Search

Abstract This research focuses on utilizing injection moulding to assess defects in plastic products, including sink marks, shrinkage, and warpages. Process parameters, such as pure cooling time, mould temperature, melt temperature, and pressure holding time, are carefully selected for investigation. A full factorial design of experiments is employed to identify optimal settings. These parameters significantly affect the physical and mechanical properties of the final product. Soft computing methods, such as finite element (FE), help mitigate behaviour by considering different input parameters. A CAD model of a dashboard component integrates into an FE simulation to quantify shrinkage, warpage, and sink marks. Four chosen parameters of the injection moulding machine undergo comprehensive experimental design. Decision tree, multilayer perceptron, long short-term memory, and gated recurrent units models are explored for injection moulding process modelling. The best model estimates defects. Multiple objectives particle swarm optimisation extracts optimal process parameters. The proposed method is implemented in MATLAB, providing 18 optimal solutions based on the extracted Pareto-Front.

Abstract This work implements the recently developed nth state Markovian jumping particle swarm optimisation (PSO) algorithm with local search (NS-MJPSOloc) awareness method to address the economic/environmental dispatch (EED) problem. The proposed approach, known as the Non-dominated Sorting Multi-objective PSO with Local Best (NS-MJPSOloc), aims to enhance the performance of the PSO algorithm in multi-objective optimisation problems. This is achieved by redefining the concept of best local candidates within the search space of multi-objective optimisation. The NS-MJPSOloc algorithm uses an evolutionary factor-based mechanism to identify the optimum compromise solution, a Markov chain state jumping technique to control the Pareto-optimal set size, and a neighbourhood’s topology (such as a ring or a star) to determine its size. Economic dispatch refers to the systematic allocation of available power resources in order to fulfill all relevant limitations and effectively meet the demand for electricity at the lowest possible operating cost. As a result of heightened public consciousness regarding environmental pollution and the implementation of clean air amendments, nations worldwide have compelled utilities to adapt their operational practises in order to comply with environmental regulations. The (NS-MJPSOloc) approach has been utilised for resolving the EED problem, including cost and emission objectives that are not commensurable. The findings illustrate the efficacy of the suggested (NS-MJPSOloc) approach in producing a collection of Pareto-optimal solutions that are evenly dispersed within a single iteration. The comparison of several approaches reveals the higher performance of the suggested (NS-MJPSOloc) in terms of the diversity of the Pareto-optimal solutions achieved. In addition, a measure of solution quality based on Pareto optimality has been incorporated. The findings validate the effectiveness of the proposed (NS-MJPSOloc) approach in addressing the multi-objective EED issue and generating a trade-off solution that is both optimal and of high quality. We observed that our approach can reduce $$\sim $$ ∼ 6.4% of fuel costs and $$\sim $$ ∼ 9.1% of computational time in comparison to the classical PSO technique. Furthermore, our method can reduce $$\sim $$ ∼ 9.4% of the emissions measured in tons per hour as compared to the PSO approach.

Medical ultrasound is a widely used diagnostic imaging modality that provides real-time imaging at a relatively low cost. However, its widespread application is hindered by the need for expert operation, particularly in remote regional areas where trained sonographers are scarce. This paper presents the development of HaptiScan, a state-of-the-art telerobotic ultrasound system equipped with haptic feedback. The system utilizes a commercially available robotic manipulator, the UR5 robot from Universal Robots, integrated with a force/torque sensor and the Phantom Omni haptic device. This configuration enables skilled sonographers to remotely conduct ultrasound procedures via an internet connection, addressing both the geographic and ergonomic limitations faced in traditional sonography. Key innovative features of the system include real-time force feedback, ensuring that sonographers can precisely control the ultrasound probe from a remote location. The system is further enhanced by safety measures such as over-force sensing, patient discomfort monitoring, and emergency stop mechanisms. Quantitative indicators of the system’s performance include successful teleoperation over long distances with time delays, as demonstrated in simulations. These simulations validate the system’s control methodologies, showing stable performance with force feedback under varying time delays and distances. Additionally, the UR5 manipulator’s precision, kinematic, and dynamic models are mathematically formulated to optimize teleoperation. The results highlight the effectiveness of the proposed system in overcoming the technical challenges of remote ultrasound procedures, offering a viable solution for real-world telemedicine applications.

