Efficient Machine Research Articles

Machine learning models for predicting of PD-1 treatment efficacy in Pan-cancer patients based on routine hematologic and biochemical parameters

Immune checkpoint blockade therapy targeting the programmed death-1(PD-1) pathway has shown remarkable efficacy and durable response in patients with various cancer types. Early prediction of therapeutic efficacy is important for optimizing treatment plans and avoiding potential side effects. In this work, we developed an efficient machine learning prediction method using routine hematologic and biochemical parameters to predict the efficacy of PD-1 combination treatment in Pan-Cancer patients. A total of 431 patients with nasopharyngeal carcinoma, esophageal cancer and lung cancer who underwent PD-1 checkpoint inhibitor combination therapy were included in this study. Patients were divided into two groups: progressive disease (PD) and disease control (DC) groups. Hematologic and biochemical parameters were collected before and at the third week of PD-1 therapy. Six machine learning models were developed and trained to predict the efficacy of PD-1 combination therapy at 8–12 weeks. Analysis of 57 blood biomarkers before and after three weeks of PD-1 combination therapy through statistical analysis, heatmaps, and principal component analysis did not accurately predict treatment outcome. However, with machine learning models, both the AdaBoost classifier and GBDT demonstrated high levels of prediction efficiency, with clinically acceptable AUC values exceeding 0.7. The AdaBoost classifier exhibited the highest performance among the 6 machine learning models, with a sensitivity of 0.85 and a specificity of 0.79. Our study demonstrated the potential of machine learning to predict the efficacy of PD-1 combination therapy based on changes in hematologic and biochemical parameters.

Load Balancing in Cloud Computing Using Meta-Heuristic Algorithm: Survey

Load balancing is essential within the cloud. Distributing the workload over many servers permits for a more efficient machine. Optimal resource use, decreased time to response, and more advantageous gadget performance are all results. Among the numerous challenges that traditional methods of accomplishing equilibrium come upon are problems with adaptability and the unpredictability of cloud structures. This survey focuses on the demanding situations associated with load balancing in cloud computing and proposes the usage of specialized algorithms as an answer. It determines the most reliable alternatives for facts placement in the cloud. Meta-heuristic algorithms draw concept from herbal approaches, which includes the foraging behavior of ants or the hunting strategies of predators. These algorithms excel at rapidly finding super answers in situations where conventional optimization algorithms fail to get great results. Various strategies have been proposed to attain paintings equilibrium in cloud computing. Evidence has shown that these techniques can enhance work balance in cloud computing.

Frictional Properties of Two-Dimensional Materials: Data-Driven Machine Learning Predictive Modeling.

Friction, typically associated with reduced efficiency and reliability of machines and devices, occurs when two objects are displaced against each other. This is a strongly material-dependent phenomenon, and the emergence of many 2D materials has opened up new opportunities to design systems with desired tribological properties. Here, we combine high throughput simulations and machine learning models to develop a statistical approach of adhesion, van der Waals, and corrugation energies of a large dataset of monolayered materials. The machine learning models are used to predict these closely related to friction energetic properties and link them to easily accessible atomistic and monolayer features. This approach elevates the materials' perspective of frictional properties. It demonstrates that data-driven models are extremely useful in discovering important structure-property functionalities for frictional property interpretations as a fruitful route toward desired tribological materials.

Optimizing data acquisition: a Bayesian approach for efficient machine learning model training

Acquiring a substantial number of data points for training accurate machine learning (ML) models is a big challenge in scientific fields where data collection is resource-intensive. Here, we propose a novel approach for constructing a minimal yet highly informative database for training ML models in complex multi-dimensional parameter spaces. To achieve this, we mimic the underlying relation between the output and input parameters using Gaussian process regression (GPR). Using a set of known data, GPR provides predictive means and standard deviation for the unknown data. Given the predicted standard deviation by GPR, we select data points using Bayesian optimization to obtain an efficient database for training ML models. We compare the performance of ML models trained on databases obtained through this method, with databases obtained using traditional approaches. Our results demonstrate that the ML models trained on the database obtained using Bayesian optimization approach consistently outperform the other two databases, achieving high accuracy with a significantly smaller number of data points. Our work contributes to the resource-efficient collection of data in high-dimensional complex parameter spaces, to achieve high precision ML predictions.

