Search

This study aims to analyze sales performance in a case study of a vending machine company in Central New Jersey in 2022. This type of research is a type of quantitative descriptive approach obtained from sales datasets. The indicators in case are transtotal per month per quarter in difference locations, total quantity per product categories, transtotal per machines, transtotal per payment type, and average price per product category. Using a data analysis process which consists of understanding business problems, data cleaning processes, data visualization processes, and providing recommendations based on the insights that have been obtained. The results showed that there was a decline in sales in the Q3 period from July to August of 10%. Based on the visualization data obtained insight that the locations that have the highest total sales are Gutten Plans, EB Public Library, BSQ Mall, then the lowest is Earle Asphalt. The best-selling product categories are food, carbonated, non-carbonated, then water and customers use more cash payment types. So that conclusions can be drawn to improve vending machine sales performance in the next period based on insight from the metrics that have been obtained. Such as adding vending machines in locations where there is a lot of demand, diverting products that are not selling well with products that have the highest sales. Relocating machines that have the lowest sales to more profitable locations. Adding non-cash payment types and lowering the selling price of mineral water due to the small demand. [ABSTRACT FROM AUTHOR]

It is compared how well a novel recurrent neural network predicts email spam to a support vector machine. Support vector machines and novel recurrent neural networks are two of the groupings included in this study. There are ten samples in each group, and the study's parameters include alpha value 0.8 and beta value 0.2. The G-power value of 80% was taken into consideration while determining the significance value of the dataset using SPSS. In the electronic mail spam detector, the Novel Recurrent Neural Network outperforms the Support Vector Machine by 97.96%, with a significance value of p=0.030 (p<0.05). The Novel Recurrent Neural Network performance study outperforms the Support Vector Machine performance analysis in the electronic mail spam predictor. [ABSTRACT FROM AUTHOR]

Linac output is one of physical parameters which determine the dose delivery to patients. The constancy of Linac output is important to be evaluated. The study employed 6 MV Linac SHINVA XHA 600C for the measurements of the absorbed dose to water were carried out with 0.6 cc ionization chamber type NE 2571 Farmer. In addition, the Percentage Depth Dose (PDD) and dose profiles were measured in water phantom which was equipped with ionization chamber Exradin A28. The PDD and dose profile were evaluated in the radiation fields 8 × 8 cm2, 10 × 10 cm2, and 15 × 15 cm2. The study of performance of Linac machine was done from 2020 to 2022. The absolute dose deviations were 0.708 ± 0.259%, 1.581 ± 0.739%, and 1.584 ± 0.736% for 2020, 2021 and 2022 respectively. In general, the average of Linac output within the tolerance level, though the standard deviation increasing for 2021 and 2022. Furthermore, comparison the PDD to baseline data shows the highest average deviations are 0.467% in the field of 10 × 10 cm2 in 2020, 0.55% in 2021, and 0.492% in 2022. On the other hand, the flatness and symmetry has the highest deviation to baseline data at about 0.202% to flatness and 0.115% to symmetry for three years study. The average machine output performance of Linac Shinva are within 2% tolerance limit based on recommendation of AAPM TG 40 and 142 for daily and monthly dosimetry constancy. The performance of the PDD constancy, flatness, and symmetry are also within tolerances limit ± 2% compared to baseline commissioning data. [ABSTRACT FROM AUTHOR]

Glass fiber polymeric composites (GFRP) are employed in airplanes and other structures due to several advantages over traditional materials. Conventional drilling of polymeric composites causes various types of damage, such as fiber pull-out, matrix cracking, fuzzing, delamination, spalling, and poor surface quality of the drilled surfaces, mainly owing to the anisotropic and inhomogeneous nature of composites. To mitigate these damages, Nanoclay with 1.25 wt% and 2.5 wt% were incorporated into the GFRP composite to explore their effect on the performance of drilling in terms of surface roughness (SR), entry and exit delamination factor (Fd). The influence of machining parameters, such as feed rate (FR) and spindle speed (SS), on these machining performances was also investigated. Comparing the 2.5 wt% woven GFRP to the neat and 1.25 wt% woven GFRP, the 2.5 wt% woven GFRP has shown less delamination and surface damage. The outcomes for all varieties of composites demonstrate that the SS and FR significantly influence SR and Fd. The main factors that optimize the intended machining performances are a decrease in the FR and a rise in the SS and nanoclay wt%. [ABSTRACT FROM AUTHOR]

Nowadays, induction machines can be considered the backbone of various industrial applications due to the many characteristics such as rigidity, simplicity, high reliability, and low maintenance that can be manufactured for a long time. However, poor efficiency and power factor and increased amounts of torque ripple and losses significantly impact the performance and hence its efficiency. Therefore, in order to improve the performance of induction machines, the special design topology for stator and rotor configurations must be investigated and correctly estimated. This paper presents the analysis of the variable geometries of the cage's rotating bars. More specifically, the influence of dimensions and positions, as well as the shapes of the rotor rods, have a significant impact on the dynamic performance (developed torque, starting torque, ripple torque, starting current, power factor, harmonics, output power, and efficiency) are investigated. The Finite Element Method (FEM) is used to create the optimum designs as well as calculations are used to optimize the shapes of rotor slots in order to improve starting performance characteristics such as starting current, initial torque, magnetic flux connection under starting conditions, and efficiency. Furthermore, the characteristic of the manufacturing material of the rotor are examined, and methods to reduce losses for an induction motor to enhance efficiency are examined. This paper focuses on the squirrel cage induction motor (SCIM). [ABSTRACT FROM AUTHOR]

