Klasifikasi Chest X-Ray Images Berdasarkan Kriteria Gejala Covid-19 Menggunakan Convolutional Neural Network

Deteksi dini terhadap adanya indikasi pasien dengan gejala COVID-19 perlu dilakukan untuk mengurangi penyebaran virus. Salah satu cara yang dapat dilakukan untuk mendeteksi virus COVID-19 adalah dengan cara mempelajari citra chest x-ray pasien dengan gejala Covid-19. Citra chest x-ray dianggap mampu menggambarkan kondisi paru-paru pasien COVID-19 sebagai alat bantu untuk diagnosa klinis. Penelitian ini mengusulkan pendekatan deep learning berbasis convolutional neural network (CNN) untuk klasifikasi gejala COVID-19 melalui citra chest X-Ray. Evaluasi performa metode yang diusulkan akan menggunakan perhitungan accuracy, precision, recall, f1-score, dan cohens kappa. Penelitian ini menggunakan model CNN dengan 2 lapis layer convolusi dan maxpoling serta fully-connected layer untuk output. Parameter-parameter yang digunakan diantaranya batch_size = 32, epoch = 50, learning_rate = 0.001, dengan optimizer yaitu Adam. Nilai akurasi validasi (val_acc) terbaik diperoleh pada epoch ke-49 dengan nilai 0.9606, nilai loss validasi (val_loss) 0.1471, akurasi training (acc) 0.9405, dan loss training (loss) 0.2558.

Development of virtual instrument model for parameter estimation of fractal antenna array

This paper presents the parameter estimation of the fractal antenna array with the virtual instrument model designed in laboratory virtual instrument engineering workbench software. In this work resonant frequency, gain and voltage standing wave ratio have been used as an output parameter with the change in three input parameters such as radius of a circular patch, height of substrate, and dielectric constant of the material. Measured output parameters have been compared with neural network outputs and error has been represented in a graphical way for each output parameter of the antenna array. Along with output parameter estimation, a designing parameter such as radius of the circular patch has also been estimated with virtual instrument model and absolute error for radius has been shown in the display window of the designed model. The proposed antenna array has been fabricated and simulated results have been validated with measured results.

Prediction of Jacking Force in Vertical Tunneling Projects Based on Neuro-Genetic Models

The vertical tunneling method is an emerging technique to build sewage inlets or outlets in constructed horizontal tunnels. The jacking force used to drive the standpipes upward is an essential factor during the construction process. This study aims to predict the jacking forces during the vertical tunneling construction process through two intelligence systems, namely, artificial neural networks (ANNs) and hybrid genetic algorithm optimized ANNs (GA-ANNs). In this paper, the Beihai hydraulic tunnel constructed by the vertical tunneling method in China is introduced, and the direct shear tests have been conducted. A database composed of 546 datasets with ten inputs and one output was prepared. The effective parameters are classified into three categories, including tunnel geometry factors, the geological factor, and jacking operation factors. These factors are considered as input parameters. The tunnel geometry factors include the jacking distance, the thickness of overlaying soil, and the height of overlaying water; the geological factor refers to the geological conditions; and the jacking operation factors consist of the dead weight of standpipes, effective overburden soil pressure, effective lateral soil pressure, average jacking speed, construction hours, and soil weakening measure. The output parameter, on the other hand, refers to the jacking force. Performance indices, including the coefficient of determination (R2), root mean square error (RMSE), and the absolute value of relative error (RE), are computed to compare the performance of the ANN models and the GA-ANN models. Comparison results show that the GA-ANN models perform better than the ANN model, especially on the RMSE values. Finally, parametric sensitivity analysis between the input parameters and output parameter is conducted, reaching the result that the height of overlaying water, the average jacking speed, and the geological condition are the most effective input parameters on the jacking force in this study.

Ensuring the quality of the surface in the processing of hardened steels, titanium alloys and polymer composite materials

A multifactorial approach to ensuring the required quality of the machined surface of difficult-to-machine and hardened materials is considered, which takes into account a wide combination of controllable parameters of machining. A scheme of multifactorial influence on the output parameter of the cutting process — roughness is proposed.

