Prediction of postpartum depression using machine learning techniques from social media text

Early screening of mental disorders plays a crucial role in diagnosis and treatment. This study explores how data‐driven methods can leverage the information available on social media platforms to predict postpartum depression (PPD). A generalized approach is proposed where linguistic features are extracted from user‐generated textual posts on social media and categorized as general, depressive, and PPD representative using multiple machine learning techniques. We find that techniques used in our study exhibit strong predictive capabilities for PPD content. Holdout validation showed that multilayer perceptron outperformed other techniques such as support vector machine and logistic regression used in this study with 91.7% accuracy for depressive content identification and up to 86.9% accuracy for PPD content prediction. This work adopts a hierarchical approach to predict PPD. Therefore, the reported PPD accuracy represents the performance of the model to correctly classify PPD content from non‐PPD depressive content.     

Boundary stabilisation of the wave equation in the presence of singularities

We study the boundary stabilisation of the wave equation by a nonlinear feedback active on a part of the boundary in geometric situations for which the solutions have singularities. These singularities appear at the interfaces at which the mixed Neumann–Dirichlet boundary conditions meet. Under a simple geometrical condition concerning the orientation of the boundary, we obtain sharp energy decay rates under a general growth assumption on the feedback. We show that the singularities do not affect the energy decay rates and give examples.     

Comparison of total ozone column observations from space-borne Ozone Monitoring Instrument with ground-based Dobson Ozone Spectrophotometer measurements at an urban location in Indo-Gangetic Basin

This article presents a comparison analysis of OMIT (Ozone Monitoring Instrument retrieved overpass total ozone column (TOC)), and DOST (Dobson Ozone Spectrophotometer observed TOC) over Delhi during a period from October 2004 to June 2011. Megacity Delhi, located in Indo-Gangetic Basin, is an important site for comparison of ground-based and satellite retrieved TOCs due to significant anthropogenic emissions of ozone precursors, large shift in seasons, and large-scale crop residue burning in the region. DOST and OMIT data show an overall bias of 3.07% and significant correlation with coefficient of determination R² = 0.73. Large seasonal fluctuations in the biases and correlations have been observed ranging from 2.46% (winter) to 3.82% (spring), and R² = 0.84 (winter) to R² = 0.09 (summer), respectively. The large biases are attributed to changes in temperature, cloud cover, pollutants emissions from urban area, and crop-residue burning events. We also find notable variations in correlations between the datasets due to the varying burden of absorbing aerosols from open field crop-residue burning. The R² has changed from 0.67 (for aerosol optical depth, AOD 1.5–3.5) to 0.77 (for AOD 0–0.99). The dependence of the bias on solar zenith angle, cloud fraction, and satellite distance is also discussed. A simple linear regression analysis is applied to check the linkage between DOST and OMIT. The influence of atmospheric air temperature and relative humidity on OMIT at different pressure levels between 1000 and 20 hPa has been discussed.     

IoMT-Based Smart Monitoring Hierarchical Fuzzy Inference System for Diagnosis of COVID-19

The prediction of human diseases, particularly COVID-19, is an extremely challenging task not only for medical experts but also for the technologists supporting them in diagnosis and treatment. To deal with the prediction and diagnosis of COVID-19, we propose an Internet of Medical Things-based Smart Monitoring Hierarchical Mamdani Fuzzy Inference System (IoMTSM-HMFIS). The proposed system determines the various factors like fever, cough, complete blood count, respiratory rate, Ct-chest, Erythrocyte sedimentation rate and C-reactive protein, family history, and antibody detection (lgG) that are directly involved in COVID-19. The expert system has two input variables in layer 1, and seven input variables in layer 2. In layer 1, the initial identification for COVID-19 is considered, whereas in layer 2, the different factors involved are studied. Finally, advanced lab tests are conducted to identify the actual current status of the disease. The major focus of this study is to build an IoMT-based smart monitoring system that can be used by anyone exposed to COVID-19; the system would evaluate the user’s health condition and inform them if they need consultation with a specialist for quarantining. MATLAB-2019a tool is used to conduct the simulation. The COVID-19 IoMTSM-HMFIS system has an overall accuracy of approximately 83%. Finally, to achieve improved performance, the analysis results of the system were shared with experts of the Lahore General Hospital, Lahore, Pakistan.     

An Efficient Mechanism for Product Data Extraction from E-Commerce Websites

A large amount of data is present on the web which can be used for useful purposes like a product recommendation, price comparison and demand forecasting for a particular product. Websites are designed for human understanding and not for machines. Therefore, to make data machine-readable, it requires techniques to grab data from web pages. Researchers have addressed the problem using two approaches, i.e., knowledge engineering and machine learning. State of the art knowledge engineering approaches use the structure of documents, visual cues, clustering of attributes of data records and text processing techniques to identify data records on a web page. Machine learning approaches use annotated pages to learn rules. These rules are used to extract data from unseen web pages. The structure of web documents is continuously evolving. Therefore, new techniques are needed to handle the emerging requirements of web data extraction. In this paper, we have presented a novel, simple and efficient technique to extract data from web pages using visual styles and structure of documents. The proposed technique detects Rich Data Region (RDR) using query and correlative words of the query. RDR is then divided into data records using style similarity. Noisy elements are removed using a Common Tag Sequence (CTS) and formatting entropy. The system is implemented using JAVA and runs on the dataset of real-world working websites. The effectiveness of results is evaluated using precision, recall, and F-measure and compared with five existing systems. A comparison of the proposed technique to existing systems has shown encouraging results.     

