Search

Abstract COVID-19 is a worldwide epidemic that seriously affected the lives of people. Since its inception, physicians have tried their best to trace the virus and reduce its spread. Several diagnostic approaches have been reported to detect the coronavirus in research, clinical, and public health laboratories. Although the existing systems aid medical experts in the diagnosis, they still lack precise detection and may fail to detect COVID-19 in a timely manner. Therefore, in this study, we recommend two approaches i.e., the first approach is based on the VGGish network that focuses on vocal signals, such as breathing and coughing, and the second approach is based on ResNet50, which takes chest X-rays as input. With the help of VGGish, the patient’s cough, voice, and respiration audios have been classified as patient and non-patient achieving an accuracy of more than 98%. We also assessed the performance of several methods for X-ray classification, such as ResNet50, VGG16, VGG19, Densnet201, Inceptionv3, Darknet, GoogleNet, squeezeNet, and Alex-Net. TheResNet50 outpaced all supplementary CNN models with a precision of 94%. However, when we took both types of inputs simultaneously, the accuracy for detection was increased to 99.7%. After extensive experimentation, we believe that our proposed hybrid method is robust enough to take X-rays and audio as mel-spectrograms and identify COVID-19 at early stages, attaining an accuracy of 99.7%.

This study explores the optimization and performance of a hybrid energy system combining a geothermal heat pump (GHP) with a wind turbine in Izmir, Turkey. Utilizing a 4E (Energy, Exergy, Economic, and Exergoenvironmental) analysis approach, the system aims to enhance winter heating efficiency. Geothermal heat pumps leverage the Earth's consistent temperatures for heating and cooling, offering a sustainable alternative to traditional energy sources. Key findings include a high coefficient of performance (COP) of 3.916 for the heat pump, a net power output of 118.9 kW, total energy efficiency of 67.93 %, and exergy efficiency of 45.18 %. Economically, the system proves viable with a unit exergy cost of 0.1246 $/kWh, highlighting its cost-effectiveness. The exergoenvironmental analysis demonstrates a factor of 0.8059, indicating a substantial reduction in environmental impact. The integration of geothermal and wind energy demonstrates substantial potential for sustainable energy solutions, crucial for environmental conservation and economic advancement. This comprehensive evaluation highlights the system's operational dynamics, presenting an innovative approach to renewable energy utilization.

Abstract This study aims to explore the precise resolution of the nonlinear Benjamin Bona Mahony Burgers (BBMB) equation, which finds application in a variety of nonlinear scientific disciplines including fluid dynamics, shock generation, wave transmission, and soliton theory. Within this paper, we employ two versatile methodologies, specifically the extended $$\exp (-\Psi (\chi ))$$ exp ( - Ψ ( χ ) ) expansion technique and the novel Kudryashov method, to identify the exact soliton solutions of the nonlinear BBMB equation. The solutions we discovered involve trigonometric functions, hyperbolic functions, and rational functions. The uniqueness of this research lies in uncovering the bright soliton, kink wave solution, and periodic wave solution, and conducting stability analysis. Furthermore, the solutions’ graphical characteristics were explored through the utilization of the mathematical software Maple 2022 ( https://maplesoft.com/downloads/selectplatform.aspx?hash=61ab59890f2313b2241fde3423fd975e ). The system’s physical interpretation is defined through various types of graphs, including contour graphs, 3D-surface graphs, and line graphs, which use appropriate parameter values. These recommended techniques hold significant importance and are applicable in diverse nonlinear evolutionary equations found in the field of nonlinear sciences for illustrating nonlinear physical models.

Significance: The thermal analysis of nanofluid in a vertical cylinder (artery) in a magnetized environment holds significant implications in physiological and thermal regulation networks. This research is significant in biomedical engineering with applications like medical diagnostics and treatment strategies. Motive: This study investigates the thermal behavior of a magnetized blood-based ternary Carreau nanofluid flowing through a vertically bounded artery with quadratic convection. Velocity and heat transfer analysis is conducted within the artery, utilizing thermal radiation and quadratic convection in a magnetized setting. The base fluid consists of blood, augmented with three nanoparticles: CuO, Al2O3, and TiO2. The investigation centers on examining the properties of blood nanofluid, arterial geometry, and thermal dynamics. Methodology: The physical model generates a set of partial differential equations (PDEs) and similarities mechanism is utilized to fetch its non dimensional form in terms of ordinary differential equations (ODEs). Furthermore, numerical outcomes are obtained with Matlab function bvp4c and obtained data set is trained through robust scheme Levenberg-Marquardt neural network (LMNN) procedure to predict the solution. Findings: Velocity of blood is reduced with increased values of wiessenberg number, magnetic parameter and mixed convection parameter and velocity increases for Second-order convection parameter. Temperature profile decreases with curvature parameter, mixed convection parameter and permeability parameter.

Diabetic retinopathy is a serious eye disease that may lead to loss of vision if it is not treated. Early detection is crucial in preventing further vision impairment and enabling timely interventions. Despite notable advancements in AI-based methods for detecting diabetic retinopathy, researchers are still striving to enhance the efficiency of these techniques. Therefore, obtaining an efficient technique in this field is essential. In this research, a new strategy has been proposed to improve the detection of diabetic retinopathy by increasing the accuracy of diagnosis and identifying cases in the initial stages. To achieve this, it has been proposed to integrate the MobileNet-V2 deep learning-based neural network with Improved Fire Hawk Optimizer (IFHO). The MobileNet-V2 network has been renowned for its efficiency and accuracy in image classification tasks, making it a suitable candidate for diabetic retinopathy detection. By combining it with the IFHO, the feature selection process has been optimized, which is essential for identifying relevant patterns and abnormalities related to diabetic retinopathy. The Diabetic Retinopathy 2015 dataset has been used to evaluate the effectiveness of the MobileNet-V2/IFHO model. The study results indicate that the DRMNV2/IFHO model consistently outperforms other methods in terms of precision, accuracy, and recall. Specifically, the model achieves an average precision of 97.521 %, accuracy of 96.986 %, and recall of 98.543 %. Moreover, when compared to advanced techniques, the DRMNV2/IFHO model demonstrates superior performance in specificity, F1-score, and AUC, with average values of 97.233 %, 93.8 %, and 0.927, respectively. These results underscore the potential of the DRMNV2/IFHO model as a valuable tool for improving the accuracy and efficiency of DR diagnosis. Nevertheless, additional validation and testing on larger datasets are required to verify the model's effectiveness and robustness in real-world clinical scenarios.

