Optimal Machining Research Articles

Instance reduction algorithm based on elitist min-max ant colony optimization technique

Although the advancement of technology has made data processing quite easier, it is still an enormous task, especially if the volume is large and can affect the learning capability of the classifier. Instance Reduction techniques can be employed on data to attain best results while making a substantial difference in terms of data storage needs, and processing speed. The proposed novel algorithm – Elitist Min-Max Ant Colony based Instance Reduction (ÆIR), can be attributed to the hybridization of bio-inspired optimization algorithms and Machine Learning algorithms for instance reduction. The primary features of ÆIR are the introduction of new hyperparameters such as the elitist ants, the min-max bounding of pheromones, and the incorporation of the length of the reduced set, all which aid in electing better instances for the reduced set. To evaluate the performance of the proposed ÆIR algorithm, 18 benchmark datasets of various dimensions were used alongside 4 different classifiers: Random Forest, Decision Tree, K-Nearest Neighbor and Naïve Bayes. The experiments demonstrated the effectiveness of ÆIR in reducing the size of the instances. On an average, approximately 50 % reduction in the number instances was observed. This can result in an equivalent decline in terms of the storage requirements, while contemporaneously improving the prediction accuracy.

Identification and immunological characterization of genes associated with ferroptosis in Alzheimer's disease and experimental demonstration.

The incidence of Alzheimer's disease (AD) is rising globally, yet its treatment and prediction of this condition remain challenging due to the complex pathophysiological mechanisms associated with it. Consequently, the objective of the present study was to analyze and characterize the molecular mechanisms underlying ferroptosis‑related genes (FEGs) in the pathogenesis of AD, as well as to construct a prognostic model. The findings will provide new insights for the future diagnosis and treatment of AD. First, the AD dataset GSE33000 from the Gene Expression Omnibus database and the FEGs from FerrDB were obtained. Next, unsupervised cluster analysis was used to obtain the FEGs that were most relevant to AD. Subsequently, enrichment analyses were performed on the FEGs to explore biological functions. Subsequently, the role of these genes in the immune microenvironment was elucidated through CIBERSORT. Then, the optimal machine learning was selected by comparing the performance of different machine learning models. To validate the prediction efficiency, the models were validated using nomograms, calibration curves, decision curve analysis and external datasets. Furthermore, the expression of FEGs between different groups was verified using reverse transcription quantitative PCR and western blot analysis. In AD, alterations in the expression of FEGs affect the aggregation and infiltration of certain immune cells. This indicated that the occurrence of AD is strongly associated with immune infiltration. Finally, the most appropriate machine learning models were selected, and AD diagnostic models and nomograms were built. The present study provided novel insights that enhance understanding with regard to the molecular mechanism of action of FEGs in AD. Moreover, the present study provided biomarkers that may facilitate the diagnosis of AD.

Optimal extreme learning machine for diagnosing brain tumor based on modified sailfish optimizer

This study proposes a hierarchical automated methodology for detecting brain tumors in Magnetic Resonance Imaging (MRI), focusing on preprocessing images to improve quality and eliminate artifacts or noise. A modified Extreme Learning Machine is then used to diagnose brain tumors that are integrated with the Modified Sailfish optimizer to enhance its performance. The Modified Sailfish optimizer is a metaheuristic algorithm known for efficiently navigating optimization landscapes and enhancing convergence speed. Experiments were conducted using the “Whole Brain Atlas (WBA)” database, which contains annotated MRI images. The results showed superior efficiency in accurately detecting brain tumors from MRI images, demonstrating the potential of the method in enhancing accuracy and efficiency. The proposed method utilizes hierarchical methodology, preprocessing techniques, and optimization of the Extreme Learning Machine with the Modified Sailfish optimizer to improve accuracy rates and decrease the time needed for brain tumor diagnosis. The proposed method outperformed other methods in terms of accuracy, recall, specificity, precision, and F1 score in medical imaging diagnosis. It achieved the highest accuracy at 93.95 %, with End/End and CNN attaining high values of 89.24 % and 93.17 %, respectively. The method also achieved a perfect score of 100 % in recall, 91.38 % in specificity, and 75.64 % in F1 score. However, it is crucial to consider factors like computational complexity, dataset characteristics, and generalizability before evaluating the effectiveness of the method in medical imaging diagnosis. This approach has the potential to make substantial contributions to medical imaging and aid healthcare professionals in making prompt and precise treatment decisions for brain tumors.

