A feature boosted deep learning method for automatic facial expression recognition.

Automatic facial expression recognition (FER) plays a crucial role in human-computer based applications such as psychiatric treatment, classroom assessment, surveillance systems, and many others. However, automatic FER is challenging in real-time environment. The traditional methods used handcrafted methods for FER but mostly failed to produce superior results in the wild environment. In this regard, a deep learning-based FER approach with minimal parameters is proposed, which gives better results for lab-controlled and wild datasets. The method uses features boosting module with skip connections which help to focus on expression-specific features. The proposed approach is applied to FER-2013 (wild dataset), JAFFE (lab-controlled), and CK+ (lab-controlled) datasets which achieve accuracy of 70.21%, 96.16%, and 96.52%. The observed experimental results demonstrate that the proposed method outperforms the other related research concerning accuracy and time.

Self-Learning Network-based segmentation for real-time brain M.R. images through HARIS.

In recent years in medical imaging technology, the advancement for medical diagnosis, the initial assessment of the ailment, and the abnormality have become challenging for radiologists. Magnetic resonance imaging is one such predominant technology used extensively for the initial evaluation of ailments. The primary goal is to mechanizean approach that can accurately assess the damaged region of the human brain throughan automated segmentation process that requires minimal training and can learn by itself from the previous experimental outcomes. It is computationally more efficient than other supervised learning strategies such as CNN deep learning models. As a result, the process of investigation and statistical analysis of the abnormality would be made much more comfortable and convenient. The proposed approach's performance seems to be much better compared to its counterparts, with an accuracy of 77% with minimal training of the model. Furthermore, the performance of the proposed training model is evaluated through various performance evaluation metrics like sensitivity, specificity, the Jaccard Similarity Index, and the Matthews correlation coefficient, where the proposed model is productive with minimal training.

AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays.

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect and diagnose a wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches and have produced impressive chest-related clinical outcomes, specific techniques may not contribute many advantages if one type of disease is detected without the rest being identified. Those who tried to identify multiple chest-related diseases were ineffective due to insufficient data and the available data not being balanced. This research provides a significant contribution to the healthcare industry and the research community by proposing a synthetic data augmentation in three deep Convolutional Neural Networks (CNNs) architectures for the detection of 14 chest-related diseases. The employed models are DenseNet121, InceptionResNetV2, and ResNet152V2; after training and validation, an average ROC-AUC score of 0.80 was obtained competitive as compared to the previous models that were trained for multi-class classification to detect anomalies in x-ray images. This research illustrates how the proposed model practices state-of-the-art deep neural networks to classify 14 chest-related diseases with better accuracy.

Application of improved fuzzy best worst analytic hierarchy process on renewable energy.

In this work, a novel fuzzy decision making technique namely trapezoidal fuzzy Best-Worst method (fuzzy BWM) is developed which is based on Best-Worst method (BWM) and Trapezoidal fuzzy number. The real motive behind our work is to take a broad view of the existing fuzzy BWM based on triangular fuzzy number by trapezoidal fuzzy number. Also, we have presented a new hybrid MCDM technique called as Trapezoidal fuzzy Best Worst Analytic Hierarchy based on proposed trapezoidal fuzzy BWM and existing trapezoidal fuzzy Analytic Hierarchy Process (AHP). BWM approach is employed in evaluating the PV of considering criteria and trapezoidal fuzzy AHP is used to assess the local priority vale (PV) of considering alternatives (or indicators) of a decision problem. Moreover it used to identify the most significant alternative which is responsible for performance efficiency of a hydro power plant under climatic scenario. From the result, it is undoubtedly found that hydraulic had is most responsible indicator. Further, the CR (consistency ratio) value which is determined by our proposed trapezoidal fuzzy BWM is less than that of existing BWM and fuzzy BWM techniques. Finally, we have validated our result by comparative study, scenario analysis and sensitivity analysis.

Prioritization of Information Security Controls through Fuzzy AHP for Cloud Computing Networks and Wireless Sensor Networks.

With the advent of cloud computing and wireless sensor networks, the number of cyberattacks has rapidly increased. Therefore, the proportionate security of networks has become a challenge for organizations. Information security advisors of organizations face difficult and complex decisions in the evaluation and selection of information security controls that permit the defense of their resources and assets. Information security controls must be selected based on an appropriate level of security. However, their selection needs intensive investigation regarding vulnerabilities, risks, and threats prevailing in the organization as well as consideration of the implementation, mitigation, and budgetary constraints of the organization. The goal of this paper was to improve the information security control analysis method by proposing a formalized approach, i.e., fuzzy Analytical Hierarchy Process (AHP). This approach was used to prioritize and select the most relevant set of information security controls to satisfy the information security requirements of an organization. We argue that the prioritization of the information security controls using fuzzy AHP leads to an efficient and cost-effective assessment and evaluation of information security controls for an organization in order to select the most appropriate ones. The proposed formalized approach and prioritization processes are based on International Organization for Standardization and the International Electrotechnical Commission (ISO/IEC) 27001:2013. But in practice, organizations may apply this approach to any information security baseline manual.

RAIRS2 a new expert system for diagnosing tuberculosis with real-world tournament selection mechanism inside artificial immune recognition system.

Tuberculosis is a major global health problem that has been ranked as the second leading cause of death from an infectious disease worldwide, after the human immunodeficiency virus. Diagnosis based on cultured specimens is the reference standard; however, results take weeks to obtain. Slow and insensitive diagnostic methods hampered the global control of tuberculosis, and scientists are looking for early detection strategies, which remain the foundation of tuberculosis control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose the disease. The objective of this study is to diagnose tuberculosis using a machine learning method. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. In order to increase the classification accuracy, this study introduces a new hybrid system that incorporates real tournament selection mechanism into the AIRS. This mechanism is used to control the population size of the model and to overcome the existing selection pressure. Patient epacris reports obtained from the Pasteur laboratory in northern Iran were used as the benchmark data set. The sample consisted of 175 records, from which 114 (65 %) were positive for TB, and the remaining 61 (35 %) were negative. The classification performance was measured through tenfold cross-validation, root-mean-square error, sensitivity, and specificity. With an accuracy of 100 %, RMSE of 0, sensitivity of 100 %, and specificity of 100 %, the proposed method was able to successfully classify tuberculosis cases. In addition, the proposed method is comparable with top classifiers used in this research.

Improved delay-range-dependent stability analysis of a time-delay system with norm bounded uncertainty.

This paper presents improved robust delay-range-dependent stability analysis of an uncertain linear time-delay system following two different existing approaches - (i) non-delay partitioning (NDP) and (ii) delay partitioning (DP). The derived criterion (for both the approaches) proposes judicious use of integral inequality to approximate the uncertain limits of integration arising out of the time-derivative of Lyapunov-Krasovskii (LK) functionals to obtain less conservative results. Further, the present work compares both the approaches in terms of relative merits as well as highlights tradeoff for achieving higher delay bound and (or) reducing number of decision variables without losing conservatism in delay bound results. The analysis and discussion presented in the paper are validated by considering relevant numerical examples.