In this work, we propose a machine learning-based approach to predict the efficiency of the semiconductor neutron detector for planar configuration detector design at different Low-Level Discrimination (LLD) value setting for boron carbide converter material. Prior to the fabrication of a semiconductor neutron detector, it is pertinent to optimize several parameters relevant to detector design. Monte Carlo techniques are used for this purpose. GEANT4 toolkit, which utilizes the Monte Carlo approach, is commonly utilized to estimate these parameters. A noteworthy limitation of the GEANT4 simulation is its high computational complexity. The simulation demands substantial computational resources and can be computationally demanding. As a consequence, the processing times can become lengthy, and this may pose challenges in conducting simulations on a larger scale or with intricate systems. Therefore, in this study, we adopted a different novel approach by leveraging machine learning techniques to predict the efficiency of a planar semiconductor neutron detector under varying settings of the LLD values. The efficiency values obtained from the GEANT4 simulations formed the basis of the dataset used in this study. Subsequently, different machine learning techniques, such as Linear Regression, Polynomial Regression, Support Vector Regression (SVR), and Neural Networks were explored in order to develop an optimized model. The aim was to accurately predict efficiency values by considering the influence of converter layer thickness and different LLD settings. Initially, we trained these models by utilizing the GEANT4 dataset, specifically focusing on efficiency up to 700 keV LLD. Subsequently, we employed the trained model to predict the efficiency for LLD values of 800 keV and 900 keV. Through our analysis, we determined that the neural network emerged as the most accurate model for predicting efficiency, closely aligning with the efficiency simulated by GEANT4 software toolkit.

Background: Knee osteoarthritis (OA) is a significant global health burden, causing pain, disability, and rising healthcare costs. Conventional imaging (e.g., X-ray, MRI) is effective yet expensive and not ideal for routine monitoring. Vibroarthrography (VAG), which analyses knee joint acoustic emissions (AE), offers a promising non-invasive, cost-effective alternative; however, its diagnostic performance hinges on robust signal decomposition and feature extraction. Methods: This study proposes a novel Adaptive Weighted Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (AWCEEMDAN) framework to enhance VAG-based OA assessment. Combined with adaptive envelope distortion and segment-based micro-shifting augmentation, AWCEEMDAN reduces noise, mode mixing, and baseline wander while emphasizing transients linked to chondral damage and osteophyte impact. We analysed 120 original and 300 augmented AE signals spanning Normal to KL Grades 1-4 using unsupervised clustering and supervised machine-learning classifiers. Results: AWCEEMDAN with augmentation outperformed traditional EMD and ICEEMDAN, yielding cleaner signals and more distinct patterns across Normal and KL Grades 1-4. Classifiers trained on the resulting features achieved high diagnostic performance, with accuracies up to 97 %. The improved features enabled clearer separation between early and advanced OA stages. Conclusions: This methodology improves knee OA detection and staging by capturing transient, high-frequency signals and supports refined severity stratification for clinical decision-making. Future research will expand patient demographics, incorporate additional clinical variables, and optimize computational methods for realtime use.

The present research work explores on the estimation of thermal neutron detection efficiency for the novel embedded spherical configuration design using GEANT4 toolkit. Initially, single and multiple layer of embedded spherical configurations were designed in geometry category class of GEANT4 toolkit using Boron (B-10) converter material followed by, estimation of simulated thermal neutron detection efficiency at different radii which varies between 0.05 mu m and 5 mu m for both single and multiple layer embedded spherical detector configuration. The maximum thermal neutron detection efficiency obtained for the single layer embedded spherical detector configuration is similar to 5.1 % at an optimum (critical) radius of similar to 4.55 mu m. It was noticed that with the rise in the number of layers of embedded spherical detector configuration the thermal neutron detection efficiency was also increasing. Furthermore, investigation the effect of varying level of Low Level Discriminator and different enrichment level of B-10 on the efficiency was also studied. Finally, the histoplot was investigated for a typical 10 layers of embedded spherical detector configuration at typical lower (200 nm) and higher (3 mu m) radius.

