Regression testing is an activity that ensures software quality as new features develop and needs to be conducted during software development. Practically, regression test suites have been growing with the development of software products. Test suite reduction is a classic technique that speeds up the regression test process by removing redundant test cases in the regression test suite. Thus, the execution time of the regression tests and software development costs can be effectively reduced. However, the method of test suite reduction may be time-consuming with large software or test suites and may lose some essential test cases while using only one testing criteria. The aim of this paper is to reduce test suite size with the same or higher fault detection capability by applying cluster-based test suite reduction (CB-TSR) methods with two testing criteria during regression testing. First, we applied three cluster algorithms to cluster test cases based on the similarity of function coverage and considered the silhouette coefficient to find the best cluster result. Second, two test suite reduction algorithms were applied with statement coverage against each cluster of the test case. Experiments based on real subject programs were evaluated using fault detection effectiveness (FDE) loss and other comparison criteria. Experimental results indicate that our proposed CB-TSR methods provide a lower processing cost and improves effectiveness with the same or better fault detection capability of the reduced test suite.

As the mobile Internet and social computing developing, online event-based social networks (EBSNs) were derived, which mainly assign events to users according to the scores a linear combination of some features (i.e., location, similarity, friendship). Most of existing research work only take offline scenarios into consideration, where users’ full information is known in advance. However, on real-world EBSN platforms, online scenarios have practical application value. Besides, Existing works did not consider online learning and modeling users’ feedbacks (i.e., accept or reject arrangement). In this paper, we investigate the online modeling and learning users’ feedback, where users can feedback by accepting a set of events arranged or reject events arranged due to less interest events. In particular, we first model the problem as a stochastic bandit, and then applying Upper Confidence Bound based method with expected regret, which is the polynomial in the events quantity in combinatorial settings. Finally, we evaluate the performance of our proposed algorithms with real data sets and syn-thetic data sets.

Low power devices have always been important in all electronics and computer devices. In this paper, a proposed design has been implemented for the full adder circuit with significant modifications in the existing hybrid GDI (Gate Diffusion Input) based full adder. All the results are implemented using CADENCE tool at 45nm scale and 0.4V. Existing hybrid GDI based adder design delivers 7.135x10^-9 watt power dissipation. The proposed hybrid GDI-PTL design delivers a significant reduction in power dissipation equal to 6.70x10^-9 watt. Further, this power dissipation has been reduced to 6.55x10^-9 watt by using high Vth (threshold voltage) PMOS transistor in the proposed hybrid GDI-PTL design for one-bit full adder.

The field of optics is flourishing day by day due to the wide usage of the Internet and its associated technologies. Free Space Optics (FSO) is a data transmission technique that employs light propagation to send data. This technology is effective in circumstances where fiber optic cables cannot be deployed. This paper provides a model and simulation of the Fiber Bragg Grating (FBG) based FSO network under different conditions, such as modulation types and data rates. The paper also investigates the impact of Multiple Access Interference (MAI) on FSO under design parameters. The designed system performance is analyzed under the multiuser optical wireless network by changing data rates and modulation types. The proposed model's security is achieved through the use of the FBG encoder/decoder and the FSO channel for transmission. It has been inferred that the CRZ modulation type provides the best BER and Q factor compared to other formats. A data rate as high as 1Gbps can be achieved using the CRZ modulation format. It has been noticed that as the number of users grows, the BER value begins to deteriorate.

A cutting tool is a significant constituent in the manufacturing process and a framework assisting its self-monitoring is one of the requirements of Industry 4.0. The Deep Learning (DL) approach is suitable for modeling such a framework and the application of multi-layer fully connected neural nets makes the model robust. This article presents the design of an Artificial Neural Network (ANN) classifier based on statistical learning of machining vibrations. Six distinct tool faults have been analyzed considering turning operations incorporating feature computation, choice, and classification. The output of the trained ANN is utilized for the classification of the fault and fault-free condition in the cutting tool and exhibited an accuracy of 93.33%. Later, the performance of this model has been compared with Machine Learning (ML) classifiers. Considering the comparative study, it is understood that the Deep Learning-based ANN model shows higher accuracy and can therefore be suggested for condition monitoring of a single-point cutting tool.

Objectives: the crop yield prediction rate has been improved using a machine learning regression algorithm (MLR) using a Naïve Bayes classifier. The optimal utilization of fertilizer is enhanced based on a potential of hydrogen (pH) value and alkalinity of soil. Method:the implementation of the proposed algorithm has been carried out by considering the various types of soils, percentage of nutrients like potassium (Pm), nitrogen (N) and Phosphorus (P) in the soil in that region, four to five years of data analysis of the amount of rainfall, atmosphere humidity, and crop yield to fertilizer utilization ratio of a particular region and duration. Finding: The designed system has a model to accurately and precisely predict crop yield and give required recommendations to the end-user regarding fertilizer ratio depending on soil and weather conditions of the land to improve the crop yield, thereby increasing the revenue of farmers. Novelty: the farmers have to determine the expected crop yield and required fertilizer by themselves. It is achieved more accurately by implementing the proposed algorithm compared to the existing Random Forest (RF) algorithm using data mining Decision support system. The analysis has been carried out on the above-mentioned attributes of data by adopting the data pre-processing, data testing, and validation to achieve a precise and accurate crop yield and fertilizer utilization model.

This work is devoted to a modeling of the maintenance of multi-component systems which are subject to several covariates capable of strongly influencing the behavior of the system. This is ensured by several reliable models having the characteristic of introducing, during the evaluation of the operating state of the system, several concomitant information. In this work, we are interested in the modeling of the behavior of the system by the proportional intensity model (PIM) by incorporating, on the basis of a maintenance history of a turbocompressor having worked for nearly nine years, two covariates representing “temperature” and “programming of maintenance shutdowns”. The estimation of the parameters of the models, examined for two functions of failure intensities of the non-homogeneous Poisson process (NHPP) (power law and the log linear law), is carried out by the Maximum likelihood approach ( MLE) which makes it possible to choose the best adjustment model validated by the likelihood ratio (LR). The results found by this model show the effect of each covariate on the proper functioning of the system.

Power from blowing wind is converted mainly to electricity in the Wind based Energy Conversion System (WBECS). In such applications, a dedicated wind turbine along with other necessary arrangements such as a gear, controller, brake system etc. converts the kinetic energy of the blowing wind into an electrical counterpart. Earlier, asynchronous generators were used in such applications. However, with the advent of solid-state devices now-a-days AC generators, particularly permanent magnet synchronous generators (PMSG), are mostly used in such applications. In small scale applications, the output of WBECS is converted to DC through a rectifier mechanism. However, due to variation in the wind profile, the output is not a steady one, which is not suitable for DC applications. In this regard, power electronic based converters lay a vital role. Such an application may find its usefulness particularly in coastal regions where wind has a good potential from an electricity generation point of view particularly to charge up electric vehicles (EV). In the present study, a small-scale application of a WBECS system incorporated with PMSG is modelled in MATLAB/Simulink environment with a DC load. The o utput of the system is regulated with buck and boost converters and a comparison of their performance was done. Duty ratio of the converters was controlled by the maximum power point tracking algorithm (MPPTA). In the present study, the Hill Climbing method was adopted.