Abstract Energy loss during the transportation of energy is the main concern of researchers and industrialists. The primary cause of heat exchange gadget inefficiency during transportation was applied to traditional fluids with weak heat transfer characteristics. Instead, thermal devices worked much better when the fluids were changed to nanofluids that had good thermal transfer properties. A diverse range of nanoparticles were implemented on account of their elevated thermal conductivity. This research addresses the significance of MHD Maxwell nanofluid for heat transfer flow. The flow model comprised continuity, momentum, energy transport, and concentration equations in the form of PDEs. The developed model was converted into ODEs by using workable similarities. Numerical simulations in the MATLAB environment were employed to find the outcomes of velocity, thermal transportation, and concentration profiles. The effects of many parameters, such as Hartman, Deborah, buoyancy, the intensity of an external heat source, chemical reactions, and many others, were also evaluated. The presence of nanoparticles enhances temperature conduction. Also, the findings are compared with previously published research. In addition, the Nusselt number and skin friction increase as the variables associated with the Hartman number and buoyancy parameter grow. The respective transfer rates of heat are 28.26 $$\%$$ % and 38.19 $$\%$$ % respectively. As a result, the rate of heat transmission increased by 14.23 $$\%$$ % . The velocity profiles enhanced while temperature profiles declined for higher values of the Maxwell fluid parameter. As the external heat source increases, the temperature profile rises. Conversely, buoyancy parameters increase as it descends. This type of problem is applicable in many fields such as heat exchangers, cooling of electronic devices, and automotive cooling systems.

Affiliation Revision [...]

Transportation relies heavily on petroleum products, forcing the adoption of alternative energy sources like hydrogen. Hydrogen is considered the cleanest fuel for the twenty-first century due to its water-based combustion and no CO2 emissions. However, challenges persist in production, utilization, and storage; employing composite material-based high-pressure storage vessels is increasing in the hydrogen storage sector. The paper analyzes the impact of the winding angles on the mechanical performance of the filament wound Type 4 composite pressure vessels (CPVs) for compressed hydrogen gas storage at 70 MPa. This work examines the individual winding angles and combined angles winding patterns to promote the efficiency of Type 4 CPVs by achieving maximum burst pressure, ensuring safe burst mode, and reducing CPV weight by applying maximum principal stress theory with the aid of the Ansys ACP Prep/Post and static modules. The weight and burst pressure of CPVs are significantly influenced by fiber orientation; a combination of positive and negative helical winding angles promotes higher burst pressure at a lower weight. A hoop angle and intermediate helical angles can be combined to create high-efficiency CPVs that provide mechanical performance comparable to that of a combination of high and low helical angles. Finally, a one-factor-at-a-time (OAT) sensitivity analysis was performed to determine how the winding angle and the thicknesses of layers affect the CPVs' performance. It was found that the performance of the CPVs is significantly influenced by the thicknesses of the wound layers.

Abstract The use of renewable energy sources is leading the charge to solve the world’s energy problems, and non-Newtonian nanofluid dynamics play a significant role in applications such as expanding solar sheets, which are examined in this paper, along with the impacts of activation energy and solar radiation. We solve physical flow issues using partial differential equations and models like Casson, Williamson, and Prandtl. To get numerical solutions, we first apply a transformation to make these equations ordinary differential equations, and then we use the MATLAB-integrated bvp4c methodology. Through the examination of dimensionless velocity, concentration, and temperature functions under varied parameters, our work explores the physical properties of nanofluids. In addition to numerical and tabular studies of the skin friction coefficient, Sherwood number, and local Nusselt number, important components of the flow field are graphically shown and analyzed. Consistent with previous research, this work adds important new information to the continuing conversation in this area. Through the examination of dimensionless velocity, concentration, and temperature functions under varied parameters, our work explores the physical properties of nanofluids. Comparing the Casson nanofluid to the Williamson and Prandtl nanofluids, it is found that the former has a lower velocity. Compared to Casson and Williamson nanofluid, Prandtl nanofluid advanced in heat flux more quickly. The transfer of heat rates are $$25.87\%$$ 25.87 % , $$33.61\%$$ 33.61 % and $$40.52\%$$ 40.52 % at $$Rd =0.5, Rd=1.0$$ R d = 0.5 , R d = 1.0 , and $$Rd=1.5$$ R d = 1.5 , respectively. The heat transfer rate is increased by $$6.91\%$$ 6.91 % as the value of Rd rises from 1.0 to 1.5. This study is further strengthened by a comparative analysis with previous research, which is complemented by an extensive table of comparisons for a full evaluation.

Abstract In this paper, we study linear and nonlinear mixed convection, activation energy, and heat radiation effects caused by nanoparticles. This study aims to improve the understanding of how nanofluids behave in the presence of rotating disks and develop more efficient and effective cooling technologies. The flow problem consisted of partial differential equations (PDE). It is challenging to calculate these equations as a result of these nonlinear PDEs. Consequently, we use appropriate similarities to transform them into ordinary differential equations (ODEs). The bvp4c Matlab built-in technique is then used to resolve these ODEs. The velocities, temperature, and concentration outcomes with the various factors are examined graphically. Additionally, tables are employed to analyze the skin friction and Nusselt number values. It is analyzed that increasing the linear and linear mixed convection parameters enhances the velocity profiles of nanofluid. Enhancements in heat are analyzed by increasing nonlinear thermal radiation and enhancement in concentration is examined by increasing activation energy. Furthermore, as the variables for thermophoresis and Brownian motion are increased, the Nusselt number falls. The heat transfer rate is 27.16% for $$Rd=0.6$$ R d = 0.6 and 39.28% for $$Rd=1.4$$ R d = 1.4 . Thus, the heat transfer rate is enhanced 12.12%. This study’s practical applications include improving the behavior of fluids and the transfer of heat in rotating frameworks, which may affect energy systems, heat exchangers, and cooling advances in technology.

