Gender recognition from unconstrained selfie images: a convolutional neural network approach

<p>Human gender recognition is an essential demographic tool. This is reflected in forensic science, surveillance systems and targeted marketing applications. This research was always driven using standard face images and hand-crafted features. Such way has achieved good results, however, the reliability of the facial images had a great effect on the robustness of extracted features, where any small change in the query facial image could change the results. Nevertheless, the performance of current techniques in unconstrained environments is still inefficient, especially when contrasted against recent breakthroughs in different computer vision research. This paper introduces a novel technique for human gender recognition from non-standard selfie images using deep learning approaches. Selfie photos are uncontrolled partial or full-frontal body images that are usually taken by people themselves in real-life environment. As far as we know this is the first paper of its kind to identify gender from selfie photos, using deep learning approach. The experimental results on the selfie dataset emphasizes the proposed technique effectiveness in recognizing gender from such images with 89% accuracy. The performance is further consolidated by testing on numerous benchmark datasets that are widely used in the field, namely: Adience, LFW, FERET, NIVE, Caltech WebFaces and<br />CAS-PEAL-R1.</p>

Statistical and Artificial Neural Networks Models for Electricity Consumption Forecasting in the Brazilian Industrial Sector

Forecasting the industry’s electricity consumption is essential for energy planning in a given country or region. Thus, this study aims to apply time-series forecasting models (statistical approach and artificial neural network approach) to the industrial electricity consumption in the Brazilian system. For the statistical approach, the Holt–Winters, SARIMA, Dynamic Linear Model, and TBATS (Trigonometric Box–Cox transform, ARMA errors, Trend, and Seasonal components) models were considered. For the approach of artificial neural networks, the NNAR (neural network autoregression) and MLP (multilayer perceptron) models were considered. The results indicate that the MLP model was the one that obtained the best forecasting performance for the electricity consumption of the Brazilian industry under analysis.

An Industrial IoT-Based Blockchain-Enabled Secure Searchable Encryption Approach for Healthcare Systems Using Neural Network

The IoT refers to the interconnection of things to the physical network that is embedded with software, sensors, and other devices to exchange information from one device to the other. The interconnection of devices means there is the possibility of challenges such as security, trustworthiness, reliability, confidentiality, and so on. To address these issues, we have proposed a novel group theory (GT)-based binary spring search (BSS) algorithm which consists of a hybrid deep neural network approach. The proposed approach effectively detects the intrusion within the IoT network. Initially, the privacy-preserving technology was implemented using a blockchain-based methodology. Security of patient health records (PHR) is the most critical aspect of cryptography over the Internet due to its value and importance, preferably in the Internet of Medical Things (IoMT). Search keywords access mechanism is one of the typical approaches used to access PHR from a database, but it is susceptible to various security vulnerabilities. Although blockchain-enabled healthcare systems provide security, it may lead to some loopholes in the existing state of the art. In literature, blockchain-enabled frameworks have been presented to resolve those issues. However, these methods have primarily focused on data storage and blockchain is used as a database. In this paper, blockchain as a distributed database is proposed with a homomorphic encryption technique to ensure a secure search and keywords-based access to the database. Additionally, the proposed approach provides a secure key revocation mechanism and updates various policies accordingly. As a result, a secure patient healthcare data access scheme is devised, which integrates blockchain and trust chain to fulfill the efficiency and security issues in the current schemes for sharing both types of digital healthcare data. Hence, our proposed approach provides more security, efficiency, and transparency with cost-effectiveness. We performed our simulations based on the blockchain-based tool Hyperledger Fabric and OrigionLab for analysis and evaluation. We compared our proposed results with the benchmark models, respectively. Our comparative analysis justifies that our proposed framework provides better security and searchable mechanism for the healthcare system.

Neural Network Algorithm for Stabilizing Mechanized Systems

The article describes an experimental model of stabilization of a mechanized system. The following are shown: a skate; an element of the program code; an algorithm for stabilizing a proportional-integral-differential controller (PID). The experimental model uses the calculation and adjustment of the regulator according to the Ziegler-Nichols method. For the case of applying the neural network approach to the search for equilibrium, the Hopfield neural network is used. The technology of calculating the balancing of the values of the coefficients: proportional, integral, differential components are described. The design of the rolling system is described. The experimental model is designed to identify the balancing range of the rolling system of small-diameter balls. The experimental module balances the ball at a distance of 4.5 to 7 cm (SW-range). The shortcomings of the experimental model of stabilization of the mechanized system are revealed. The analysis of experimental studies of spacecraft stabilization is carried out. It is determined that it is advisable to use the mathematical tools of the sixth-order Butterworth polynomial in the training of a neural network. Complex neural network calculations make it possible to calculate the stabilization coefficients of the spacecraft when the coordinate system does not coincide with the axes of inertia. An overview of the authors ' research on the use of intelligent quality control systems for the production of medicines is given. An overview of neural network solutions for stabilizing the turning angle of high-speed cars is given. The expediency of selecting the stabilization coefficients of a proportional-integral-differential regulator by a trained neural network for various rolling ranges is proved.