Multicriteria Optimisation of Machining Operations Using a Spreadsheet Model

The rapid development of new materials and tools demonstrates the need for efficient and feasible machining processes. Modern production systems must guarantee sustainable, flexible, productive and high-quality production at low cost. Therefore, the combination of technological data with advanced software solutions is very important, especially when using complex CNC machining systems, where the reliability of the technological information is crucial, as simple measures can make a very positive contribution to the productivity achieved. When optimising the machining parameters, costs and machining time must be taken into account. The article deals with the optimisation of the turning process with a large number of influencing variables (machine, workpiece material, tool, cutting parameters, costs, etc.) and two objectives: the fastest possible machining (minimisation of machining time) and the lowest possible machining costs. The model is designed in an Excel spreadsheet and the multi-criteria optimisation is carried out using the approximation method. Step by step, we can find the optimal processing regime for each selected case.

Study of damage mechanism on single crystal 4H-SiC surface layer by picosecond laser modification (PLM)

The stable structure, high hardness, and brittleness of single-crystal 4H-SiC present challenges in achieving efficient and damage-free polishing processing. Ultra-short pulsed laser-induced surface modification provides a new solution to enhance the manufacturability of 4H-SiC. This paper aims to investigate the underlying mechanism of the picosecond laser-induced surface structural changes in 4H-SiC and the process of material removal from solid to vapour, elucidating the interaction mechanism between picosecond laser and 4H-SiC. A temperature gradient distribution model for picosecond laser irradiation on 4H-SiC was built to reveal the formation mechanism of subsurface crack damage. The results show that a combination of phase explosion and thermal effects controlled picosecond laser-modified 4H-SiC surfaces deposited spherical SiO2 particles and the process. The study demonstrates that the cracking behaviour in the subsurface of picosecond laser-modified SiC predominantly occurs in the recast region. The fundamental cause of cracking is attributed to the tensile stresses generated by thermal effects and the volumetric changes in the molten material resulting from the overlapping of neighbouring spots in alternating hot–cold cycles. The nanoindentation demonstrated that laser modification can effectively enhance the machinability of SiC. The findings of this study can provide a theoretical basis for efficient non-destructive machining of hard and brittle materials.

Efficient machine learning for strength prediction of ready-mix concrete production (prolonged mixing)

Purpose This paper aims to clarify the efficient process of the machine learning algorithms implemented in the ready-mix concrete (RMC) onsite. It proposes innovative machine learning algorithms in terms of preciseness and computation time for the RMC strength prediction. Design/methodology/approach This paper presents an investigation of five different machine learning algorithms, namely, multilinear regression, support vector regression, k-nearest neighbors, extreme gradient boosting (XGBOOST) and deep neural network (DNN), that can be used to predict the 28- and 56-day compressive strengths of nine mix designs and four mixing conditions. Two algorithms were designated for fitting the actual and predicted 28- and 56-day compressive strength data. Moreover, the 28-day compressive strength data were implemented to predict 56-day compressive strength. Findings The efficacy of the compressive strength data was predicted by DNN and XGBOOST algorithms. The computation time of the XGBOOST algorithm was apparently faster than the DNN, offering it to be the most suitable strength prediction tool for RMC. Research limitations/implications Since none has been practically adopted the machine learning for strength prediction for RMC, the scope of this work focuses on the commercially available algorithms. The adoption of the modified methods to fit with the RMC data should be determined thereafter. Practical implications The selected algorithms offer efficient prediction for promoting sustainability to the RMC industries. The standard adopting such algorithms can be established, excluding the traditional labor testing. The manufacturers can implement research to introduce machine learning in the quality controcl process of their plants. Originality/value Regarding literature review, machine learning has been assessed regarding the laboratory concrete mix design and concrete performance. A study conducted based on the on-site production and prolonged mixing parameters is lacking.