Abstract Hybrid nanofluids offer higher stability, synergistic effects, and better heat transfer compared to simple nanofluids. Their higher thermal conductivity, lower viscosity, and interaction with magnetic fields make them ideal for various applications, including materials science, transportation, medical technology, energy, and fundamental physics. The governing partial differential equations are numerically solved by employing a finite volume approach, and the effects of various parameters on the nanofluid flow and thermal characteristics are systematically examined from the simulations based on a self-developed MATLAB code. The parameters included magnetic field strength, the Reynolds number, the nanoparticle volume fraction, and the number and position of the strips in which the magnetic field is localized. It has been noted that the magnetized field induces the spinning of the tri-hybrid nanoparticles, which generates the intricate structure of vortices in the flow. The local skin friction (CfRe) and the Nusselt number (Nu) increase significantly when the magnetic field is intensified. Moreover, adding more nanoparticles in the flow enhances both Nu and CfRe, but with different effects for different nanoparticles. Silver (Ag) shows the highest increase in both Nu (52%) and CfRe (110%), indicating strong thermal-fluid coupling. Alumina (Al2O3) and Titanium Dioxide (TiO2) show lower increases in both Nu (43% and 34%) and CfRe (14% and 10%), indicating weaker coupling in the flow. Finally, compared with the localized one, the uniform magnetic field has a minor effect on the flow and temperature distributions.

Abstract This investigation relates to the research on Hall current on propagation and reflection of elastic waves through non-local fractional-order thermoelastic rotating medium with voids. The system is split up into longitudinal and transverse components using the Helmholtz vector rule. It is observed that, through the frequency dispersion relation four coupled quasi-waves exist in the medium. The rotating solid modifies the nature of purely longitudinal and transverse waves toward the quasi-type waves. All the propagating waves are dispersive as they depend upon angular frequency. The quasi-longitudinal wave qP and quasi-transverse wave qSV faces cut-off frequencies. The nonlocal parameter affect all the waves except the quasi void wave. Analytically, the reflection coefficients of the wave are computed using suitable boundary conditions. MATLAB software is used to perform numerical computations for a chosen solid material. The amplitude ratios and the speed of propagation of the wave are plotted graphically for rotational frequency, nonlocal, fractional order, and Hall current parameter. The significant effect of the physical parameters on the computed results has been observed. The cut-off frequency of the waves is also presented graphically. The energy conservation law is proved in the form of energy ratios. The earlier findings in the literature are obtained as special case in the absence of rotation, Hall current parameter and porous voids.

The construction industry's rapid growth poses challenges tied to raw material depletion and increased greenhouse gas emissions. To address this, alternative materials like agricultural residues are gaining prominence due to their potential to reduce carbon emissions and waste generation. In this context this research optimizes the use of banana leaves ash as a partial cement substitution, focusing on durability, and identifying the ideal cement-to-ash ratio for sustainable concrete. For this purpose, concrete mixes were prepared with BLA replacing cement partially in different proportions i.e. (0 %, 5 %, 10 %, 15 %, & 20 %) and were analyzed for their physical, mechanical and Durability (Acid and Sulphate resistance) properties. Compressive strength, acid resistance and sulphate resistance testing continued for 90 days with the intervals of 7, 28 and 90 days. The results revealed that up to 10 % incorporation of BLA improved compressive strength by 10 %, while higher BLA proportions (up to 20 %) displayed superior performance in durability tests as compared to the conventional mix. The results reveal the potentials of banana leave ash to refine the concrete matrix by formation of addition C–S–H gel which leads towards a better performance specially in terms of durability aspect. Hence, banana leaf ash (BLA) is an efficient concrete ingredient, particularly up to 10 % of the mix. Beyond this threshold, it's still suitable for applications where extreme strength isn't the primary concern, because there may be a slight reduction in compressive strength.

Nonlinear evolution equations are employed in the representation of diverse intricate physical events, and the identification of precise solutions for these equations holds significance about their practical implementations. One of the significant challenges is the identification of traveling wave solutions inside established nonlinear evolution systems in the field of mathematical physics. In the present research, we employ the modified sub-equation approach, a very effective and strong technique, to ensure the solutions for the Klein–Gordon featuring cubic nonlinearity and Zakharov Kuznetsov–Benjamin Bona Mahony equations. Several restriction requirements that ensure the existence of these solutions are emphasized. By employing a linearization technique, we ascertain the stability gain. This methodology acquires original precise solutions of soliton nature. Furthermore, the nonlinear wave structures of both equations are illustrated through the consideration of several three-dimensional and two-dimensional plots. These plots are generated by selecting appropriate values for the parameters. It is expected that these innovative solutions would facilitate an in-depth understanding of the evolution and fluidity of these models. The solutions obtained comprise periodic functions, mixed periodic functions, rational solutions, and exponential solutions.