Chemical machining is one of the basic non-traditional machining methods, material removal is based on controlled corrosion. The selected chemical solution which is called etchant is employed to attack material in a corrosive environment. Ultrasonic-assisted chemical machining is a kind of hybrid machining method to increase the performance of the basic method. In this study, AZ31B magnesium alloy is machined by this method and the effects of selected chemical machining parameters (temperature and etchant type) on the surface roughness and depth of etch are investigated. Two different etchants (hydrochloric acid-HCl and nitric acid-HNO3) are used at two different chemical machining temperatures (25°c and 50°C). It was observed that ultrasonic-assisted chemical machining performed faster machining comparing to chemical machining. Moreover, HCl etchant accomplished better machining performance than HNO3 etchant as well as high process temperature (50°C) against low one (25°C). Surface finish results were better comparing to chemical machining process to ultrasonic-assisted chemical machining. [ABSTRACT FROM AUTHOR]

Dry beans are a type of edible legume that is widely farmed around the world. The quality of the seedhas an impact on crop productivity. As a result, it is critical to classify the seed for large-scale manufacturingand marketing. Raisin is also one of the most common agricultural products derived from grape drying. We usedthe dry bean and raisin datasets from the UCI ML repository in this research work, which have 16 characteristics and seven classes in the dry bean dataset with 13611 observations and 7 attributes and two classes in the raisin dataset with 900 instances. The primary goal of this research work is to offer a comparative performance analysis of Machine Learning (ML) techniques: Logistic Regression (LR), Decision Tree (DT), and Artificial Neural Network (ANN). We have used the principal components analysis PCA technique to decrease the attributes of the datasets. The performance of these three classifiers‟ was compared using dataset parameters such as size, number of attributes, number of classes, class imbalance, and missing values. The accuracy, precision, recall, and F1-score of the classifiers were also compared. According to our findings, the ANN classifier surpasses all other techniques on two datasets: dry bean and raisin, with an accuracy of 89%. The results also show that the LR and ANN perform nearly identically, whereas the DT performs the lowest of all classifiers. [ABSTRACT FROM AUTHOR]

The current (mA) control is necessary to controlling the number of electrons and x-ray intensity at x-ray machine. Radiographers are likewise impacted by the presence of high radiation levels. This study aimed to improve performance the x-ray machine with wireless mA control system prototype. One of the important benefits of the proposed study is the simplicity to controlling intensity of x-ray based on wireless mA control system. This research method uses rheostat as current selection (mA). The current settings that can be selected are 20 mA, 30 mA, 40 mA, 50 mA and 60 mA, which can be done manually and via the mobile phone (cellphone) connected to this device via wireless using Wemos D1Mini. Tool testing is carried out by comparing the results of measuring the output voltage of the filament transformer using AVOmeter with the results of voltage calculation through formula analysis. In addition, tests are carried out for the distance of the tool control connection in the presence of obstacles and no obstacles. Based on the test results obtained, it is known that the smallest correction value is 0,01 VAC for the mA option of 30 mA. The x-ray device can be controlled wirelessly using Android up to a distance of 20 meters with a 14 cm thick wall obstructed condition. [ABSTRACT FROM AUTHOR]

The study aims to evaluate the performance of the Music Genre Prediction System using a Novel Support Vector Machine and Decision Tree. The MARSYAS website provided the GTZAN dataset utilised in this investigation, which is comprised of one thousand.au-formatted music files and is intended for use in Music Information Retrieval. It is currently considered the gold standard dataset. Mel-frequency cepstralcoefficients (MFCC) are retrieved from music files and used to make predictions about the genre. All steps, from analysing data to training a model to testing it, take place within Jupyter. SPSS is used to analyse the mean accuracies of two algorithms side-by-side. Accuracy, precision, etc., numbers came out differently depending on the size of the input data set. SVM and Decision Tree are used for classification, with N equal to 20 for each of the two groups (proposed and comparative). The value of the pre-test achieved is 0.08. This research shows that compared to the Decision Tree method, Novel SVM is more effective. In the Research study, SVM with 81.10% accuracy is found more effective, efficient, and faster when compared to the Decision Tree with 59.88% accuracy. [ABSTRACT FROM AUTHOR]

The primary purpose of this investigation is to compare and contrast the performance of two machine learning algorithms, namely the Lasso regression Algorithm and the Support Vector Machine Algorithm, in the context of accident prediction. Over the course of 20 iterations, utilising N=10 samples, the Support Vector Machine approach, and Lasso regression, the accuracy of accident predicting was tested. A substantial gap (84.28 percent) separates the performance of the Support Vector Machine method from that of the Lasso regression methodology (94.56 percent). A significance level of 0.001 has been assigned to the new SVM classifier (p0.05 independent sample test). Comparisons of data showed that the Support Vector Machine Novel classifier was more accurate than the Lasso regression in predicting the occurrence of traffic accidents. [ABSTRACT FROM AUTHOR]

Recently, the study of machine learning has gained prominence in the medical field. One of the most challeng-ing tasks in machine learning is creating accurate and reliable classifiers for medical applications. To find the best classi-fier, a comparative analysis of the most prominent machine learning classifiers—SVM, DT, RF, NB, KNN, XGBoost, AdaBoost, and CatBoost—has been done using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The perfor-mance of classifiers is evaluated in terms of accuracy, precision, recall, AUC, confusion matrices, and ROC. The results of the analytical comparison revealed that the SVM and RF classifiers outperformed other classifiers. Furthermore, the WDBC dataset used in this study has a class imbalance issue (malignant 212; benign 357). Imbalanced data sets produce skewed outcomes and deceptive accuracy. Data resampling was performed to fix the problem of class imbalance. [ABSTRACT FROM AUTHOR]

