Optimal feature selection for COVID-19 detection with CT images enabled by metaheuristic optimization and artificial intelligence.

There is a broad range of novel Coronaviruses (CoV) such as the common cold, cough, and severe lung infections. The mutation of this virus, which originally started as COVID-19 in Wuhan, China, has continued the rapid spread globally. As the mutated form of this virus spreads across the world, testing and screening procedures of patients have become tedious for healthcare departments in largely populated countries such as India. To diagnose COVID-19 pneumonia by radiological methods, high-resolution computed tomography (CT) of the chest has been considered the most precise method of examination. The use of modern artificial intelligence (AI) techniques on chest high-resolution computed tomography (HRCT) images can help to detect the disease, especially in remote areas with a lack of specialized physicians. This article presents a novel metaheuristic algorithm for automatic COVID-19 detection using a least square support vector machine (LSSVM) classifier for three classes namely normal, COVID, and pneumonia. The proposed model results in a classification accuracy of 87.2% and an F1-score of 86.3% for multiclass classifications from simulations. The analysis of information transfer rate (ITR) revealed that the modified quantum-based marine predators algorithm (Mq-MPA) feature selection algorithm reduces the classification time of LSSVM by 23% when compared to the deep learning models.

Comparison of magnetic resonance elastography and diffusion-weighted imaging for differentiating benign and malignant liver lesions.

OBJECTIVES: Comparison of magnetic resonance elastography (MRE) and diffusion-weighted imaging (DWI) for differentiating malignant and benign focal liver lesions (FLLs). METHODS: Seventy-nine subjects with 124 FLLs (44 benign and 80 malignant) underwent both MRE and DWI. MRE was performed with a modified gradient-echo sequence and DWI with a free breathing technique (b = 0.500). Apparent diffusion coefficient (ADC) maps and stiffness maps were generated. FLL mean stiffness and ADC values were obtained by placing regions of interest over the FLLs on stiffness and ADC maps. The accuracy of MRE and DWI for differentiation of benign and malignant FLL was compared using receiver operating curve (ROC) analysis. RESULTS: There was a significant negative correlation between stiffness and ADC (r = -0.54, p < 0.0001) of FLLs. Malignant FLLs had significantly higher mean stiffness (7.9kPa vs. 3.1kPa, p < 0.001) and lower mean ADC (129 vs. 200 × 10(-3)mm(2)/s, p < 0.001) than benign FLLs. The sensitivity/specificity/positive predictive value/negative predictive value for differentiating malignant from benign FLLs with MRE (cut-off, >4.54kPa) and DWI (cut-off, <151 × 10(-3)mm(2)/s) were 96.3/95.5/97.5/93.3% (p < 0.001) and 85/81.8/88.3/75% (p < 0.001), respectively. ROC analysis showed significantly higher accuracy for MRE than DWI (0.986 vs. 0.82, p = 0.0016). CONCLUSION: MRE is significantly more accurate than DWI for differentiating benign and malignant FLLs. KEY POINTS: • MRE is superior to DWI for differentiating benign and malignant focal liver lesions. • Benign lesions with large fibrous components may have higher stiffness with MRE. • Cholangiocarcinomas tend to have higher stiffness than hepatocellular carcinomas. • Hepatocellular adenomas tend to have lower stiffness than focal nodular hyperplasia. • MRE is superior to conventional MRI in differentiating benign and malignant liver lesions.

iSAT: a visual learning analytics tool for instructors.

Interactive Stratified Attribute Tracking (iSAT) is a visual analytics tool for cohort analysis. In this paper, we show how instructors can use iSAT to visualize transitions of groups of students during teaching-learning activities. Interactive visual analytics gives the instructor the affordance of understanding the dynamics of the class of students and their activities from the data collected in their own teaching-learning context. We take an example of a peer instruction (PI) activity and describe how iSAT can be used to analyze its clicker responses. During PI, typically instructors only use histograms to visualize the distribution of clicker responses in the pre- and post-discussion phases. We show that the use of iSAT to analyze clicker data in real time to trace transitions of participants' responses during various voting phases can support them in planning for their post-PI activities. Seven patterns of transitions that emerge are aligned, returns, starburst, slide, attractor, switching, and void. We interpret them in the context of the example. Such transition patterns are neither available in multiple histograms of individual voting phase nor generated in real time to be visualized as a flow diagram. We had conducted two workshops to introduce iSAT to the instructors and demonstrated the workflow of using iSAT with their dataset. Here, we report usefulness and usability data collected from those workshops. In conclusion, we highlight the power of iSAT for instructors to do cohort analysis in their teaching-learning practice.

An exploration of problem posing-based activities as an assessment tool and as an instructional strategy.

