Search

COVID-19 (Corona Virus Disease 2019) is a pandemic, which has been spreading exponentially around the globe. Many countries adopted stay-at-home or lockdown policies to control its spreading. However, prolonged stay-at-home may cause worse effects like economical crises, unemployment, food scarcity, and mental health problems of individuals. This article presents a smart consumer electronics solution to facilitate safe and gradual opening after stay-at-home restrictions are lifted. An Internet of Medical Things enabled wearable called EasyBand is introduced to limit the growth of new positive cases by autocontact tracing and by encouraging essential social distancing.

Sustainable urban mobility and traffic congestion are the key challenges in a smart city. Nevertheless, a sustainable mobility approach such as real-time ridesharing as a solution is likely to fail, if not integrated with actions aimed at increasing the awareness of citizens, encouragement through incentives and influencing their behavioral change. This article analyzes the possibility of quantifying an individual contribution toward sustainability and reciprocal incentive approach to encourage voluntary behavioral development toward sustainable mobility solutions. Furthermore, the challenges faced by the interested carpoolers were analyzed. This work proposes an IoT-based framework called WeDoShare for real-time ridesharing as a solution aimed at resolving the issues of carpoolers and quantifying their sustainability contribution with a reciprocal auto-incentive approach. Additionally, on top of social network, a gamification approach is proposed to involve, spread, and engage the citizens in ridesharing activity.

Fiber Bragg grating sensing technology provides a new look to the healthcare monitoring system due to its spectral encoding capacity, dielectric property, sensitivity, inert, nontoxic, resistive to the electromagnetic environment, self-referencing, and low cost. This article presents a design and construction of an FBG sensor for the monitoring of cardiac vibrations. A sensor element is designed by depositing polydimethylsiloxane (PDMS) polymer on the FBG sensing element. The elastic and thermal property of the sensor element is also discussed in this article. The stress and strain distribution profile is addressed using finite element analysis (FEA). Further, the bonding of the FBG sensor element is discussed in this article with adequate design specifications. In addition to the FBG sensor design considerations, the real-time acquisition of the cardiac signal is also experimented with in this research work to validate the sensor performance. Finally, the architecture of a cardiac monitoring approach by utilizing the Internet of things (IoT) and machine learning (ML) is proposed in this article.

Virtual Reality (VR) technology is widely used in scientific, engineering and educational applications all over the world. The technology is also widely advancing day by day, but, the applications in medical fields are limited. Medical technology is one of the most advancing technologies which are evolving due to unlimited need of health requirement. Further, Computational Intelligence (CI) contributed much promising aspects of many healthcare practices such as treatment, disease diagnosis, direct follow-ups, rehabilitation setups, preventive measures and administrative management practices etc. Dental sciences have witnessed many developments. In many ways, VR based surgery practices are governed by computer assistance. The conjunction of these two technological aspects to a larger extent can solve various issues in modern healthcare systems. With the introduction of newer healthcare technology, the medical issues nevertheless happen to be overcome. Nevertheless the scope in this kind of study is boundless.

IoT is redefining the way we look at things today. “Things” today are able to communicate and with AI being deployed at the edge, a whole new window of possibilities has opened up. Things with communication capabilities which we called Intelligent Internet of Things are able to bring transformations to healthcare, manufacturing, transportation, automobiles, and many other industries in many ways. Connected vehicles is one outcome of the IoT and intelligence of edge devices which is bringing infotainment, remote diagnosis, entertainment, automatic braking, lane detection, collision avoidance and lot of other systems that are being helpful in increasing the passenger safety, pedestrian safety and at the same time decreasing congestion, traffic delays as a result of which reducing the effect environmental pollution due to over burning of fuel during congestion. Road accidents today are one of the top ten reasons of human death according to various reports. In this kind of scenario, connected vehicle technology along with intelligent traffic system can help a lot in increasing the safety of people on road.

