The assessment of artificial neural network models-sigmoid (ANN-sigmoid) and hyperbolic tangent (ANN-tanh) for real-time air pollution forecasting in a Korean coastal city was performed using 15 input independent variables (3 hours' earlier PM, gas and meteorological data influenced by 48 hours’ earlier PM and gas data of a Chinese city). A feed-forward ANN technique of multilayer perception (MLP) with back-propagation training algorithm for error calculation was adopted with 15 hidden nodes and each prediction formula on four output variables was suggested. Root mean square error (RMSE) and the coefficient of determination (R2 ) assess each model’s prediction ability between the predicted and measured values, before, during, and after the Yellow Dust period (March 18~27). Pearson R coefficients from the ANN-sigmoid (or ANN-tanh) model on PM10, PM2.5, NO2, and O3 were 0.907 (0.935), 0.860 (0.942), 0.860 (0.925), and 0.957 (0.946) before the dust period, 0.917 (0.943), 0.959 (0.969), 0.855 (0.853), and 0.954 (0.949) during its period, and 0.920 (0.947), 0.928 (0.938), 0.917 (0.896), and 0.923 (0.952) after its period, showing very high prediction accuracy overall. Scatter plots with empirical formulae and temporal distributions between the predicted and measured values showed excellent prediction performance by two models, and the ANN-tanh model produced more accurate results.

In this paper, we propose a pipeline algorithm for analysis of human gait in video for orthopedic diagnostic tasks. It is based on 3D human pose estimation that is used to detect human skeletons in 3D space. Images have depth blur in the third dimension, so obtaining accurate 3D pose estimates is more difficult. In this experiment, pre-training masks the data and uses Transformer based on the addition of parallel temporal and spatial feature modules to complete the 2D pose estimation of 3D pose. For such representations, there is a possibility to calculate angles at the articulation of the joint lines of the skeleton, changing such angles during human motion, and define the pathological direction of motion. This analysis calculates the changing of angles between key points of the constructed skeleton during the walking cycle. Angles are defined as dynamical characteristics. Such characteristics are very important for the diagnostics of orthopedic diseases, the definition of the treatment pipeline, and the determination of the type of corrective footwear.

In this study, we present a new Elliptic Curve Cryptosystem using the bi-periodic Fibonacci matrix sequence. We propose a new cryptographic method on elliptic curves over a finite field. We map a plaintext matrix constructed from points corresponding to letters on an elliptic curve. The 2m*2m message matrix M is divided into 2*2 block matrices, Bi, for i=1,...,m^2, and each block is multiplied by the corresponding elements of the bi-periodic Fibonacci matrix sequence. Finally, the resulting matrix is multiplied by a permutation matrix to increase the complexity of the encryption algorithm.

Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and VIseKriteri-jumska Optimizacija I Kompromisno Resenje (VIKOR) are two very popular decision-making strategies to solve Multi-Attribute Decision Making (MADM) problems. Here, we develop TOPSIS and VIKOR strategies in the Quadripartition Neutrosophic Number (QNN) environ-\nment. The attribute weight information is considered to be unknown when developing these\ntwo techniques. To evaluate the value of the attribute weight, we dened a new entropy measure for QNNs and studied their properties thoroughly. The proposed strategies are illustrated\nnumerically with a realistic example of COVID-19 vaccine selection. The performance of the alternatives obtained from the proposed two strategies is also compared. This study will help to make the best choice out of different vaccines available.

The capacitated vehicle routing problem (CVRP) is one of the most studied combinatorial optimization problems in logistics. There are different algorithms with different neighborhood structures for the solution of the problem under consideration. Determining these neighborhood structures in order to reach an effective solution is also a sub-problem of CVRP. Multi criteria decision making methods are widely used for different optimization problems in the literature. In this paper, we develop a performance measurement framework for selecting the neighborhood structure of the capacitated vehicle routing problem using the Analytical Network Process (ANP). 2-opt, swap, and insert operators were chosen to analyze the problem as a multi criteria decision making process to determine the most efficient neighborhood structure for the problem under study. Thirty-three test problems were determined for three different neighborhood structures. All calculation results are given in detail for comparison on different test problems taken from the literature. The results demonstrate that 2-opt is the best alternative for the studied capacitated vehicle routing problem.

