The combined Duffing–Holmes (D–H)–based quantizer and one-dimensional (1D) convolutional neural network (CNN)-based multilayer classifier were applied to perform the nontechnical loss (NTL’s) (electricity fraud) feature quantification, feature extraction, and classification tasks to analyze electricity consumption data and to identify either normal or abnormal consumption patterns for NTL detection. The metering data is gathered every 15 minutes and a 3-hour screening window is used to distinguish between the normal conditions and likely NTL events or power outage events. The D–H-based quantizer in the feature quantification layer may quantify the different levels among three events for preliminary screening differences using D–H self-synchronization dynamic errors. In the feature extraction layer, two 1D convolutional-pooling processes are used to extract 1D key feature signals to enhance the distinguished levels for further classification applications. The gray relational analysis (GRA)-based multilayer network is trained as a classifier. In the classification layer, to identify electricity fraud events. The proposed method is verified and validated using simulation data and the electricity fraud attack model. The correlation coefficient and unitary averaged changed intensity index are applied in correlation analysis to discover apparent abnormality between historical consumption and metering consumption patterns within the short-time monitoring. The D-H-based quantizer and 1D CNN-based classifier then work together to accomplish classification tasks on the time-series metering data. The experimental results show that the suggested classifier model demonstrates promising performance and efficiency compared to the traditional multilayer classifier in feature extraction, training, and recall processing, and accurate classification.

A remotely operated underwater vehicle (ROV) is crucial in ocean exploration and underwater missions. An ROV is manipulated through a tether cable by an operator on shore or mother boat, and it can be used for underwater observations or as a robotic arm to take samples back. The position control and movement of an ROV are not stable due to buoyancy, ocean current, and surge waves. To overcome the influence of these disturbances on the ROV, we propose a switch proportional-integral (PI) controller combined with a buck-boost converter (BBC) to process the ROV’s position following. In this paper, a six-axis ROV was designed and implemented. The ROV controller was designed by a NI-roboRIO-based embedded system, which includes a pressure sensor, an accelerometer, six thrusters, and two webcams. The LabVIEW human–machine interface was designed to integrate the control system, sensors, and thrusters. The PI controller was employed to perform the station-keeping and trajectory following. Different PI control parameters were used for the ROV floating-up and diving-down in the sine-wave trajectory following. Experimental results showed that the proposed switch PI control scheme is robust for the position tracking of the underwater robot. The contribution of this study is that we proposed a novel switch proportional-integral controller combined with a buck-boost converter and applied the controller to a natural underwater vehicle, not a mathematical model. The experiments showed that the proposed controller can resist the disturbance of the aquatic environment.

Among imaging examinations, mammography noninvasively aids in the early detection and diagnosis of diseases inside the body for first-line examination and helps physicians to treat medical conditions. As digital medical images can be transmitted by computer or telecommunication network, ensuring image infosecurity in public spaces is difficult. In infosecurity considerations, digital signature and encryption of individual anamnesis plain images should prevent data from being stolen, tampered, or peeked by unauthorized people. Hence, infosecurity has become an important issue in the digital era. This study proposes right/left shift 2 ${n-1}$ pixel values, hash transformation with multi-secret gold keys, and an optimization-based controller to integrate two symmetric cryptography processes for medical image encryption and decryption with the same secret gold keys. Then, swarm optimization-based controllers, which are based on particle swarm optimization and firefly algorithm, are implemented to search the decryption key parameters. For a case study on mammographic images consisting of 50 benign tumors and 50 malignant tumors, the peak signal-to-noise ratio is used to evaluate the relation between the original plain images and decrypted images. Conclusively, the FA-based controller performed better than the PSO-based controller in terms of recovery reliability and speeds up the computation of the desired optimal solution.

Automated meter reading systems (AMRS) are employed to measure and record electricity consumption data in smart grids, facilitating the construction of various consumption models for residential, commercial, and industrial electricity users. These standard electricity-consumption models (SECM), along with their associated consumption patterns, can be further used for applications in load forecasting, technical loss (TL) analysis, and non-technical loss (NTL) detection. Therefore, this study applies the SECM to NTL detection by proposed novel screening model that combines the endpoint detection (EPD) and short-time Fourier transform (STFT) with a one-dimensional (1D) convolutional neural network (1D CNN) based classifier. The EPD method is employed to preliminarily detect discrepancies between metering data and historical records, focusing on the time-domain variations in electricity consumption. Subsequently, the STFT is applied to analyze the frequency contains in the drastically changing time-domain data and then generates the visualization color feature patterns. With theses feature patterns, the 1D-CNN based classifier is used to identify the data into normal (Nor), suspected incidents (SI), fraud incidents (FI), and fault or power outage (OUT) events. In experimental tests, this study simulates the electricity consumption data involving Nor and NTL events by using SECM for training and validating the “STFT + 1D-CNN-based classifier" model. Through ten-fold cross-validation, the feasibility of the proposed method is evaluated, and the experimental results demonstrate the promising performances, achieving average Recall (%) of 99.12%, average Precision (%) of 87.50%, and average Accuracy (%) of 90.48%, and average F1 Score of 0.9333 for NTL (SI and FI) events detection, and also show average Recall (%) of 99.35%, average Precision (%) of 86.36%, and average Accuracy (%) of 88.89%, and average F1 Score of 0.9268 for NTL and OUT events detection, respectively. These findings confirm the effectiveness and robustness of the proposed classifier model.