Brain Tumor Classification and Detection Using Hybrid Deep Tumor Network

Electronics, Journal Year: 2022, Volume and Issue: 11(21), P. 3457 - 3457

Published: Oct. 25, 2022

Brain tumor (BTs) is considered one of the deadly, destructive, and belligerent disease, that shortens average life span patients. Patients with misdiagnosed insufficient medical treatment BTs have less chance survival. For analysis, magnetic resonance imaging (MRI) often utilized. However, due to vast data produced by MRI, manual segmentation in a reasonable period time difficult, which limits application standard criteria clinical practice. So, efficient automated techniques are required. The accurate early detection difficult challenging task biomedical imaging. Automated an issue because considerable temporal anatomical variability brain tumors. Early therefore essential. To detect cancers or tumors, different classical machine learning (ML) algorithms been main difficulty these models manually extracted features. This research provides deep hybrid (DeepTumorNetwork) model binary classification overcomes above-mentioned problems. proposed method GoogLeNet architecture CNN eliminating 5 layers adding 14 extracts features automatically. On same Kaggle (Br35H) dataset, key performance indicator was compared transfer (TL) (ResNet, VGG-16, SqeezNet, AlexNet, MobileNet V2) ML/DL. Furthermore, approach outperformed based on (Acc, Recall, Precision, F1-Score) classification. Additionally, methods exhibited high measures, Accuracy (99.51%), Precision (99%), Recall (98.90%), F1-Score (98.50%). approaches show its superiority recent sibling for current using MRI images.

Language: Английский

---

Body-Worn Sensors for Recognizing Physical Sports Activities in Exergaming via Deep Learning Model

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 12460 - 12473

Published: Jan. 1, 2023

Obesity and laziness are some of the common issues in majority youth today. This has led to development a proposed exergaming solution where users can play first-person physical games. research study not only proposes for fitness form game using wearable sensors but also multi-purpose system that provides different applications when trained domain-specific dataset. Critical tasks gesture recognition depiction virtual reality be applied many domains crime detection, fitness, healthcare, online learning, sports. In particular, enables user perform, detect, depict gestures game. First, pre-processes input data by applying median filter overcome anomalies. Then, features extracted through convolutional neural network, power spectral density, skewness, kurtosis methods. Further, optimizes grey wolf optimization. Lastly, feature set which is optimized fed recurrent network classification. When Compared traditional methods, suggested gives better results while being easier use. The IMSporting behaviors (IMSB) dataset includes badminton other activities, WISDM locomotor motions, ERICA variety exercises, were used experimentation. According experimental findings, approach outperformed current showed detection accuracies 85.01%, 88.46%, 93.18% over IMSB, WISDM, datasets, respectively.

Language: Английский

---

Design of a Compact Quad-Channel Microstrip Diplexer for L and S Band Applications

Micromachines, Journal Year: 2023, Volume and Issue: 14(3), P. 553 - 553

Published: Feb. 26, 2023

In this paper, two novel dual-band bandpass filters (BPFs) and a compact quad-channel diplexer working at 1.7/3.3 GHz 1.9/3.6 are proposed. the proposed design, triangular loop resonators rectangular used together to reduce circuit size improve performances. Insertion loss (IL) return (RL) of better than 0.8 dB 21 dB, respectively, these four operating frequencies. Output ports isolation parameter is 30 dB. With achieved specifications, can be in L S band applications.

Language: Английский

---

Application of artificial neural network to multiphase flow metering: A review

Flow Measurement and Instrumentation, Journal Year: 2024, Volume and Issue: 97, P. 102601 - 102601

Published: April 26, 2024

Language: Английский

---

Extraction of Time-Domain Characteristics and Selection of Effective Features Using Correlation Analysis to Increase the Accuracy of Petroleum Fluid Monitoring Systems

Energies, Journal Year: 2022, Volume and Issue: 15(6), P. 1986 - 1986

Published: March 9, 2022

In the current paper, a novel technique is represented to control liquid petrochemical and petroleum products passing through transmitting pipe. A simulation setup, including an X-ray tube, detector, pipe, was conducted by Monte Carlo N Particle-X version (MCNPX) code examine two-by-two mixture of four diverse (ethylene glycol, crude oil, gasoline, gasoil) in various volumetric ratios. As feature extraction system, twelve time characteristics were extracted from received signal, most effective ones selected using correlation analysis present reasonable inputs for neural network training. Three Multilayers perceptron (MLP) networks applied indicate volume ratio three kinds products, fourth product can be feasibly achieved results aforementioned networks. this study, increasing accuracy placed on agenda, RMSE < 1.21 indicates high accuracy. Increasing predicting ratio, which due use appropriate as input, important innovation why proposed system used efficient method oil industry.

Language: Английский

---

The Comprehensive Overview of Large-Volume Surfactant Slugs Injection for Enhancing Oil Recovery: Status and the Outlook

Energies, Journal Year: 2022, Volume and Issue: 15(21), P. 8300 - 8300

Published: Nov. 7, 2022

Despite the development of alternative energy sources, oil and gas still remain predominant sources in most countries world. Due to gradual hydrocarbon reserve depletion existing downward trend production level, there is a need search for methods technical approaches level off falling rates. Chemically enhanced recovery (EOR) by surfactant solution injections are one possible addressing this issue already developed fields. Most often, surfactants injected together with polymers or alkalis. These technologies called surfactant–polymer (SP) alkali–surfactant–polymer (ASP) flooding. Basically, SP ASP have been distributed China Canada. In article, addition these countries, we paid attention results pilot full-scale tests Russia, Hungary, Oman. This study was comprehensive overview laboratory field solutions used displacement technologies. The first part article discussed physical fundamentals interaction surfactants. second presented main chemical reagents increase recovery. third part, described facilities preparation injection Further, abovementioned were considered. discussion based on considered results, issues uncertainties identified, which some recommendations proposed improving process particular, identified an area additional scientifically practical research. outcomes work will provide clearer picture ASP, as well information about their limitations, current challenges, potential paths forward from economic technological point view.