The Digital Signal Processing (DSP) in Telecommunications is widely used for its outstanding performance. Hence, the sophisticated design and implementation of the digital Finite Impulse Response ( FIR) filter is , the optimal results would be obtained. In this paper, the design and implementation of the FIR filter for processing of the audio signal is obtained through the field-programmable gate array ( FPGA) platform -Altera DE1 board. The design is divided into three main blocks: Codec initialization block, S2P Adapter block and FIR filter block. Which were then interfaced together after every block is compiled and simulated in order to obtain accurate results. The whole system was built to be functional and finally the frequency response was obtained. High quality and Significant accuracies of 100% are investigated for carrying out the filter by FPGA platform chip board which programmed by Very high speed integrated circuits Hardware Description Language (VHDL).

Students struggle to get good grades in Computer\nProgramming courses. One of the most important ways to\nimprove the pass rate of a difficult subject, such as programming,\nis to implement a learning support system based on Artificial\nIntelligence (AI) technology. This system can provide students\nwith a customised learning experience. This paper proposed\na Revision-Bot (abbreviated as called RevBot), an intelligent\ninteractive system that assists students in practicing past exam\nquestions in a Python programming course. RevBot was created and implemented using the Snatchbot Chatbot API. An evaluation was conducted to determine the usefulness of RevBot,\nand the results show that RevBot can help students improve their performance in the Python programming course. RevBot\nis available on the following link: https://tinyurl.com/revbot2021.

Background: When clinicians moved from paper records to digital documents the expectation was better information management. Unfortunately, Electronic Health Records (EHR) are quite variable in quality and benefits are present in a fifty-fifty chance. It could be said there are three basic elements behind a good EHR: the clinician, the clinical software and the coding nomenclature.\nAim: To conduct a non-systematic review to assess the impact each of these areas has on the quality of EHRs in the literature.\nMethods: A search on nine databases regarding “quality” and “Electronic Health Record” or “Problem-Oriented Medical Record” and one of three basic elements studied: “clinician” or “physician” or “doctor”, “Code” or “coding”, and “software” in their title or abstract was conducted. Around 10% of papers found were considered of interest and analysed.\nResults: 1. Clinicians are not engaged enough; they do not see the EHR as a powerful tool but rather as a digital notepad. For this to change, adequate training is paramount. 2. Software needs to be more user friendly, better organized, with improved interoperability. 3. Coding structure does not allow the flexibility needed in a field where there are so many time-related changes, so many distinct opinions and perspectives. \nConclusions: Changes are needed to facilitate the coding and to improve the usability of the clinical software, to engage clinicians with more advanced possibilities, making the electronic health record much more than a digitalized paper record.

The purpose of this paper is to study on migration and immigration of prey-predator with unlimited resources for the prey. The system comprises of a prey (S1), a predator (S2) that survives upon S1 with migration of prey and immigration of predator. Here, the prey species having unlimited resources quantized by the respective carrying capacity. The model equations of the system constitute a set of two simultaneous first order non-linear ordinary differential equations. The system would be stable if all the characteristic roots are negative, in case they are real, and have negative real parts, in case they are complex. All the three equilibrium points are identified and their stability discussed. Further, the trajectories of solution curves for the equilibrium points are established.

Compensatory multi-attribute decision-making (MADM) methods are founded on the trade-offs between attributes, allowing an alternative to compensate for its weakness in an attribute with its strength in another attribute. We call them heterogeneous MADM methods because they generally consider the unlimited trade-off between attributes. In other words, they even allow that very poor performance of an attribute to be compensated by the strong performance of another attribute. However, this may not be acceptable to decision-makers (DMs). They may accept the limited trade-offs between attributes, making them more homogeneous. In these situations, MADM methods should be modified to consider the limited trade-offs between attributes. This modification comes with some conceptual and technical difficulties. This study presents some examples to show the concept of limited trade-offs clearly. It also presents a modified version of the simple additive weighting (SAW) method considering the limited trade-offs between attributes. We call this the homogeneous SAW (H-SAW) method and use a real example to illustrate its application when ranking the suppliers. The H-SAW method opens a window on modifying the MADM methods to consider the limited trade-offs between attributes.