Milling is the most common machining method, a material removal procedure by cutting away the unwanted material. During the process, the engagement between cutting tool and workpiece will cause the fluctuation of cutting force and consumption of cutting energy. The cutting energy consumed affected the power consumption of the production and indirectly increase the production cost. The tool engagement also has a big impact on machining performances such as chip formation, tool wear, and integrity of the machined surface. The study related to tool engagement focused more on the effect on cutting force. However, not much attention given on the study of the effect of tool engagement on cutting energy. Hence, this study is to explore how different tool engagement angle affected the cutting energy. In addition, the result of tool wear and surface roughness also will be analyzed. In this study the experiment was conducted by using AISI P20 tool steel and 2 flutes coated carbide end mill. Cutting speed, feed rate and depth of cut are remains constant during the machining process which are 250 m/min, 100 mm/min and 0.2 mm respectively. The tool engagement angle varies from 90˚, 135˚ and 180˚. The cutting energy, surface roughness and tool wear were measured. From the result, it shows that cutting energy and tool wear is directly proportional to the tool engagement while the surface roughness is inversely proportional to the tool engagement. [ABSTRACT FROM AUTHOR]

The prevalence of gaps and outliers within datasets presents substantial challenges, particularly in the realm of time series fore-casting and various other predictive machine learning (ML) tasks. This paper, introduces an effective technique for correcting gaps and outliers in data and validates the approach by applying it to datasets with outlier zones drawn from three diverse contexts. This innovative technique holds promising potential to enhance the performance of machine learning models by treating the data to alleviate the complications posed by these issues and in doing so contributes a valuable tool to the data science toolbox. [ABSTRACT FROM AUTHOR]

Rotary electric discharge machining (REDM) is modification of traditional EDM in order to deploy rotating tool electrode suitable for improving performance characteristics such as surface finish. Cryogenic treatment of tool electrodes and work materials may also improve the machining performance of EDM process. The current study reports the influence of important control parameters on surface roughness of while cryogenic treated copper electrode was used for machining of cryogenic treated alloy Monel-400 alloy in rotary EDM process. The one factor at a time (OFAT) approach was used to conduct the experiments to investigate the effect of input variables such as current, pulse on time; duty cycle on surface roughness. SEM examination was also conducted to understand machined surfaces produced by rotary and stationary tool electrode. [ABSTRACT FROM AUTHOR]

One of the major factors for rising death rates around the world is diabetes. Diabetes is a condition that occurs due to a deficiency, inefficiency, or inadequate secretion of the hormone insulin in the patient body, and from chronic problems that affect carbohydrate metabolism and rise blood glucose levels. The rising rates of diabetes require scientific works to early predict diabetes for the prevention and treatment. Researchers have recognized the effectiveness of classification models created using machine learning approaches for disease prediction. In relation to diabetes, researchers are working to provide data-based scientific methods for detecting the disease. The aim of this study is to classify people based on their diabetes condition using different machine learning methods. Two datasets are utilized for this purpose; Pima dataset collected from Indian society and dataset obtained from Iraqi society. The results show that Logistic Regression has highest accuracy of 0.77% when applying Pima dataset, while Gradient Boosting Classifier gives best performance with accuracy 0.977 when using Iraqi society dataset. [ABSTRACT FROM AUTHOR]

The Research Center for Agroindustry developed the two-stage pasta extruder machine for making pasta products, such as noodles, macaroni, and sago rice. This machine has been used in several regencies in Indonesia. This supports the national program of food diversification based on local resources. The machine must be evaluated to get the best results and satisfy its users. The objective of this research was to evaluate the performance of the two-stage pasta extruder machine and to formulate product improvement strategies. Data was collected through questionnaires to the machine users in Grobogan (Central Java), Kupang (East Nusa Tenggara), and Jayapura (Papua) regencies. The data processing technique used in this research is to translate user desires into the technical specifications of products using the Quality Function Deployment (QFD) method. The level of user satisfaction with the machine was used to assess machine performance. The results of this study obtained 25 product satisfaction attributes, all considered necessary by users. The average level of user satisfaction with the machine's performance reached a score of 3.19 or was in the satisfied category. Strategies to improve the quality of this machine include: a) using a reliable driving machine by paying attention to the energy required; b) availability of spare parts components; c) adding a fan to the motor housing; d) housing screw equipped with an automatic heat limiter indicator; e) use of a blade mixer and speed controller; and variations in the gear size for the screw. [ABSTRACT FROM AUTHOR]

This paper presents machine learning algorithms for predicting different stages of breast cancer tumour such as benign and malignant. Machine learning (ML) models such as Logistic regression (LR), Decision tree (DT), Naive Bayes (NB), Support vector machine (SVM), K-nearest neighbour (KNN), Random Forest (RF) and XG Boost (XGB) used for predicting different stages of breast cancer. The Breast cancer data is collected from UCI machine learning Repository, this data is used training and testing the machine algorithms. Performance and evaluation of machine learning algorithms using confusion matrix and metrics are used Accuracy, Precision, Recall and f1-score. Support vector machine (SVM) performed better result of metrics score to compared with other machine learning algorithms. [ABSTRACT FROM AUTHOR]

There are many coating materials, coating structures and different coating thicknesses. During the milling process, it is necessary to investigate the impact of coating thickness. The paper's main objective is to numerically compare the performance of tungsten carbide (WC) with and without a TiAlN coating while milling of AISI 1045 medium carbon steel in terms of tool temperature, cutting forces and tool wear. The effect of variation of the TiAlN coating thickness (between 1 to 4 µm) was observed; to study its significance on the machining performance of the tool and to find out if there is a particular optimum coating thickness. Following this, the milling process was simulated in Deform 3D simulation software for the uncoated tool and different coating thicknesses. In terms of tool wear, coated tools outperformed uncoated tools, and the coated tool with the highest machining performance had a coating thickness of 2 µm. [ABSTRACT FROM AUTHOR]