Monitoring of physiological parameters during treatment procedure is vital, thus recommended in various medical conditions such as claustrophobia, pediatric, implanted artificial pacemakers, dementia, coma, and local anesthesia conditions etc. Further, electronic equipment and sensors are not allowed to be used everywhere inside the healthcare facility and medical experts are typically not aware about the patient’s cardiac conditions. Therefore, there is a requirement of such additional systems in the already existing or new healthcare facilities. As of now, many research works have been published for design and test various sensing schemes using FBGs. However, there is no cost effective solution available yet, which is in practice at commercial healthcare facilities. The proposed work provides an experimental validation of such cardiac and respiration monitoring systems to develop a test case in a real scenario. The design considerations and process of the sensor element is discussed in details in this article. In addition to that the implementation of Internet of Things (IoT) based approach for remote monitoring and notification mechanism are portrayed in this article.

The healthcare industry has come a long way with a series of revolutions starting from Healthcare 1.0 up to Healthcare 4.0 where innovation made efforts to save human lives better than the past. Today IoT devices around the world and especially in healthcare domain generate a huge amount of data with 3Vs of big data, i.e., velocity, variety, and volume. This is where fog computing and cloud computing have come up in utilizing those data which can be utilized for analytics and modeling purposes which can keep records as well as predict the patients’ health by performing analysis. In the age of IoT and AI, which is bringing amazing possibilities and intelligence in various industries, it has brought revolutions in healthcare as well by giving real-time analytics on patient’s data without fail with help of fog computing and cloud computing. In this chapter, the role of IoT, fog computing, and cloud computing has been described along with applications of machine learning and big data that runs on these paradigms has been explained. Issues related to cloud computing and motivation behind bringing fog computing paradigm have also been explained in detail. Several architectures of fog computing are also discussed in this chapter along with their application and comparison. Application of big data and machine learning modeling has also been explained in later part of the chapter. Lastly, case studies related to fog computing, big data, and machine learning in healthcare has been explained and compared.

Background An association between rotavirus vaccination and intussusception has been documented in post-licensure studies in some countries. We evaluated the risk of intussusception associated with monovalent rotavirus vaccine (Rotavac) administered at 6, 10 and 14 weeks of age in India. Methods Active prospective surveillance for intussusception was conducted at 22 hospitals across 16 states from April 2016 through September 2017. Data on demography, clinical features and vaccination were documented. Age-adjusted relative incidence for 1–7, 8–21, and 1–21 days after rotavirus vaccination in children aged 28–364 days at intussusception onset was estimated using the self-controlled case-series (SCCS) method. Only Brighton Collaboration level 1 cases were included. Results Out of 670 children aged 2–23 months with intussusception, 311 (46.4%) children were aged 28–364 days with confirmed vaccination status. Out of these, 52 intussusception cases with confirmed receipt of RVV were included in the SCCS analysis. No intussusception case was observed within 21 days of dose 1. Only one case occurred during 8–21 days after the dose 2. Post-dose 3, two cases in 1–7 days and 7 cases during 8–21 days period were observed. There was no increased risk of intussusception during 1–7 days after the doses 1 and 2 (zero cases observed) or dose 3 (relative incidence [RI], 1.71 [95% confidence interval {CI} 0.0–5.11]). Similarly, no increased risk during 8–21 days after the dose 1 (zero cases observed), dose 2 (RI, 0.71 [95% CI, 0.0–3.28]) or dose 3 (RI, 2.52 [95% CI, 0.78–5.61]). The results were similar for 1–21 day periods after the doses separately or pooled. Conclusions The risk of intussusception during the first 21 days after any dose of rotavirus vaccine (Rotavac) was not higher among the Indian infants than the background risk, based on limited SCCS analysis of 52 children.

Internet of Things (IoT) connects many physical devices to many individuals from earth to space. This new concept covers almost all applications such as smart cities, industries, autonomous systems...

