Explore the vast range of titles available.

A large number of parameters significantly affect the performance of electrical discharge machining (EDM) which is a non-conventional technique. The choice of the EDM parameters depends on workpiece-electrode material combination. So, the selection of parameters becomes intricate. This manuscript presents the surface characteristics of the machined surface in EDM on Ti-5Al-2.5Sn titanium alloy. The surface roughness and the microstructure of the machined surface are explored for different EDM parameters and electrode materials. Experimentation was accomplished using negative polarity of copper, copper-tungsten and graphite electrode. In this study, peak current, pulse-on time, pulse-off time and servo-voltage are taken into consideration as process variables. The surface roughness is greatly influenced by peak current and pulse-on time among the selected electrical parameters. Among the three electrodes, the copper electrode produces the lowest surface roughness whilst graphite electrode gives the highest surface roughness. The surface characteristics (crater, crack and globule) are distorted on account of discharge energy. In context of fine surface characteristics, the copper can become as first choice electrode materials.

Consolidated efforts have been made to enhance the treatment and diagnosis of heart disease due to its detrimental effects on society. As technology and medical diagnostics become more synergistic, data mining and storing medical information can improve patient management opportunities. Therefore, it is crucial to examine the interdependence of the risk factors in patients' medical histories and comprehend their respective contributions to the prognosis of heart disease. This research aims to analyze the numerous components in patient data for accurate heart disease prediction. The most significant attributes for heart disease prediction have been determined using the Correlation-based Feature Subset Selection Technique with Best First Search. It has been found that the most significant factors for diagnosing heart disease are age, gender, smoking, obesity, diet, physical activity, stress, chest pain type, previous chest pain, blood pressure diastolic, diabetes, troponin, ECG, and target. Distinct artificial intelligence techniques (logistic regression, Naïve Bayes, K-nearest neighbor (K-NN), support vector machine (SVM), decision tree, random forest, and multilayer perceptron (MLP)) are applied and compared for two types of heart disease datasets (all features and selected features). Random forest using selected features has achieved the highest accuracy rate (90%) compared to employing all of the input features and other artificial intelligence techniques. The proposed approach could be utilized as an assistant framework to predict heart disease at an early stage.

Electrical discharge machining (EDM) is a non-conventional process for shaping hard metals and forming deep and complex-shaped holes by spark erosion in all kinds of electroconductive materials. The choice of the electrical parameters on the EDM process depends impressively on workpiece-electrode material combination. In this research, an effort has been made to study the surface finish characteristics of the machined surface in EDM on Ti-5Al-2.5Sn titanium alloy. The microstructure of the machined surface is investigated for discharge energy and electrode materials. The peak current, pulse-on time, pulse-off time, servo-voltage and electrode material (copper, copper–tungsten and graphite) are considered as process variables. The experimental work was performed based on an experiment design (central composite design). The surface roughness (SR) increases with peak current and pulse-on time and decreases with servo-voltage. Besides, the effect of the process parameters on surface roughness depends on electrode material. At low discharge energy, copper–tungsten electrode produces the finest surface structure whilst graphite delivers worst surface characteristics. Copper–tungsten with low discharge energy (low peak current and pulse-on time) can be used to obtain better surface finish.

In the internet of things (IoT) domain, there has currently been a growing interest, leading to the idea of the IoT ecosystem. But the standards, technology, and structures of the conventional IoT framework do not provide the necessary QoS for today's massive data. Thus, for today's IoT ecosystem, a framework called SD-DRFC (software-defined dew, roof, fog, and cloud computing) is suggested in this article. The framework delivers facilities from the closest possible position of end-user gadgets and thus increases the QoS in an IoT system. Clear description about the role and features of each tier is also presented. The path to a multi-tier computational architecture assisted by SDN can be realized from the given detailed literature review. Using the iFogSim simulator, a use case based on the architecture provided is then given and evaluated. This article considers four QoS parameters (latency, network use, cost, and energy consumption). When compared the findings of the simulation, the proposed framework execution performs much better than cloud-only execution.

The internet of things (IoT) creates immense volume of objects online. But cloud computing isn't suited to environmental demands. Hence, fog computing (FC) emerged which shifts the computation load into edge fog devices. However, FC also faces some obstacles which can be mitigated by software-defined networking (SDN). By combining SDN and FC, the network form can overcome almost all cloud limitations and can boost QoS. Within this article, architecture is proposed by combining SDN and FC to improve QoS for IoT ecosystem. With the architecture, an algorithm is propounded based on virtual partition. Then a use case is presented and evaluated through iFogSim simulator. The result shows a significant improvement of several QoS parameters in the execution of fog with SDN compared to the cloud-only execution. The results also show better results for energy consumption, network use (212.21% reduction), and latency (275.9% reduction) compared with previous similar use case.

In this paper, the dispersion management using soliton pulses in optical communication system is studied. The performance of the system with and without soliton parameters in terms of Q -factor, BER, and eye diagram is also studied. The proposed system with soliton parameters provides an improvement in Q -factor value by 82.1118 dB compared to that without soliton parameters at bit rate of 20 Gbps at a wavelength of 1550 nm with minimum BER of 0. Thus, soliton pulse can be transmitted dispersion free over optical fiber due to the exact compensation between nonlinearity and group velocity dispersion. The impact of wavelengths and bit rates for the soliton system on Q -factor, BER, and eye height is also investigated. The analysis of the simulation results provides that the values of Q -factor and eye height are inversely proportional to wavelength and proportional to bit rates in the proposed system with soliton parameters. Besides, it is proposed that the soliton pulse is best suited for long-range communication system with dispersion management.

