Swaleha Zubair’s research while affiliated with Aligarh Muslim University and other places

UNSTRUCTURED Objective: Recent Coronavirus Disease 2019 (COVID-19) pandemic has inflicted the whole world critically. Despite the fact that India has not been listed amongst the top ten highly affected countries, one cannot rule out COVID-19 associated complications in the near future. The accumulative testing facilities has resulted in exponential increase in COVID-19 infection cases. In figures, the number of positive cases have risen up to 33,614 as of 30 April, 2020. Keeping into consideration the serious consequences of pandemic, we aim to establish correlations between the numerous features which was acquired from the various Indian-based COVID datasets, and the impact of the containment of the pandemic on the current state of Indian population using machine learning approach. We aim to build the COVID-19 severity model employing logistic function which determines the inflection point and help in prediction of the future number of confirmed cases. Methods: An empirical study was performed on the COVID-19 patient status in India. We performed the study commencing from 30 January, 2020 to 30 April, 2020 for the analysis. We applied the machine learning (ML) approach to gain the insights about COVID-19 incidences in India. Several diverse exploratory data analysis ML tools and techniques were applied to establish a correlation amongst the various features. Also, the acute stage of the disease was mapped in order to build a robust model. Results: We collected five different datasets to execute the study. The data sets were integrated extract the essential details. We found that men were more prone to get infected of the coronavirus disease as compared to women. Also, the age group was the middle-young age of patients. On 92-days based analysis, we found a trending pattern of number of confirmed, recovered, deceased and active cases of COVID-19 in India. The as-developed growth model provided an inflection point of 85.0 days. It also predicted the number of confirmed cases as 48,958.0 in the future i.e. after 30th April. Growth rate of 13.06 percent was obtained. We achieved statistically significant correlations amongst growth rate and predicted COVID-19 confirmed cases. Conclusion: This study demonstrated the effective application of exploratory data analysis and machine learning in building a mathematical severity model for COVID-19 in India.

Alzheimer’s disease (AD) is the most common type of neurological disorder that leads to the brain’s cell death overtime. It is one of the major important causes of memory loss and cognitive decline in elderly subjects around the globe. Early detection and streamlining of diagnostic practices are the prime domains of the interest to the healthcare community. Machine learning (ML) algorithms and numerous multivariate data exploratory tools have been extensively used in the field of AD research. The primary purpose of this study is to present an automated classification system to retrieve information patterns. We proposed a five-stage ML pipeline, where each stage was further categorized in different sub-levels. The study relied on the Open Access Series of Imaging Studies (OASIS) database of MRI (Magnetic Resonance Imaging) brain images for the analysis. The dataset comprised of 343 MRI sessions involving 150 subjects. Three different scores namely, MMSE (Mini-Mental State Examination), CDR (Clinical Dementia Rating), and ASF (Atlas Scaling Factor) were used in the analysis. The proposed ML pipeline constitutes a classifier system along with data transformation and feature selection techniques that have been embedded inside an experimental and data analysis design. Performance metrics for Random Forest (RF) classifier showed the highest output in the classification accuracy.

Information is rising exponentially over the Internet. The World Wide Web has emerged as a treasure trove of knowledge and provide relevant information pertaining to any exclusive topic as per the individual's performance or demand. Frequently, the user gets confused while seeing such a large number of over the Internet to choose which one to buy. In this situation, it is essential to filter the available information so as to recommend user about items and determine what different users prescribe. To avoid information overload, we can employ the recommended system that helps us to effectively filter, prioritize and deliver tremendously vital information. A recommendation system refers to a system that can personalize or filter preference in a set of items. Various similarity measures are the key to the analysis. The collaborative filtering recommendation system is supported to be the best approach for personalized user or service recommendations. User-based collaborative filtering approach possesses certain shortcomings, thus item-based collaborative filtering method is taken into consideration. To fill this gap, we compared correlation similarity measures and the distance similarity measures to study the performance of various existing similarity calculation models in order to enhance the recommendation performance. The results of the study were then used to develop an improved method by employing statistical accuracy metrics to give the most accurate recommendation. Therefore, similarity measures can be assessed and contrasted with the outcomes of the similarity measures as discussed in this study. The objective of this paper is to identify appropriate distance measures for datasets and furthermore to facilitate comparison and assessment of the proposed similarity measures with that of conventional ones.

