals without necessitating manual selection. Raw surface myoelectric signals are processed with a deep model in this study to investigate the feasibility of recognizing upper-limb motion intents and real-time control of auxiliary equipment for upper-limb rehabilitation training. Surface myoelectric signals are collected on six motions of eight subjects’ upper limbs. A light-weight convolutional neural network (Lw-CNN) and support vector machine (SVM) model are designed for myoelectric signal pattern recognition. The offline and online performance of the two models are then compared. The average accuracy is (90 ± 5)% for the Lw-CNN and (82.5 ± 3.5)% for the SVM in offline testing of all subjects, which prevails over (84 ± 6)% for the online Lw-CNN and (79 ± 4)% for SVM. The robotic arm control accuracy is (88.5 ± 5.5)%. Significance analysis shows no significant correlation ( p = 0.056) among real-time control, offline testing, and online testing. The Lw-CNN model performs well in the recognition of upper-limb motion intents and can realize real-time control of a commercial robotic arm.

ACCURACY OF EXPERT FRAUD DETECTION TECHNOLOGY IN REMOTE TEST EXAMS (PROCTORING)

The purpose (objective) of the empirical study is the measurement of the accuracy of expert-proctors in detecting cheating in online testing. Sample of the study. 35 test takers passed an online test of general knowledge on the basis of 30 multiple choice questions. Half of the subjects (18 persons) were “artificial cheaters” — they used cheat sheets with correct answers. Methods. The video recording of the testing process included a “screen capture” so that expert-proctors could observe all cursor movements, see a recording of the subject’s facial expressions and a visual focus of attention in a separate window (recording from the front camera), and could listen to the subject pronouncing the task conditions and answers (“oral decision”). 14 experts took part in rating of video recordings, of which 8 experts showed satisfactory results in terms of the level of accuracy in detecting cheating (their accuracy that was measured using the Kappa coefficient was higher than 0.5). Conclusions. A high asymmetric validity of expert assessments is revealed. More accurate experts allowed a negligible (about 5 percent) number of errors of the “false alarm” type, but a relatively large number of errors of the “skip” type. Recommendations are made for the practical use of the expert assessment method in combination with automatic chronometric analysis of the degree of atypical protocols and subsequent control of face-to-face offline testing of all suspected subjects (examinees).

Introduction of Balinese Script Handwriting Using Zoning and Multilayer Perceptron

Handwriting identification is one out of the many research ever conducted. In its development, the handwriting can be written in real time by the user by using the mouse (online character recognition). Various studies on the traditional character handwriting recognition continue to be developed. One of them is the recognition of the Balinese characters. Balinese characters have their own unique characters compared with the other regions. The difference between the shapes of the characters with the other characters are quite similar, or there are some characters that can only be distinguished by a small sketch or doodle.This study uses Artificial Neural Network with Backpropagation algorithm to perform the Balinese characters recognition and zoning as a method of feature extraction. In a variation of the extraction method, the characteristics used are Image Centroid and Zone (ICZ), Zone Centroid and Zone (ZCZ) and normalization of features. Of the three methods, it will be determined the best method used in the Balinese characters recognition.From the test results of the extraction method, the combined characteristics of the ICZ, ZCZ and normalization of features were the most effective to be used for the recognition of the Balinese characters. The level of accuracy obtained from the results of the online testing was 71,28% and 72,31% for offline testing, with parameters of Backpropagation, which used the value of learning rate of 0,03, a momentum value of 0,5 and the number of neurons in the hidden layer of 130.