Efficient Classification of ECG Images Using a Lightweight CNN with Attention Module and IoT.

Cardiac disorders are a leading cause of global casualties, emphasizing the need for the initial diagnosis and prevention of cardiovascular diseases (CVDs). Electrocardiogram (ECG) procedures are highly recommended as they provide crucial cardiology information. Telemedicine offers an opportunity to provide low-cost tools and widespread availability for CVD management. In this research, we proposed an IoT-based monitoring and detection system for cardiac patients, employing a two-stage approach. In the initial stage, we used a routing protocol that combines routing by energy and link quality (REL) with dynamic source routing (DSR) to efficiently collect data on an IoT healthcare platform. The second stage involves the classification of ECG images using hybrid-based deep features. Our classification system utilizes the "ECG Images dataset of Cardiac Patients", comprising 12-lead ECG images with four distinct categories: abnormal heartbeat, myocardial infarction (MI), previous history of MI, and normal ECG. For feature extraction, we employed a lightweight CNN, which automatically extracts relevant ECG features. These features were further optimized through an attention module, which is the method's main focus. The model achieved a remarkable accuracy of 98.39%. Our findings suggest that this system can effectively aid in the identification of cardiac disorders. The proposed approach combines IoT, deep learning, and efficient routing protocols, showcasing its potential for improving CVD diagnosis and management.

Improved angelization technique against background knowledge attack for 1:M microdata.

With the advent of modern information systems, sharing Electronic Health Records (EHRs) with different organizations for better medical treatment, and analysis is beneficial for both academic as well as for business development. However, an individual's personal privacy is a big concern because of the trust issue across organizations. At the same time, the utility of the shared data that is required for its favorable use is also important. Studies show that plenty of conventional work is available where an individual has only one record in a dataset (1:1 dataset), which is not the case in many applications. In a more realistic form, an individual may have more than one record in a dataset (1:M). In this article, we highlight the high utility loss and inapplicability for the 1:M dataset of the θ-Sensitive k-Anonymity privacy model. The high utility loss and low data privacy of (p, l)-angelization, and (k, l)-diversity for the 1:M dataset. As a mitigation solution, we propose an improved (θ∗, k)-utility algorithm to preserve enhanced privacy and utility of the anonymized 1:M dataset. Experiments on the real-world dataset reveal that the proposed approach outperforms its counterpart, in terms of utility and privacy for the 1:M dataset.

fNIRS-Based Upper Limb Motion Intention Recognition Using an Artificial Neural Network for Transhumeral Amputees.

Prosthetic arms are designed to assist amputated individuals in the performance of the activities of daily life. Brain machine interfaces are currently employed to enhance the accuracy as well as number of control commands for upper limb prostheses. However, the motion prediction for prosthetic arms and the rehabilitation of amputees suffering from transhumeral amputations is limited. In this paper, functional near-infrared spectroscopy (fNIRS)-based approach for the recognition of human intention for six upper limb motions is proposed. The data were extracted from the study of fifteen healthy subjects and three transhumeral amputees for elbow extension, elbow flexion, wrist pronation, wrist supination, hand open, and hand close. The fNIRS signals were acquired from the motor cortex region of the brain by the commercial NIRSport device. The acquired data samples were filtered using finite impulse response (FIR) filter. Furthermore, signal mean, signal peak and minimum values were computed as feature set. An artificial neural network (ANN) was applied to these data samples. The results show the likelihood of classifying the six arm actions with an accuracy of 78%. The attained results have not yet been reported in any identical study. These achieved fNIRS results for intention detection are promising and suggest that they can be applied for the real-time control of the transhumeral prosthesis.

Experimental and Statistical Analysis of Saw Mill Wood Waste Composite Properties for Practical Applications.

The utilization of composite materials is increasing at a growing rate in almost all types of products, due to their strength-to-stiffness ratio. From this perspective, natural waste composites, i.e., wood waste composites, have also been investigated for their effective and sustainable employment. This paper deals with the application of hard and soft wood waste (i.e., acacia and cedar wood) with epoxy resin polymer to develop high strength and thermally stable wood composites. Mechanical (tensile, flexural, impact, and hardness) and thermal properties of samples are studied using Differential Scanning Calorimeter (DSC) and Thermo Gravimetric Analysis (TGA), respectively. The properties are evaluated by varying the type of wood waste and its percentage by weight. Based on the Taguchi Orthogonal Array Mixture Design, eighteen experiments are investigated. Analysis of variance (ANOVA) results show that wood waste type and wood waste content have a significant effect on all mechanical properties. From the TGA analysis, it is predicted that both types of wood waste composites exhibit similar thermal-induced degradation profiles in terms of the initial and final degradation temperatures. From the DSC results, higher glass transition temperature Tg is detected in 10% of the hardwood waste composite, and a reducing tendency of glass transition temperature Tg is observed with exceeding wood waste content. Moreover, hardwood waste at 10% demonstrated improved decomposition temperature Td, due to strong adhesion between waste and matrix.

