A joint and simultaneous prediction framework of weekday and weekend daily-activity travel pattern using conditional dependency networks

Daily activity pattern (DAP) prediction models within the Activity-based Modelling paradigm are being currently developed without adequate consideration of the various interdependencies among activities within a multi-day planning horizon. We hereby propose a conditional dependency network structure based interdependent multilabel-multiclass classification framework for joint and simultaneous prediction of weekday and weekend DAP of an individual. The prime advantage of the proposed modelling framework is flexibility of application of any algorithm for parameter estimation. Random Forest Decision Tree (RFDT), eXtreme Gradient Boosting and Light Gradient Boosting Machine (LightGBM) as the base classifier and probabilistic and non-probabilistic inference approaches are explored for measuring their comparative performance to provide insights for future researchers. Several variables representing neighbourhood characteristics are also investigated as DAP de-terminants along with socio-economic characteristics of individuals for the first time.This model is estimated based on two-days (weekday and weekend) activity-travel diary of 1808 households (6521 individuals) in Bidhanangar Municipal Corporation, India. The non-probabilistic approach-based models are found to achieve higher accuracy (0.81-0.92) compared to probabilistic models (0.76 to 0.82). RFDT and LightGBM are found to be the best performers in the probabilistic and non-probabilistic frameworks respectively. External validation results show that all proposed multiday-interdependent models (80%-94%) perform better than independent models (64%-83%).This framework can be applied to other transportations planning problems like household interaction in ac-tivity generation, joint destination and mode choice. This is also one of the first attempts to investigate the determinants of DAPs of urban commuters in an emerging country like India.

Biomedical waste plastic: bacteria, disinfection and recycling technologies—a comprehensive review

Plastic recycling reduces the wastage of potentially useful materials as well as the consumption of virgin materials, thereby lowering the energy consumption, air pollution by incineration, soil and water pollution by landfilling. Plastics used in the biomedical sector have played a significant role. Reducing the transmission of the virus while protecting the human life in particular the frontline workers. Enormous volumes of plastics in biomedical waste have been observed during the outbreak of the pandemic COVID-19. This has resulted from the extensive use of personal protective equipment such as masks, gloves, face shields, bottles, sanitizers, gowns, and other medical plastics which has created challenges to the existing waste management system in the developing countries. The current review focuses on the biomedical waste and its classification, disinfection, and recycling technology of different types of plastics waste generated in the sector and their corresponding approaches toward end-of-life option and value addition. This review provides a broader overview of the process to reduce the volume of plastics from biomedical waste directly entering the landfill while providing a knowledge step toward the conversion of "waste” to "wealth.” An average of 25% of the recyclable plastics are present in biomedical waste. All the processes discussed in this article accounts for cleaner techniques and a sustainable approach to the treatment of biomedical waste. Graphical

Preliminary assessment of COVID-19 Waste management scenario during lockdown in Chandigarh & nearby areas

Covid - 19 brought about a change in process of working in all the spheres. A change could be seen in the education sector, hospitality, transport, manufacturing, medical sector, etc. The economy and lifestyle were majorly hit at all levels. Even a single-unit family faced the brunt of the pandemic in several ways. The family size increased because members of the family who were away from homes working in different cities other than their native places shifted back. That resulted in variation in the quantity of waste generation at residences and a change in the composition of waste as well. While socialists, scientists, architects, and environmentalists are concerned about fancy topics like sustainability, climate change, environmental awareness, etc., one should not forget about the waste management system to add on points towards sustainability & healthy life. A proper waste management system plays a major role when the world faces such a pandemic situation. The study is aimed to find out the changes in the waste composition and change of mode and frequency of collection in the residential sector during the lockdown period. The need for such a study will help us frame better guidelines for future. It will also help us know the awareness level of public and how much more is required for better segregation of waste. This will further help us for better waste management. The methodology used in the paper is questionnaire based besides self-observation. The questionnaire was floated in tricity of Chandigarh, Mohali and Punchkula and Kharar. The findings of the paper reveal that there was considerable lowering in the frequency of collection of waste from the residential area which caused a lot of inconvenience to the owners. It has been found that the waste composition has changed over a period of time with more usage of plastics which were frequently used in the form sanitizer bottles, surface disinfectant bottles, and vegetable cleaning liquid bottle etc. besides packaging material used because of online shopping and extra usage of placebo medicines. © Published under licence by IOP Publishing Ltd.