Nanoparticle–Plant Interactions: Two‐Way Traffic

In this Review, an effort is made to discuss the most recent progress and future trend in the two‐way traffic of the interactions between plants and nanoparticles (NPs). One way is the use of plants to synthesize NPs in an environmentally benign manner with a focus on the mechanism and optimization of the synthesis. Another way is the effects of synthetic NPs on plant fate with a focus on the transport mechanisms of NPs within plants as well as NP‐mediated seed germination and plant development. When NPs are in soil, they can be adsorbed at the root surface, followed by their uptake and inter/intracellular movement in the plant tissues. NPs may also be taken up by foliage under aerial deposition, largely through stomata, trichomes, and cuticles, but the exact mode of NP entry into plants is not well documented. The NP–plant interactions may lead to inhibitory or stimulatory effects on seed germination and plant development, depending on NP compositions, concentrations, and plant species. In numerous cases, radiation‐absorbing efficiency, CO₂ assimilation capacity, and delay of chloroplast aging have been reported in the plant response to NP treatments, although the mechanisms involved in these processes remain to be studied.     

Osteoporosis Prediction for Trabecular Bone using Machine Learning: A Review

Trabecular bone holds the utmost importance due to its significance regarding early bone loss. Diseases like osteoporosis greatly affect the structure of the Trabecular bone which results in different outcomes like high risk of fracture. The objective of this paper is to inspect the characteristics of the Trabecular Bone by using the Magnetic Resonance Imaging (MRI) technique. These characteristics prove to be quite helpful in studying different studies related to Trabecular bone such as osteoporosis. The things that were considered before the selection of the articles for the systematic review were language, research field, and electronic sources. Only those articles written in the English language were selected as it is the most prominent language used in scientific, engineering, computer science, and biomedical researches. This literature review was conducted on the articles published between 2006 and 2020. A total of 62 research papers out of 1050 papers were extracted which were according to our topic of review after screening abstract and article content for the title and abstract screening. The findings from those researches were compiled at the end of the result section. This systematic literature review presents a comprehensive report on scientific researches and studies that have been done in the medical area concerning trabecular bone.     

Convolutional Neural Network Based Intelligent Handwritten Document Recognition

This paper presents a handwritten document recognition system based on the convolutional neural network technique. In today’s world, handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired users. This technology is also helpful for the automatic data entry system. In the proposed system prepared a dataset of English language handwritten character images. The proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten documents. In this research, multiple experiments get very worthy recognition results. The proposed system will first perform image pre-processing stages to prepare data for training using a convolutional neural network. After this processing, the input document is segmented using line, word and character segmentation. The proposed system get the accuracy during the character segmentation up to 86%. Then these segmented characters are sent to a convolutional neural network for their recognition. The recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given dataset. The proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%, and for validation that accuracy slightly decreases with 90.42%.     

Implementation of convolutional neural network categorizers in coronary ischemia detection

The heart is one of the most important and sophisticated organ of the human body. Coronary ischemia is a condition in which the coronary muscles do not receive sufficient blood and oxygen because of blocked or tightened heart vessels. This syndrome is called cardiac vessel illness. There have been numerous attempts to detect the impact of cardiac vessel illness on the heart muscles using noninvasive experiments. Most of the effects of ischemia as well as severe cardiac conditions on the muscles of the ventricle parts can be detected using ultrasonic images. If treatment is provided to suspected cases in the early stage of cardiac vessel illness, the chance of survival is high; for this, many software‐based detection approaches have been used. In this study, we propose an approach that can automatically diagnose the cardiac artery disease by using the cardiac echo images of the four parts of the heart.     

A comprehensive survey of AI-enabled phishing attacks detection techniques

In recent times, a phishing attack has become one of the most prominent attacks faced by internet users, governments, and service-providing organizations. In a phishing attack, the attacker(s) collects the client’s sensitive data (i.e., user account login details, credit/debit card numbers, etc.) by using spoofed emails or fake websites. Phishing websites are common entry points of online social engineering attacks, including numerous frauds on the websites. In such types of attacks, the attacker(s) create website pages by copying the behavior of legitimate websites and sends URL(s) to the targeted victims through spam messages, texts, or social networking. To provide a thorough understanding of phishing attack(s), this paper provides a literature review of Artificial Intelligence (AI) techniques: Machine Learning, Deep Learning, Hybrid Learning, and Scenario-based techniques for phishing attack detection. This paper also presents the comparison of different studies detecting the phishing attack for each AI technique and examines the qualities and shortcomings of these methodologies. Furthermore, this paper provides a comprehensive set of current challenges of phishing attacks and future research direction in this domain.