Narrow Results

Reliability has become a major concern when link-wires in on-chip networks (NoCs) suffer from stuck-at faults (SAFs). This paper presents an extended and scalable test scheme that addresses these faults in NoC links to improve yield and reliability. The scheme detects the stuck-at faults on and identifies faulty link-wires. Experiments demonstrate the effectiveness of the proposed scheme and reveal deep insights of the faults on several performance metrics.

Today’s datasets are usually very large with many features and making analysis on such datasets is really a tedious task. Especially when performing classification, selecting attributes that are salient for the process is a brainstorming task. It is more difficult when there are many class labels for the target class attribute and hence many researchers have introduced methods to select features for performing classification on multi-class attributes. The process becomes more tedious when the attribute values are imbalanced for which researchers have contributed many methods. But, there is no sufficient research to handle extreme imbalance and feature selection together and hence this paper aims to bridge this gap. Here Particle Swarm Optimization (PSO), an efficient evolutionary algorithm is used to handle imbalanced dataset and feature selection process is also enhanced with the required functionalities. First, Multi-objective Particle Swarm Optimization is used to transform the imbalanced datasets into balanced one and then another version of Multi-objective Particle Swarm Optimization is used to select the significant features. The proposed methodology is applied on eight multi-class extremely imbalanced datasets and the experimental results are found to be better than other existing methods in terms of classification accuracy, G mean, F measure. The results validated by using Friedman test also confirm that the proposed methodology effectively balances the dataset with less number of features than other methods.

The medical field has been revolutionized by the medical imaging system, which plays a key role in providing information on the early life-saving detection of dreadful diseases. Diabetic retinopathy is a chronic visual disease that is the primary reason for the vision loss in most of the patients, who left undiagnosed at the initial stage. As the count of the diabetic retinopathy affected people kept on increasing, there is a necessity to have an automated detection method. The accuracy of the diagnosis of the automatic detection model is related to image acquisition as well as image interpretation. In contrast to this, the analysis of medical images by using computerized models is still a limited task. Thus, different kinds of detection methods are being developed for early detection of diabetic retinopathy. Accordingly, this paper focuses on the various literature analyses on different detection algorithms and techniques for diagnosing diabetic retinopathy. Here, it reviews several research papers and exhibits the significance of each detection method. This review deals with the analysis on the segmentation as well as classification algorithms that are included in each of the researches. Besides, the adopted environment, database collection and the tool for each of the research are portrayed. It provides the details of the performance analysis of the various diabetic detection models and reveals the best value in the case of each performance measure. Finally, it widens the research issues that can be accomplished by future researchers in the detection of diabetic retinopathy.

Multifocus image fusion is a demanding research field due to the utilization of modern imaging devices. Generally, the scene to be captured contains objects at different distances from these devices and so a set of multifocus images of the scene is captured with different objects in-focus. However, to improve the situational awareness of the captured scene, these sets of images are required to be fused together. Therefore, a multifocus image fusion algorithm based on Convolutional Neural Network (CNN) and triangulated fuzzy filter is proposed. A CNN is used to extract information regarding focused pixels of input images and the same is used as fusion rule for fusing the input images. The focused information so extracted may still need to be refined near the boundaries. Therefore, asymmetrical triangular fuzzy filter with the median center (ATMED) is employed to correctly classify the pixels near the boundary. The advantage of using this filter is to rely on precise detection results since any misdetection may considerably degrade the fusion quality. The performance of the proposed algorithm is compared with the state-of-art image fusion algorithms, both subjectively and objectively. Various parameters such as edge strength ($Q$), fusion loss (FL), fusion artifacts (FA), entropy ($H$), standard deviation (SD), spatial frequency (SF), structural similarity index measure (SSIM) and feature similarity index measure (FSIM) are used to evaluate the performance of the proposed algorithm. Experimental results proved that the proposed fusion algorithm produces a fused image that contains all-in-one focused pixels and is better than those obtained using other popular and latest image fusion works.

Diabetes Mellitus (DM) is a chronic disease and it is characterized based on the increase in the sugar level in the blood. The other diseases such as the cardiomyopathy, neuropathy and retinopathy may occur due to the DM pathology. The RR-time series or heart rate (HR) signal quantifies the beat-to-beat variations in the electrocardiogram (ECG) and it has been widely used for the detection of various cardiac diseases. Detection of DM based on the features of HR signal is a challenging problem. This paper copes with a new method for the detection of Diabetes Mellitus (DM) based on the features extracted from the HR signal. The Singular Spectrum Analysis (SSA) of HR signal and the Kernel Sparse Representation Classifier (KSRC) are the mathematical foundations used to achieve the detection. SSA is used to decompose the HR signal into sub-signals, and diagnostic features such as the maximum value of each sub-signal and eigenvalues are evaluated. Then, the KSRC uses the proposed diagnostic features as inputs for detecting diabetes. The experimental results reveal that the proposal attains the accuracy, sensitivity, and specificity values of 92.18%, 93.75% and 90.62%, respectively, employing the KSRC and the hold-out cross-validation approach. The method is compared with existing approaches for detecting diabetes from HR signal.

In this paper we propose a Regional Internet Exchange (RIX) scheme for MENA countries intra-regional traffic, compared with the existing situation for Internet service provision. The RIX architecture is proposed, implemented, and evaluated using simulation. Simultaneous comparative performance evaluation of Internet service provision for the existing and the proposed scenarios are presented. It is focused to measure utilization, message delays, access time and client perceived latencies performance metrics. The study shows that the proposed scheme results in less international bandwidth utilization and it reduces significantly the access time and most importantly it is inherently cost-effective.