Deep Learning Approach for Discovery of In Silico Drugs for Combating COVID-19.

Early diagnosis of pandemic diseases such as COVID-19 can prove beneficial in dealing with difficult situations and helping radiologists and other experts manage staffing more effectively. The application of deep learning techniques for genetics, microscopy, and drug discovery has created a global impact. It can enhance and speed up the process of medical research and development of vaccines, which is required for pandemics such as COVID-19. However, current drugs such as remdesivir and clinical trials of other chemical compounds have not shown many impressive results. Therefore, it can take more time to provide effective treatment or drugs. In this paper, a deep learning approach based on logistic regression, SVM, Random Forest, and QSAR modeling is suggested. QSAR modeling is done to find the drug targets with protein interaction along with the calculation of binding affinities. Then deep learning models were used for training the molecular descriptor dataset for the robust discovery of drugs and feature extraction for combating COVID-19. Results have shown more significant binding affinities (greater than -18) for many molecules that can be used to block the multiplication of SARS-CoV-2, responsible for COVID-19.

Multi-Response Optimization of Tensile Creep Behavior of PLA 3D Printed Parts Using Categorical Response Surface Methodology.

Three-dimensional printed plastic products developed through fused deposition modeling (FDM) endure long-term loading in most of the applications. The tensile creep behavior of such products is one of the imperative benchmarks to ensure dimensional stability under cyclic and dynamic loads. This research dealt with the optimization of the tensile creep behavior of 3D printed parts produced through fused deposition modeling (FDM) using polylactic acid (PLA) material. The geometry of creep test specimens follows the American Society for Testing and Materials (ASTM D2990) standards. Three-dimensional printing is performed on an open-source MakerBot desktop 3D printer. The Response Surface Methodology (RSM) is employed to predict the creep rate and rupture time by undertaking the layer height, infill percentage, and infill pattern type (linear, hexagonal, and diamond) as input process parameters. A total of 39 experimental runs were planned by means of a categorical central composite design. The analysis of variance (ANOVA) results revealed that the most influencing factors for creep rate were layer height, infill percentage, and infill patterns, whereas, for rupture time, infill pattern was found significant. The optimized levels obtained for both responses for hexagonal pattern were 0.1 mm layer height and 100% infill percentage. Some verification tests were performed to evaluate the effectiveness of the adopted RSM technique. The implemented research is believed to be a comprehensive guide for the additive manufacturing users to determine the optimum process parameters of FDM which influence the product creep rate and rupture time.

Numerical Modeling and Analysis of Ti6Al4V Alloy Chip for Biomedical Applications.

The influence of cutting forces during the machining of titanium alloys has attained prime attention in selecting the optimal cutting conditions to improve the surface integrity of medical implants and biomedical devices. So far, it has not been easy to explain the chip morphology of Ti6Al4V and the thermo-mechanical interactions involved during the cutting process. This paper investigates the chip configuration of the Ti6Al4V alloy under dry milling conditions at a macro and micro scale by employing the Johnson-Cook material damage model. 2D modeling, numerical milling simulations, and post-processing were conducted using the Abaqus/Explicit commercial software. The uncut chip geometry was modeled with variable thicknesses to accomplish the macro to micro-scale cutting by adapting a trochoidal path. Numerical results, predicted for the cutting reaction forces and shearing zone temperatures, were found in close approximation to experimental ones with minor deviations. Further analyses evaluated the influence of cutting speeds and contact friction coefficients over the chip flow stress, equivalent plastic strain, and chip morphology. The methodology developed can be implemented in resolving the industrial problems in the biomedical sector for predicting the chip morphology of the Ti6Al4V alloy, fracture mechanisms of hard-to-cut materials, and the effects of different cutting parameters on workpiece integrity.

Experimental Investigation and Statistical Evaluation of Optimized Cutting Process Parameters and Cutting Conditions to Minimize Cutting Forces and Shape Deviations in Al6026-T9.