The efficiency and uniformity of irrigation can be maintained from the complex and diverse information based systems by considering weather, soil, water, and crop data. The model is created by suitable decision support system (DSS) algorithm. The DSS model acquires real-time soil and environmental data using our wireless sensor network mechanism. A radial basis function type of neural network is performed to predict hourly soil moisture content (MC) requirement as well as required soil evapotranspiration using Blaney–Criddle method. In this work, a fuzzy logic based weather dependent irrigation control mechanism is also developed and it is integrated with the DSS to generate adequate SMS notifications by interfacing a GSM modem. The soil MC prediction algorithm is implemented by collecting field data from a test land in Bhubaneswar located in the eastern region of India. The comparative analysis is also performed by calculating prediction RMSE, RSE, MSE, RPD and algorithm running time. The proposed smart DSS model is used to compensate the amount of water loss through evapotranspiration by considering weather, soil, water, and crop data.

Agriculture is a basic and most important profession of any country as it balances the food requirement and also the essential raw materials of industry. In the similar sense, the adaptation of implementing smart technology in agriculture practices needs to be focused on better land productivity. The fertilizer and manure should be precisely applied during agriculture practice throughout the countryside with the use of digital technologies. This motivates us to develop a reactive web application which will accurately predict the required soil N-P-K (Nitrogen-Phosphorus-Potassium) content by utilizing one time soil testing results of available soil N-P-K contents as per the yield target. This predictive model is designed by considering standard experimental data sets from Indian Council for Agriculture Research (ICAR), India. The prediction model is designed using Random Forest (RF) algorithm which is capable of handling large dataset. The predicted N-P-K content are shown in a reactive R Shiny user interface to notify required N-P-K values for the necessary action by the farmer. The complete web based prediction model is efficiently conveying the required N-P-K content information of the particular farm location to the farmer as well as the agriculture specialists.

Breast cancer is the most communal form of cancer among women. It is becoming one of the major causes of female death around the world. The only key to reduce its morality rates is early detection of the disease. Mammography screening is considerable technique for the detection of breast cancer. But it is not always satisfactory at early stages. With the period of time, medical data expanded which can be molded to utilize as an alternative for the recognition of disease. Historical medical data can minimize morality rate by analyzing new correlation and pattern with the help of machine learning (ML). ML and artificial intelligence aided early detection of breast cancer and can be lifesaving option in the world of medical domain. In this chapter, role of ML as an effortless detection technique of breast cancer is presented. Several ML approaches such as logistic regression, support vector machine, decision tree, Naive Bayes, neural network (NN), etc., are used for the classification of extracted features from the mammograms as benign or malignant tumors. Breast cancer detection systems constructed are further compared through several matrix and measures to attain best model. NN model has been observed to fabricate preeminent result and therefore considered as superlative model. It can be considered as imperative tool for detection and diagnosis of the disease in an efficient and fastest mode than other traditional approaches and can be obliging to doctors.

Credit card fraud is a form of financial frauds growing every year and causing losses to financial multinationals as well as government sector. Traditional methods like manually detecting credit card frauds are feasible only for small datasets, but with the rise of big data, these methods are of no worth, hence has been proved as an unrealistic and time-consuming solution. Therefore, the finance industry is looking for help from data mining and machine learning methodologies in order to handle problems. But constructing rule for fraud detection algorithms is difficult because of imbalance nature of credit card dataset. Several challenges while mining credit card dataset with the experimental solution are presented through this paper. Undersampling and SMOTE oversampling techniques are applied to balance the real-time credit card transaction dataset, and then several supervised machine learning algorithms are compared to classify credit card frauds precisely. Credit card fraud detection model using logistic regression is pragmatic as the best classifier when compare to decision tree, support vector machine, and K-nearest neighbor. Confusion matrix and several other matrices are used during experiments to evaluate the performances of the credit card fraud detection model.

Watering system in agricultural lands plays a major activity in water and soil conservations. The future expectation of soil moisture content (MC) utilizing online soil and ecological parameters may give an effective stage to agriculture land watering system prerequisites. This article focuses on two optimization strategies, for example, Scaled Conjugate Gradient and BFGS Quasi-Newton based neural network algorithms utilized to predict hourly requirement of soil MC. The prediction performance of these two optimization techniques are also studied by calculating MSE (Mean Square Error), RMSE (Root Mean Square Error), and R-squared error. The calculations are tried for the forecast of soil MC in every one hour advance by considering eleven distinctive soil and environmental parameters. The best technique is used for the final prediction, and the predicted soil MC is utilized for generating appropriate notifications using fuzzy logic based weather model. The proposed system is hybrid system utilized to solve a single problem that is the generation of best irrigation suggestions for the farmers.