DynamicWeighted Particle Swarm Optimization - Support Vector Machine Optimization in Recursive Feature Elimination Feature Selection

Feature Selection is a crucial step in data preprocessing to enhance machine learning efficiency, reduce computational complexity, and improve classification accuracy. The main challenge in feature selection for classification is identifying the most relevant and informative subset to enhance prediction accuracy. Previous studies often resulted in suboptimal subsets, leading to poor model performance and low accuracy. This research aims to enhance classification accuracy by utilizing Recursive Feature Elimination (RFE) combined with Dynamic Weighted Particle Swarm Optimization (DWPSO) and Support Vector Machine (SVM) algorithms. The research method involves the utilization of 12 datasets from the University of California, Irvine (UCI) repository, where features are selected via RFE and applied to the DWPSO-SVM algorithm. RFE iteratively removes the weakest features, constructing a model with the most relevant features to enhance accuracy. The research findings indicate that DWPSO-SVM with RFE significantly improves classification accuracy. For example, accuracy on the Breast Cancer dataset increased from 58% to 76%, and on the Heart dataset from 80% to 97%. The highest accuracy achieved was 100% on the Iris dataset. The conclusion of these findings that RFE in DWPSO-SVM offers consistent and balanced results in True Positive Rate (TPR) and True Negative Rate (TNR), providing reliable and accurate predictions for various applications.

Leveraging multivariate analysis and adjusted mutual information to improve stroke prediction and interpretability.

To develop a machine learning model to accurately predict stroke risk based on demographic and clinical data. It also sought to identify the most significant stroke risk factors and determine the optimal machine learning algorithm for stroke prediction. This cross-sectional study analyzed data on 438,693 adults from the 2021 Behavioral Risk Factor Surveillance System. Features encompassed demographics and clinical factors. Descriptive analysis profiled the dataset. Logistic regression quantified risk relationships. Adjusted mutual information evaluated feature importance. Multiple machine learning models were built and evaluated on metrics like accuracy, AUC ROC, and F1 score. Key factors significantly associated with higher stroke odds included older age, diabetes, hypertension, high cholesterol, and history of myocardial infarction or angina. Random forest model achieved the best performance with accuracy of 72.46%, AUC ROC of 0.72, and F1 score of 0.74. Cross-validation confirmed its reliability. Top features were hypertension, myocardial infarction history, angina, age, diabetes status, and cholesterol. The random forest model robustly predicted stroke risk using demographic and clinical variables. Feature importance highlighted priorities like hypertension and diabetes for clinical monitoring and intervention. This could help enable data-driven stroke prevention strategies.

Chronic Kidney Disease Prediction Using Machine Learning

Abstract: Chronic kidney disease (CKD) is a progressive condition in which the kidneys lose their ability to function effectively over time. Individuals with hypertension, diabetes, or a family history of CKD are at increased risk, emphasizing the importance of early detection for effective intervention and management. Recent research has focused on employing machine learning techniques, including Ant Colony Optimization (ACO) and Support Vector Machine (SVM) classifiers, to predict CKD presence using a minimal set of features. This study aims to optimize predictive accuracy through advanced machine learning methodologies, facilitating timely and targeted healthcare interventions for at-risk individuals. By analyzing relevant clinical data, predictive models developed in this research offer promising avenues for early identification of CKD, enabling proactive disease management strategies. The integration of machine learning techniques in CKD prediction not only enhances predictive accuracy but also contributes to advancing personalized healthcare. Early detection allows for the implementation of preventive measures and personalized treatment plans, ultimately improving patient outcomes and reducing the burden on healthcare systems. The proposed methodology seeks to optimize predictive accuracy, aiding in timely and targeted healthcare interventions.