Researchers are turning to nanofluids in PV/T hybrid systems for enhanced efficiency due to nanoparticle dispersion, improving thermal and optical properties over conventional fluids. Three different concentrations of formulated soybean oil based MXene nanofluids are considered 0.025, 0.075 and 0.125 wt.%. Maximum specific heat capacity nanofluids ( $c_{pNF}$ ) augmentation is 24.49% at 0.125 wt.% loading of Ti3C2 in the base oil. The calculation of the $c_{pNF}$ based on the temperature and nanoflakes concentration is very expensive and time-consuming as it should be calculated via the practical test investigation. This study employs a long short-term memory (LSTM) as an efficient machine learning method to extract the surrogate model for calculating the $c_{pNF}$ based on the temperature and nanoflakes concentration. In addition, a couple of other machines learning methods, including support vector regression (SVR), group method of data handling (GMDH), and multi-layer perceptron (MLP), are developed to prove the higher efficiency of the recently proposed LSTM model in the calculation of the $c_{pNF}$ . In addition, the Bayesian optimization technique is employed to calculate the optimal hyperparameters of the developed SVR, GMDH, MLP and LSTM to reach the highest efficiency of the system in predicting the $c_{pNF}$ based on temperature and nanoflakes concentration. Notably, 95% of the recorded data via differential scanning calorimetry (DSC) is used for training machine learning techniques. In comparison, 5% is used for testing and validation purposes of the developed algorithm. The newly proposed optimized SVR, GMDH, MLP, and LSTM are modelled in MATLAB software. The results show that the newly proposed optimized LSTM model can reduce the mean square error in calculating the $c_{pNF}$ by 99%, 99% and 91% compared with SVM, GMDH and MLP, respectively. The proposed methodology can be used to calculate other thermophysical properties of nanofluids.

With an increase in the number of processing cores or systems, the high-performance edge-computing system’s power consumption along with its computational speed will increase, essentially. However, this comes at the expense of high-energy utilization. One notable solution to reduce the energy consumption of these systems is to execute these systems at the slowest feasible speed so that the job’s deadline times are met. Unfortunately, this method is at the expense of more response time and performance loss. To resolve this issue, in this paper, we propose a scheduling approach that associates the genetic algorithm (GA) with the first feasible speed (FiFeS) technique i.e. GA-FiFeS algorithm. This does not jeopardize real-time tasks’ deadlines. The GA-FiFeS algorithm proposes an energy-efficient schedule while still ensuring high response times. The results of the proposed approach, using plausible assumptions and experimental parameters, are compared with currently in-practice approaches, i.e. FiFeS and LeFeS (least feasible speed) approaches. Using numerical simulations and plausible assumptions, our investigation suggests that the proposed GA-FiFeS technique outperforms the FiFeS technique in terms of energy consumption (~18.56%) and response times (~2.78%). Furthermore, the GA-FiFeS has comparable outcomes with the LeFeS method while taking the expected time of execution as an assessment feature for analysis.

In an era dominated by digital communication, the vast amounts of data generated from social media and financial markets present unique opportunities and challenges for forecasting stock market prices. This paper proposes an innovative approach that harnesses the power of social media sentiment analysis combined with stock market data to predict stock prices, directly addressing the critical challenges in this domain. A major challenge in sentiment analysis is the uneven distribution of data across different sentiment categories. Traditional models struggle to accurately identify fewer common sentiments (minority class) due to the overwhelming presence of more common sentiments (majority class). To tackle this, we introduce the Off-policy Proximal Policy Optimization (PPO) algorithm, specifically designed to handle class imbalance by adjusting the reward mechanism in the training phase, thus favoring the correct classification of minority class instances. Another challenge is effectively integrating the temporal dynamics of stock prices with sentiment analysis results. Our solution is implementing a Transductive Long Short-Term Memory (TLSTM) model that incorporates sentiment analysis findings with historical stock data. This model excels at recognizing temporal patterns and gives precedence to data points that are temporally closer to the prediction point, enhancing the prediction accuracy. Ablation studies confirm the effectiveness of the Off-policy PPO and TLSTM components on the overall model performance. The proposed approach advances the field of financial analytics by providing a more nuanced understanding of market dynamics but also offers actionable insights for investors and policymakers seeking to navigate the complexities of the stock market with greater precision and confidence.

The motion cueing algorithm (MCA) enhances the realism of simulator driving experiences by generating vehicle motions within platform limitations. Existing MCAs are typically tuned for worst-case scenarios, limiting their efficiency for medium or slow driving motions. This study proposes a comprehensive MCA unit using learning-based models to overcome this problem and efficiently utilise the simulator workspace for all driving scenarios. Data samples are regenerated to cover various motion signal levels, and three classical washout filters are tuned to extract optimal motion signals. A multilayer perceptron (MLP) is trained with these extracted datasets, forming an AI-based MCA that provides high-fidelity driving motions for any scenario while optimising the platform workspace. Simulink/MATLAB is used for modelling and evaluation. Results demonstrate the proposed model's superior performance, with lower motion sensation errors, a higher correlation between sensed motion signals, and more efficient platform workspace usage.

