Wyniki wyszukiwania - BazTech

1

Optimizing infectious disease diagnostics through AI-driven hybrid decision making structures based on image analysis

Ahsan Muhammad, Damaševičius Robertas, Shahzad Sarmad

International Journal of Applied Mathematics and Computer Science

|

2024

|

Vol. 34, no. 4

549--563

EN

Infectious diseases significantly impact global mortality rates, with their complex symptoms complicating the assessment and determination of infection severity. Various countries grapple with different forms of these diseases. This research utilizes three AI-based decision-making techniques to refine diagnostic processes through the analysis of medical imagery. The goal is achieved by developing a mathematical model that identifies potential infectious diseases from medical images, adopting a multi-criteria decision-making approach. The avant-garde, AI-centric methodologies are introduced, harnessing an innovative amalgamation of hypersoft sets in a fuzzy context. Decision-making might include recommendations for isolation, quarantine in domestic or specialized environments, or hospital admission for treatment. Visual representations are used to enhance comprehension and underscore the importance and efficacy of the proposed method. The foundational theory and outcomes associated with this innovative approach indicate its potential for broad application in areas like machine learning, deep learning, and pattern recognition.

2

Analysis of the Vehicle Engine Misfires using Frequency-Domain Approaches at Various RPMs with ADXL1002 Accelerometer

Ahsan Muhammad, Bismor Dariusz, Fabiś Paweł

Archives of Acoustics

|

2024

|

Vol. 49, nr 4

507--516

EN

Vehicle engine vibration signals acquired using MEMS sensors are crucial in the diagnosis of engine malfunctions, notably misfires due to unwanted signals and external noises in the recorded vibration dataset. In this study, the ADXL1002 accelerometer interfaced with the Beaglebone Black microcontroller is employed to capture vibration signals emitted by the vehicle engine across various operational states, including unloaded, loaded, and misfire conditions at 1500 RPMs, 2500 RPMs, and 3000 RPMs. In conjunction with the acquisition of this raw vibration data, frequency-domain signal processing techniques are employed to meticulously analyze and diagnose the distinct signatures of misfire occurrences across various engine speeds and loads. These techniques encompass the fast Fourier transform (FFT), envelope spectrum (ES), and empirical mode decomposition (EMD), each tailored to discern and characterize the nuanced vibration patterns associated with misfire events at different operational conditions.

3

A numerical Haar wavelet-finite difference hybrid method and its convergence for nonlinear hyperbolic partial differential equation

Lei Weidong, Ahsan Muhammad, Khan Waqas, Uddin Zaheer, Ahmad Masood

Demonstratio Mathematica

|

2023

|

Vol. 56, nr 1

art. no. 20220203

EN

In this research work, we proposed a Haar wavelet collocation method (HWCM) for the numerical solution of first- and second-order nonlinear hyperbolic equations. The time derivative in the governing equations is approximated by a finite difference. The nonlinear hyperbolic equation is converted into its full algebraic form once the space derivatives are replaced by the finite Haar series. Convergence analysis is performed both in space and time, where the computational results follow the theoretical statements of convergence. Many test problems with different nonlinear terms are presented to verify the accuracy, capability, and convergence of the proposed method for the first- and second-order nonlinear hyperbolic equations.

4

ARL-Wavelet-BPF optimization using PSO algorithm for bearing fault diagnosis

Ahsan Muhammad, Bismor Dariusz, Manzoor Muhammad Arslan

Archives of Control Sciences

|

2023

|

Vol. 33, No. 3

589--606

EN

Rotating element bearings are the backbone of every rotating machine. Vibration signals measured from these bearings are used to diagnose the health of the machine, but when the signal-to-noise ratio is low, it is challenging to diagnose the fault frequency. In this paper, a new method is proposed to enhance the signal-to-noise ratio by applying the Asymmetric Real Laplace wavelet Bandpass Filter (ARL-wavelet-BPF). The Gaussian function of the ARL-wavelet represents an excellent BPF with smooth edges which helps to minimize the ripple effects. The bandwidth and center frequency of the ARL-wavelet-BPF are optimized using the Particle Swarm Optimization (PSO) algorithm. Spectral kurtosis (SK) of the envelope spectrum is employed as a fitness function for the PSO algorithm which helps to track the periodic spikes generated by the fault frequency in the vibration signal. To validate the performance of the ARL-wavelet-BPF, different vibration signals with low signal-to-noise ratio are used and faults are diagnosed.