A Comparative and Experimental Study of Parametric Influence on Drilling Process of Hybrid AMMC

Abstract: To aim for the highest quality product quality and a high metal removal rate, metal cutting is crucial. The primary obstacle to attaining optimal quality and high production is the short tool life. The hybrid aluminum metal matrix AA 6082, with reinforcement consisting of titanium dioxide (7.5%) and cenosphere (2.5%), was optimized using the Modified Taguchi optimization method for simultaneous minimization and maximization of surface roughness (Ra), machining time, and material removal rate. The surface finish was affected by different types of geometrical precision values of the CNC drilling process parameters in order to both minimize and maximize the responses. The experiments, including call for the machining of hybrid AMMC and the use of an HSS drill bit, will be performed using a CNC with different process parameters. The L16 orthogonal array will be used for the examinations, and each experiment will be run under a distinct set of circumstances, including feed, speed, and pecking. Using the TAGUCHI design, the optimal geometrical and machining parameters were determined from the experimental output responses, and significant influences were discovered for the corresponding specific output responses.

Multi-group exploration of the built environment and metro ridership: Comparison of commuters, seniors and students

Understanding the associations between demographic groups’ metro travel behaviors and the built environment is crucial for addressing automobile dependence and promoting transportation equity and reasonable urban construction. This study examines the nonlinear relationships and threshold effects of the built environment on the metro travel patterns of three groups (i.e., commuters, seniors, and students) by applying smart card data in Kunming, China. We select the optimal machine learning model—gradient boosting decision trees (GBDTs)—and consider various built environment attributes. Our findings indicate that: 1) built environment attributes universally have nonlinear and threshold effects on metro travel for all groups; 2) the collective contributions of density and diversity differ greatly across groups compared to other attributes; and 3) only a few built environment attributes have similar effect directions and degrees across all three groups, while most have unique effects on each group. The findings suggest metro station area planning strategies to promote metro use and transportation equity for different groups.

Sustainability assessment of machining Al 6061-T6 using Taguchi-grey relation integrated approach

Modern machining requires reduction in energy usage, surface roughness, and burr width to produce finished or near-finished parts. To ensure high surface quality in machining processes, it is crucial to minimize surface finish and minimize burr width, which are considered as significant parameters as specific cutting energy. The objective of this study was to identify the optimal machining parameters for milling in order to minimize surface roughness, burr width, and specific cutting energy. To achieve this, the research investigated the impact of feed per tooth, cutting speed, depth of cut, and number of inserts on the responses across three intervals using Taguchi L9 array. Observing the responses by varying these parameters, underlined the need for multi objective optimisation. Machining conditions of 0.14 mm/tooth fz, 350 m/min Vc and 2 mm ap using 1 cutting insert (exp no 9) was identified as the best machining run using grey relational analysis owing to its highest grey relational grade of 0.936. ANOVA examination identified cutting speed as the leading factor impacting the grey relational grade with 31.07 % contribution ratio, with the number of inserts, depth of cut, and feed per tooth also making notable contributions. Conclusively, machining parameters identified through response surface optimisation resulted in 21.69 % improvement in surface finish, 11.39 % reduction in specific energy consumption, and 6.2 % decrease in burr width on the down milling side albeit with an increase of 9 % in burr width on the up-milling side.

Ransomware Early Detection using Machine Learning Approach and Pre-Encryption Boundary Identification