Exponentially improved efficient machine learning for quantum many-body states with provable guarantees

Solving the ground state and the ground-state properties of quantum many-body systems is generically a hard task for classical algorithms. For a family of Hamiltonians defined on an m-dimensional space of physical parameters, the ground state and its properties at an arbitrary parameter configuration can be predicted via a machine learning protocol up to a prescribed prediction error ɛ, provided that a sample set (of size N) of the states can be efficiently prepared and measured. In a recent work [Huang , ], a rigorous guarantee for such a generalization was proved. Unfortunately, an exponential scaling for the provable sample complexity, N=mO(1ɛ), was found to be universal for generic gapped Hamiltonians. This result applies to the situation where the dimension of the parameter space is large, while the scaling with the accuracy is not an urgent factor, not entering the realm of more precise learning and prediction. In this work, we consider an alternative relevant scenario, where the effective dimension m is a finite, not necessarily large constant, while the scaling with the prediction error becomes the central concern. By jointly preserving the fundamental properties of density matrices in the learning protocol and utilizing the continuity of quantum states in the parameter range of interest, we rigorously obtain a polynomial sample complexity for predicting quantum many-body states and their properties, with respect to the prediction error ɛ and the number of qubits, n, with N=poly(ɛ−1,n,ln1δ), where poly denotes a polynomial function, and (1−δ) is the probability of success. Moreover, if restricted to learning local quantum-state properties, the number of samples can be further reduced to N=poly(ɛ−1,lnnδ). Numerical demonstrations confirm our findings, and an alternative approach utilizing statistical learning theory with reproducing kernel Hilbert space achieves consistent results. The mere continuity assumption indicates that our results are not restricted to gapped Hamiltonian systems and properties within the same phase. Published by the American Physical Society 2024

An Efficient Machine Learning based Framework for Alcoholic Liver Disease Prediction

An Efficient Machine Learning based Framework for Alcoholic Liver Disease Prediction

Preventive Maintenance on CNC Machines Using the OEE Method to Reduce Downtime at PT. MTAT

This study examines the performance of CNC machines at PT MTAT Indonesia from January to March 2023. Monthly production data, machine uptime, defect rates, and non-productive periods were collected to assess Overall Equipment Effectiveness (OEE). This study aims to analyze the effectiveness of preventive maintenance of CNC machines at PT MTAT Indonesia using the Overall Equipment Effectiveness (OEE) method to reduce downtime. This study uses monthly data from January to March 2023, including production uptime, defect rates, and non-productive periods, to calculate OEE. The analysis showed that the CNC machines achieved an average OEE of 86.52%, surpassing the global standard of 85%, indicating high efficiency and quality. The study used Pareto analysis to identify the main causes of downtime, finding technical and maintenance issues as the main contributors. By addressing these factors, PT MTAT Indonesia can further improve machine efficiency and productivity. This study contributes to this field by providing a comprehensive analysis of CNC machine maintenance and proposing strategies for continuous improvement.

Removal mechanism of double-diamond-abrasive-grinding GaN single crystals under graphene lubrication

Gallium nitride (GaN) is an advanced material used to manufacture chip wafers and high-power devices. Recently, grinding processing, has been applied in the fields of machinery manufacturing, aerospace, and medical devices as a highly efficient machining method. An in-depth understanding of the material removal mechanism produced by the double-grinding processes can provide guidance for the design of GaN-based nanodevices. Herein, molecular dynamics simulations were used to investigate the mechanism of removal of double-diamond-abrasive-grinding gallium nitride crystals under graphene lubrication, and a systematic study was performed to investigate the involved surface morphology, grinding force, stress distribution, and subsurface damage behavior. Results reveal that graphene can substantially enhance the wear resistance of GaN substrates by reducing surface wear, atomic displacement., potential energy, and subsurface damage, thereby playing a protective role toward the substrate. As the grinding depth increases, the grinding force and subsurface damage depth also increase. Furthermore, the effects of abrasive grain spacing on subsurface damage depth and phase change atoms were analyzed and found to have limited influence on material removal efficiency. These results deepen our understanding of material removal and protection mechanisms relative to substrates resulting from double-grinding processes as well as offer valuable insights for the rational design of abrasive wheels.

