Fog computing is an emerging technology which enables computing resources accessibility close to the end-users. It overcomes the drawbacks of available network bandwidth and delay in accessing the computing resources as observed in cloud computing environment. Resource allocation plays an important role in resource management in a fog computing environment. However, the existing traditional resource allocation techniques in fog computing do not guarantee less execution time, reduced energy consumption, and low latency requirements which is a pre-requisite for most of the modern fog computing-based applications. The complex fog computing environment requires a robust resource allocation technique to ensure the quality and optimal resource usage. Motivated from the aforementioned challenges and constraints, in this article, we propose a resource allocation technique for SDN-enabled fog computing with Collaborative Machine Learning (CML). The proposed CML model is integrated with the resource allocation technique for the SDN-enabled fog computing environment. The FogBus and iFogSim are deployed to test the results of the proposed technique using various performance evaluation metrics such as bandwidth usage, power consumption, latency, delay, and execution time. The results obtained are compared with other existing state-of-the-art techniques using the aforementioned performance evaluation metrics. The results obtained show that the proposed scheme reduces 19.35% processing time, 18.14% response time, and 25.29% time delay. Moreover, compared to the existing techniques, it reduces 21% execution time, 9% network usage, and 7% energy consumption.

The number of client applications on the fog computing layer is increasing due to advancements in the Internet of Things (IoT) paradigm. Fog computing plays a significant role in reducing latency and enhancing resource usage for IoT users’ tasks. Along with its various benefits, fog computing also faces several challenges, including challenges related to resource overloading, security, node placement, scheduling, and energy consumption. In fog computing, load balancing is a difficult challenge due to the increased number of IoT devices and requests, which requires an equal load distribution throughout all available resources. In this study, we proposed a secure and energy-aware fog computing architecture, and we implemented a load-balancing technique to improve the complete utilization of resources with an SDN-enabled fog environment. A deep belief network (DBN)-based intrusion detection method was also implemented as part of the proposed techniques to reduce workload communication delays in the fog layer. The simulation findings showed that the proposed technique provided an efficient method of load balancing in a fog environment, minimizing the average response time, average energy consumption, and communication delay by 15%, 23%, and 10%, respectively, as compared with other existing techniques.

Governments and industries are developing aggressive policies to reduce carbon emissions and shift from fossil fuels to renewable energy. On the other hand, industries struggle to reduce energy consumption and depend on production lot sizes to control energy requirements. In this regard, energy-efficient processing through CNC machine tools can potentially influence energy demand and requires energy-aware power consumption strategies for machining processes. For manufacturing a single product, predicting energy demand can be decisive in determining parametric control and other factors. Previously analytical models have been largely used to model machining requirements and energy demand. However, these models largely depend on parameterization and do not facilitate the integration of external sub-systems. Therefore, in this paper, an artificial intelligence-based power reduction strategy is developed and implemented on single material (Inconel 718), four control parameters (cutting speed, feed rate, depth of cut and flow rate) and two sub-systems (minimum quantity lubrication (MQL) and nanofluids-based minimum quantity lubrication (NF-MQL)). The paper employs four machine learning algorithms,’ K-Nearest Neighbor’, ‘Gaussian Regression’, ‘Decision Tree’, and ‘Logistic Regression’, to evaluate their functionality in predicting power consumption (Pc) of CNC machining systems using a real experimental data set. As per evaluation based on five performance metrics (R-square, MSE, RMSE, MAE, and MedAE), ‘Decision Tree’ has achieved the most accurate power consumption predictions. The comparative results highlight ‘Decision Tree’ as the most better predictor with the optimal max_depth of 2 showing Pc MQL R² of 0.915 and Pc NF-MQL R² of 0.931.

Today's health-care services have come a long way to provide medical care to the patients and protect them from various diseases. This paper comprises the development of a framework based on associative classification techniques on heart dataset for early diagnosis of heart based diseases. It is hard to diagnose the heart diseases with just observation that arrives suddenly and may prove fatal when it's uncontrolled. The implementation of work is done on Cleveland heart diseases dataset from the University of California Irvine (UCI) machine learning repository to test on different data mining techniques. The various attributes related to cause of heart diseases are viz: gender, age, chest pain type, blood pressure, blood sugar etc that can predict early symptoms heart disease. Various data mining algorithms such as Aprior, FP-Growth, Naive bayes, ZeroR, OneR, J48 and k-nearest neighbor are applied in this study for prediction of heart diseases. On basis of best results the development of heart disease prediction system is done by using hybrid technique for classification associative rules (CARs) to achieve the prediction accuracy of 99.19%.