This paper presents the work carried out to study the effect of EDM process parameters viz., flushing pressure, pulse-on time, current and pulse-off time using Ti-6Al-4V as workpiece material. The output parameters considered are material removal rate (MRR), surface roughness and Tool Wear Rate (TWR) and three different tool materials viz, copper, bronze and brass were used for comparison. To control the economic issues, experiments were conducted using Taguchi's techniques by varying machining process parameters at three levels and the number of experiments were limited to 18 following the L18 orthogonal array of Taguchi's method. The results obtained were analyzed by comparing the effect of each input parameter on the characteristics of machining, and for predicting the optimal choice for each machining requirement. From this study, observed that the pulse-on time is the highly influencing input process parameter for the substrate machined using copper (Cu) electrode. [ABSTRACT FROM AUTHOR]

Among the various machining processes, turning is one of the most common and essential process. This process generates a high temperature due to the frictional interaction of tool with the workpiece material. To reduce this temperature, cutting fluids based on mineral oil are extensively utilized as a lubricant and coolant. However, these cutting fluids have an adverse effect on human health as well as on the ecosystem. So, to accomplish sustainable machining, researchers are forced to pay attention to the development of environmentally friendly cutting fluids, which could also result in a significant improvement in machining performance. This paper describes an experimental investigation executed during the turning operation of AISI 1040 steel using palm oil as a cutting fluid, and the results are compared with dry cutting and mineral oil-based cutting fluid. The effectiveness of palm oil was evaluated by considering tool wear, chip morphology, and surface roughness. Results showed that palm oil as a cutting fluid would have a 55 percent lesser reduction in tool wear compared to dry cutting and 25 percent less compared to mineral oil-based cutting fluid. Palm oil as a lubricant also showed better heat carrying capacity from the cutting zone, which reduces the surface roughness and extends the tool life. [ABSTRACT FROM AUTHOR]

The article deals with the issue of formation and depletion of the plasticity reserve of the metal of the product in the process of its life cycle. A method of acoustic emission is proposed for monitoring and predicting the operational characteristics of mechanical engineering products. The results of the study allow us to recommend a method for introducing into the structure of the processes of both the manufacture of a product and its operation. The perspective directions of pyrene acoustic emission systems for monitoring infrastructure facilities are considered. [ABSTRACT FROM AUTHOR]

Selection of the optimum machining parameters is essential to enhance the performance of the machining process. These parameters will determine the quality of surface finish, rate of tool wear, material removal rate and production cycle time. This research focused on obtaining the optimum machining parameters by minimizing the machining time in pocket milling operations. The parameter such as feed per tooth, cutting speed,and depth of cut are considered the important variables to minimize the machining time in milling process since it has produced a significant consequence on the machining process. Genetic Algorithm (GA) has been implemented to obtain the optimum parameters. A fitness function of production time incorporated of roughing and finishing process has been developed in Matlab Software. Then, Genetic Algorithm Toolbox has been employed to conduct the computational experiment. Mastercam software has been used to verify the algorithm's results by applying the optimum parameter generated by GA in the Mastercam. Based on the comparison, it has been found that the difference in machining for both methods is 3.48%. It shows that optimization based on GA is capable of reducing production time in the machining process. [ABSTRACT FROM AUTHOR]

In a factory and firm, Sawdust has been commercially produced as an activated carbon briquette. Research on this 'waste' raw material gradually becomes interesting for finding an alternative fuel for the roof tile furnace. The bio-conversion can be conducted to transform the sawdust into heat energy. The flame stability influences the quality of a good roof tile in the furnace. The method to conduct this research was true experimental research as the data gained was the result of the experiments conducted. This experimental study was selected to test the hypothesis properly. This study shows that opening the valve is 3 mm wide during 480 seconds and 0.0063 kg of sawdust as the fuel gives optimum calorific energy, 53.307 kJ. Meanwhile, the calorific energy of 7.6152 kJ is obtained with 0.0036 kg sawdust as the fuel and the opening time of the valve within 120 seconds. [ABSTRACT FROM AUTHOR]

Machine learning algorithms are applied for measuring the performance of robot-assisted cerebral palsy rehabilitation training system. Such approach allows an analysis and predictions about the system reaction to be done with high accuracy. The rehabilitation training actions of children with cerebral palsy are focused on imagination and conscious control of the face, such as left or right exercises. The aim of the designed interface interaction module is to motivate and to improve the training enthusiasm of the children with cerebral palsy to continue with the rehabilitation therapy avoiding the thoughts about the pain, tiredness and discomfort. The robot is simulated in the platform CopeliaSim. [ABSTRACT FROM AUTHOR]

Plastics are one of the biggest waste in the world and are difficult to recycle. One of the methods used to recycle plastics is by a distillation machine. Condensor is one part of the distillation machine that is used to condense liquid vapor from the plastic burning process. There are three variables used to investigate the performance of the condenser, namely heat released, condensation rate, and condenser efficiency. Consideration in using temperature difference for analysis is developed in this study. The temperature difference is obtained based on the cooling water temperatur used. Extrapolation is used to get the outlet temperature of the cooling water. Five variations of cooling water temperature were used in this study to get the temperature difference, namely 10 oC, 15 oC, 23 oC, 27 oC, and 30 oC. The temperature difference obtained is based on the cooling water temperature, namely 20 oC, 26,6 oC, 35,4 oC, 53 oC, 64 oC. The result shows that from the temperature 20 oC to 64 oC, there is an increase in heat released from 83,72 kJ/s to 267,904 kJ/s, the condenssation rate and condenser efficiency are also increased from 0,468 kg/s to 1,499 kg/s and 12,369 % to 39,582 %. [ABSTRACT FROM AUTHOR]