Agriculture holds profound significance in the lives and livelihoods of Bangladesh’s population. The escalating population has contributed to a reduction in available arable land, exacerbating concerns about the feasibility of farming. In various regions of Bangladesh, there is a prevailing perception that certain areas are unsuitable for cultivation. Consequently, a substantial amount of land still needs to be tapped and explored for agricultural purposes, contributing to underutilization and hindering potential agricultural development in these regions. Considering these issues, this study seeks to forecast the optimal crop choices for specific soil classes, enabling individuals to make more informed decisions about crop cultivation on their land. Initially, the soil class is identified based on its unique characteristics within a given area, and subsequently, crop selection is determined based on these distinct soil classes. This study explores the performance of Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). It proposes a hybrid PSO-GA technique to optimize the Decision Tree model for forecasting crop cultivation based on classifying soil. The performance of a standalone decision tree model is also measured. In soil classification, the hybrid PSO-GA approach demonstrates superior performance, achieving an accuracy of 96.04%, surpassing individual PSO, GA, and standalone decision tree methods. In crop cultivation prediction, the hybrid approach outperforms individual PSO, GA, and decision tree methods with an accuracy of 92.63%. The results highlight the efficacy of the integrated PSO-GA strategy in optimizing the DT model for precise agricultural predictions. This research contributes valuable insights for enhancing decision support systems in agriculture, providing a promising avenue for improved accuracy in soil classification and crop cultivation prediction.

Education systems have significantly changed with the emergence of the internet. It has a significant impact on how students learn things. Nevertheless, its impact can also be contradicting. Internet addiction can slowly poison the minds of our youths and stand in the way of pursuing their goals. Although Bangladesh has internet connectivity across the country, its potential could be more utilized, particularly in the educational sector. Therefore, proper analysis of the effects of the internet on students, as well as determining the prominent factors relevant to the internet, is a necessary task. In addition, predicting students' academic performance can help determine the changes that must be incorporated to improve the educational system. Hence, this research analyzes the effects of internet usage on students' academic progress and then predicts the students' performance using distinct machine learning (ML) algorithms. The data were collected through an offline survey from Noakhali, Bangladesh. The collected data is preprocessed to select the most relevant features. The preprocessed data were fed into ML algorithms to investigate their behaviors. We have employed logistic regression, decision tree, random forest, and Naïve Bayes algorithms to see their classification performance on our dataset. To minimize the overfitting issue, k-fold cross-validation and hyperparameter optimization have been applied. The results were presented in two parts—exploratory data analysis and classification. Exploratory data analysis shows that the main purpose of internet usage is education and entertainment for school students, social media and entertainment for college students, and education and social media for university students. School and university students browse the internet mainly for academic purposes, whereas college students browse mainly for non-academic purposes. Students prefer to browse the internet at night. For all schools, colleges, and universities, students with better results generally visited websites like Google and YouTube. Students with moderate or bad results generally spent time on social media platforms (mainly Facebook and WhatsApp). Then, the results of the numerical analysis performed with classification algorithms are presented. Results indicate that random forest gives the maximum score in our dataset in all sectors, like accuracy, precision, recall, and f1 score. It gives a maximum of 85% accuracy on the test set. Logistic regression gives the second-best score of 69%. The practical applications and policy recommendations for Bangladesh's education sector are also discussed. The output of this work can contribute to building a policy on internet usage. In this way, it is possible to make the students more concentrative on their education and learning.

The liver is one of the most vital organs of the human body. Even when partially injured, it functions normally. Therefore, detecting liver diseases at the early stages is challenging. Early detection of liver problems can improve patient survival rates. This research enlightens on several Artificial Intelligence techniques, including the Bagged Tree, Support Vector Machine, K-Nearest Neighbor, and Fine Tree classifier, to predict the presence of liver disease in a patient at an early stage. This study compares those models and selects the best technique to detect liver disease at an early stage. The classification performance is measured using the confusion matrix, True Positive Rate (TPR), False Positive Rate (FPR), ROC curve, and accuracy. The result shows that the Bagged Tree classifier achieves the highest classification accuracy (81.30%), which is very promising compared to the other algorithms. The proposed system also performs sensitivity analysis on the dataset to investigate the impact of each attribute on the model’s performance. It has been demonstrated that Alanine Aminotransferase (sgpt) attribute has the most significant impact on the prediction of liver disease. The proposed method could be used as an assistant framework for liver disease detection at an early stage.

The usage of electrical discharge machining (EDM) is increasing gradually owing to its capability to cut precisely, geometrically complex material regardless hardness. Many process parameters greatly affect the EDM performance and complicated mechanism of the process result the lag of established theory. Hence, it becomes important to select the proper parameter set for different machining stages in order to promote efficiency. In view of these barriers, it is attempted to establish a model which can accurately predict the material removal rate (MRR) of titanium alloy by correlating the process parameter. Effect of the parameters on MRR is investigated as well. Experiment is conducted utilizing the graphite electrode maintaining negative polarity. Analysis and modelling is carried out based on design of experiment as well as response surface methodology. The agreeable accuracy is obtained and thus the model can become a precise tool setting the EDM process cost effective and efficient. Moreover, high ampere, short pulse-off time and low servo-voltage combined with about 250 μs pulse-on time generate the highest MRR.