The escalating ransomware threat has catalysed the formation of a sophisticated network of cybercriminal enterprises. Addressing this issue, our research provides a detailed exploration of the ransomware menace and an evaluation of contemporary detection methodologies. A successful ransomware attack leverages many factors: robust encryption methods that defy decryption, the anonymity of cyber currencies, and the widespread availability of ransomware kits that enable even inexperienced actors to launch attacks. Such dynamics have cultivated a niche for cybercriminal specialists in the digital underworld. In response to these challenges, our study proposes a detection framework based on machine learning, a domain where regression algorithms have gained popularity without yielding a definitive protective model. We employ API call analysis as the foundation to assess various machine learning classifiers' efficiency in identifying ransomware. The evaluation demonstrates that the Naive Bayes classifier underperforms due to suboptimal accuracy, making it unsuitable for this application. Conversely, Logistic Regression, with an AUC of 0.951, minimal training time, and substantial efficacy gains, emerges as a strong contender. The Decision Tree and Random Forest classifiers exhibit comparable proficiency; however, the Decision Tree's interpretability and Random Forest's computational swiftness present unique advantages. Superior still, SVM and Gradient Boosted Trees command the highest AUC and gains, albeit at the cost of increased training duration. Our findings affirm the pivotal role of API call analysis in ransomware detection and the potency of machine learning approaches in learning from extensive datasets to identify novel malware strains. Given the continual evolution of malware, detection methodologies must adapt correspondingly. This study's comparative analysis elucidates the trade-offs between accuracy, computational speed, and training time, guiding the selection of the optimal machine learning algorithm for robust ransomware detection.

Smart charging process development based on ant colony optimization machine learning for controlling lead-acid battery charging capacity

The Indonesian government has targeted 2.1 million two-wheeled electric vehicles and 2,200 four-wheeled electric vehicles (EV) by 2025. This is hampered by limited electricity supply and EV charging, which takes long time. Multi device interleaved DC-DC bidirectional converter has been applied and assessed as the most suitable method for battery EV and plug-in hybrid EV because it produces high power >10 kW. For power below 10 kW, it is recommended to use a sinusoidal, Z-Source, and boost amplifier type converter. The smart charging (SC) system will be applied to electric vehicles, which only require a minimum charging power of around 169 W for four lead acid batteries. This paper focuses on an SC system that is capable of charging the battery quickly while still paying attention to the state of health (SoH) of the battery. The SC developed uses a DC-DC boost converter to increase the voltage produced by the switch mode power supply (SMPS). Estimated charging time is less than 30 minutes and still pay attention to the battery SoH. SC will also use pulse width modulation (PWM) as a duty power cycle regulator. This research applies a multi-layer perceptron (MLP) classifier to a neural network (NN). The results of the research show that smart charging can charge up to 600 W with an estimated charging time of around 11 minutes. The charging condition is above 60 % and the power duty cycle setting is 100 %. The power estimation results processed using the ant colony optimization (ACO) based neural network method show a root mean square deviation value of 0.010013430 for charging four lead acid batteries. These results are useful to help solve the problem of capacity requirements and battery charging speed for EVs, with good SoH

A New Energy Management Strategy for Electric Vehicles Based on Optimal Adaptive State Machine Control

A New Energy Management Strategy for Electric Vehicles Based on Optimal Adaptive State Machine Control

Experimental Investigation on Surface Characteristics of Finish Hobbed Gear using Grey Relational Analysis

Introduction: Spur gears are important for transferring motion and power among shafts. The surface characteristics of these gears are important for their life and smooth operation. To improve profitability and customer satisfaction, a study was conducted to analyze the surface quality of spur gears produced through CNC hobbing machining. Objectives: The objective this investigation is to conduct experimental trials to estimate the best hobbing parameters to minimize surface roughness and microgeometric deviations. In this investigation, effect of varying cutting speed and feed rate on surface finish have been reported. Methods: An experiment are conducted according to Taguchi L9 experimental design. Grey Relational Analysis is performed to estimate the optimum machining parameters. Results: The experimental finding reveals, at cutting speed 400 rpm, the feed rate 8 mm/min, and depth of cut 3.91 mm gives good quality of surface (Ra 0.5530). The gear hobbing process has increased to a greater level of performance. The roughness of the flank surface and microgeometry deviations decreases with an increase in hob cutter speed. Conclusions: This ultimately reduces the inherent vibrations between the hob cutter and the gear blank, thus minimizing microgeometric deviations. The variation in feed rate was noticed and had a very significant impact on the efficiency and surface quality of the gear. The study recommends that a cutting speed of 400 rpm is the most effective for obtaining the best results.

Enhancing Internet of Things Security Through Optimization Algorithms and Machine Learning

Enhancing Internet of Things Security Through Optimization Algorithms and Machine Learning

Integrated analysis of single-cell RNA-seq, bulk RNA-seq, Mendelian randomization, and eQTL reveals T cell-related nomogram model and subtype classification in rheumatoid arthritis.