This study investigates the comparison of the simulated thermal neutron detection efficiency of a threedimensional embedded spherical detector using the GEANT4 toolkit and machine learning driven approach. Multi-layer configurations with ${ }^{10} \mathrm{~B}$ which is well known converter material were modeled. The efficiency $\eta$ was evaluated for sphere radii ($\mathrm{R}_{\mathrm{s}}$). A Low-Level Discriminator (LLD) of 300 keV was applied in all simulations to suppress the background gamma radiation. A new approach of machine learning technique was used. It was seen that the machine learning approach was able to predict the simulated thermal neutron detection efficiency very close to the GEANT4 simulated efficiency.

Pulsed electromagnetic field therapy is increasingly recognized for its capacity to promote tissue healing, reduce inflammation, and minimize pain across a diverse spectrum of health conditions. However, optimizing the therapy's settings, including pulse frequency, current, coil turns, and proximity to the target tissue, presents significant challenges. These arise from the complex nature of human tissue and the dynamic responses to PEMF. To address these challenges, we propose a data-oriented approach that employs advanced machine-learning algorithms to rigorously analyze simulation data and refine the parameters of PEMF therapy. Our strategy involves simulating the interactions between PEMF and biological tissues under various conditions, followed by the application of a Random Forest Regressor model to analyze the resulting data. This process helps determine the most effective combination of parameters, balancing deep tissue penetration against the risk of thermal effects. Our findings indicate that optimal therapeutic outcomes are achieved with lower frequencies and higher currents, coupled with an increased number of coil turns and reduced distance from the tissue. Through detailed visual tools like correlation heat maps, scatter plots, and 3D visualizations, we provide a nuanced understanding of the parameter interplay, guiding the fine-tuning of therapy settings. Our findings therefore have the potential to lead to personalized PEMF therapy protocols tailored to individual patient needs and treatment objectives.

Cleaning motion and muscle artifacts from EEG signals is challenging because they are large, unpredictable, and occur without clean reference data. Existing methods either oversimplify the noise or are too computationally expensive. We introduce TS-MoNDiff, a self-supervised framework that cleans multivariate biosignals without needing clean examples. Our method combines a diffusion model that learns from the data itself by predicting masked segments, with a robust statistical model that ignores large artifacts. A key innovation is a highly efficient one-step denoising process, making it practical for use. Tested on EEG data, TS-MoNDiff reduces reconstruction error by 64% compared to the best classical baseline, while successfully preserving the brain’s natural rhythms and sharp waveform.

Osteoarthritis is a common cause of disability among elderly significantly affecting their quality of life due to pain and functional limitations. This study proposes a novel, non-invasive, and cost-effective diagnostic technique using vibroarthrography (VAG) for early detection and grading of knee osteoarthritis (KOA) overcoming the limitations of traditional methods like X-rays, CT scans, and MRIs. Signal acquisition involved capturing of VAG signals from KOA patients using Thinklabs One digital stethoscope and a specialized knee brace within a frequency range of 20 Hz to 2000 Hz with a ± 3 dB tolerance at 44,000 samples per second. Various signal processing techniques, like time domain, statistical, PSD, wavelet, and Hilbert-Huang transform analysis, were used to study the resultant signal. Subsequently, a novel combination of self-organizing maps (SOMs) and K-means clustering was proposed to categorize VAG signals into distinct OA grade clusters. The resulting analysis identified distinct patterns in the time domain correlating with joint alteration severity. A SD/Mean ratio differentiated OA grades. Hilbert-Huang Transform established intrinsic mode functions relating frequency bands to OA stages, while wavelet and spectrogram analysis demonstrated increased signal complexity and variability with disease progression. The effectiveness of proposed clustering model was indicated by high mean Silhouette Coefficient (∼0.80) and low Davies-Bouldin Index (∼0.33) indicating distinct and accurate segmentation of OA stages. These findings clearly highlighted the potential of SOMs and K-means clustering in analysing VAG signals for classifying into different KOA grades. These results demonstrate the substantial potential of advanced signal processing, SOMs, and K-means clustering in uncovering complex patterns in VAG data, linking increasing knee sound signal complexity with OA progression. This highlights the potential of our approach in medical diagnostics, especially for chronic conditions like KOA, where early detection and ongoing monitoring are crucial.