The creation and manipulation of synthetic images have evolved rapidly, causing serious concerns about their effects on society. Although there have been various attempts to identify deep fake videos, these approaches are not universal. Identifying these misleading deepfakes is the first step in preventing them from spreading on social media sites. We introduce a unique deep-learning technique to identify fraudulent clips. Most deepfake identifiers currently focus on identifying face exchange, lip synchronous, expression modification, puppeteers, and other factors. However, exploring a consistent basis for all forms of fake videos and images in real-time forensics is challenging. We propose a hybrid technique that takes input from videos of successive targeted frames, then feeds these frames to the ResNet-Swish-BiLSTM, an optimized convolutional BiLSTM-based residual network for training and classification. This proposed method helps identify artifacts in deepfake images that do not seem real. To assess the robustness of our proposed model, we used the open deepfake detection challenge dataset (DFDC) and Face Forensics deepfake collections (FF++). We achieved 96.23% accuracy when using the FF++ digital record. In contrast, we attained 78.33% accuracy using the aggregated records from FF++ and DFDC. We performed extensive experiments and believe that our proposed method provides more significant results than existing techniques.

This paper investigates the (n+1) dimensional integrable extension of the Kadomtsev–Petviashvili (KP) equation. The study focuses on extracting Auto-Bäcklund transformations for the given model using the extended homogeneous balance (HB) method in conjunction with Maple. These transformations are then employed to obtain explicit analytic solutions for the equation. Additionally, a Bilinear Bäcklund transformation is constructed based on the Hirota bilinear form, leading to the acquisition of exponential function solutions. Furthermore, complexiton solutions for the KP equation are obtained utilizing the bilinear form and the extended transformed rational function technique. The physical properties of the obtained solutions are explored through visualization techniques, including 3D, 2D, and contour plots. The analysis reveals the presence of dark, bright, and periodic solitons. The obtained solutions of the KP equation have practical applications in nonlinear optics, plasma physics, and wave propagation analysis.

Considering that it satisfies high strength and stiffness at a low weight, the grid structure is the ideal option for meeting the requirements for developing the wall panel structure for the satellite. The most attractive grid structures for the satellite wall panel industry are isogrid and honeycomb structures. The first part of this work involves studying the mechanical and dynamic performance of five designs for the satellite wall panel made of 7075-T0 Al-alloy. These designs include two isogrid structures with different rib widths, two honeycomb structures with different cell wall thicknesses, and a solid structure for comparison. The performance of these designs was evaluated through compression, bending, and vibration testing using both finite element analysis (FEA) with the Ansys workbench and experimental testing. The FEA results are consistent with the experimental ones. The results show that the isogrid structure with a lower rib thickness of 2 mm is the best candidate for manufacturing the satellite wall panel, as this design reveals the best mechanical and dynamic performance. The second part of this work involves studying the influence of the length of the sides of the best isogrid structure in the range of 12 mm–24 mm on its mechanical and dynamic performance to achieve the lowest possible mass while maintaining the structure’s integrity. Then, a modified design of skinned wall panels was introduced and dynamically tested using FEA. Finally, a CAD model of a hexagonal satellite prototype using the best-attained design of the wall panel, i.e., the isogrid structure with a 2 mm rib width and 24 mm-long sides, was built and dynamically tested to ensure its safe design against vibration. Then, the satellite prototype was manufactured, assembled, and successfully assessed.

Estimating design factors like concrete strength and durability is complicated by the cement industry's practice of producing multiple grades of cement for different uses, necessitating substantial labor hours and monetary investment. The experimental findings of accelerated carbonation-induced corrosion and associated durability characteristics of concrete built with high-volume Class F Fly Ash (FA), including AC impendence, half-cell potential, water permeability, and volume of permeable voids. FA was added to ordinary portland cement at varied replacement amounts (0–70%) to create concrete specimens. The concrete specimen has been prepared by varying different proportions of water cement ratio (0.45, 0.40, and 0.35). To predict the compressive strength and carbonation level of concrete, this study presents a simulation environment based on Artificial Intelligence (AI) that makes use of input parameters such as water/cement ratio, fly-ash percentage, and time duration. Here, One-Dimensional Convolution Neural Network based Long Short-Term Memory (1D-CNN-LSTM) has been proposed for estimating the carbonation depth and compressive strength of concrete. The developed model will be compared with other state-of-the-art techniques, including DL and ML-based techniques. The obtained R2 values from the proposed 1D-CNN-LSTM regression network deliver accuracy of 80% for estimating carbonation depth and 96% for predicting compressive strength. The proposed methodology demonstrates the use of modern AI-based techniques in the actual design model and illustrates the development of DL methods such as LSTM and CNN.

Cement is the main constituent of the concrete structure. Using rejected brick as pozzolana in replacement of cement reduced the utilization of natural resources, conserved the environment, and controlled waste disposal. Hydrated lime has been utilized as a chemical additive to improve the pozzolanic reaction of finely ground waste brick particles. This research investigates the process of biomineralization to enhance the strength and durability characteristics of bacterial concrete incorporating hydrated lime and brick powder (HBr). In this context, cement was partially replaced with HBr in different proportions 10%, 20%, and 30% by weight. Furthermore, the HBr mixtures were meticulously prepared with and without the incorporation of Bacillus subtilis. Tests for strength and durability were performed at the age of 28 and 56 days of concrete. The self-healing proficiency of the bacterial concrete was evaluated through compressive strength, water permeability, and chloride penetration, while the microstructure analysis was conducted using field emission scanning electron microscopy (FESEM) and energy dispersive spectroscopy (EDS). The results show that at the age of 56 days, CaCO3 precipitation caused by Bacillus subtilis increases the compressive strength of BHBr10 by 19.07%. The durability properties in terms of chloride ion penetrability and water permeability exhibited substantial improvements of 40.03% and 61.9% respectively. Additionally, the FESEM micrographs along with the EDS analysis corroborated the presence of CaCO3 precipitation crystals.