Objectives: More than 30 different rare mutations, including copy number variants (CNVs), in the amyloid precursor protein gene (APP) cause early-onset familial Alzheimer disease (EOFAD), whereas the contribution of common APP variants to disease risk remains controversial. In this study we systematically assessed the role of both rare and common APP DNA variants in Alzheimer disease (AD) families. Methods: Families with EOFAD genetically linked to the APP region were screened for missense mutations and locus duplications of APP. Further, using genome-wide DNA microarray data, we examined the APP locus for CNVs in a total of 797 additional early- and late-onset AD pedigrees. Finally, 423 single nucleotide polymorphisms (SNPs) in the APP locus, including 2 promoter polymorphisms previously associated with AD risk, were tested in up to 4,200 individuals from multiplex AD families. Results: Analyses of 8 21q21-linked families revealed one family carrying a nonsynonymous mutation in exon 17 (Val717Leu) and another family with a partially penetrant 3.5-Mb locus duplication encompassing APP. CNV analysis in the APP locus revealed an additional family carrying a fully penetrant 380-kb duplication, merely spanning APP. Last, contrary to previous reports, association analyses of more than 400 different SNPs in or near APP failed to show significant effects on AD risk. Conclusion: Our study shows that APP mutations and locus duplications are a very rare cause of EOFAD and that the contribution of common APP variants to AD susceptibility is insignificant. Furthermore, duplications of APP may not be fully penetrant, possibly indicating the existence of hitherto unknown protective genetic factors. Neurology ® 2012;78:1250–1257

Ethanol is the major consumable biofuel which is highly inflammable. So the detection of ethanol at its different concentration is certainly required. In this paper a cost effective thick-film gas sensor based on ethanol detection has been described. The sensor exhibits excellent ethanol sensing characteristics at the temperatures between 175 °C to 300 °C and the characteristics of the sensor for different concentration of the ethanol gas has been successfully studied by performing a nonlinear form of principal component analysis (PCA) to cluster the different concentration of ethanol. The present method is to classify the 230 samples of each concentration levels of gas using kernel principal component analysis (KPCA). Ethanol gas is a volatile organic compound (VOC) which is little difficult to distinguish the different concentration level in their nominal method.In this regard, classifiers having the machine learning ability can be of great benefit by automatically including the newly presented patterns in the training dataset without affecting class integrity of the previously trained system. In the presented paper, the kernel principal component analysis (KPCA) is used in the clustering algorithm for ethanol concentration discrimination with the help of thick film gas sensor.

Collision Avoidance System solves many problems caused by traffic congestion worldwide and a synergy of new information technologies for simulation, real-time control and communications networks. The above system is characterized as an intelligent vehicle system. Traffic congestion has been increasing world-wide as a result of increased motorization, urbanization, population growth and changes in population density. Congestion reduces utilization of the transportation infrastructure and increases travel time, air pollution, fuel consumption and most importantly traffic accidents. The main objective of this work is to develop a machine vision system for lane departure detection and warning to measure the lane related parameters such as heading angle, lateral deviation, yaw rate and sideslip angle from the road scene image using standard image processing technique that can be used for automation of steering a motor vehicle. The exact position of the steering wheel can be monitored using a steering wheel sensor. This core part of this work is based on Hough transformation based edge detection technique for the detection of lane departure parameters. The prototype designed for this work has been tested in a running vehicle for the monitoring of real-time lane related parameters.

