Deep learning is one of the most unexpected machine learning techniques which is being used in many applications like image classification, image analysis, clinical archives and object recognition.With an extensive utilization of digital images as information in the hospitals, the archives of medical images are growing exponentially. Digital images play a vigorous role in predicting the patient disease intensity and there are vast applications of medical images in diagnosis and investigation. Due to recent developments in imaging technology, classifying medical images in an automatic way is an open research problem for researchers of computer vision. For classifying the medical images according to their relevant classes a most suitable classifier is most important. Image classification is beneficial to predict the appropriate class or category of unknown images. The less discriminating ability and domain-specific categorization are the main drawbacks of low-level features. A semantic gap that exists between features of low-level as machine understanding and features of human understanding as high-level perception. In this research, a novel image representation method is proposed where the algorithm is trained for classifying medical images by deep learning technique. A pre-trained deep convolution neural network method with the fine-tuned approach is applied to the last three layers of deep neural network. The results of the experiment exhibit that our method is best suited to classify various medical images for various body organs. In this manner, data can sum up to other medical classification applications which supports radiologist’s efforts for improving diagnosis.

Dengue fever is viral disease which spreads due to the bite of the Aedes aegypti mosquito. In recent years, it has affected around 40% population of the world. Its endemic flow has led to a large disease burden, in terms of human and financial resources. Geographical Information Systems (GIS) are normally used to develop epidemiological thematic maps. This study explores the patterns and hotspots, associated with the catastrophic outbreak of dengue, in Punjab, in 2011. The ArcView software was used to analyze the data reported by the district hospitals of Punjab. Twenty-one-thousand cases were reported from March to December 2011, with 300 causalities. This research reveals that from among the total 37 epidemiological weeks, the maximum impact was observed between weeks 22 and 27. The geographical flow and hotspots associated with dengue have been shown through thematic maps. A positive correlation between the risk for dengue and age was observed. The findings of this research can help health officials and decision-makers alert the public about future outbreaks and take preventive measures to considerably reduce the mortality and morbidity associated with the disease.

The substantial rise in the demand for electric vehicles (EVs) has emphasized an environment-friendly and intelligent design for speed control strategies. In this paper, a Mamdani fuzzy logic controller (MFLC) was proposed to vigorously control the speed of EVs at discrete levels. MFLC member functions (MFs) are tuned for EVs operating at three different speed modes (40, 60, and 80 km/h). The proposed speed controller operation for the speed tracking of EVs was designed and tested in MATLAB (Simulink) environment. The proposed speed controller validated a remarkable improvement in dynamic speed control compared with existing P-I, FLC, Fuzzy FOPID (ACO), Fuzzy FOPID (GA), and Fuzzy FOPID (PSO) controllers. Its stability under a user-defined drive pattern is also observed. In this proposed work, the speed controller highlights the better tracking of user-defined speed response compared to the conventional aforementioned controllers. Moreover, the speed tracking of the designed model was tested for robustness against speed transients at predefined time instants, respectively. The comparison suggests that the MFLC model removes overshoot and significantly reduces the steady-state time.

Among the numerous anthropogenic pollutants, nitrogen dioxide (NO₂) is one of the leading contaminants mainly released by burning fossil fuels in industrial and transport sectors. This study evaluates the impact of COVID-19 lockdown on the growing trend of NO₂ emissions in South Asia. Satellite imagery data of Sentinel-5 Precursor with Tropomi instrument was employed in this study. The analysis was performed using time series data from February–May 2019 and February–May 2020. The time frame from February–May 2020 was further divided into two sub-time-frames, i.e., from 1 February–20 March (pre-lockdown) and from 21 March–May 2020 (lockdown). Results show the concentration of NO₂ pollutants over the region declined by 6.41% from February–May 2019 to February–May 2020. Interestingly, an increasing trend of NO₂ concentration by 6.58% occurred during the pre-lockdown phase in 2020 (1 February–20 March) compared to 2019 (February–May). However, the concentration of NO₂ pollutants reduced considerably by 21.10% during the lockdown phase (21 March–10 May) compared to the pre-lockdown phase in 2020. Furthermore, the country-specific detailed analysis demonstrates the significant impact of COVID-19-attributed lockdown on NO₂ concentration in South Asia.

Sparseness is the distinctive aspect of big data generated by numerous applications at present. Furthermore, several similar records exist in real-world sparse datasets. Based on Iterative Trimmed Transaction Lattice (ITTL), the recently proposed TRICE algorithm learns frequent itemsets efficiently from sparse datasets. TRICE stores alike transactions once, and eliminates the infrequent part of each distinct transaction afterward. However, removing the infrequent part of two or more distinct transactions may result in similar trimmed transactions. TRICE repeatedly generates ITTLs of similar trimmed transactions that induce redundant computations and eventually, affects the runtime efficiency. This paper presents D-GENE, a technique that optimizes TRICE by introducing a deferred ITTL generation mechanism. D-GENE suspends the process of ITTL generation till the completion of transaction pruning phase. The deferral strategy enables D-GENE to generate ITTLs of similar trimmed transactions once. Experimental results show that by avoiding the redundant computations, D-GENE gets better runtime efficiency. D-GENE beats TRICE, FP-growth, and optimized versions of SaM and RElim algorithms comprehensively, especially when the difference between distinct transactions and distinct trimmed transactions is high.

The complexity and high dimensionality are the inherent concerns of big data. The role of feature selection has gained prime importance to cope with the issue by reducing dimensionality of datasets. The compromise between the maximum classification accuracy and the minimum dimensions is as yet an unsolved puzzle. Recently, Monte Carlo Tree Search (MCTS)-based techniques have been invented that have attained great success in feature selection by constructing a binary feature selection tree and efficiently focusing on the most valuable features in the features space. However, one challenging problem associated with such approaches is a tradeoff between the tree search and the number of simulations. In a limited number of simulations, the tree might not meet the sufficient depth, thus inducing biasness towards randomness in feature subset selection. In this paper, a new algorithm for feature selection is proposed where multiple feature selection trees are built iteratively in a recursive fashion. The state space of every successor feature selection tree is less than its predecessor, thus increasing the impact of tree search in selecting best features, keeping the MCTS simulations fixed. In this study, experiments are performed on 16 benchmark datasets for validation purposes. We also compare the performance with state-of-the-art methods in literature both in terms of classification accuracy and the feature selection ratio.