The design of the small-sized equipment package is presented, where the base machine was a gravity-forced mixer for the preparation of high-quality polystyrene-concrete mixture with the addition of fiber elements and its further use in production. All equipment included in the package works with the same production when combining operations over time. The design of the basic machine - the mixer working in the cascade mode is resulted. Dependencies to determine the main performance of machines (production, power), which show their relationship to each other are also given. [ABSTRACT FROM AUTHOR]

Business owners, investors, governments, banks, securities, and other financial participants have increasingly relied on bankruptcy prediction as a way to protect their assets. Managers and investors can make informed decisions about economic strategies by analysing data such as financial position, cash flows, balance sheets, income statements and other financial ratios available in financial statements. A thorough investigation into how the presence of samples of varying natures in the positive class may affect the predictive performance of machine learning models could be instructive, given the significance of incorrectly identifying default or bankrupt cases. In this study, we used an imbalanced dataset of Polish businesses to predict bankruptcy and investigated the performance of oversampling techniques combined with ensemble machine learning models to improve forecasting accuracy. According to simulation results, our approach achieved 99% accuracy and outperformed existing approaches in the literature. [ABSTRACT FROM AUTHOR]

Utilization is the percentage of resources or machinery used in a manufacturing operation. Machine utilization could operate at a lower percentage due to maintenance, production management, machine failure, and workforce issues. Machine utilization is one of the critical metrics to analyze the performance of machines in an assembly line. Thus, this research was conducted to simulate a set of logical process flows along a sub-assembly line to analyze machine utilization over a period of simulation time by using discrete event simulation model. The simulation results show that Testing Machine 1, Testing Machine 2, and Testing Machine 3 each has utilization rate of 81.562%, 71.402%, and 56.242% respectively. The machine utilization rate is capped at 100%, which indicates that it is fully utilized. The utilization rate provides the information that the machine is being utilized or in a busy state. On the other hand, the remaining rate by subtracting 100% and utilization rate means that the machine is not being utilized or in an idle state. As conclusion, effective use of available resources such as machinery is beneficial to productivity. In addition, simulation is a useful tool to analyze the expected performance of new or existing equipment or machinery. [ABSTRACT FROM AUTHOR]

Feature selection is method of removing features from a data set that are unrelated to the task at hand. Many factors influence feature selection, including simplistic analysis, efficiency, computation time, and feature interpretability. It applies to both unsupervised and supervised learning methods. Multimedia technology is increasing interest, and everyone involved in technology must understand the possibilities it presents and current limitations of technology. Such strategies are capable of increasing the performance of machine learning methods as well as training. Feature selection decreases learning run time while enhancing data quality and comprehension. In this paper, different methods of feature selection and research gaps are discussed for large scale data. [ABSTRACT FROM AUTHOR]

The CNC vertical milling machine is widely used by many manufacturing industries due to its ability to produce high variety of products with moderate production quantities. The performance of machine tools determined by the quality of the product. Therefore, the machine must be checked periodically to determine its condition and its ability. Testing, an activity to check the condition of the machine tools, were done by measuring the geometric error so that the accuracy of the machine tools can be known. In general, there is more than one method of geometric accuracy testing of machine tools and each has its advantages and disadvantages. This research aims to compare the advantages and the disadvantages of geometric accuracy testing methods and its applications. Hence, maintenance operators in the industry can choose the right method. There are two kinds of methods to measure geometric errors in machine tools, namely direct measurement and indirect measurement. Direct measurement method is often used by operators to measure the geometric errors in machine tools due to its ease to use. The indirect measurement method is performed by involving several axes movement to measure geometric errors and machine tools errors are determined from further examination of the resulting workpiece, making it more difficult and rarely used. The method of direct measurement could be divided into three, namely material-based instrument, laser-based instrument, and gravity-based instrument. These three methods were compared using comparative method based on seven specified criteria. The result showed that material-based instrument method is more suitable if the measurement length is less than 1600 mm and laser-based instrument method such as laser interferometer is more suitable to measure high precision machine tools and has a large dimension, above 1600 mm, like a gantry machine. [ABSTRACT FROM AUTHOR]

Many types of machines widely used in Industrial application process. The main objective is to recognize faults failure based on motor speed and vibration signal. To find fault machine with the use of vibration analysis in turning equipment and induction motor. Every defect can associated with cost and performance of the machine. Due to these associated risk such as cost, time, efficiency early detection, isolation and failure prediction is important. Using machine learning algorithm to predict the fault failure rate of machine easily. Signal level are monitored with vibration analysis. Depends upon the vibration signal faults are identified and classified. In this paper we discuss to classify the bearing the fault using different data mining techniques. To predict the imbalance condition, fault in bearing, and broken rotor bars faults are predicted using machine learning algorithm. [ABSTRACT FROM AUTHOR]

Breast cancer starts in the breast and develops into a tumour as a result of aberrant cell proliferation. One out of every four cancer cases in women worldwide is breast cancer. As the disease advances, survival becomes more difficult, and the woman in Indiawith more than half of breast cancer cases is diagnosed with advanced stages of breast cancer. Three data mining approaches are used in this study to build a model for early breast cancer diagnosis: Decision Tree, Support Vector Machine, and Artificial Neural Network, and their performance are compared to find the best method for breast cancer prediction. These approaches were tested using the Breast Cancer Wisconsin Original Dataset, which is available in the UCI Machine Learning Repository. The K-Nearest Neighbor approach is used to pre-process the data in this study so that missing attribute values can be filled in the dataset. According to the findings and comparison of outcomes, the algorithm Artificial Neural Network outperforms the other two methods for breast cancer prediction. [ABSTRACT FROM AUTHOR]