Rheumatoid arthritis (RA) is a systemic disease that attacks the joints and causes a heavy economic burden on humans worldwide. T cells regulate RA progression and are considered crucial targets for therapy. Therefore, we aimed to integrate multiple datasets to explore the mechanisms of RA. Moreover, we established a T cell-related diagnostic model to provide a new method for RA immunotherapy. scRNA-seq and bulk-seq datasets for RA were obtained from the Gene Expression Omnibus (GEO) database. Various methods were used to analyze and characterize the T cell heterogeneity of RA. Using Mendelian randomization (MR) and expression quantitative trait loci (eQTL), we screened for potential pathogenic T cell marker genes in RA. Subsequently, we selected an optimal machine learning approach by comparing the nine types of machine learning in predicting RA to identify T cell-related diagnostic features to construct a nomogram model. Patients with RA were divided into different T cell-related clusters using the consensus clustering method. Finally, we performed immune cell infiltration and clinical correlation analyses of T cell-related diagnostic features. By analyzing the scRNA-seq dataset, we obtained 10,211 cells that were annotated into 7 different subtypes based on specific marker genes. By integrating the eQTL from blood and RA GWAS, combined with XGB machine learning, we identified a total of 8 T cell-related diagnostic features (MIER1, PPP1CB, ICOS, GADD45A, CD3D, SLFN5, PIP4K2A, and IL6ST). Consensus clustering analysis showed that RA could be classified into two different T-cell patterns (Cluster 1 and Cluster 2), with Cluster 2 having a higher T-cell score than Cluster 1. The two clusters involved different pathways and had different immune cell infiltration states. There was no difference in age or sex between the two different T cell patterns. In addition, ICOS and IL6ST were negatively correlated with age in RA patients. Our findings elucidate the heterogeneity of T cells in RA and the communication role of these cells in an RA immune microenvironment. The construction of T cell-related diagnostic models provides a resource for guiding RA immunotherapeutic strategies.

Anodic dissolution behavior of a Zr-based bulk metallic glass and the electrochemical machining of small structures with high geometrical precision and good surface quality

Bulk metallic glasses (BMGs) have excellent mechanical properties, however, it is still challenging to process high-qualtiy BMG structures for their widespread engineering applications. In this work, electrochemical machining (ECM) is adopted to process various small BMG structures with high geometrical precision and surface quality. Firstly, the electrochemical dissolution behavior of a Zr57Cu20Al10Ni8Ti5 (at.%) BMG in NaNO3, H3PO4, NaCl, and HCl solutions was investigated and discussed. The results shown that obvious corrosion occurred in HCl and NaCl solutions, while mass by-products and pitting corrosion on the workpiece surface in NaCl solution affect the corrosion continuity and surface quality. Therefore, the HCl solution is selected as the electrolyte for the following ECM process. Secondly, the effects of machining parameters on the ECM performance of BMG workpieces were investigated, where the optimal machining performance was achieved with an electrolyte of 0.1 mol/L HCl, a cathode feed rate of 3 μm/s, a machining voltage of 10 V, and a duty cycle of 15%. Finally, a small round hole with a roughness (Ra) of about 0.2 μm, a sidewall taper of less than 2.83°, and a relative error of diameters of 2.1% was obtained. Another square structure (0.899 mm × 0.891 mm) with high geometrical precision and surface quality was also achieved by the optimal parameters, which validates the feasibility to machine small BMG structures using the ECM technique with its optimal parameters.