Background Alzheimer disease (AD) is a degenerative progressive brain disorder where symptoms of dementia and cognitive impairment intensify over time. Numerous factors exist that may or may not be related to the lifestyle of a patient that result in a higher risk for AD. Diagnosing the disorder in its beginning period is important, and several techniques are used to diagnose AD. A number of studies have been conducted on the detection and diagnosis of AD. This paper reports the empirical study performed on the longitudinal-based magnetic resonance imaging (MRI) Open Access Series of Brain Imaging dataset. Furthermore, the study highlights several factors that influence the prediction of AD. Objective This study aimed to correlate the effect of various factors such as age, gender, education, and socioeconomic background of patients with the development of AD. The effect of patient-related factors on the severity of AD was assessed on the basis of MRI features, Mini-Mental State Examination (MMSE), Clinical Dementia Rating (CDR), estimated total intracranial volume (eTIV), normalized whole brain volume (nWBV), and Atlas Scaling Factor (ASF). Methods In this study, we attempted to establish the role of longitudinal MRI in an exploratory data analysis (EDA) of AD patients. EDA was performed on the dataset of 150 patients for 343 MRI sessions (mean age 77.01 [SD 7.64] years). The T1-weighted MRI of each subject on a 1.5-Tesla Vision (Siemens) scanner was used for image acquisition. Scores of three features, MMSE, CDR, and ASF, were used to characterize the AD patients included in this study. We assessed the role of various features (ie, age, gender, education, socioeconomic status, MMSE, CDR, eTIV, nWBV, and ASF) on the prognosis of AD. Results The analysis further establishes the role of gender in the prevalence and development of AD in older people. Moreover, a considerable relationship has been observed between education and socioeconomic position on the progression of AD. Also, outliers and linearity of each feature were determined to rule out the extreme values in measuring the skewness. The differences in nWBV between CDR=0 (nondemented), CDR=0.5 (very mild dementia), and CDR=1 (mild dementia) are significant (ie, P<.01). Conclusions A substantial correlation has been observed between the pattern and other related features of longitudinal MRI data that can significantly assist in the diagnosis and determination of AD in older patients.

BACKGROUND Alzheimer’s disease (AD) is a degenerative progressive brain disorder where symptoms of dementia and cognitive impairment intensify over time. Numerous factors exist which may or may not be related to the lifestyle of a patient, can trigger off a higher risk for AD. Diagnosing the disorder in its beginning period is of incredible significance and several techniques are used to diagnose AD. A number of studies have been conducted for the detection and diagnosis of AD. This paper reports the empirical study performed on the longitudinal-based MRI OASIS data set. Furthermore, the study highlights several factors which influence in the prediction of AD. OBJECTIVE This study aims to examine the effect of longitudinal MRI data in demented and non-demented older adults. The purpose of this study is to investigate and report the correlation among various MRI features, in particular, the role of different scores obtained while MR image acquisition. METHODS In this study, we attempted to establish the role of the longitudinal magnetic resonance imaging (MRI) in exploratory data analysis (EDA) of AD patients. EDA was performed on the dataset of 150 patients for 343 MRI sessions [Mean age ± SD = 77.01 ± 7.64]. T1-weighted MRI of each subject on a 1.5-T Vision scanner was used for the image acquisition. Scores of three features, viz.- mini-mental state examination (MMSE), clinical dementia rating (CDR), and atlas scaling factor (ASF) were used to characterize the AD patients included in this study. We assessed the role of various features i.e. age, gender, education, socioeconomic status, MMSE, CDR, estimated total intracranial volume, normalized whole brain volume and ASF in the prognosis of AD. RESULTS The analysis further establishes the role of gender in prevalence and development of AD in older people. Moreover, a considerable relationship has been observed between education and socioeconomic position on the progression of AD. Also, outliers and linearity of each feature were determined to rule out the extreme values in measuring the skewness. The differences in nWBV between CDR = 0 (non-demented), CDR = 0.5 (very mild dementia), CDR = 1 (mild dementia) comes out to be significant i.e. p<0.01. CONCLUSIONS A substantial correlation has been observed between pattern and other related features of longitudinal MRI data that can significantly assist in the diagnosis and determination of AD in older patients.

The growing global demand for power supply is likely to exhaust available resources soon. It is advisable to avoid wastage of electricity as it may overburden consumer adversely. In the present study, we propose an IoT based solution to reduce electric power wastage in organizations. As the organizations are generally divided into sub sections or departments, a frame work can be proposed which allows the managers and supervisors to keep an online track of the ON/OFF status of appliances in their respective departments/sectors. The access to appliances can be provided with a Secure Shell connection through a dedicated server which keeps monitoring all the appliances in the whole organization continuously. Each manager and in-charge along with other officials can be provided with a user ID and password to login with. Each of them is likely to entertain with different level of rights to control various gadgets of the department. This frame work can prove itself to be useful in reducing the problem of various appliances ON in an organization. The frame work has provision for further improvements such that with slight modification it can be implemented controlling and monitoring a weather station situated in the remote forest.

Machine learning (ML) is the best way to make progress towards human level artificial intelligence, which allows software applications to become more accurate in predicting results. It is the most promising technique that has profound realization in reorganizing practices pertaining to various fields viz. healthcare, education world industry, retail and manufacturing sectors, traffic and urban planning etc. The compilation and storage followed by specific training of the stored data are some of the salient features of the machine learning process that has tremendous scope in discovering novel output in various relevant fields. There are plenty of tools in ML that may help in the training of data without being explicitly programmed. Tools are categorized into- framework, platform, library, and interface. For the successful development and effective execution of ML, one can categorically manipulate various related tools. Working through such tools advances the process as applied to the various applications. In the present study, we intend to exploit recommendation engines for the development of tools that can handle the huge quantity of data. The usage of the overwhelming quantity of multimodal data and streamlining the same for its personalized usage are some of the unique features of the study. We also focus on the evaluation of a toolkit with loads of data and furthering several ML tools along with their features and use for the desired application in the relevant field.