This study delves into the capabilities of thermal neutron semiconductor detectors using Boron Carbide (10B4 C) as the conversion material in a stack design with an enrichment of 50% of 10B (Boron-10) content. The efficiencies have been determined under different Lower Level Discriminator (LLD) settings from 100 keV to 700 keV. Monte Carlo based GEANT4 toolkit was used for simulation and the analysis reveals insights into the stack design. This design shows a remarkable efficiency for neutron detection. A 40-layer stack achieved an efficiency of approximately 33.8%. Moreover, the study underlines the importance of LLD optimization, where the higher LLD thresholds tends to lower the efficiency and vice versa. These revelations enrich our understanding of thermal neutron semiconductor detectors and additionally highlights the advantages of the stack design, particularly pertinent in fields requiring a greater thermal neutron detection like nuclear safety, security, and research endeavour.

Knee Osteoarthritis (KOA) is a prevalent degenerative disease that significantly diminishes quality of life in older adults, causing pain, stiffness, reduced mobility, and increasing healthcare costs. Current treatments often fail to adequately address KOA, particularly in personalizing therapy to individual needs. Therefore, the purpose of this study was to evaluate the efficacy of Pulsed Electromagnetic Field (PEMF) therapy, a non-invasive and drug-free intervention customized to KOA severity, with the aim of enhancing therapeutic outcomes. A PEMF generator was developed to emit frequencies between 0 and 300 Hz and duty cycles of 5-90

The gas metal arc welding (GMAW) process, prevalent in construction and fabrication sectors, traditionally relies on postproduction evaluations, which are both costly and time-consuming. This study proposes a more efficient, real-time monitoring approach utilizing high-speed data acquisition and analysis systems to record and scrutinize voltage and current fluctuations during welding. Various decomposition techniques, including EMD (empirical mode decomposition), EEMD (ensemble empirical mode decomposition with noise), CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise), and ICEEMDAN (improved complete ensemble empirical mode decomposition with adaptive noise), were analyzed to assess arc variations and thereby evaluate GMAW process quality. The research identified an optimal technique for analyzing non-stationary welding signals, further applied to real-time signals using decomposition and time–frequency representation (TFR) techniques. Findings indicate that key GMAW parameters, such as metal transfer mode and penetration depth, correlate significantly with the intrinsic mode functions (IMFs) and TFRs of decomposed signals. The study suggests that the introduced techniques can effectively analyze the influence of different shielding gases and arc currents on the GMAW process, presenting a promising method for real-time GMAW process monitoring.

This research work introduces a new way of analyzing soil, combining an innovative sensor technology with complex mathematical models. Central to our methodology is an economically efficient charcoal sensor system, meticulously designed to proficiently identify primary soil components like moisture, urea, and organic content. We capitalized on the inherent attributes of raw wood charcoal, employing a potential divider network for reliable voltage detection. The comprehensive analysis of charcoal powder, achieved through Finite Element Scanning Electron Microscopy (FE-SEM) and Energy-Dispersive Spectroscopy (EDS), confirmed its ideal composition for the envisaged sensing functions. The functionality of the sensor was evaluated by targeting two vital parameters—moisture and nitrogen/urea content. Notably, we discovered an almost linear association between the sensor's node voltages and the soil's water or urea volume, validating the sensor's sensitivity and consistency. Furthering the frontier of soil analysis, we conceptualized an algorithm to estimate soil organic content. This representation was iteratively fine-tuned to attain an accuracy of 0.9999. The ramifications of our study extend significantly into precision agriculture. By providing an accessible yet potent instrument for electronic soil evaluation, the proposed work has the potential to revolutionize crop management and amplify agricultural productivity. The unique combination of affordability, precision, and simplicity makes this sensor system an ideal candidate for global implementation, signaling the dawn of a new epoch of sustainable agriculture and bolstered food security worldwide.