Precise, economical and sustainable cutting operations are highly desirable in the advanced manufacturing environment. For this aim, the present study investigated the influence of cutting parameters (i.e., the cutting speed (c), feed rate (f), depth of cut (d) and positive rake angle (p)) and sustainable cutting conditions (dry and minimum quantity lubricant (MQL)) on cutting forces (i.e., feed force (Ff), tangential forces (Ft), radial force (Fr) and resultant cutting forces (Fc) and shape deviations (i.e., circularity and cylindricity) of a 6026-T9 aluminum alloy. The type of lubricant and insert used are virgin olive oil and uncoated tungsten carbide tool. Turning experiments were performed on a TAKISAWA TC-1 CNC lathe machine and cutting forces were measured with the help of a Kistler 9257B dynamometer. Shape deviations were evaluated by means of a Tesa Micro-Hite 3D DCC 474 coordinate measuring machine (CMM). Experimental runs were planned based on Taguchi mixture orthogonal array design L16. Analysis of variance (ANOVA) was performed to study the statistical significance of cutting parameters. Taguchi based signal to noise (S/N) ratios are applied for optimization of single response, while for optimization of multiple responses Taguchi based signal to noise (S/N) ratios coupled with multi-objective optimization on the basis of ratio analysis (MOORA) and criteria importance through inter-criteria correlation (CRITIC) are employed. ANOVA results revealed that feed rate, followed by a depth of cut, are the most influencing and contributing factors for all components of cutting forces (Ff, Ft, Fr, and Fc) and shape deviations (circularity and cylindricity). The optimized cutting parameters obtained for multi responses are c = 600 m/min, f = 0.1 mm/rev, d = 1 mm and p = 25°, while for cutting conditions, MQL is optimal.

Effect of Alumina Nano-Particles on Physical and Mechanical Properties of Medium Density Fiberboard.

This research aims to explore the effects of nanoparticles such as alumina (Al2O3) on the physical and mechanical properties of medium density fiberboards (MDF). The nanoparticles are added in urea-formaldehyde (UF) resin with different concentration levels e.g., 1.5%, 3%, and 4.5% by weight. A combination of forest fibers such as Populus Deltuidess (Poplar) and Euamericana (Ghaz) are used as a composite reinforcement due to their exceptional abrasion confrontation as well as their affordability and economic value with Al2O3-UF as a matrix or nanofillers for making the desired nanocomposite specimens. Thermo-gravimetric analysis (TGA) and thermal analytical analysis (TAA) in the form of differential scanning calorimetry (DSC) are carried out and it has been found that increasing the percentage of alumina nanoparticles leads to an increase in the total heat content. The mechanical properties such as internal bonding (IB), modulus of elasticity (MOE) and modulus of rupture (MOR), and physical properties such as density, water absorption (WA), and thickness swelling (TS) of the specimens have been investigated. The experimental results showed that properties of the new Nano-MDF are higher when compared to the normal samples. The results also showed that increasing the concentration of alumina nanoparticles in the urea-formaldehyde resin effects the mechanical properties of panels considerably.

Evaluation of chemical constituents and antinociceptive properties of Myricaria elegans Royle.

The phytochemical screening of Myricaria elegans Royle (Tamaricaceae) gave strongly positive results for terpenes. A total of six triterpenes were isolated from the CHCl3 fraction, including eleganene-A, eleganene-B, corsolic acid, betulin, ursolic acid, and erythrodiol. The in vivo antinociceptive investigation of the plant showed a significant increase in the tail-flick latency, accompanied by mild sedation and severe ataxia. Considering the known activities of some of the compounds isolated from the plant, it may be hypothesized that the increase in the tail-flick latency may be the combined effect of analgesia, ataxia, and sedation, rather than analgesia alone. These findings suggest M. elegans to be a potential source for activity-guided isolation of important natural compounds with a variety of effects.

Anti-inflammatory study on crude methanol extract and different fractions of Eremostachys laciniata.

CONTEXT: Eremostachys laciniata (L.) Bunge (Lamiaceae), which has been reported as a rich source of flavonoids, is one of the rarely explored species of the genus Eremostachys. OBJECTIVE: In this study, the crude methanol extract and different fractions of E. laciniata were investigated for in vivo anti-inflammatory properties. MATERIAL AND METHODS: Shade-dried leaves of E. laciniata were exhaustively extracted by percolation with methanol (80%) to obtain 250 g of crude methanol extract (El), followed by fractionation with different organic solvents to get the n-hexane (Elh), chloroform (Elc), ethyl acetate (Ele), butanol (Elb), and water (Elw) fractions. An in vivo anti-inflammatory study of the crude extract and sub-crude fractions was carried out in rats using the carrageenan model. RESULTS: The Ele fraction was found to be the most potent inhibitor of edema formation by inducing a maximum inhibitory effect of 74.2% at the 300 mg/kg dose, during 3 h post carrageenan injection. The El extract and Elc fraction also showed good anti-inflammatory properties at the same dose. DISCUSSION: The demonstration of excellent anti-inflammatory activity by the plant chiefly concentrating in the Ele fraction and the appearance of peak activity in the latter phase of the experiment suggested the presence of relatively low-polar substances with arachidonic acid metabolite inhibition property. CONCLUSION: The plant may be an excellent source in the future for activity-guided isolation of important anti-inflammatory substances.