is a special case of CT scan who adopts X-ray method & uses the high resolution film so that it can detect well the tumors in the breast. Low radiation is the strength of this method. Mammography is especially used only in the breast tumor detection Mammogram breast cancer images have the ability to assist physicians in detecting disease caused by cells normal growth. Developing algorithms and software to analyse these images may also assist physicians in there daily work. This study that shows the outcome of applying image processing threshold, edge based and watershed segmentation on mammogram breast cancer image and also presents a case study between them based on time consuming and simplicity. The real-time implementation of this paper can be implemented using data acquisition hardware and software interface with the mammography systems. KEYWORDSprocessing; CT scan; Low Radiation; Watershed Image Segmentation; Data acquisition; Mammography; X-ray

Irrigation in agricultural lands plays a crucial role in water and soil conservation. Real-time prediction of soil moisture content using wireless sensor network (WSN) based soil and environmental parameters sensing may provide an efficient platform to meet the irrigation requirement of agriculture land. In this research article, we have proposed Resilient Back-propagation optimization technique to train neural network pattern classification algorithm for the prediction of soil moisture content. Finally, the predicted soil moisture content is used by fuzzy weather model for generating adequate suggestions regarding irrigation requirement. The fuzzy model is developed by considering different weather parameters like sun light intensity, wind speed, environment humidity and environment temperature. Different weather conditions like cloudy situation, low pressure, cyclone and storm conditions are simulated in the fuzzy model. The soil moisture content prediction algorithm is tested with soil moisture content in each 1 h advance by considering eleven different soil and environmental parameters collected during a field test. The prediction errors are analysed using MSE (Mean Square Error), RMSE (Root Mean Square Error), and R-squared error.

Differential dilatometry has been employed to study the austenite (γ)-ferrite (α) massive phase transformation of Fe-3.1 at.% Ni upon cooling under the influence of an applied constant uniaxial tensile stress. The applied stress level was chosen to be below the yield stress of the alloy. It was found that an extra length change in the specimens occurs during the transformation as a result of transformation-induced plasticity. The local plastic deformation induced by transformation plasticity results in an anisotropic volume change of the specimen in the longitudinal direction. A phase transformation model, involving site saturation, interface-controlled continuous growth and an appropriate impingement correction, has been employed to extract the velocity of the γ/α interface. The observed scatter in the interface velocity decreases with increasing applied stress due to relaxation of misfit deformation energy by transformation-induced inhomogeneous plastic deformation. The interface velocity remains almost constant during the whole transformation.

Dilatometry is a thermo-analytical technique used to measure the expansion or shrinkage of materials during heating or cooling, whether or not in association with a phase transformation. A temperature correction procedure has been developed to correct for the temperature inhomogeneity that exists in an inductively heated specimen during the heating/cooling process and to represent the dilation as a function of a homogeneous temperature. As an example, taking an Fe–5.91 at.% Ni specimen and subjecting it to two different cooling rates, the temperature correction has been performed for the temperature range where the austenite to ferrite phase transformation takes place as well as for the pure austenite and ferrite phases close to the temperature range of the transformation.

Dilatometry is a technique for precise measurement of thermal dilatation of materials during heating or cooling. A procedure has been presented for calibration of a differential dilatometer operating with electromagnetic heating for metallic specimens both upon heating and cooling as well as under uniaxial compressive and tensile loading. The dilation signal has been calibrated for both heating and cooling and for uniaxial loading (compressive and tensile) using platinum or iron reference specimens, for which recommended dilational data are available. The ferro- to paramagnetic transition (characterised by the Curie temperature) of pure iron or iron-based alloys has been adopted to calibrate the temperature in the dilatometric measurement under different loading modes during heating and cooling. On this basis calibrated data for the thermal expansion coefficients of Fe and Fe–Ni alloys have been obtained.

Irrigation in agricultural lands plays a vivacious role in water and soil conservation. Future prediction of soil moisture content using real-time soil and environmental parameters may provide an efficient platform for agriculture land irrigation requirements. In this paper we have proposed one optimization technique like Gradient Descent with Momentum is used to train neural network pattern classification algorithm. The algorithm is tested for the prediction of soil moisture content in each one hour advance by considering eleven different soil and environmental parameters collected during a field test. The prediction errors are analysed using MSE (Mean Square Error), RMSE (Root Mean Square Error), and R-squared error. The performance of the proposed soil moisture content prediction is well documented in this article.