Human Activity Recognition (HAR) is becoming increasingly important in the fast-evolving landscapes of wearable sensors, smart applications, and the Internet of Things (IoT) paradigms. HAR is rapidly gaining importance, especially in health monitoring, elderly and infant care, fitness tracking, and security. Machine learning (ML) and Deep Learning (DL) methods are used significantly for HAR problems. ML and DL methods often face four significant problems. Firstly, they lack the adaptability to evolve network architectures dynamically, which is vital in complex tasks like HAR. Secondly, classical ML and DL methods could fall short in comprehensively navigating potential solution spaces. Thirdly, finding optimal hyperparameters is a computationally expensive process, and lastly, expert knowledge is required to configure the hyperparameters. This paper proposes the NeuroHAR, a transformative neuroevolutionary method for HAR, to address these problems. NeuroHAR integrates feedforward deep neural networks (FDNN) with evolutionary algorithms. The highlights of NeuroHAR include its dynamic optimization of network architectures and hyperparameters. It is simple to configure and computationally efficient. Due to its adaptable design, it offers a more flexible and robust solution that handles task complexities better than traditional methods. Results are promising, which is evidence of the effectiveness of the proposed NeuroHAR, which outperformed the explicit contender, the state-of-the-art Grid Search approach. NeuroHAR and Grid Search evaluated 900 and 1080 models in Case I. Even with broader hyperparameter ranges in Case II, NeuroHAR still executed 900 models, whereas Grid Search would need over 2 billion models, which proves the computational efficiency of NeuroHAR. Additionally, for HARTH and HAR70Plus imbalanced datasets, the NeuroHAR model achieved a higher prediction accuracy of 89.91% versus Grid Search’s 84.04%. NeuroHAR can facilitate advanced monitoring and analytics, which are crucial for health monitoring, elderly care, and urban management powered by wearable sensors, IoT, and smart applications.

Nurses are essential in managing the healthcare of older adults, particularly those over 65, who often face multiple chronic conditions. This group requires comprehensive physical, mental, and functional care. Recent advancements in artificial intelligence (AI) have significantly improved nursing capabilities by enabling real-time health monitoring, thus bolstering the early detection and prevention of severe health issues. Despite these advancements, the current systematic literature predominantly focuses on machine learning (ML) applications for a limited set of chronic diseases, often overlooking the extensive capabilities of deep learning (DL) technologies. Additionally, these reviews cover a narrow spectrum of studies, potentially needing broader insights and developments in the field. To address these shortcomings, our study conducts a systematic literature review of ML and DL applications in geriatric care for chronic disease management. We meticulously analyzed peer-reviewed articles published from 2014 to 2024, concentrating on AI technologies in elderly care. This review included 76 selected articles from leading publishers such as Elsevier, Springer, IEEE, MDPI, Wiley, Taylor & Francis, Nature, Cambridge University Press, Oxford University Press, and arXiv, which we categorized into three main groups: Neurological disorders (27 articles), Mental Health disorders (22 articles), and Physical/physiological disorders (27 articles). Our findings reveal that Random Forest, logistic regression, and convolutional neural network (CNN) are the most frequently used AI techniques, typically evaluated by accuracy metrics and the area under the curve (AUC). The findings indicate that although AI applications in geriatric care are promising, they require significant enhancements in technology and methodology to improve accuracy and reliability. Future research should focus on developing advanced AI tools, integrating cutting-edge deep learning models and comprehensive datasets to refine diagnostics and treatment protocols for chronic diseases in the elderly, ultimately enhancing patient outcomes.

In recent years, color Local Binary Pattern (LBP) based descriptors have garnered substantial attention in computer vision and image analysis. This study presents a comprehensive review of color LBP-based descriptors developed over the past decade, focusing on their performance in image retrieval tasks. The research compares these descriptors based on mean Average Precision (mAP) scores, the dimensionality of their feature vectors, feature extraction time, and retrieval time. From this analysis, the top five descriptors are carefully selected and evaluated across multiple datasets Wang, Corel-5k, and Corel-10K. Among these, Weighted Color Radial Mean Completed Local Binary Pattern (WCRMLBP) emerges as the top-performing descriptor, demonstrating the effectiveness of feature weighting in enhancing color LBP-based descriptor performance. This research emphasizes the progress made in color LBP-based descriptors and their significance in contemporary image analysis and proposes the possibility of additional enhancements through improved feature weighting techniques. It contributes to the continual evolution of image processing and computer vision, particularly in deep learning methods.