Esports domain is growing with an goal to give the player a skill set to improve his skills. The paper, gives detail analysis performed on a dataset which is built by our team. The data used in the dataset is collected from Counter-Strike: Global Offensive (CS:GO) world championship major where top teams from all over the world had participated. The main goal was to create a customized dataset, predict the winning percentage for a team based on various features. It also provides descriptive analysis for a team's performance and prescriptive analysis for any improvements required to made by the team in order to improve their winning percentage and implementing different machine algorithms on the same. Extra features such as assigning roles, ranking and rating were also performed to provide in depth results. [ABSTRACT FROM AUTHOR]

Most real-world classifications problem provides an uneven, skewed dataset. Imbalanced datasets are a key issue in machine learning. The challenge for any machine learning algorithm to learn from imbalanced dataset is correctly classifying cases from the minority class. Imbalanced dataset leads machine learning algorithms to misclassify cases from the minority class which is undesirable for real world classification applications and also degrades the performance of algorithm. Glass identification dataset is one of the datasets that serve as a example of skewed imbalance real world dataset. The majority of research on glass identificationtasks ignores the data outlier and class imbalance found in this dataset. Class imbalance, data outlier, and insignificant featuresare only a few of the factors that contribute to the poor performance of distance-based machine learning methods such as kNN. Thus, this paper explores the performance of one of the most simple and efficient machine learning classifier kNN. The authors performed interquartile range (IQR) thresholding to eliminate data outliers, ReliefF ranking to find significant features and SMOTE to cope with the class imbalance occurring in the dataset. The Inverse distance weighted kNN is utilized for classification in the improved dataset. The results revealed that using the strategies mentioned improves the performance of the kNN algorithm while also providing accuracy that is better and more dependable than much of the research done in this dataset. In this paper the authorsfound the highest accuracy of glass identification task is 78.923% with F-measure 0.791. [ABSTRACT FROM AUTHOR]

A study of vibratory signals is used in order to evaluate the condition of the dried vacuum pump. The use of smart data-driven health performance in manufacturing facilities minimizes maintenance expenses. Monitoring reductions in machine performance or degraded performance will make maintenance scheduling more effective. Measuring the performance of the dried vacuum pump before an unexpected failure allows early troubleshooting and industrial-specific pump replacement. The semblance analysis is used for the assessment of a healthy vacuum pump and a long-operated pump which is about to fail. Significant differences in the semblance analysis suggest significant reductions in pump performance and maintenance. This indicator is very important for industrial players so that proper early action can be taken. This early action extends the life of the pump before severe failure. [ABSTRACT FROM AUTHOR]

Obesity problems have actually come to be a worldwide epidemic that has increased since 1980, with significant repercussions for health and wellness in young adults, adults, and youngsters. Obesity problems are an issue that has actually been expanding steadily which is why daily appear new studies entailing youngsters' excessive weight, specifically those looking for influence elements as well as exactly how to predict the appearance of the condition under these elements; for this reason, early detection is called for. Data mining and also machine learning (ML) algorithms approaches are made use of in obesity problems forecast in our research. We made use of the Obesity Level dataset for our study, accumulated from the UCI Machine Learning Repository. The dataset includes information about 638 patients as well as their matching 17 attributes. We made use of nine ML algorithms on the dataset to predict obesity problems. We found that the model with Logistic Regression algorithm is well on obesity level prediction. The result validated Logistic Regression algorithm has the best performance of accuracy (100%), sensitivity (100%), specificity (100%), as well as AUC (1). The Logistic Regression model was selected because to its best performance, best gain, and fastest total time. [ABSTRACT FROM AUTHOR]

The reduction of the twist triangle on ring spinning machines has a significant impact on the quality of the yarn and the performance of the machine. However, various design changes can also cause inconvenience in servicing the machine. In this study, a new design was proposed by the researchers to reduce the torsion triangle, and preliminary experiments were conducted on this structure as a device. Experiments have shown that the reduction of the twist triangle in ring spinning machines has a positive effect on machine productivity and the number of yarn breaks. At the same time, the increase in the strength of the yarn also indicated the need to continue research as well as theoretical research. [ABSTRACT FROM AUTHOR]

This review is based on the analysis of different papers published with experiments conducted for better surface finish while varying disimilar cutting parameters throughout CNC machining of Titanium (Ti) Alloy. It deals with the analysis of operations done on CNC machine in order to perform turning on titanium alloy, Ti-6AL-4V. Analysis was conducted considering number of factors while varying cutting variables like feed rate, depth of cut, spindle speed/ rotational speed and also lubricants were varied into different combinations to find the effects on the material and the performance of the machine and different outputs thus obtained. [ABSTRACT FROM AUTHOR]

Selection of suitable parametric combinations for micro-electro discharge machining (micro-EDM) process to attain desired response values is usually observed as a complex task as it is mostly affected by a large number of process parameters and differing responses. It mostly depends on the operators' experience or requires a number of trial runs which is not desirable from the economic viewpoint. The present paper emphasize towards the application fuzzy logic as a prediction tool for prediction of machining performance measures for micro-EDM process while machining on Ti-6Al-4V work material. Machining process parameters for example pulse-on-time, peak current, gap voltage and flushing pressure are selected as the controllable parameters, while material removal rate, tool wear rate, overcut and taper are observed as the responses. The values attained for each response using the developed fuzzy-based model is found to have a close match with those obtained in actual experimental runs. The calculated root mean square percentage error (RMSPE) and correlation coefficient (R) also justifies the effectiveness of fuzzy logic as a prediction tool for prediction of response values for micro-EDM process. [ABSTRACT FROM AUTHOR]