Factors that Impact the Efficiency of Cream Separator Machine for the Food Industry

This study examines the variables that impact the effectiveness of cream separator machines in the dairy sector, with a specific emphasis on centrifugal force, temperature, and vibration. The process of cream separation, which is crucial in dairy production, has progressed from manual techniques to sophisticated mechanical centrifugal separators. The objective of this study is to optimize the performance of these machines, which is imperative due to the increasing need for low-fat skimmed milk. The study utilizes a disc centrifuge to examine the impact of centrifugal forces. The setup consists of more than 24 discs, which are used to measure the volume of fluid passing through the spaces between the discs and to determine the efficiency of separation. The experiments involved using flow rates of 600 ml/min, 1200 ml/min, and 1800 ml/min to alter the temperature from 7 °C to 15 °C, 25 °C, and 35 °C. The findings indicated that decreased temperatures significantly enhance the efficiency of skimming. The study also examines the impact of machine-induced vibration on the efficiency of separation. The study concludes that excessive vibration negatively impacts productivity, therefore, it is essential to incorporate vibration control into the design of separators. The key findings suggest that optimizing centrifugal force is crucial. Inadequate force leads to incomplete separation of fat, while higher flow rates decrease separation efficiency. Temperature regulation is equally crucial, and reducing temperatures enhances efficiency. Effective vibration control is essential for maintaining optimal separation quality. This study makes a valuable contribution to the advancement of cream separator machines by highlighting the importance of accurate management of centrifugal force, temperature, and vibration. This is crucial for enhancing productivity and meeting the requirements of the market. The findings offer valuable insights for the dairy industry, assisting in the development and functioning of advanced cream separators that provide enhanced performance and economic advantages for producers.

AUTOMATED COMPLEX FOR MEASURING THE WINDING TEMPERATURE OF TRACTION ELECTRIC MACHINES DURING THEIR HEATING TEST

Purpose. The development and implementation of automated complexes for testing traction electric machines of rolling stock at the current stage is an extremely important task. Automated test complexes provide an opportunity to significantly increase the quality and efficiency of tests on traction electric machines. Thanks to the use of advanced technologies, these complexes ensure accurate data collection and analysis during tests. One of the main advantages of automated complexes is the reduction of cost and labor costs for conducting tests. Instead of manual intervention by operators, automation systems can perform many tasks automatically, saving time and reducing labor costs. Methodology. The methodological basis of the research is analytical research methods based on the compilation of a calculation system of differential equations based on the accepted test scheme, as well as the development of an algorithm for conducting tests on a designed stand. Findings. The proposed test complex allows to conduct tests of collector traction electric machines, to determine the excess temperature of the windings of electric machines without the need to stop them. The functional scheme of the measuring complex allows you to automatically record the parameters of the tested electric machines, and if necessary, it is possible to output the test results to a computer with the subsequent formation of the test protocol in electronic form. The accuracy of the determination of the measured parameters is ensured by the accuracy of the measuring devices and the algorithm of the measuring complex. Originality. The proposed automated measuring complex is a big step in the direction of improving the efficiency and reliability of heating tests of traction electric machines. One of its key advantages is the ability to perform tests without stopping the machine, which significantly reduces the time and costs of conducting tests. Automatic registration of measured parameters allows to record several controlled indicators at the same time, which provides a more complete and objective assessment of the state of the electric machine during testing. This complex not only facilitates the testing process and reduces the cost of time and resources, but also increases the reliability of the obtained results, which is important for manufacturers and operators of transport systems. In general, the automated measuring complex opens up new opportunities for increasing the efficiency and reliability of testing electric traction machines, contributing to the further development of transport technologies. Practical value. The implementation of the obtained results by enterprises for the repair of traction electric machines of rolling stock will allow to reduce the material costs of carrying out repairs while simultaneously improving the quality of the conducted tests.

Influence of Process Parameters on Kerf Width in Abrasive Waterjet Machining of GFRP Composites

This study investigates the influence of process parameters on kerf width in abrasive waterjet (AWJ) machining of glass fiber reinforced polymer (GFRP) composites. The experimental analysis was conducted using a Taguchi L27 orthogonal array to optimize the machining parameters: pressure, feed rate, abrasive flow rate, and standoff distance. The top kerf width (TKW) and bottom kerf width (BKW) were measured to evaluate the impact of these parameters. Results indicate that higher pressures and abrasive flow rates generally increase both TKW and BKW due to enhanced material removal rates. Conversely, increased feed rates tend to reduce kerf widths, highlighting the importance of optimizing cutting speeds. Standoff distance exhibited a less pronounced effect but still influenced the kerf widths. The optimal parameters for minimizing TKW and BKW were identified, providing valuable insights for improving precision and efficiency in AWJ machining of GFRP composites. These findings contribute to the development of more effective manufacturing practices for high-performance composite materials.