Prediction of frost resistance and multiobjective optimisation of low-carbon concrete on the basis of machine learning

The use of Portland cement is a major source of carbon dioxide emissions, causing considerable environmental pollution worldwide. Therefore, reducing carbon emissions in concrete is of paramount importance. This study presents a multiobjective optimisation method for low-carbon concrete mix design, combining the use of optimal machine learning models for prediction, with the aim of minimising the cost and carbon emissions of concrete. Several optimisation models, including SVR, CatBoost, RF, XGBoost, DBO-RF and VMD-DBO-RF, were employed to predict the frost resistance of low-carbon concrete. The research findings demonstrate that the VMD-DBO-RF optimisation algorithm achieves high prediction accuracy in terms of RDEM and MLR. For RDEM prediction, R2 = 0.9346, MSE = 0.0508, MAE = 0.1686, and RMSE = 0.2253. For MLR prediction, R2 = 0.9557, MSE = 0.0245, MAE = 0.1042, and RMSE = 0.1565. Furthermore, the model’s interpretability was improved by combining SHAP and PDP analyses.

Hazard regressive multipoint elitist spiral search optimization for resource efficient task scheduling in cloud computing

Cloud computing, a revolutionary paradigm, connects computing resources and users via the internet, offering services like cloud storage and on-demand computing. In this context, efficient task scheduling is crucial, aiming to minimize costs and makespan. We introduce hazard regressive multipoint elitist spiral search optimization (HRMESSO), a novel technique for efficient task scheduling with reduced time consumption. User tasks are initially received, prioritized, and optimized. Cox proportional hazard regression is applied to establish relationships between task attributes (e.g., priority level, request arrival time, file size) and task prioritization. The great deluge elitist spiral search optimization identifies optimal virtual machines, considering factors like energy, memory, and CPU availability. The spiral search employs logarithmic spirals and Jenson Shannon divergence to find global optimal virtual machines. Finally, the task assigner schedules prioritized tasks onto the identified optimal virtual machines. Experimental evaluation is conducted with different metrics such as task scheduling efficiency, makespan, throughput and energy consumption. The quantitatively compared results exhibit the HRMESSO technique provides better scheduling efficiency, lesser makespan, throughput and energy consumption.

Optimizing the Electrical Discharge Machining Process Parameters of the Nimonic C263 Superalloy: A Sustainable Approach

Engineers continue to be concerned about electrical discharge-machined components’ high energy consumption, machining debris, and poor dimensional precision. The aim of this research is to propose a hybrid neuro-genetic approach to improve the machinability of the electrical discharge machining (EDM) of the Nimonic C263 superalloy. This approach focuses on reducing the energy consumption and negative environmental impacts. The material removal rate (MRR), electrode wear ratio (EWR), specific energy consumption (SEC), surface roughness (Ra), machining debris (db), and circularity (C) are examined as a function of machining parameters such as the voltage (V), pulse on time (Ton), current (I), duty factor (τ), and electrode type. By employing the VIKOR method, all the responses are transformed into a distinctive VIKOR index (VI). Neuro-genetic methods (a hybrid VIKOR-based ANN-GA) can further enhance the best possible result from the VIKOR index. During this step, the hybrid technique (VIKOR-based ANN-GA) is used to estimate an overall improvement of 9.87% in the response, and an experiment is conducted to confirm this condition of optimal machining. This work is competent enough to provide aeroengineers with an energy-efficient, satisfying workplace by lowering the machining costs and increasing productivity.

Research on machining Technology of Electrospark-electrochemical Hybrid Energy Field with tungsten hole

The machining technology for tungsten hole faces considerable challenges. Electrical Discharge Machining (EDM), as a non-traditional machining technique, is widely applied due to its capability to process conductive materials. This technique is characterized by high precision metal processing, high material removal rate, and low tool wear rate. Molecular dynamics simulation technology is employed in this study to model the single pulse discharge process, with the aim of elucidating the erosion mechanism of different melting point metal materials in the melt pool during spark discharge and the effect of pressure difference inside and outside the melt pool. Moreover, for the efficient machining of tungsten materials, Electrospark-electrochemical Hybrid Energy Field Machining (ECEM) method is proposed, which is conducted under a certain conductivity salt solution. The simultaneous high-speed electric spark discharge and electrochemical action effectively promote the rapid formation of spark plasma discharge channels. Orthogonal experimental data and images are utilized in this paper to study the machining of tungsten micropores, with the effects of pulse width, pulse interval, peak current, and concentration of NaNO3 being analyzed, and the optimal machining parameters being determined.