SMAW (Shielded Metal Arc Welding) and GMAW (Gas Metal Arc Welding) are two of the most prominent welding processes commonly utilized in almost all types of modern industries. Among various aspects of these processes, some of the important parameters that govern the quality of the final weld product are the skill level of welders, welding consumables, and the role of shielding gases (in GMAW). Currently, the role of these parameters in determining the quality of the welded product is examined by evaluating the final weld produced and not by investigating how these factors affect the welding process. This is an indirect way to evaluate such welding parameters, which are both time-consuming and expensive. During the actual welding process, random variations in arc signals (voltage and current) take place. These dynamic variations are so short and rapid that ordinary ammeters and voltmeters cannot monitor the rate of such variations. However, the reliable acquisition of such variations and its subsequent analysis can provide very useful information in determining the quality of the final weld product. In this study, arc voltage and current were acquired at 100,000 samples/sec, filtered and subsequently analyzed using Continuous Wavelet Transform based on Fast Fourier Transform (CWT-FFT) technique to evaluate welding skill, welding electrodes (in SMAW process), and the effect of shielding gases (in GMAW process). Results thus obtained clearly differentiated the skill level of different trainee welders and welding electrodes in the SMAW process and the effect of shielding gases and arc current in the GMAW process. Very good correlation among the obtained results, its weld bead and its weld pool images were observed. Hence, this research proposes a simple yet effective methodology to evaluate the arc welding process parameters using CWT-FFT analysis of the welding signals.

In this research paper, we have developed a novel approach using the machine learning models to predict the efficiency of semiconductor neutron detector for boric acid based converter material. Considering the over head of computational resources and time to compute the efficiency of a neutron detector, it becomes imperative to find the models that can take much lesser resources and time. In this novel work, the model was trained from the earlier research work done on GEANT4 simulation software and the predicted data was also compared with the simulated data. The various machine learning regression model were designed for stacked detector. Further, comparison have been done to find the best fit for the experimental data.

Arc welding, due to its simplicity, ease of use and low maintenance cost is one of the most widely used welding process in almost all types of modern industries. In this process, voltage, current and welding speeds are the major variable which influences the final weld product. Among these, monitoring welding speed is relatively easy, while monitoring voltage and current is not. This is because welding is a stochastic process in which wide variations in voltage and current occurs and durations of these variations are so short that the ordinary ammeters and voltmeters cannot measure these variations. However, using suitable sensors coupled with a high-speed data acquisition system, real time variations taking place in an actual welding process can be recorded and subsequently analyzed. A careful analysis of these variations using various signal processing, statistical and data mining techniques can provide a very useful information in estimating the quality of final weld product. In this research, a first of its kind, detailed review on various aspects of weld monitoring systems used for weld data acquisition and its subsequent analysis are presented. This will include an in-depth analysis of various electronic sensing and data sampling modules which can be used in the design and development of a Weld Monitoring System. Additionally, this review also includes a brief study on various soft computing, data mining and machine learning techniques on weld data in predicting the quality of different welding parameters. Finally, summary of the review is followed by the scope of future research to pave out some of the new dimensions in exploring the multi-disciplinary area of evaluating the arc welding quality using data acquisition and analysis techniques.

A linear regression-based method for extracting the threshold voltage of tunnel field-effect transistors (TFETs) is presented. The minimum tunneling width at the threshold voltage of a TFET is expressed as a linear function of tunneling widths corresponding to gate voltages. The regression is carried out using known simulated TFETs and verified on unknown TFETs, achieving an R-2 value of 96.50%. The model is compared with and verified against methods and devices reported in literature, confirming that it is effective for predicting the threshold voltage.