Liver disease is a disease that affects many humans. Machine learning that is developing at this time, is also widely implemented in the medical field. In this study, machine learning was used to estimate liver disease. To improve the performance of the estimation results, data pre-processing is carried out in the form of data transformation with exponential smoothing (ES). From the experiments carried out, it turns out that the results of the machine learning performance increase. And the lowest RMSE results were obtained from the optimization of the knn method and the best average RMSE was obtained from the neural network (NN) method. [ABSTRACT FROM AUTHOR]

The best job selection is enhanced with job assortment, PM selection and VV algorithms. The performance of Machine Utilization Algorithm (MUA) compared with other task scheduling algorithms In the cloud computing environment most noteworthy problem is task scheduling to augment the concert and effectiveness of cloud it is an important move. Informed search algorithms in Artificial intelligence are applied to execute the arrangement in cloud. The MUA is used to allocate the job to Practical Machine (PM) and Virtual Vehicle (VV). In the MUA the best one as first priority assortment of job is used which may relegate the concert of cloud for minimization of mean flow time with given process time and travel in the example problem [ABSTRACT FROM AUTHOR]

In the MUA the best one as first priority assortment of job is used which may relegate the concert of cloud for minimization of mean flow time with process time double and travel time halves in the example problem. In the cloud computing environment most noteworthy problem is task scheduling to augment the concert and effectiveness of cloud it is an important move. Informed search algorithms in Artificial intelligence are applied to execute the arrangement in cloud. The MUA is used to allocate the job to Practical Machine (PM) and Virtual Vehicle (VV). The best job selection is enhanced with job assortment, PM selection and VV algorithms. The performance of Machine Utilization Algorithm (MUA) compared with other task scheduling algorithms [ABSTRACT FROM AUTHOR]

Proper measurement is essential to ensure a good performance of a machine to produce a high-quality product. To have a good measurement, the first thing to consider is the datum since it is used primarily for manufacturing and inspection setups. However, the common datum as defined by ASME and ISO somehow is not practical to be used for a rotating machine tool. Thus, this paper focuses to define an appropriate datum for a 3D simulated surface by including a possible source of variation or error that may exist. To achieve the objective of this paper, surface reversal measurement is used as the main approach along with aid of the correlation function in the image-processing tool. Development of the surface reversal algorithm begins as two simulated surfaces are created and undergo surface correlation to achieve the best match point between both surfaces. Then, after one of the surfaces is translated to the desired position, surface subtraction is conducted to determine the inclined plane (real datum) of the simulated surface. The algorithm ends with the validation process through surface characterization by comparing the Sz value. As a result, both surfaces show different Sz values although both have the same surface topography and result for A minus with the real datum (LSPAB) providing less error on the surface topography data compared to A-minus with AB. This evaluation proves that an appropriate datum is necessary for every measurement so that the result obtained is accurate. Moreover, the objective to improvise the datum definition is successfully achieved since the error found along with the datum has been removed. [ABSTRACT FROM AUTHOR]

Papua and West Papua Province have the largest sago potential with about 4.75 million ha and 0.51 million ha, respectively. Unfortunately, relative to its potential, sago starch production and usage in these areas is very low. Every year, millions of tons of starch go unused. This is due to the fact that the majority of farmers continue to employ the old-fashioned way of processing. The most laborious stage in traditional sago processing is pith disintegration, which usesa pounder. Using a rasping machine to dissolve the pith, on the other hand, saves a lot of time and energy. The goal of this research was to see how cylinder diameter and hopper angle affected cylinder-type sago rasping machine performance. The study looked at two different cylinder diameters, 15 cm, and 20 cm, as well as three different hopper angles, 0 degrees, 22.5 degrees, and 45 degrees. The rasping capacity, starch rendement, and starch losses in sago pith waste were all measured to assess the rasping performance. The results showed that the combination of cylinder diameter and hopper angle had a significant impact on rasping capacity and starch rendement, but not on starch losses in sago pith waste. The combination of a 20 cm cylinder diameter and a 22.5-degree hopper angle produced the best rasping results. At the condition, the rasping capacity was 1,603 kg per hour, the starch rendement was 43.93 percent, and the starch losses in sago pith waste were 15%. [ABSTRACT FROM AUTHOR]

The continuous development of the 3D printing machines will bring a negative impact for the environment due to an increase in the amount of plastic waste that might occur. The production of 3D printing filament from recycled plastic material is one of the aLDPEropriate steps to overcome the problem of plastic waste, besides, this is also in line with the increasingly widespread use of 3D printing machines, especially with the FDM method. However, the right parameters are needed to process the filament from recycled plastic materials into printed product by considering the quality of the result. Therefore, this research was conducted with the aim to obtain the optimum process parameter toproduce the maximum product quality for 3D printing process with FDM technique using filaments from recycled plastic materials. This research uses a 3D Printing machine type FDM and recycled plastic filament of LDPE (Low Density Polyethylene)as printing material. The parameters are printing temperature, layer height and printing speed. The quality is measured by the dimensions which consist of length (x-axis) and width (y-axis), geometry which consist of perpendicularity and parallelism, and roughness of product surfaces. Data processing uses Taguchi method combined with PCR-TOPSIS. The results show that the optimum parameters for LDPE recycled filament are combination from printing temperature of 230 °C, 0.16 mm layer height and printing speed of 30 mm/s. The most decisive parameter to the quality of 3D printing products from recycled LDPE is printing speed. [ABSTRACT FROM AUTHOR]