This study employs friction stir processing to create a surface alloy using Al1050 aluminum as the base material, with Cu powder applied to enhance surface properties. Various parameters, including tool rotation speed, feed rate, and the number of passes, are investigated for their effects on the microstructure and mechanical properties of the resulting surface alloy. The evaluation methods include tensile testing, microhardness measurements, and metallographic examinations. The initial friction stir alloying pass produced a non-uniform stir zone, which was subsequently homogenized with additional passes. Through the plasticization of Al1050, initial agglomerates of copper particles were compacted into larger ones and saturated with aluminum. The alloyed samples exhibited up to an 80% increase in the strength of the base metal. This significant enhancement is attributed to the Cu content and grain size refinement post-alloying. Additionally, machine learning techniques, specifically Genetic Programming, were used to model the relationship between processing parameters and the mechanical properties of the alloy, providing predictive insights for optimizing the surface alloying process.

Optimisation models have transcended their origins to become indispensable tools across many fields, including engineering, economics, the environment, health, systems of systems, businesses, and beyond [...]

In this research, the control of a hexarot parallel mechanism is investigated. Parallel kinematic simulators or machine tools manipulators suffer from many problems to have a good motion tracking. The inverse kinematics and dynamic formulation that have been developed recently via the Newton–Euler method for a general hexarot mechanism is briefly presented. PID controller and fuzzy incremental controller have been designed and developed as an alternative option of the model-based controller. The efficiency of the model-based controller compared to other controllers has been evaluated. An important contribution of this paper is an appropriate control strategy that improves the tracking performance utilizing the cost effective joint-space sensor. The control scheme development starts with the robust design of the controller-observer of the single actuators. The single objective genetic algorithm is used to tune the controller gains to achieve the least tracking error of joint position. This, moreover, is improved by a centralized feedforward dynamics compensation of the gravity. The validity of the developed model is checked under Simulink environment of MATLAB software, and it is found that the developed model-based controller has the preferable tracking performance rather than the traditional PID and fuzzy incremental controllers The proposed model-based controller is able to decrease the motion tracking error from 55, 20 and 12 to 4 (deg2) for spiral motion compared with PID, FIC and observer-PD, respectively.

Reverse engineering plays an important role in the manufacturing and automobile industries in designing complicated spare parts, reducing actual production time, and allowing for multiple redesign possibilities, including shape alterations, different materials, and changes to other significant parameters of the component. Using reverse engineering methodology, damaged gears can be identified and modeled meticulously. Influential parameters can be obtained in the shortest time. Because most of the time it is impossible to solve gear-related inverse equations mathematically, metaheuristic methods can be used to reverse-engineer gears. This paper presents a methodology based on measurement over balls and span measurement along with evolutionary optimization techniques to determine the geometry of a pure involute of a cylindrical helical gear. Advanced optimization techniques, i.e., Grey Wolf Optimization, Whale Optimization, Particle Swarm Optimization, and Genetic Algorithm, were applied for the considered reverse engineering case, and the effectiveness and accuracy of the proposed algorithms were compared. Confirmatory calculations and experiments reveal the remarkable efficiency of Grey Wolf Optimization and Particle Swarm Optimization techniques in the reverse engineering of helical gears compared to other techniques and in obtaining influential gear design parameters.

The purpose of this research is to investigate different milling parameters for optimization to achieve the maximum rate of material removal with the minimum tool wear and surface roughness. In this study, a tool wear factor is specified to investigate tool wear parameters and the amount of material removed during machining, simultaneously. The second output parameter is surface roughness. The DOE technique is used to design the experiments and applied to the milling machine. The practical data is used to develop different mathematical models. In addition, a single-objective genetic algorithm (GA) is applied to numerate the optimal hyperparameters of the proposed adaptive network-based fuzzy inference system (ANFIS) to achieve the best possible efficiency. Afterwards, the multi-objective GA is employed to extract the optimum cutting parameters to reach the specified tool wear and the least surface roughness. The proposed method is developed under MATLAB using the practically extracted dataset and neural network. The optimization results revealed that optimum values for feed rate, cutting speed, and depth of cut vary from 252.6 to 256.9 (m/min), 0.1005 to 0.1431 (mm/rev tooth), and from 1.2735 to 1.3108 (mm), respectively.