Gagandeep Singh

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder affecting cognitive and behavioral functions, resulting in ongoing inattention, hyperactivity, and impulsivity. Early and accurate diagnosis is essential, but traditional methods mainly depend on questionnaire-based assessments, detailed interviews with individuals and their families, and reviews of medical history. These are then scored using standardized scales like the Conners Rating Scale, Vanderbilt ADHD Diagnostic Parent Rating Scale, and Adult ADHD Self-Report Scale. However, these methods are often subjective, time-consuming, and costly, which limits their usefulness for early diagnosis. The proposed approach seeks to improve ADHD diagnosis by using machine learning techniques applied to electroencephalogram (EEG) data. Two classifiers, Random Forest and AdaBoost, are used to identify complex patterns in EEG data. Feature selection is performed with the Reptile Search Algorithm combined with an autoencoder for feature extraction, which improves data representation and model accuracy. The performance of this approach is evaluated based on accuracy, precision, recall, F1-score, AUC, and statistical significance at a 95% confidence level. Random Forest outperformed AdaBoost, achieving 92.36% in precision, recall, accuracy, and F1-score, while AdaBoost reached 89.78% in these metrics. Random Forest showed better effectiveness than AdaBoost in distinguishing ADHD cases, with an ROC AUC score of 0.93 and higher diagnostic accuracy. The study demonstrates that machine learning offers a promising, objective, and reliable tool for diagnosis, providing effective alternatives to traditional ADHD assessments for timely intervention and improved treatment management.

The surface quality of biomedical implants, such as shoulder joint caps, plays a critical role in their performance, longevity, and biocompatibility. Most biomedical shoulder joints fail to reach their optimal functionality when finished through conventional techniques like grinding and lapping due to their inability to achieve nanometer-grade smoothness, which results in greater wear and friction along with potential failure. The advanced magnetorheological finishing (MRF) approach provides enhanced surface quality through specific dimensional control material removal. This research evaluates how MRF treatment affects the surface roughness performance and microhardness properties and wear resistance behavior of cobalt–chromium alloy shoulder joint caps which have biocompatible qualities. The study implements a magnetorheological finishing system built with an electromagnetic tool to achieve the surface roughness improvements from 0.35 µm to 0.03 µm. The microhardness measurements show that MRF applications lead to a rise from HV 510 to HV 560 which boosts the wear protection of samples. After MRF finishing, the coefficient of friction demonstrates a decrease from 0.12 to 0.06 which proves improved tribological properties of these implants. The results show that MRF technology delivers superior benefits for biomedical use as it extends implant life span and decreases medical complications leading to better patient health outcomes. The purposeful evaluation of finishing techniques and their effects on implant functionality demonstrates MRF is an advanced technology for upcoming orthopedic implants while yielding high precision and enhanced durability and functional output.

This study investigates the effectiveness of a newly developed magnetorheological fluid (MRF) finishing process in improving the surface quality of P20 steel mold punches, which are crucial for producing smooth plastic components in casting. Surface quality of molds and punches improves product quality, enhances precision, reduces wear, optimizes material flow, minimizes defects, and extends the lifespan of the die and punch. The MRF finishing process utilizes abrasive particles suspended in MR fluid to achieve a fine surface finish. The research aims to evaluate the feasibility of the new developed MRF process for finishing hard materials and examines the influence of a new finishing parameter percentage of abrasive particle concentration along with four other key finishing parameters using the Taguchi method. After 45 min of finishing, a significant reduction in surface roughness is observed, decreasing from 0.247 µm to 0.065 µm. Among the parameters studied, abrasive particle concentration is identified as the most influential factor in achieving this reduction. To assess the process's effectiveness, the initial surface and the MR-finished surface are compared using a Taylor Hobson Surftest-25 roughness tester, scanning electron microscopy, and mirror image tests. The results confirm that the newly developed MRF process significantly enhances surface quality, reducing roughness to the nano level and refining the microscopic surface of the mold punch.