This study background highlights the increasing need for effective management of risks in tall buildings due to their complexity and potential hazards. BIM has been accepted as a potential solution for management of risks in tall buildings; however, its adaptation has been slow due to several obstacles. The purpose of this study is to identify and validate the impediments to the adaptation of BIM for management of risks. The study adopted a two-step methodology, consisting of exploratory factor analysis (EFA) and structural equation modelling (SEM). The data were collected through an online survey of professionals involved in design, construction, and management. Results of the study reveal six significant impediments: technical, integration, operational, creativity, privacy, and standardization. The findings provide theoretical contributions to the literature by identifying and validating the impediments to adaptation of BIM for risks in tall buildings. Practical implications suggest that organizations involved in design, construction, and management of tall buildings need to address the identified impediments to ensure successful adaptation of BIM for management of risks. This study contributes to the understanding of the obstacles to the adaptation of BIM for management of risks in tall buildings and provides insights for organizations to overcome these impediments.

Reinforced thermoplastic pipes (RTPs) are instantly being broadly scrutinized as a feasible surrogate for metallic pipes due to their superior corrosion resistance, low weight, and low maintenance worth, they have three primary layers inner, outer, and reinforcement. Process parameters for manufacturing reinforced layers are critically essential to enhancing the mechanical performance of RTPs. However, limited comparative research on the impact of braiding parameters on RTP’s mechanical characteristics appears to be publicly available. Therefore, this study examines how these variables affect the mechanical characteristics of braid RTP. This new class of braid RTP is constructed of an HDPE liner pipe, over-wrapped with a single braid layer of resin glass fiber. L9 Taguchi orthogonal array design for experiments was used to create specimens. Furthermore, specimens were subjected to tensile and compression to assess their mechanical properties. Epoxy and ±75 were the most promising parameters in achieving the highest number of tensile and compression properties among choices of thermoplastic polymer matrices and braid angles, respectively. ANOVA suggested that both parameters are significant and significantly impact the mechanical properties of the prototype braid RTP. Also, A1B3 is considered the best combination for producing braid RTP with higher mechanical performance; no notable interaction among factors was found.

Purpose: The aim of this research is to investigate the factors that facilitate the adoption of artificial intelligence (AI) in order to establish effective human resource management (HRM) practices within the Indian pharmaceutical sector.Design/methodology/approach: A model explaining the antecedents of AI adoption for building effective HRM practices in the Indian pharmaceutical sector is proposed in this study. The proposed model is based on task-technology fit theory. To test the model, a two-step procedure, known as partial least squares structural equational modeling (PLS-SEM), was used. To collect data, 160 HRM employees from pharmacy firms from pan India were approached. Only senior and specialized HRM positions were sought.Findings: An examination of the relevant literature reveals factors such as how prepared an organization is, how people perceive the benefits, and how technological readiness influences AI adoption. As a result, HR systems may become more efficient. The PLS-SEM data support all the mediation hypothesized by proving both full and partial mediation, demonstrating the accuracy of the proposed model.Originality: There has been little prior research on the topic; this study adds a great deal to our understanding of what motivates human resource departments to adopt AI in the pharmaceutical companies of India. Furthermore, AI-related recommendations are made available to HRM based on the results of a statistical analysis.

The findings of the experimental study into optimizing the heat transfer rate of a PCM-based heat sink for high-power LEDs are presented in this work. The study investigated five heat sink types, with and without PCM. The LED case and junction temperatures, LED module temperatures, heat storage and release rate analyses, analyses of three types of cyclic operation modes, luminous flux, and heat sink thermal resistance were all examined independently. The results indicated that the PCM-based LED heat sink had improved thermal performance. The LED junction temperature of the PCM-equipped E-20 heat sink is nine degrees Celsius lower at 10 W than that of the heat sink without PCM. Furthermore, the E-20 heat sink with PCM extends the LED module’s critical lifespan. As a bonus, the E-20 with PCM had a 38.19 percent lower thermal resistance at 10 W than the E-20 without PCM. According to these results, the heat sink E-20 emits 715 lm at 10 W when operated without a phase-change material (PCM). With the same input power, the luminous flux of an E-20 equipped with a heat sink and a phase-change material (PCM) is 750 lm, a gain of 4.7%. Finally, clearly recommend the heat E-20 sink with PCM suitable for high-power LED thermal management system.

Fibrous concrete has good properties such as high ductility, high strength, suitable energy absorption and cracking resistance, which can be useful in many applications. This type of concrete is one of the best materials used in the construction of impact-resistant masonries, such as burial masonry structures, and explosive masonry warehouses. In this study, an artificial intelligence assessment based on the experimental test data from a laboratory has been performed on the fibrous concrete to evaluate the behavior of the samples at elevated temperatures and determine the most governing parameter on the mechanical properties of the fibrous concrete at elevated temperatures. For the first time, a hybrid intelligence algorithm has been developed based on the neural network structure using both genetic and swarm optimization algorithms. The ANFIS-PSO-GA (APG) algorithm was trained with experimental data and evaluated the flexural load and deflection of the samples. In order to detect the most prominent feature in the fire resistance of the fibrous concrete, five different subdatasets were designed. The results of the APG algorithm have been challenged with the ANFIS-PSO algorithm, which is a well-known hybrid numerical evaluation algorithm. As per the results, the newly designed APG algorithm has been successfully performed on both deflection and flexural prediction phases. Based on the numerical achievements, fiber features such as the fiber content and fiber mechanical properties are governing factors on the fibrous concrete resistance at elevated temperatures.

Esophagitis, cancerous growths, bleeding, and ulcers are typical symptoms of gastrointestinal disorders, which account for a significant portion of human mortality. For both patients and doctors, traditional diagnostic methods can be exhausting. The major aim of this research is to propose a hybrid method that can accurately diagnose the gastrointestinal tract abnormalities and promote early treatment that will be helpful in reducing the death cases. The major phases of the proposed method are: Dataset Augmentation, Preprocessing, Features Engineering (Features Extraction, Fusion, Optimization), and Classification. Image enhancement is performed using hybrid contrast stretching algorithms. Deep Learning features are extracted through transfer learning from the ResNet18 model and the proposed XcepNet23 model. The obtained deep features are ensembled with the texture features. The ensemble feature vector is optimized using the Binary Dragonfly algorithm (BDA), Moth–Flame Optimization (MFO) algorithm, and Particle Swarm Optimization (PSO) algorithm. In this research, two datasets (Hybrid dataset and Kvasir-V1 dataset) consisting of five and eight classes, respectively, are utilized. Compared to the most recent methods, the accuracy achieved by the proposed method on both datasets was superior. The Q_SVM’s accuracies on the Hybrid dataset, which was 100%, and the Kvasir-V1 dataset, which was 99.24%, were both promising.