Online Affinity of Instructing Methods for Using Personal-Efficacy and Reading Capacious During Covid-19

Now a days in EFL procedure of education the ability of reading became as significant belief and personal-efficacy reading as a basic understanding for students. By monitoring the acknowledged participates under the ballpark figure of large studying and methods of understanding, the impact of their observation is premeditated on reading of each one’s personal-efficacy. On a daily routine all these things are comparatively considered which are put into effect by teachers of handful in number. Approach towards exhibiting Extensive reading (ER) is inspected to be “more expensive, difficult, and time-consuming”. Method of recognition of elements in a various way for effective impact in putting its efforts to utilize for its empowerment. Paper has been segregated into two contexts: Association with attitude is considered as primary one and attitude is considered as secondary one. Whether knowledge work is understood by student or not is considered as the impact of ER by the first review. Procedure which are convenient is taken as the observations of student and is analysed as second one. The examinations are quantifiable to utilize the observations as information in terms of subjective way taken from students who belong to first academic year of reading course in a systematic way and 603 details of undergraduate students from KLEF of Guntur were chosen as participants for extant examination. In ER programme of includes and excludes “comprehension reading work” is treated as fundamental in the proposal of disclosures. In case of any, “the programme appeared to positively affect contributing students”. Techniques of classification like “decision tree and Mixed Model Database Miner (MMDBM)” are employed in this paper which leads to improvements of post-test to pre-test in ER group. Observations of students in ER results as optimistic and algorithm of MMDBM which leads to accuracy in higher rate in pre-test and post-test detection. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Mental health impact of COVID-19 and machine learning applications in combating mental disorders: a review

Mental disorders are a critical issue in modern society, yet it remains to be consistently neglected. The COVID19 pandemic has made it much more difficult to seek assistance when one needs it. People are feeling increasingly anxious and uncertain about their futures while being socially separated from their friends and relatives. As people continue to quarantine among the limitations imposed by governments, interaction between clinical therapists or social workers and those suffering from mental illness has gotten increasingly limited. Machine learning is a vital approach for allowing virtual analysis of many forms of textual, audio, and visual data for sentiment analysis and understanding the mental health of people utilizing numerous critical parameters in this situation. This chapter aims to provide a systematic review of the current literature investigating COVID-19's impact on mental well-being, as well as studies that explore machine learning and artificial intelligence techniques to detect and treat mental illnesses when traditional therapies are unavailable due to lockdown and social distancing norms imposed. The different machine learning algorithms and deep learning approaches utilized in earlier studies are thoroughly discussed in this chapter. Detailed explanation of the data sources utilized and a review of the types of features investigated in mental disorder identification are included as well. The study's major findings are thoroughly discussed. The obstacles of employing machine learning techniques in biomedical applications are explored, as well as possibilities to enhance and progress the discipline. © 2022 Elsevier Inc. All rights reserved.

A Review of Machine Learning Techniques to Detect and Treat COVID-19 Using EHR Data