In our study, we addressed the operational productivity of road machinery — the main criterion linking the life cycle of the road and that of the road machine. Methods. Most road machinery operation studies address such issues as maintaining the technically sound state: reducing the failure rate, optimizing the time and adjusting the frequency of maintenance and repair, etc. However, this is not sufficient for high-quality performance since it depends on many other random factors. An integrated approach is required that, based on the volume of work, would allow us to determine, analyze, and forecast machinery performance. Results. By integrating the values of the planned and actual volume of work, we obtained the values of the planned and actual operational productivity — the necessary and sufficient condition for performing the required volume of work. The locations or days of the month when the required volume of work was not performed in the period under review were determined by the actual utilization factor. Discussion. From a technical point of view, the situation when the values of the planned and actual operational productivity coincide is ideal since in this case the resource balance is ensured to the fullest extent. Possible cases of critical decreases in the operational productivity were analyzed mathematically. Conclusions. The proposed methodology makes it possible to analyze road machinery performance at the operation stage and evaluate road machines during their design, production, and disposal. In this case, it is enough to use in-house resources and mathematical apparatus for scientific analysis. [ABSTRACT FROM AUTHOR]

This paper presents the image-based tool wear detection using an image processing approach for face milling operation to prevent the workpiece surface roughness which is affected by the worn cutting tool. Based on the previous research, it was found that lack of monitoring of detection tool wear percentage to determine the condition of the cutting tool which the cutting tool needs a replacement or can continue used for the machining process. When the workpiece machining length increases, the machining time increases. The cutting requirement will increase based on their tool lifespan which will increase the percentage of tool wear rapidly. Therefore, the tool wear monitoring procedures applied after several milling processes such as image-based tool wear percentage detection by using an image processing approach for uncoated carbide tools, tool life criteria based on flank wear according to ISO 8688-1:1989 for uncoated carbide tools, and surface roughness quality according to ISO 4288:1996 for mild steel (AISI 1045) workpiece. The results indicated that the percentage of wear increase up to 50 percent with the cutting length and machining time. The surface roughness of the test material also increased linearly with increases in cutting length and machining time. In conclusion, the image-based tool wears percentage value detection by using an image processing approach has a potentially sustainable and economical expenditure for determining tool life criteria to sustain the machining performance. [ABSTRACT FROM AUTHOR]

The use of proper geometrical feature of cutting tool can improve machinability of hard material such as titanium alloy. In addition, machining titanium alloy leads to localized temperature increment at the machining zone, and their reactivity with most cutting tool materials becomes a problem for machinist. The objective of this study is to relate the effect of differential pitch angle and margin presence of end mill in terms of machining performance when end milling titanium alloy Ti6Al4V. In this study, side milling with the implementation of minimum quantity lubrication (MQL) technique was investigated. Cutting temperature and cutting force during machining were observed. Tool T2 recorded 24% increment of cutting temperature and 48% increment of cutting force compared to tool T1. From the results of cutting temperature and cutting force, Tool T1 is better compared to tool T2 due to the presence of geometrical design features. [ABSTRACT FROM AUTHOR]

The boom is considered the most critically affected part of Long Arm Excavators in severe work conditions, where high forces and unpredictable environmental elements at the worksite could severely affect the machine's overall performance. A potential solution to improve the boom's robustness is via stiffening. As an industrial collaborative project, the present study examined the performance of an existing machine via simulated improvement of the boom with such an approach, i.e. incorporation of stiffeners on the boom. Simulation works were carried out with Ansys Workbench 19.2 to assess the boom's performance in terms of resulting stress, strain and deformation under a series of stiffening configurations, which included varying the dimensions and positions of the stiffeners on the boom. The improved conditions were Improvement I: stiffener's thickness reduction to 10 mm, Improvement II: a combination of different stiffener's thickness reduction to 10 and 8 mm at critical and non-critical parts of the boom, Improvement III: removal of half intermediate 12 mm thick stiffeners, and Improvement IV: removal of half intermediate 8 mm thick stiffeners. From the analysis, it was found that the maximum equivalent stress of the boom decreased with the number of stiffeners incorporated. The combination of different stiffener's thickness could also increase the boom's strength while decreasing the maximum equivalent stress. The lowest maximum equivalent stress of the boom was achieved via Improvement II with a reduction of 26.1%. Removal of non-critical part stiffeners also kept stress values under the designated stress limits against fatigue failure, i.e. 44 MPa. In summary, performance optimisation appeared to be achievable with improvement II. [ABSTRACT FROM AUTHOR]

Aluminium alloys are commonly used in the aerospace, automobile and electricity transmission industries due to its excellent strength to low weight ratio. The demand of high accuracy machining in the market today has made the optimizing of the machining parameters an important aspect of machining. Aluminium alloy Al7075-T651 is a ductile material. In continuous machining operation like turning, high amount of friction and heat is generated. This may cause the workpiece's material to adhere to the rake face of the cutting insert and lead to the built-up edge (BUE) formation. This BUE will detach and adhere to the chips in a way the surface roughness of the workpiece would be affected. This project is focusing on the machinability of aluminum alloy Al7075-T651 by measuring the performance of KW10 uncoated carbide cutting tool in terms of flank wear, surface roughness of the machined surface, wear mechanism and volume of material removed. The turning experiment was conducted in dry condition. The cutting speed range was 250 and 450 m/min whereas the feed rate range was 0.05 and 0.15 mm/rev. The depth of cut was kept constant at 1 mm. The results showed that the higher cutting speed and feed rate produced higher flank wear progression and higher surface roughness reading (Ra). The adhesive and abrasive wear can be seen through the SEM for all sets of parameters. It was identified that higher cutting parameters removed higher amounts of volume material with shorter tool life. [ABSTRACT FROM AUTHOR]