This paper investigated the influence of cutting parameters, including feed rate, cutting speed, tool nose radius, and wet or dry cutting conditions, on the resultant force, cutting edge/workpiece temperature, and surface roughness when turning grey cast iron. Results showed that increasing the feed rate increased the resultant force, cutting temperature, and surface roughness. At the same time, increasing the cutting speed and nose radius increased the cutting temperature, which in turn reduced the resultant force. For practical applications, basic mathematical calculations based on the sole effect of each parameter on the output of the experiments were used to estimate the extent of percentage increase in cutting temperature due to increasing feed rate, cutting speed, and nose radius. Similarly, the same approach was used to estimate the effect of increasing feed rate, cutting speed, and nose radius on average surface roughness. Results showed that increasing the feed rate increases the cutting temperature by 5 to 11% depending on the nose radius and cutting speed. On the other hand, increasing the cutting speed was found to have limited effect on cutting temperature with small nose radius whereas this effect increases with increasing the nose radius reaching about 11%. Increasing the nose radius also increases the cutting temperature, depending mainly on cutting speed, reaching a maximum of 21% at higher cutting speeds. Results also showed that increasing the feed rate increased the average surface roughness considerably to about 120% at high cutting speeds and a large nose radius. On the other hand, increasing the cutting speed and nose radius reduced the surface roughness (i.e., improved surface quality) by a maximum of 29 and 23%, respectively. In order to study the combined effects of the cutting parameters on the three responses, namely, the resultant cutting force, cutting temperature, and surface roughness, full factorial design and ANOVA were used, where it was found to be in good agreement with mathematical calculations. Additionally, the desirability function optimization tool was used to minimize the measured responses whilst maximizing the material removal rate.

Research on multi-pass hot processing of 7075 Al-alloy was rarely discussed. This study aims to design and evaluate different thermomechanical processing strategies (TMPS) to produce 3 mm-thick sheets of 7075 Al-alloy. A physical simulation was performed using the hot compression test of a Gleeble 3500 to study flow mechanisms and microstructural evolution, while an experimental investigation was carried out using a rolling mill to examine the effect of TMPS on the mechanical properties. Four hot forming strategies were designed and tested at a constant strain rate of 0.1 s−1 over a temperature range of 200–450 °C. These strategies involved applying a constant amount of deformation of 65–70% in single (SP), double (DP), triple (TP), and quadruple (QP) passes of thermomechanical processing to study the influence of multi-pass thermomechanical processing on the final mechanical properties and industrial feasibility. The microstructure analysis showed a significant refinement and more uniform distribution of precipitates with an increasing number of passes, as observed through optical micrographs and the full width at half maximum (FWHM)-position relationship of XRD data. The results indicate that QP is the optimum strategy for producing the best mechanical properties in the shortest production time.

Red, blue, white, pink, or black spots with irregular borders and small lesions on the skin are known as skin cancer that is categorized into two types: benign and malignant. Skin cancer can lead to death in advanced stages, however, early detection can increase the chances of survival of skin cancer patients. There exist several approaches developed by researchers to identify skin cancer at an early stage, however, they may fail to detect the tiniest tumours. Therefore, we propose a robust method for the diagnosis of skin cancer, namely SCDet, based on a convolutional neural network (CNN) having 32 layers for the detection of skin lesions. The images, having a size of 227 × 227, are fed to the image input layer, and then pair of convolution layers is utilized to withdraw the hidden patterns of the skin lesions for training. After that, batch normalization and ReLU layers are used. The performance of our proposed SCDet is computed using the evaluation matrices: precision 99.2%; recall 100%; sensitivity 100%; specificity 99.20%; and accuracy 99.6%. Moreover, the proposed technique is compared with the pre-trained models, i.e., VGG16, AlexNet, and SqueezeNet and it is observed that SCDet provides higher accuracy than these pre-trained models and identifies the tiniest skin tumours with maximum precision. Furthermore, our proposed model is faster than the pre-trained model as the depth of its architecture is not too high as compared to pre-trained models such as ResNet50. Additionally, our proposed model consumes fewer resources during training; therefore, it is better in terms of computational cost than the pre-trained models for the detection of skin lesions.

Fruit is an essential element of human life and a significant gain for the agriculture sector. Guava is a common fruit found in different countries. It is considered the fourth primary fruit in Pakistan. Several bacterial and fungal diseases found in guava fruit decrease production daily. Leaf Blight is a common disease found in guava fruit that affects the growth and production of fruit. Automatic detection of leaf blight disease in guava fruit can help avoid decreases in its production. In this research, we proposed a CNN-based deep model named SidNet. The proposed model contains thirty-three layers. We used a guava dataset for early recognition of leaf blight, which consists of two classes. Initially, the YCbCr color space was employed as a preprocessing step in detecting leaf blight. As the original dataset was small, data augmentation was performed. DarkNet-53, AlexNet, and the proposed SidNet were used for feature acquisition. The features were fused to get the best-desired results. Binary Gray Wolf Optimization (BGWO) was used on the fused features for feature selection. The optimized features were given to the variants of SVM and KNN classifiers for classification. The experiments were performed on 5- and 10-fold cross validation. The highest achievable outcomes were 98.9% with 5-fold and 99.2% with 10-fold cross validation, confirming the evidence that the identification of Leaf Blight is accurate, successful, and efficient.