A genetic algorithm‐based virtual machine scheduling algorithm for energy‐efficient resource management in cloud computing

SummaryTo address the unbalanced resource load of a virtual machine cluster, the author proposes an energy‐saving virtual machine scheduling algorithm based on resource management cloud computing technology. This article analyzes the current cloud computing and virtual machine scheduling research in the cloud computing environment. It discusses the concept, characteristics, classification, application scenarios, and key cloud computing technologies. A genetic algorithm is used to solve the problem of high energy consumption in the data center. The test results show that in the same original configuration scheme, the migration times based on the greedy algorithm adopted by GA2ND are about 1000, and the migration times of GA1ST are between 200 and 500. The GA2ND migration scheme requires fewer virtual machines. In the result analysis, the experiments compare the proposed algorithms—DVFS, IMC, GA1ST, and GA2ND—with a focus on energy consumption and virtual machine migration. Notably, DVFS serves as a reference for energy efficiency, IMC represents the proposed algorithm without genetic optimization, GA1ST denotes the genetic algorithm under a heterogeneous model, and GA2ND signifies the enhanced genetic algorithm introduced in this article. The comparison aims to assess the energy efficiency and virtual machine migration performance of each algorithm in the context of a simulated cloud computing environment. Therefore, the algorithm proposed in this article can effectively reduce energy consumption and avoid frequent migration of virtual machines.

Impact of specialized renal technologists on optimizing delivery of continuous kidney replacement therapy in critical care areas a retrospective study.

Continuous renal replacement therapy (CKRT) is delivered to some of the most critically ill patients in hospitals. This therapy is expensive and requires coordination of multidisciplinary teams to ensure the prescribed dose is delivered. With increased demands on the critical care nursing staff and increased complexities of patients admitted to critical care units, we evaluated the role of specialized renal technologists in ensuring the prescribed dose is delivered. Therefore, the aim of this study is to investigate the impact of supporting intensive care unit nurses with specialized renal technologists on optimizing efficiency of CKRT sessions in the United Arab Emirates. This is a retrospective study that compared critically ill patients on CKRT overseen by specialized renal technologists versus who are non-covered in the year 2021. A total of 331 sessions on 158 patients were included in the study. The mean filter life was longer in specialized renal technologists-covered patients compared to the non-covered group (66 vs. 59 h, p = 0.019). After adjustment by multiple regression analysis for risk factors (i.e., age, gender, mechanical ventilation, sepsis, mean arterial pressure, vasopressors, and SOFA) that may affect CKRT machines' filter life, presence of a specialized renal technologists resulted in significantly longer filter life (co-efficient 0.129; CI 95% 1.080, 11.970; p-value: 0.019). Our study suggests that specialized renal technologists play a vital role in prolonging CKRT machine's filter life span and optimizing CKRT machine's efficiency. Further research should focus on other potential benefits of having specialized renal technologists performing CKRT sessions, and to confirm the finding of this study. Additionally, a cost-benefit analysis could be conducted to determine the economic impact of having specialized teams performing CKRT.

Analysis Of The Effect Of Mass Variation On The Coefficient Of Friction On Wood

The purpose of this study is to determine the coefficients of kinetic and static friction in order to identify areas where we can reduce unwanted friction, thereby enhancing the performance and efficiency of various devices or machines we use daily. This research employs a quantitative approach with an experimental design or practical activities conducted in a laboratory or controlled environment, where specific variables can be accurately measured. The collected data will be analyzed in numerical or statistical form. The values indicate that the kinetic friction coefficient between wood and wood is the smallest, at 0.14. The kinetic friction coefficient between metal and wood ranges from 0.28 to 0.30. This means that the kinetic friction force acting on a wooden block on a wooden surface is the smallest compared to other materials. The static friction coefficient between wood and wood is the highest, at 0.40. The static friction coefficient between metal and wood ranges from 0.23 to 0.32. This indicates that the static friction force required to initiate the movement of a metal object on a wooden surface varies depending on the mass of the metal.