Shielded metal arc welding (SMAW) is one of the most important welding process used in the industry for joining ferrous and nonferrous metals. In SMAW process random fluctuations in current and voltage takes place. Reliable acquisition of these variations during actual welding process and its subsequent analysis can be very useful to study different arc welding parameters. Now a day, the welding power sources have a provision of advance arc control to suitably adjust the welding parameters with minimum time delay and to set the right welding parameters during actual process. Hence, to study the exact behaviour of these modern power sources used for welding it is essential to acquire all the possible minute variations taking place while welding is in progress. In the present study, performance evaluation of six different welding power sources has been performed using probability density distributions (PDD) and self organized maps (SOM). Further the quantification of their performance has also been attempted and the final results were compared with the results obtained using existing techniques. The effect of varying input current on SMAW process has also been studied by acquiring the data at different current values (from 70 A to 120 A). In both the cases data acquisition was carried out at the rate of 100,000 samples/s for 20 s duration using a general purpose digital storage oscilloscope while welding is in progress. These welds were prepared using same type of welding electrode by the same welder employing the identical parameters. From the PDDs and self organized maps (SOM) generated using the data acquired, it is possible to evaluate the performances of the different welding power sources. Grading of the power sources based on PDD and SOM technique matched well with the grading obtained using visual examination of weld beads. Further using these analyses, it is also possible to differentiate various weld geometry. Results clearly indicated that the procedure presented here can be effectively used to assess the various SMAW parameters.

The present work focuses on Monte Carlo-based GEANT4 simulation for estimating the efficiency of thermal neutron detection for stacked semiconductor neutron detector configuration with enriched B10 as neutron converter material. The simulation revealed that the efficiency of stacked detector configuration is ~56.93% for 90 stacks, which is significantly much higher than its planar configuration counterpart. The low-level discriminator value for background gamma radiation rejection was fixed at a value of 300 keV in the simulation.

Arc welding uses power sources of the constant current type having drooping characteristics or constant voltage characteristics. However, in reality, arc welding is a stochastic process due to random arc behaviour and metal transfer. The quality of a weld depends on the extent of these variations. The random signal amplitudes and time characteristics of the weldingsignal (voltage and current) allow a quality analysis of the welding process and disturbances. These random variations in current and voltage cannot be recorded with ordinary instruments. In the present work, a Programmable System on Chip based embedded Weld Monitoring System (WMS) with suitable software package was designed and developed to measure all the dynamic variations of welding voltage and current. Welding data were acquired using this WMS for the duration of 20 seconds at a sampling rate of 100,000 samples/s. The data obtained were filtered and subjected to the time domain and statistical analyses to evaluate various arc-welding parameters. The results obtained with WMS indicated that the same can be used for evaluating the welding consumables and assessing the skill of the welders. Thus, this work proposes a standalone, affordable, and an innovative tool for comprehensive on-line analysis of an arc-welding process.

This paper reports the fabrication and system design of a low cost charcoal based moisture sensor of dimension 1 cm × 1 cm × 260 μm. Seven different samples were prepared and calibrated for 25 μL of water. The sensitivities are reported for the different samples. It has been discovered that the final node voltage (post-exposure to moisture) depends on the initial node voltage linearly when the experimental data points are fitted. A ratio in the range 1.16–1.27 is obtained while calibrating for the presence of 25 μL of moisture.

Shielded Metal Arc Welding (SMAW) Process utilizes a constant current type power source with drooping characteristics. Due to complex nature of welding arc and metal transfer that occurs during welding, there is a lot of random variations in welding current and voltage which cannot be recorded directly by normal ammeter or voltmeter. However, acquisition of welding data while welding is in progress and subsequent analysis of this data can be very useful to evaluate various welding parameters (i.e. welding consumables etc.). For this purpose, high speed of data acquisition is essential. As noise level in the data will be high hence, before performing any meaningful analysis filtering of this data is also important. In the present study, a technique is proposed for the reliable acquisition of welding data to acquire all the possible variations in arc voltage while welding is in progress using a Digital Storage Oscilloscope (DSO). Various signal processing methods were used for selecting the appropriate filtering technique. Filtered data thus obtained were used to evaluate arc welding electrodes with different flux coating using probability density distributions. The results thus obtained were correlated with the images obtained using high speed camera setup. This clearly brings out the differences in the arc characteristics for welding consumables. They also indicate that the proposed technique can be developed as a tool to compare the performance of different welding electrodes. (C) 2018 Elsevier Ltd. All rights reserved.