The Human Activity Recognition (HAR) system is the hottest research area in clinical research. The HAR plays a vital role in learning about a patient’s abnormal activities; based upon this information, the patient’s psychological state can be estimated. An epileptic seizure is a neurological disorder of the human brain and affects millions of people worldwide. If epilepsy is diagnosed correctly and in an early stage, then up to 70% of people can be seizure-free. There is a need for intelligent automatic HAR systems that help clinicians diagnose neurological disorders accurately. In this research, we proposed a Deep Learning (DL) model that enables the detection of epileptic seizures in an automated way, addressing a need in clinical research. To recognize epileptic seizures from brain activities, EEG is a raw but good source of information. In previous studies, many techniques used raw data from EEG to help recognize epileptic patient activities; however, the applied method of extracting features required much intensive expertise from clinical aspects such as radiology and clinical methods. The image data are also used to diagnose epileptic seizures, but applying Machine Learning (ML) methods could address the overfitting problem. In this research, we mainly focused on classifying epilepsy through physical epileptic activities instead of feature engineering and performed the detection of epileptic seizures in three steps. In the first step, we used the open-source numerical dataset of epilepsy of Bonn university from the UCI Machine Learning repository. In the second step, data were fed to the proposed ELM model for training in different training and testing ratios with a little bit of rescaling because the dataset was already pre-processed, normalized, and restructured. In the third step, epileptic and non-epileptic activity was recognized, and in this step, EEG signal feature extraction was automatically performed by a DL model named ELM; features were selected by a Feature Selection (FS) algorithm based on ELM and the final classification was performed using the ELM classifier. In our presented research, seven different ML algorithms were applied for the binary classification of epileptic activities, including K-Nearest Neighbor (KNN), Naïve Bayes (NB), Logistic Regression (LR), Stochastic Gradient Boosting Classifier (SGDC), Gradient Boosting Classifier (GB), Decision Trees (DT), and three deep learning models named Extreme Learning Machine (ELM), Long Short-Term Memory (LSTM), and Artificial Neural Network (ANN). After deep analysis, it is observed that the best results were obtained by our proposed DL model, Extreme Learning Machine (ELM), with an accuracy of 100% accuracy and a 0.99 AUC. Such high performance has not attained in previous research. The proposed model’s performance was checked with other models in terms of performance parameters, namely confusion matrix, accuracy, precision, recall, F1-score, specificity, sensitivity, and the ROC curve.

This article presents an experimental investigation and statistical analysis of the effects of cutting conditions on the machining performance of AISI 1045 steel using a wiper-shaped insert. Experimental findings are used to compare the machining performance obtained using wiper inserts with those obtained using conventional round-nose inserts as recently reported in the literature. In addition, the effects of process conditions, namely cutting speed, feed rate, and depth of cut, are analyzed in order to obtain optimum conditions for both types of inserts. The goal is to achieve the optimal machining outcomes: minimum surface roughness, resultant cutting force, and cutting temperature, but maximum material removal rate. A full factorial design was followed to conduct the experimental trials, while ANOVA was utilized to estimate the effect of each factor on the process responses. A desirability function optimization tool was used to optimize the studied responses. The results reveal that the optimum material removal rate for wiper-shaped inserts is 67% more than that of conventional inserts, while maintaining a 0.7 µm surface roughness value. The superior results obtained with wiper-shaped inserts allow wiper tools to use higher feed rates, resulting in larger material removal rates while obtaining the same surface quality.

Incremental sheet forming (ISF) requires no or partial dies for sheet metal fabrication and is widely used for small batch production. In this process, necking is either suppressed or delayed due to the localized nature of tool–sheet contact; hence, more strains than conventional stamping and deep drawing are obtained. In the present study, two variations of ISF, namely cold ISF (CISF) and warm ISF (WISF), are compared. First, FEA modeling is carried out on ABAQUS to reach the forming forces involved in the process. It is found that WISF reduces the forming forces. The temperature for WISF is maintained at 180 °C. Following the simulation analysis, tests are carried out. The forming force in WISF is 55.77% less than that in CISF. The part fabricated by CISF is slightly more substantial than that by WISF; however, more forming depth can be achieved by WISF. There is a more uniform thickness distribution in the case of CISF than in WISF. However, the surface quality of the CISF product is inferior to that of WISF. It is observed that there is reduced forming force, increased formability, and better strain distribution in WISF compared to CISF. However, post-processing heat treatment and surface polishing of the formed parts is required to restore their mechanical properties.

Single-point incremental forming is an innovative flexible and inexpensive technique to form sheet products when prototypes or small batches are required. The process allows complex geometries to be produced using a computer numerical control machine, eliminating the need for a special die. This study reports on the effects of four important single-point incremental forming process parameters on produced surface profile accuracies. The profile accuracy was estimated by measuring the side angle errors and surface roughness and also waviness and circularity of the product inner surface. Full factorial design of experiments was used to plan the study, and the analysis of variance was used to analyze and interpret the results. The results indicate that the tool diameter (d), step depth (s), and sheet thickness (t) have significant effects on the produced profile accuracy, while the feed rate (f) is not significant. As a general rule, thin sheets with greater tool diameters yielded the best surface quality. The results also show that controlling all surface quality features is complex because of the contradicting effects of, and interactions between, a number of the process parameters.

Thin structures are often required for several engineering applications. Although thick sections are relatively easy to produce, the cutting of thin sections poses greater challenges, particularly in the case of thermal machining processes. The level of difficulty is increased if the thin sections are of larger lengths and heights. In this study, high-aspect-ratio thin structures of micrometer thickness (117–500 µm) were fabricated from D2 steel through wire electrical discharge machining. Machining conditions were kept constant, whereas the structure (fins) sizes were varied in terms of fin thickness (FT), fin height (FH), and fin length (FL). The effects of variation in FT, FH, and FL were assessed over the machining errors (FT and FL errors) and structure formation and its quality. Experiments were conducted in a phased manner (four phases) to determine the minimum possible FT and maximum possible FL that could be achieved without compromising the shape of the structure (straight and uniform cross-section). Thin structures of smaller lengths (1–2 mm long) can be fabricated easily, but, as the length exceeds 2 mm, the structure formation loses its shape integrity and the structure becomes broken, deflected, or deflected and merged at the apex point of the fins.