The software architecture of a developmental robot is a challenging new research subject. This paper presents a theory of developmental mental architecture. Five architecture types, from the simplest Type-1 (observation-driven Markov decision process) to Type-5 (DOSASE MDP), are introduced. The properties and limitations of a simpler one are discussed before the introduction of the next more complex one. Further, we present the architecture design of the Dav robot, a humanoid robot built in the Embodied Intelligence Laboratory at Michigan State University. The framework of the Dav architecture is hand-designed, but the actual controller is developed, i.e. generated autonomously by the developmental program through real-time, online interactions with the real physical environment. We present the Dav architecture and the major components that realize the architecture. The designed architecture for Dav is the next generation version from its extensively tested predecessor, the SAIL developmental robot. Closely related to the issue of performance metrics, the paper also introduces the notion of intelligence completeness (concept completeness, intelligence-metric completeness, and factor completeness) and establishes the concept of the completeness theorem for developmental robotics.

This research study addresses the critical global health issue of heart disease (HD), emphasizing the importance of early detection for improving recovery outcomes. The authors have applied various machine learning (ML) algorithms, including logistic regression (LR), linear discriminant analysis (LDA), Gaussian naive bayes (GNB), support vector machine (SVM), and XGBoost (XGB) to classify the Statlog and Cleveland HD datasets. Performance metrics such as accuracy, precision, recall, F1-score, specificity, and Cohen’s kappa have been evaluated across these HD records. This study conducted two experiments: one using default ML classifiers and another with a hybrid genetic algorithm ML (GA-ML) model. The GA has been employed as a feature selector (FS), significantly enhancing the performance of each default classifier by selecting 9 out of 13 features. Notably, the GA-XGB model achieved the highest performance with an accuracy of 94.83%, precision of 93.33%, sensitivity of 96.55%, F1-score of 94.52%, specificity of 93.10%, Cohen’s kappa of 0.90, a positive likelihood ratio (LR$+$) of 14, a negative likelihood ratio (LR-) of 0.037, and a diagnostic odds ratio (DOR) of 378 on the combined HD dataset. These results have been validated using a 10-fold cross-validation technique. A comparative analysis has been conducted with default ML classifiers, hybrid GA-ML classifiers, and state-of-the-art methods. The results of the GA-ML models confirm the superiority of the proposed method, offering valuable insights into advancing early detection strategies and improving heart health care outcomes.

This chapter discusses the challenges of using performance metrics to stimulate creativity and innovations in organizations. Formal incentive systems have proven to be effective in motivating executional behavior. Using such systems to motivate creativity is more challenging because useful creativity and innovation are notoriously difficult to measure, and use of flawed systems can produce negative outcomes. Further an innovation’s success is usually determined by the efforts of teams, not individual employees. But well-designed incentive systems, which use good measures and also allow for some slack and toleration of short-term failures, can be effective. Metrics can also serve an information role, by providing opportunities to exchange ideas, providing performance-related feedback, and enhancing individual and group accountability. The chapter concludes by discussing how the use of incentive systems in combination with other management controls can help make organizations ambidextrous; i.e., good at both execution and innovation.

This chapter presents three MS Excel programs, namely, EMOO (Excel based Multi-Objective Optimization), NDS (Non-Dominated Sorting) and PM (Performance Metrics) useful for Multi-Objective Optimization (MOO) studies. The EMOO program is for finding non-dominated solutions of a given MOO problem. It has both binary-coded and realcoded NSGA-II (Elitist Non-Dominated Sorting Genetic Algorithm), and two termination criteria based on chi-squared test and steady state detection. The known/true Pareto-optimal front for the application problems is not available unlike that for benchmark problems. Hence, a procedure for obtaining known/true Pareto-optimal front is described in this chapter. The NDS program is for non-dominated sorting and crowding distance calculations of the non-dominated solutions obtained from several optimization runs using same or different MOO programs. The PM program can be used to calculate the values of performance metrics between the non-dominated solutions obtained using a MOO program and the true/known Pareto optimal front. It is useful for comparing the performance of MOO programs to find the non-dominated solutions. Finally, use of EMOO, NDS and PM programs is demonstrated on MOO of amine absorption process for natural gas sweetening.

This chapter presents the Integrated Multi-Objective Differential Evolution (IMODE) program, useful for solving Multi-Objective Optimization (MOO) problems. The algorithm in this program has four main parts: multi-objective differential evolution, tabu list for avoiding revisit of search space, self-adaptation of algorithm parameters, and two search termination criteria besides maximum number of generations. All these features of the IMODE make it reliable and efficient for solving engineering optimization problems. As MS Excel is familiar and readily available to practitioners and researchers, the IMODE program is implemented in MS Excel. In natural gas industry, Amine Absorption Process (AAP) is commonly used to remove acid gases from natural gas. To illustrate the application of the IMODE program, this process is simulated in Aspen HYSYS, and then optimized using the IMODE program for two objectives: capital and operating costs. Finally, performance of the two improvement-based termination criteria in the IMODE program is compared using the multi-objective performance metrics.

The correct selection of performance metrics is one of the most key issues in evaluating classifier's performance. Although many performance metrics have been proposed and used in machine learning community, there is not any common conclusions among practitioners regarding which metric to choose for evaluating a classifier's performance. In this paper, we attempt to investigate the potential relationship among some common used performance metrics. Based on definitions, We first classify seven most widely performance metrics into three groups, namely threshold metrics, rank metrics, and probability metrics. Then, we focus on using Pearson linear correlation and Spearman rank correlation to investigate the relationship among these metrics. Experimental results show the reasonableness of classifying seven common used metrics into three groups. This can be useful for helping practitioners enhance understanding about the different relationships and groupings among the performance metrics.