The COVID-19 pandemic has caused a global emergency, as human life is under constant threat and medical infrastructure is being pushed to the limits. Scientists, engineers, and healthcare experts collaboratively have come up with new innovative technologies to tackle the threat posed by the disease. Artificial intelligence (AI) and machine learning (ML) have played pivotal roles in several technologies being developed. In this study, we aim to review the applications of AI and ML in developing models for diagnosis and clinical outcome prediction of the COVID-19 disease by analyzing data from Electronic Health/Medical Records (EHR/EMR) of patients. In this chapter, we reviewed various ML algorithms used by researchers to extract key features from the EHR necessary to develop predictive models;we also reviewed the performance of various predictive models developed which employed ML to assist decision-making for healthcare professionals. Gaps in the current methodology of acquiring and storing clinical data in a digital format have also been discussed thoroughly. Scientists, clinicians, healthcare experts, policymakers, academics, and ML enthusiasts might find the review useful, as important studies related to the application of ML in the field of medical decision making and alike by studying EHR has been systematically analyzed and critically reviewed, the discussion on the challenges faced by the existing researchers and possible solutions have also been discussed;which should stimulate further research in this domain. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Study and impact analysis of COVID-19 pandemic clinical data on infection spreading

In December 2019, a severe pneumonialike disease has occurred in the city of Wuhan, Hubei Province in China. Within a very short period the infection spread across the whole world, but there was no previous medical history about this virus and how, where, and when the disease infected the human body and mutated in humans is still unknown. Subsequently, the coronavirus disease 2019 (COVID-19) outbreak was declared as the world pandemic on March 2020 by the World Health Organization because of its harmfulness and super spreading nature. Till now, there is no specific medications and clinical treatment available to avoid this pandemic COVID-19 outbreak. For this, it is essential to have a detailed study and analysis through the recent technologies. The recent trends such as artificial intelligence and machine learning (ML) based models can learn from past patient medication data and can suggest improvement accordingly by analyzing the data to control the spread. In the present scenario, the correct decision could be the appropriate precaution to stop spreading as well as controlling such a pandemic disease by proposing predictive ML that analyzes past data and conclude some useful information for future control of the spread of COVID-19 infections using minimum resources. The ML-based approach can be helpful to design different models to give a predictive solution for controlling infection and spreading and taking precaution toward the COVID-19 outbreak. In this chapter, we study the basic information of COVID-19 and its effectiveness worldwide. We also state the fundamental steps of ML, discuss the ML mechanism to study the pandemic for research and academic purposes, and study the data analytics of clinical data of India through a case study. As the data is a time series data, we analyze the data from March 1, 2020 to April 15, 2020;the decision tree approach of ML is discussed through a case study. Finally, the chapter is concluded with certain future scope of work in this area of research. © 2022 Elsevier Inc.

Eastern India collaboration on multi-system inflammatory syndrome in children (eicomisc): A multi-centre observational study

Background: Few single centre studies from resourcepoor settings have reported about the epidemiology, clinical feature and outcome of multisystem inflammatory syndrome in children (MIS-C). However, larger data from multi-centre studies on the same is lacking including from Indian setting. Methods: This retrospective collaborative study constituted of data collected on MIS-C from five tertiary care teaching hospitals from Eastern India. Children ≤15 years of age with MIS-C as per the WHO criteria were included. Primary outcome was death or LAMA (leaving against medical advice). Results: A total of 134 MIS-C cases were included (median age, 84 months;males constituted 66.7%). Fever was a universal finding. Rash was present in 40%, and conjunctivitis in 71% cases. Gastro-intestinal and respiratory symptoms were observed in 68% and 53% cases, respectively. Co-morbidity was present in 23.9% cases. Shock at admission was noted in 35%, and 27.38% required mechanical ventilation. Nearly 13% children met the primary outcome. The coronary abnormalities got normalized during follow-up in all except in one child. Initial choice of immunomodulation had no effect on the outcomes. Presence of underlying co-morbidity, lymphopenia, thrombocytosis, hyponatremia, increased LDH (>300 U/L), and hypoalbuminemia are the factors significantly associated with the occurrence of primary outcome. Conclusions: MIS-C has myriad of manifestations. Underlying co-morbidity, lymphopenia, thrombocytosis, hyponatremia, increased LDH (>300 U/L), and hypoalbuminemia were associated with the occurrence of primary outcome (death or LAMA). No difference in outcome was noted with either steroid or IVIG or both. Coronary artery abnormalities resolved in nearly all cases.