Arsenite (As(III)) and Selenate (Se(VI)) are universally touted as extremely toxic oxyanions in natural and industrial water systems. Thus, the production of low-cost adsorbents that are scalable and toxic-free is of great importance today. In this work, a large-scale goethite nanorods (α-FeOOH NRs) is synthesized using a modified rapid hydrolysis method. The obtained powder is characterized using different multidisciplinary techniques. Accordingly, the results showed uniform and straight nanorods (length ~400 nm and diameter ~40 nm) resembling cigar-like morphology while the structure is confirmed to be of orthorhombic α-FeOOH phase. The potential application of this material to adsorb As (III) and Se (VI) ions in water is explored. In particular, for initial adsorbate concentrations (~500 µg/L), the removal efficiencies are found exceptional with α-FeOOH doses of 0.33 g/L and ~0.5 g/L for As (III) and Se (VI), respectively. Attractively, the adsorption capacities were estimated using trusted isotherms and then experimentally verified at ultimately high concentrations. Besides, a pH-controlled adsorption study showed that a pH of 5–8 is a favored range for higher ionic uptake, which meets the World Health Organization (WHO) benchmarks of drinking water. To conclude, the α-FeOOH NRs are potential adsorbent for the sustainable removal of toxin ions in water systems.

All manufacturing engineers are faced with a lot of difficulties and high expenses associated with grinding processes of AZ61. For that reason, manufacturing engineers waste a lot of time and effort trying to reach the required surface roughness values according to the design drawing during the turning process. In this paper, an artificial neural network (ANN) modeling is used to estimate and optimize the surface roughness (Ra) value in cutting conditions of AZ61 magnesium alloy. A number of ANN models were developed and evaluated to obtain the most successful one. In addition to ANN models, traditional regression analysis was also used to build a mathematical model representing the equation required to obtain the surface roughness. Predictions from the model were examined against experimental data and then compared to the ANN model predictions using different performance criteria such as the mean absolute error, mean square error, and coefficient of determination.

AISI 1045 has been widely used in many industrial applications requiring good wear resistance and strength. Surface roughness of produced components is a vital quality measure. A suitable combination of machining process parameters must be selected to guarantee the required roughness values. The appropriate parameters are generally defined based on ideal lab conditions since most of the researchers conduct their experiments in closed labs and ideal conditions. However, when repeating these experiments in industrial workshops, different results are obtained. Imperfect conditions such as the absence of a turning tool with definite specifications as shown in know-how “tool nose radius 0.4 mm” and its replacement with the closest existence tool “tool nose radius 0.8 mm” as well as the interruption of cutting fluid during work as a result of sudden failure in the coolant pump lead to the mentioned different lab-industrial conditions. These complications are common among normal problems that happened during the metal cutting process in realistic conditions and are called noise factors. In this paper, Taguchi robust design is used to select the optimum combination of the cutting speed, depth of cut, and feed rate to enhance the surface roughness of turned AISI 1045 steel bars while minimizing the effects of the two noise factors. The optimum parameters predicted by the developed model showed good agreement with the experimental results.

Iron−nickel based ultra-high strength steel (wt. 18~20% Ni) is characterized by its high strength and low thermal conductivity, and is normally used to make key components by forming and machining processes. The optimization of these processes is based on a deep understanding of the mechanical and dynamic behaviors under high strain, high strain rate, and high temperature. In this paper, the relationship of stress to strain, strain rate, and temperature is systematically investigated by the dynamic compression tests combined with quasi-static compression tests, and the hardening and softening is associated with the transformation in microstructures. According to the analysis, dynamic recrystallization around 600 °C is assumed to be one important influencing factor, hence hot deformation equations are established and the critical strain for dynamic recrystallization and the volume fraction of the dynamic recrystallized grains are defined.

In this paper artificial neural network (ANN) and regression analysis were used for the prediction of surface roughness. Five models of neural network were developed and the model that showed best fit with experimental results was with 6 neurons in the hidden layer. Regression analysis was also used to build a mathematical model representing the surface roughness as a function of the process parameters. The coefficient of determination was found to be 94.93% and 93.63%, for the best neural network model and regression analysis, respectively, from the comparison of the models with thirteen validation experimental tests. Optical microscopy was conducted on two machined surfaces with two different values of feed rates while maintaining the spindle speed and depth of cut at the same values. Examining the surface topology and surface roughness profile for the two surfaces revealed that higher feed rate results in relatively thick roughness markings that are distantly spaced, whereas low values of feed rate result in thin surface roughness markings that are closely spaced giving better surface finish.

The Grade-H high strength steel is used in the manufacturing of many civilian and military products. The procedures of manufacturing these parts have several turning operations. The key factors for the manufacturing of these parts are the accuracy, surface roughness (Ra), and material removal rate (MRR). The production line of these parts contains many CNC turning machines to get good accuracy and repeatability. The manufacturing engineer should fulfill the required surface roughness value according to the design drawing from first trail (otherwise these parts will be rejected) as well as keeping his eye on maximum metal removal rate. The rejection of these parts at any processing stage will represent huge problems to any factory because the processing and raw material of these parts are very expensive. In this paper the artificial neural network was used for predicting the surface roughness for different cutting parameters in CNC turning operations. These parameters were investigated to get the minimum surface roughness. In addition, a mathematical model for surface roughness was obtained from the experimental data using a regression analysis method. The experimental data are then compared with both the regression analysis results and ANFIS (Adaptive Network-based Fuzzy Inference System) estimations.