An Ensemble of Recurrent Neural Networks for Real Time Performance Modelling of Three-Spool Aero-Derivative Gas Turbine Engine

Gas turbine is a complex system operating in non-stationary operation conditions for which traditional model-based modelling approaches have poor generalization capabilities. To address this, an investigation of a novel data driven neural networks based model approach for a three-spool aero-derivative gas turbine engine (ADGTE) for power generation during its loading and unloading conditions is reported in this paper. For this purpose, a non-linear autoregressive network with exogenous inputs (NARX) is used to develop this model in MATLAB environment using operational closed-loop data collected from Siemens (SGT-A65) ADGTE. Inspired by the way biological neural networks process information and by their structure which changes depending on their function, multiple-input single-output (MISO) NARX models with different configurations were used to represent each of the ADGTE output parameters with the same input parameters. First, data preprocessing and estimation of the order of these MISO models were performed. Next, a computer program code was developed to perform a comparative study and to select the best NARX model configuration, which can represent the system dynamics. Usage of a single neural network to represent each of the system output parameters may not be able to provide an accurate prediction for unseen data and as a consequence, provides poor generalization. To overcome this problem, an ensemble of MISO NARX models is used to represent each output parameter. The major challenge of the ensemble generation is to decide how to combine results produced by the ensemble’s components. In this paper, a novel hybrid dynamic weighting method (HDWM) is proposed. The verification of this method was performed by comparing its performance with three of the most popular basic methods for ensemble integration: basic ensemble method (BEM), median rule and dynamic weighting method (DWM). Finally, the generated ensembles of MISO NARX models for each output parameter were evaluated using unseen data (testing data). The simulation results based on datasets consisting for experimental data as well as data provided by Siemens high fidelity thermodynamic transient simulation program show improvement in accuracy and robustness by using the proposed modelling approach.

Investigation of Plasmid DNA Delivery and Cell Viability Dynamics for Optimal Cell Electrotransfection In Vitro

Electroporation is an effective method for delivering plasmid DNA molecules into cells. The efficiency of gene electrotransfer depends on several factors. To achieve high transfection efficiency while maintaining cell viability is a tedious task in electroporation. Here, we present a combined study in which the dynamics of both evaluation types of transfection efficiency and the cell viability were evaluated in dependence of plasmid concentration as well as at the different number of high voltage (HV) electric pulses. The results of this study reveal a quantitative sigmoidal (R2 > 0.95) dependence of the transfection efficiency and cell viability on the distance between the cell membrane and the nearest plasmid. We propose this distance value as a new, more accurate output parameter that could be used in further optimization studies as a predictor and a measure of electrotransfection efficiency.

Tool wear monitoring in drilling of high-strength compacted graphite cast irons

Machining is such a complex system that any foreseen result is practically impossible. However, research always helps to further understand the process, which contributes to providing positive results. Tool wear is always difficult to foresee, but it can be measured and related to several output parameters. In each individual application, there will be the best parameter that most reliably represents the tool wear. In the present investigation, the hole quality parameters (roughness and cylindricity), power consumption, electrical consumption of the machine tool and the acoustic emission signals were recorded and correlated to the tool condition in order to find the best output parameter for tool wear monitoring during the drilling of compact graphite cast irons. Two high-strength grades of compacted graphite cast irons (both CGI 500 with changes in the matrix and graphitic structure) were machined and compared to the standard grade (CGI 450) usually used in the manufacturing of engines using TiAlN-coated carbide drills at a constant cutting condition. The results showed that the best output parameter to monitor the tool wear was the electric current signal.

STABILIZATION OF THE ADAPTIVE FRICTION OUTPUT PARAMETER CONTACT OF SOLIDS WITH INDIRECT CONTROL

It is shown that the introduction of structural-functional scheme of adaptive frictional contact of the second adder and comparator in the form of adaptive frictional contact with a positive feedback, allows you to feed the input of the sensor-Converter signal, the value of which, as well as the value of the output signal of the sensor-transducer is inversely proportional to the coefficient of friction. This allows you to eliminate the additional push node, equivalent to replacing it with the output signal of the sensitive elements.