Impact Analysis of COVID-19 on Various Indian Sectors

Coronavirus disease 2019 referred to as COVID-19 is a disease that has out-spread globally leading to a pandemic. As of 11 August 2021, the worldwide situation as per WHO's dashboard shows 203,944,144 confirmed cases and 4,312,902 deaths. The pandemic has remodelled the manner of living for all humans both in an extensive and small-scale manner. People had to create a novel transient routine to cope with the unfamiliar times. Several people started staying at home and saw their workplaces shift from the office to behind laptop screens. Some businesses burgeoned in the lockdown, while others declined. Organizations underwent digital evolution, and people spent a greater percentage of their day online. For instance online grocery shopping, using different platforms for e-learning, working from home and net banking comprised the everyday to-do list. Given the aforementioned changes in the world, there have bound to be various changes in one's own lifestyle. Conducting a survey on screen time was crucial for finding out the basis of the hypothesis proposed by the authors. By testing the hypothesis and achieving a strong result, the authors wanted to determine how the increase in screen time might have an impact on the different sectors. The results of hypothesis testing served as an inspiration to work on stock prices data of distinct sectors such as IT, FMCG, aviation, hospitality and analyse trends on the basis of parameters such as stock price, moving averages, volume and cumulative returns from March 2020 to July 2021.

GLCM Based LGBM classification for COVID-19 Analysis using Chest X-ray Images

The novel corona virus (COVID-19) has turned out to be the biggest challenge of 21 century. Since, it is spreading at a very high pace all over the world, fast and accurate detection of this virus becomes a necessity. However, the human annotation of images is time-consuming;it is not a good strategy for dealing with big amounts of medical imaging data. This work looks at the experimental examination of features that are well-suited for examining X-ray pictures in COVID19. This investigation encompasses the series of steps, including data augmentation, pre-processing, feature extraction using GLCM followed by feature selection using PCA, and finally classification is performed by Light Gradient Boosting Machine. The proposed method was validated by comparing it to COVID-19 X-ray dataset, with an accuracy achieved is 92.40%. © 2022 IEEE.

Asia’s (lack of) Response and Recovery Plans for the Forcibly Displaced

The insufficient and unsystematic way Asian states have singularly dealt with the different types of refugee groups living within their borders has drawn much criticism. The contours of all the different refugee crises have been stretched further with the Covid-19 outbreak. However, a common characteristic of this region is the lack of formal initiatives and actions to address the issue of forced displacement by adhering to international principles at the sub-regional and domestic levels. The descriptive part of this article outlines the national frameworks or the informal procedures of each host country in Asia, to handle the forcibly displaced population. Much of the policy initiatives, let alone actions, are ad hoc in nature, that directs us to finding lasting solutions. In the analytical part of this article, international principles, regional initiatives and contributions of the specialised agencies of the United Nations have been examined. Yet, in order to address the unique challenges faced by Asian states, a framework legislation at the domestic level is found to be the first step for systematically and uniformly dealing with the influx of displaced persons. The issue of forced displacement is not over, it is merely in abeyance. Hence, the conclusion is that a convergence of legal tools at the national, regional and international level is a pressing priority. © University of Jember & Indonesian Consortium for Human Rights Lecturers

Detection of Pneumonia Using Deep Learning

Pneumonia isa lunginfection that usually causes fever, coughing, and difficulty in breathing. Pneumonia is one of the most significant causes of death and morbidity in children under five years of age worldwide. Pneumonia is a very dangerous condition that is very difficult to diagnose at an early stage. This paper focuses on the development of a deep learning model using Convolution Neural Network for detecting Pneumonia disease from X-ray images of the Chest and improve it for efficiency and accuracy by making various hyperparameter optimizations and modifications to achieve better detection and performance accuracy. The model also uses some of the existing models by training them on the required data sets. The research focuses to develop a system that can that detect pneumonia from the chest X-ray images with an improved accuracy which can help to provide an early assistance service at places where the experts are not available easily. Also, this system can be used in the future for the detection of COVID-19 disease. © 2021 IEEE.