The effect of temperature, pressure, and grind size on Total Dissolved Solids (TDS) and extraction yield of semi-automatic espresso machines

The number of coffee shops in Indonesia has grown from 1,083 stalls in 2016 to over 2,937 booths in 2019, representing a threefold growth. Coffee shop establishments must provide two essential kinds of equipment: espresso machines, which use pressure, and filter machines, which employ infusion. The issue lies in the exorbitant cost and immense power requirements of semi-automatic and automated espresso machines, which necessitate the use of a manual espresso machine for commercial operations. The equipment can generate satisfactory espresso but encounters several challenges; specifically, the espresso generated is characterized by inconsistency, constantly varying in quality. This might arise due to the erratic nature of the manufacturing process. The two objectives of this study are: (1) to design an economically efficient semi-automatic espresso machine capable of producing products that meet the international quality standards set by the Specialty Coffee Association (SCA standard) and (2) to investigate the impact of critical factors such as pressure, temperature, and grind size, on the consistent quality of the resulting coffee (measured by Total Dissolved Solids (TDS) and extraction yield (EXT)). The research employs the Research and Development (RD) methodology. The research findings indicate that the optimal levels of Total Dissolved Solids (TDS) and extraction yield (EXT) may be attained by using a pressure setting of 8 bars, a temperature of 90ºC, and a grind size of 3.2 on the scale. The technique for optimizing the response resulted in Total Dissolved Solids (TDS) levels of 10.03% and extraction yield (EXT) values of 19.56%. The results have been deemed acceptable based on the criteria set by the global standards of Specialty Coffee Association (SCA).

Cosmetic Shop Sentiment Analysis on TikTok Shop Using the Support Vector Machine Method

User reviews are crucial in today's digital world for determining a product's quality. Nevertheless, these remarks are frequently disorganized and erratic, which confuses people and makes it challenging for them to make wise purchases. The erratic character of these reviews breeds uncertainty and makes determining a product's actual value more difficult. To help consumers more effectively evaluate and select products on platforms such as TikTok Shop, this study uses sentiment analysis tools. It hopes to accomplish this by improving the overall shopping experience and empowering customers to make more confident and informed selections. This research aims to assist consumers in evaluating and selecting products on TikTok Shop, an online shopping platform, by employing sentiment analysis techniques that help consumers make more informed decisions. In this study, a total of 500 comments from TikTok Shop users were collected as data. 350 comments have been set aside for training and 150 comments were set aside for testing. Data was gathered employing scraping, an automated process that makes use of the Python library's Selenium module to retrieve data from the internet. We employed the Support Vector Machine approach, an efficient machine learning tool for text classification, to assess the comments. 121 comments were categorized as having positive sentiment and 29 as having negative sentiment based on the test results. The system successfully recommended the "Ourluxbeauty" cosmetics store as a shop with many positive sentiments, indicating a recommendation level of 0.7 on the positive sentiment scale. The system's accuracy was measured using a Confusion Matrix, resulting in an accuracy rate of 78% and an inaccuracy rate of 22%. This demonstrates that the system can accurately classify comment sentiments and has significant potential for application in e-commerce practices to enhance the online shopping experience.

A review of intrusion detection system and security threat in internet of things enabled environment

Thousands of devices communicate globally to share data and information without any human intervention. A network of physical objects with numerous sensors and other network hardware to exchange data with servers and additional devices that are linked is referred to as the "internet of things (IoT)”. The actions hurting the communication system are known as intrusions. Security features such as (integrity, and confidentiality) within IoT networks are compromised when any kind of intrusion occurs. To identify multiple infiltration types in an environment where IoT is enabled, an intrusion detection system (IDS) is required. In environments where IoT is enabled, security vulnerabilities are now more prevalent than ever. In this study, the IoT architecture is reviewed, and potential security risks at each tier are investigated. It is also hoped that this research will stimulate thought about the expanding risks posed by unprotected IoT devices. The paper also intends to provide an in-depth analysis of intrusion detection systems for identifying and classifying security threats in an IoT-enabled environment. Furthermore, this study investigates a variety of efficient machine learning-based methods for detecting cyberattacks on IoT devices.