Classifying Single Channel Epileptic EEG data based on Sparse Representation using Shallow Autoencoder.

Patient independent epileptic seizure detection algorithm for scalp electroencephalogram (EEG) data is pro- posed in this paper. Principal motivation of this work is to integrate neural and conventional machine learning methods to develop a classification system which can advance the current wearable health systems in terms of computational complexity and accuracy. Being based on processing a single channel EEG processing, the approach is suitable for usage with small wireless sensors. A shallow autoencoder model is utilized for sparse representation of the EEG signal followed by k-nearest neighbor (kNN) classifier to categorize the data as epileptic or non-epileptic. Using a single EEG channel an optimum sparsity level is explored in the encoded sample. Attaining an accuracy, sensitivity and specificity of 98.85%, 99.29% and 98.86% respectively, for CHB-MIT scalp EEG database, proposed classification method outperforms state of- the-art seizure detection methodologies. Experiments has shown that this performance was possible by using a sparsity level of 4 in the auto-encoder. Furthermore, use of shallow learning instead of deep learning approach for generation of sparse but effective representation is computationally lighter than many other feature extraction and preprocessing methods.

Fuzzy Cloud Based COVID-19 Diagnosis Assistant for identifying affected cases globally using MCDM.

The COVID-19, Coronavirus Disease 2019, emerged as a hazardous disease that led to many causalities across the world. Early detection of COVID-19 in patients and proper treatment along with awareness can help to contain COVID-19. Proposed Fuzzy Cloud-Based (FCB) COVID-19 Diagnosis Assistant aims to identify the patients as confirmed, suspects, or suspicious of COVID-19. It categorized the patients into four categories as mild, moderate, severe, or critical. As patients register themselves online on the FCB COVID-19 DA in real-time, it creates the database for the same. This database helps to improve diagnostic accuracy as it contains the latest updates from real-world cases data. A team of doctors, experts, consultants are integrated with the FCB COVID-19 DA for better consultation and prevention. The ultimate aim of this proposed theory of FCB COVID-19 DA is to take control of COVID-19 pandemic and de-accelerate its rate of transmission among the society.

Optimized and validated spectrophotometric methods for the determination of nicorandil in drug formulations and biological fluids.

Two simple, sensitive and economical spectrophotometric methods have been developed for the determination of nicorandil in drug formulations and biological fluids. Method A is based on the reaction of the drug with brucine-sulphanilic acid reagent in sulphuric acid medium producing a yellow-coloured product, which absorbs maximally at 410 nm. Method B depends on the formation of the intensely blue-coloured product which results due to the interaction of an electrophilic intermediate of 3-methyl-2-benzothiazolinone hydrazone hydrochloride (MBTH) with oxidized product of 4-(methyl amino) phenol sulphate (metol) in the presence of nicorandil as an oxidizing agent in sulphuric acid medium. The coloured product shows absorbance maximum at 560 nm. Under the optimized experimental conditions, Beer's law is obeyed in the concentration range of 2.5-35.0 and 0.40-2.2 microg ml(-1) for Methods A and B, respectively. Both the methods have been successfully applied to the determination of nicorandil in drug formulations and biological fluids. The results are validated statistically and through recovery studies. In order to establish the bias and the performance of the proposed methods, the point and interval hypothesis tests have been performed. The experimental true bias of all samples is smaller than +/-2%.

Extractive spectrophotometric methods for the determination of nifedipine in pharmaceutical formulations using bromocresol green, bromophenol blue, bromothymol blue and eriochrome black T.

Four simple, sensitive and accurate spectrophotometric methods have been developed for the determination of nifedipine in pharmaceutical formulations. These methods are based on the formation of ion-pair complexes of amino derivative of the nifedipine with bromocresol green (BCG), bromophenol blue (BPB), bromothymol blue (BTB) and eriochrome black T (EBT) in acidic medium. The coloured products are extracted with chloroform and measured spectrophotometrically at 415 nm (BCG, BPB and BTB) and 520 nm (EBT). Beer's law was obeyed in the concentration range of 5.0-32.5, 4.0-37.5, 6.5-33.0 and 4.5-22.5 microg ml(-1) with molar absorptivity of 6.41 x 10(3), 4.85 x 10(3), 5.26 x 10(3) and 7.69 x 10(3) l mol(-1) cm(-1) and relative standard deviation of 0.82%, 0.72%, 0.66% and 0.68% for BCG, BPB, BTB and EBT methods, respectively. These methods have been successfully applied for the assay of drug in pharmaceutical formulations. No interference was observed from common pharmaceutical adjuvants. Statistical comparison of the results with the reference method shows excellent agreement and indicates no significant difference in accuracy and precision.