BACKGROUND: Problem posing, the generation of questions by learners, has been shown to be an effective instructional strategy for teaching-learning of complex materials in domains such as mathematics. In this paper, we demonstrate the potential of problem posing in two dimensions. Firstly, we present how problem posing can result in unfolding of knowledge and hence how it can be used as an instructional strategy. Then we present another problem posing-based activity as an assessment tool in an Introductory Programming course (CS1). METHOD: To explore the potential of problem posing as an instructional strategy, we conducted field studies in the two CS application courses (Data Structures (DS) and Artificial Intelligence (AI)), in which we provided a semi-structured problem posing situation to students. We performed inductive qualitative research and development the questions generated by students using grounded theory-based qualitative data analysis technique. To explore the potential of problem posing as an assessment tool, we conducted a field study in CS1 wherein we employed another problem posing (PP)-based activity in a large class for assessing the learning of computational thinking concepts in an introductory programming course and analysed how performance in traditional assessment tools (quiz score) is related with performance in our non-traditional assessment tool (quality of problems posed during a problem posing activity). RESULTS: From the studies in DS and AI courses we found that students pose questions and unfold knowledge using seven strategies - Apply, Organize, Probe, Compare, Connect, Vary, and Implement. From the field study performed in the CS1 course we found that the quality of the problems posed (difficulty level) were mostly aligned to the traditional assessment results in the case of novice learners but not in the case of advanced learners.

Effect of active learning using program visualization in technology-constrained college classrooms.

Multiple studies report that Computer Science (CS) instructors face problems on how to integrate visualizations in their teaching. This problem gets compounded for instructors in technology-constrained classrooms that are common in developing countries. In these classrooms, students are not able to interact with visualization directly; instead, their interaction is mediated by the instructor who alone may have access to the visualization. In the current study, we contrasted learning outcome from integrating program visualization at two different engagement levels in instructor-mediated classroom setting. The two levels were "Responding" (prediction activity with visualization) and "Viewing" (watching visualization with instructor commentary) as per Naps' taxonomy. The study was conducted for a programming topic of medium complexity. We found the strategy of prediction with visualization ("Responding") led to statistically significant higher active behavioral engagement and higher perception of learning among students than the strategy of watching the visualization with instructor commentary ("Viewing"). We also found statistically significant higher cognitive achievement in terms of the rate of problem solving for the "Responding" group, if the students had prior training in active learning. This study can serve as a reference guide to design effective integration of visualizations in instructor-mediated classrooms.

Geochemical characterization of oceanic basalts using Artificial Neural Network.

The geochemical discriminate diagrams help to distinguish the volcanics recovered from different tectonic settings but these diagrams tend to group the ocean floor basalts (OFB) under one class i.e., as mid-oceanic ridge basalts (MORB). Hence, a method is specifically needed to identify the OFB as normal (N-MORB), enriched (E-MORB) and ocean island basalts (OIB). We have applied Artificial Neural Network (ANN) technique as a supervised Learning Vector Quantisation (LVQ) to identify the inherent geochemical signatures present in the Central Indian Ocean Basin (CIOB) basalts. A range of N-MORB, E-MORB and OIB dataset was used for training and testing of the network. Although the identification of the characters as N-MORB, E-MORB and OIB is completely dependent upon the training data set for the LVQ, but to a significant extent this method is found to be successful in identifying the characters within the CIOB basalts. The study helped to geochemically delineate the CIOB basalts as N-MORB with perceptible imprints of E-MORB and OIB characteristics in the form of moderately enriched rare earth and incompatible elements. Apart from the fact that the magmatic processes are difficult to be deciphered, the architecture performs satisfactorily.

A novel and efficient synthesis of bicyclo[2.2.2]octenones and sigmatropic shifts in ground and excited states: stereoselective route to cis-decalins and diquinane frameworks.

A new and efficient synthesis of a variety of highly embellished bicyclooctenones having an endo-vinyl moiety and their sigmatropic shifts in ground and excited states leading to a stereoselective route to substituted cis-decalins and diquinane frameworks have been described. Functionalized bicyclo[2.2.2]octenones having an endo-vinyl group and a beta,gamma-enone chromophore were prepared by in situ generation of 6-chloromethyl-6-hydroxycyclohexadienones and cycloaddition with butadiene (also generated in situ) followed by manipulation of the adducts. The presence of contiguous carbonyl, hydroxyl, and chloromethyl groups in adducts led to the introduction of various alkyl groups alpha to the ketone in a stereoselective fashion. The 3,3-sigmatropic shift in the bridged bicyclic compounds gave the corresponding cis-decalins, whereas the triplet sensitized irradiation led to the formation of diquinanes as a result of a 1,2-acyl shift.