Movement and Solidarity: Community Mobilization to Mitigate the Adverse Impact of COVID-19 on Families with Young Children Receiving Care from Early Childhood Systems

Emerging research indicates an immense burden on children and families related to the COVID-19 pandemic. This study uses data from semi-structured interviews and focus groups with early childhood service providers (n=19) to demonstrate the pandemic's impact on families with very young children and early childhood services in two high-need communities in Massachusetts, USA. We found that although the pandemic has worsened existing inequities and severely limited resources for young children and families, community mobilization in response to the crisis and innovative strategies stemming from resilience were developed quickly. Findings highlight the usefulness of early childhood systems of care in crisis responses and leveraging public-private cooperation to serve the needs of diverse families with young children. Lessons learned are applicable to global settings with high pre-pandemic inequities and can be used to develop stronger models of crisis response within the early childhood sector in preparation for future crises.

Clinical and Postoperative Outcomes of Cancer Surgeries during the COVID-19 Pandemic: A Comparative Study with its Pre-COVID Surgical Audit at Five Major Tertiary Care Hospitals' Cancer Departments in India

Introduction There has been an exponential rise in number of coronavirus disease 2019 (COVID-19)-positive infections since March 23, 2020. However, cancer management cannot take a backseat. Objective The aim of this study was to identify any difference in the complication and mortality rates for the cancer patients operated during the ongoing COVID-19 pandemic. Materials and Methods This was a retrospective study of a prospectively maintained database of five centers situated in different parts of India. Variables such as demographics, intraoperative, and postoperative complications were compared between COVID-19 (group A-March 23, 2020-May 22, 2020) and pre-COVID time period (group B-January 1 to January 31, 2020). Results One-hundred sixty-eight cancer surgeries were performed in group B as compared with 148 patients who underwent oncosurgeries in group A. Sixty-two percent lesser cancer surgeries were performed in the COVID-19 period as compared with the specific pre-COVID-19 period. There was no significant difference in age group, gender, comorbidities, and type of cancer surgeries. Except for the duration of surgery, all other intraoperative parameters like blood loss and intraoperative parameters were similar in both the groups. Minimally invasive procedures were significantly lesser in group A. Postoperative parameters including period of intensive care unit stay, rate of infection, need for the change of antibiotics, and culture growth were similar for both the groups. While minor complication like Clavien-Dindo classification type 2 was significantly higher for group A, all other complication rates were similar in the groups. Also, postoperatively no COVID-19-related symptoms were encountered in the study group. A subset analysis was done among the study groups between those tested preoperatively for COVID-19 versus those untested showed no difference in intraoperative and postoperative parameters. No health-care worker was infected from the patient during the time period of this study. Conclusion Our study shows that there is no significant difference in the incidence of postoperative morbidity and mortality rates in surgeries performed during COVID-19 pandemic as compared with non-COVID-19 time period.

Interactive map application for real time crime reporting

In an ideal world, a society is governed by laws and any member of the society that breaks these laws faces measurable consequences. In such a case, a citizen is expected to report any violation of law to the concerned authorities. Illegal activities are an issue for every nation, and the majority of crimes committed go unreported due to fear and inconvenience of travel. This causes a need for an alternative investigative system, with non-interactive capabilities. In this work, we focus on developing a system for filing complaints online, along with a real time map for viewing hotspots and understanding crime dynamics in a neighborhood. The application comprises four functional modules, user verification, file a complaint with details and location, distributed database for storing the details of the complaint, and a live map of reported events in a web dashboard. This system paves the way for civilians to report crime incidents with the location pinpointed on a real time map along with detailed information regarding the same. Keeping in mind the restricted outdoor travel and exposure in situations of global pandemics such as the COVID-19, the proposed system could be a great alternative for offline crime reporting since crimes like domestic violence have been surfacing. © Grenze Scientific Society, 2021.