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) represents a widely prevalent and heterogeneous neurodevelopmental condition in pediatric populations, often exhibiting a substantial propensity to persist into adulthood. ADHD is a multifaceted disorder that resists straightforward diagnostic tests. Clinicians must invest substantial time and effort to secure an accurate diagnosis and implement effective treatment. ADHD diagnosis is primarily based on psychiatric tests, as there is currently no clinically utilized objective diagnostic tool. Nonetheless, several studies in have documented endeavors to create objective instruments designed to assist in the diagnostic process of ADHD, aiming to enhance diagnostic accuracy and reduce subjectivity. Method: This research endeavor sought to establish an objective diagnostic modality for ADHD through the utilization of electroencephalography (EEG) signal analysis. With the use of innovative deep learning techniques, this research seeks to improve the diagnosis of ADHD using EEG data. To capture complex patterns in EEG data, this study proposes a double-augmented attention mechanism ResNet-based model. Using an autoencoder for feature extraction, the Reptile Search Algorithm for feature selection, and a modified ResNet architecture for model training comprise the technique. Results: AUC, F1-score, accuracy, precision, recall, and other standard classifiers like Random Forest and AdaBoost were utilized to compare the model’s performance. By a wide margin, the proposed ResNet model outperforms the traditional models with a 99.42% accuracy, 99.03% precision, 99.82% recall, and 99.42% F1-score. Conclusions: ROC AUC score of 0.99 for the model underscores its remarkable capability to differentiate between children with and without ADHD, thereby minimizing misclassification errors and improving diagnostic precision.

The recent rise in the demand for high precision, close tolerances, and super surface finish quality of components and part assembly modules in the competitive manufacturing industrial environment for the enhanced working life and functional requirements of machines globally. Three revolving curved tip tools based magnetorheological process is designed and developed to fine finish the external cylindrical surfaces of soft and hard materials. The effect of the key operational machining parameters on the surface roughness of a newly developed magnetorheological process was carried out using a one factor at a time method. The magnetizing current, the revolving speed of the tools, the rotational speed of the workpiece, workpiece traverse speed are the parameters that have been considered for this purpose. The experimentation has been performed on the aluminium workpiece because of its broad applicability, such as manufacturing shafts, rods, pistons, and other circular components. The primary purpose of this study was to determine the range of essential control parameters for the newly developed finishing process. The percentage reduction in Ra, Rq, and Rz values are 69.64%, 58.21%, and 54.48%, respectively, after 60 minutes of finishing at magnetizing current 2A, the revolving speed of the tools 30 RPM, the rotation speed of the workpiece 600 RPM and feed 10 cm/min.

The cylindrical copper rollers are an essential part of the printing process. The copper roller needs to be finely finished to ensure the even distribution of the colors. Fine and precise polishing of cylindrical copper rollers is challenging using conventional finishing procedures because of their ductility and low hardness. Therefore, the magnetorheological finishing process based on three revolving flat-tip tools has been used to meet this precise requirement. The optimized parameters were found as current 3.5A for the electromagnet, rotating speed of the workpiece 510 rpm, revolving speed of the tools 35 rpm, working gap 0.7 mm and feed rate 150 mm/min for maximum percentage reduction in the surface roughness of copper roller. After 4 h of finishing with the optimal parametric settings, the Ra, Rq, and Rz values were reduced to 0.08, 0.1, and 0.67 μ m from the initial values of 0.375, 0.527, and 1.96 μ m, respectively, across the copper roller surface. Surface roughness profiles, SEM, and mirror-image tests reveal the superiority of the magnetorheologically finished roller surface compared to the unfinished one.

High-quality surface of the cylindrical workpieces would have to be very precise when used in automobile industries, vane pumps, turbines, gears, mild steel dies and punches for plastic industries. The magnetorheological finishing process based on three revolving curved tip tools has been developed for external cylindrical components to address the above issues. Three electromagnetics tools have been used in this magnetorheological method that can move radially inwards or outwards according to the external diameter of the workpiece. During finishing, the workpiece rotates in the anti-clockwise direction, and three curved tip tools revolve around the workpiece in a clockwise direction resulting in more interaction between the workpiece and active abrasive particles. Reciprocating movement is also provided to the workpiece that helps to produce the axial force on the active abrasive particles. The proposed method has been applied to a mild steel shaft to investigate the surface finish of its external surface. Response surface methodology (RSM) has been used to plan and analyse the impacts of different process factors on the percentage change in surface roughness value of the finished surface of the mild steel stepped cylindrical shaft. The optimal combination of process parameters is magnetising current 3.4A, revolving speed of tools 26 rpm, the rotational speed of workpiece 440 rpm, and transverse speed of workpiece 20 cm/min, which shows the maximum percentage change in the surface roughness value. Confirmation experiments have been performed at optimal combination. The lowest R_a value of 85 nm (nanometre) has been achieved from the initial value of 410 nm (nanometre) in the finishing duration of 90 min. The roughness profiles, scanning electron microscopy (SEM) test and reflection test show that the current finishing process can meet high standards for surface quality that aren't possible with conventional methods.