Language: Английский

---

Intelligent Measurement of Void Fractions in Homogeneous Regime of Two Phase Flows Independent of the Liquid Phase Density Changes

Fractal and Fractional, Journal Year: 2023, Volume and Issue: 7(2), P. 179 - 179

Published: Feb. 10, 2023

Determining the amount of void fraction multiphase flows in pipelines oil, chemical and petrochemical industries is one most important challenges. Performance capacitance based two phase flow meters highly depends on fluid properties. Fluctuation liquid properties such as density, due to temperature pressure changes, would cause massive errors determination fraction. A common approach fix this problem periodic recalibration system, which a tedious task. The aim study proposing method artificial intelligence (AI), offers advantage intelligent measuring regardless changes without need for recalibration. To train AI, data set different phases required. Although it possible obtain required from experiments, time-consuming also incorporates its own specific safety laboratory consideration, particularly working with flammable liquids gasoline, oil gasoil. So, COMSOL Multiphysics software was used model homogenous regime two-phase five fractions. validate simulation geometry, initially an experimental setup including concave sensor measure by LCR meter case that water phase, established. After validation simulated geometry sensor, ring investigate best type. It found type has better sensitivity. Therefore, fractions inside pipe. Finally, were Multi-Layer Perceptron (MLP) neural network MATLAB software. trained MLP able predict independent density Mean Absolute Error (MAE) 1.74.

Language: Английский

---

Using ANN and Combined Capacitive Sensors to Predict the Void Fraction for a Two-Phase Homogeneous Fluid Independent of the Liquid Phase Type

Processes, Journal Year: 2023, Volume and Issue: 11(3), P. 940 - 940

Published: March 20, 2023

Measuring the void fraction of different multiphase flows in various fields such as gas, oil, chemical, and petrochemical industries is very important. Various methods exist for this purpose. Among these methods, capacitive sensor has been widely used. The thing that affects performance capacitance sensors fluid properties. For instance, density, pressure, temperature can cause vast errors measurement fraction. A routine calibration, which grueling, one approach to tackling issue. In present investigation, an artificial neural network (ANN) was modeled measure gas percentage a two-phase flow regardless liquid phase type changes, without having recalibrate. goal, new combined capacitance-based designed. This simulated with COMSOL Multiphysics software. Five liquids were simulated: gasoil, gasoline, crude water. To estimate homogeneous distinct liquid, data obtained from used input train multilayer perceptron (MLP). proposed MATLAB Using accurate metering system, MLP model could predict mean absolute error (MAE) 4.919.

Language: Английский

---

Using Particle Swarm Optimization and Artificial Intelligence to Select the Appropriate Characteristics to Determine Volume Fraction in Two-Phase Flows

Fractal and Fractional, Journal Year: 2023, Volume and Issue: 7(4), P. 283 - 283

Published: March 24, 2023

Global demand for fossil fuels has increased the importance of flow measurement in oil sector. As a result, new submarket flowmeter business opened up. To improve accuracy gamma-based two-phase flowmeters, this study employs time-feature extraction methods, particle swarm optimization (PSO) based feature selection system, and an artificial neural network. This article proposes fraction detection system that uses 137Cs gamma source, two NaI detectors recording photons, Pyrex-glass pipe between them. The Monte Carlo N Particle method was used to simulate geometry mentioned above. Thirteen time-domain features were extracted from raw data recorded by both detectors. Optimal characteristics identified with help PSO. procedure resulted identification eight efficient features. input-output relationship approximated using Multi-Layer Perceptron (MLP) innovation present research is use technique on PSO algorithm determine volume percentages, results such as: (1) introducing appropriate time determining percentages; (2) achieving less than 0.37 root mean square error (RMSE) 0.14 (MSE) while predicting components gas-liquid flow; (3) reducing calculation load. Utilizing optimization-based techniques allowed meaningful inputs, which decreased computations boosting precision presented system.

Language: Английский

---

Applying Data Mining and Artificial Intelligence Techniques for High Precision Measuring of the Two-Phase Flow’s Characteristics Independent of the Pipe’s Scale Layer

Electronics, Journal Year: 2022, Volume and Issue: 11(3), P. 459 - 459

Published: Feb. 3, 2022

Scale formation inside oil and gas pipelines is always one of the main threats to efficiency equipment their depreciation. In this study, an artificial intelligence method presented provide flow regime volume percentage a two-phase while considering presence scale test pipe. non-invasive method, dual-energy source barium-133 cesium-137 isotopes irradiated, photons are absorbed by detector as they pass through pipe on other side The Monte Carlo N Particle Code (MCNP) simulates structure frequency features, such amplitudes first, second, third, fourth dominant frequencies, which extracted from data recorded detector. These features use radial basis function neural network (RBFNN) inputs, where two networks also trained accurately determine correctly classify all patterns, independent thickness in advantage proposed system study compared conventional systems that it has better measuring precision well simpler (using instead two).

Language: Английский

---