Patient perceptions about virtual clinical consultations during current covid-19 pandemic: A multi-city survey across india

Introduction: COVID-19 has prevented many patients from accessing health care through traditional face-to-face clinic visits. Consequently, online consultations have gained popularity. Aim: To explore patient perceptions regarding virtual consultations. Methods: A voluntary online survey using a mix of quantitative and qualitative questions was administered to patients across selected cities in India using a social media platform. Responses were used to explore the characteristics of users, perceived advantages and disadvantages of online consultations and patient satisfaction. Results: There were 679 respondents (M 52.4%: F 47.6%) that had consulted doctors online;91.8% were from 8 major metro cities. Interestingly, over 80% had never sought online consultation before the COVID-19 pandemic. 46% consultations were via videocalls, 26% through WhatsApp and 21% via telephone calls. The main advantages of online consultations cited by patients included a lower risk of infection (78.8%), reduced waiting time (56.8%) and travel time (58.3%). The main disadvantages included a lack of physical examination (73.4%), a perception that this was not as satisfying as a face-to face consultation (37.9%) and difficulty in communication (24.5%). 78.6% patients rated their online consultations as either good or very good. However, given the choice, almost two-thirds felt they would still prefer face-face consultations. Conclusion: High levels of satisfaction from this survey suggests that teleconsultation has the potential to become a complementary method to access clinical care even after restrictions from the pandemic cease. The disadvantages of online consultations could be mitigated through evolving technologies such as digital stethoscopes and improvement in communication tools. © 2021, Indian Association of Preventive and Social Medicine. All rights reserved.

Computer-Vision based Face Mask Detection using CNN

The global pandemic due to the novel corona virus, covid-19 has affected millions of lives across the globe. It has also disturbed economy, environment and social norms leading to many problems and giving birth to different rules and laws in order to ensure public safety. Wearing masks is one of the most important and primitive precautionary measures along with safe social distancing as advised by the World Health Organization. To manually monitor people not wearing face mask in order to ensure public safety is definitely a strenuous task. Therefore, this research work proposes a real time face mask detection system by applying computer vision and machine learning concepts like convolution neural networks and refined MobileNetV2 architecture to ease the deployment of proposed model in embedded devices with limited computational capacity. The dataset utilized here is available on Kaggle as Face mask detection dataset. The model is trained using Adam Optimizer algorithm which is best suited for deep learning models and is built using Keras, TensorFlow and OpenCV. The proposed model touches 99% accuracy under various training to testing ratios like 70% training and 30% testing, 50% training and 50% testing etc. Precision, recall, f-score and support are calculated for all trials. This means that the system is computationally effective and could potentially be used in places like railway stations, airports or any other public places to detect people not wearing face mask and ensure safety to certain extent during this pandemic times. © 2021 IEEE.

Convergence of two-stage iterative scheme for K-weak regular splittings of type II

Monotone matrices play a key role in the convergence theory of regular splittings and different types of weak regular splittings. If monotonicity fails, then it is difficult to guarantee the convergence of the above-mentioned classes of matrices. In such a case, K-monotonicity is sufficient for the convergence of K-regular and K-weak regular splittings, where K is a proper cone in Rn. However, the convergence theory of a two-stage iteration scheme in a general proper cone setting is a gap in the literature. Especially, the same study for weak regular splittings of type II (even if in standard proper cone setting, i.e., K=R+n), is open. To this end, we propose convergence theory of two-stage iterative scheme for K-weak regular splittings of both types in the proper cone setting. We provide some sufficient conditions which guarantee that the induced splitting from a two-stage iterative scheme is a K-regular splitting and then establish some comparison theorems. We also study K-monotone convergence theory of the stationary two-stage iterative method in case of a K-weak regular splitting of type II. The most interesting and important part of this work is on M-matrices appearing in the Covid-19 pandemic model. Finally, numerical computations are performed using the proposed technique to compute the next generation matrix involved in the pandemic model. The computation of large PageRank matrices shows that the two-stage Gauss-Seidel method performs better than the Gauss-Seidel methods. © 2021 Elsevier Inc.