Diabetes mellitus is considered one of the main causes of death worldwide. If diabetes fails to be treated and diagnosed earlier, it can cause several other health problems, such as kidney disease, nerve disease, vision problems, and brain issues. Early detection of diabetes reduces healthcare costs and minimizes the chance of serious complications. In this work, we propose an e-diagnostic model for diabetes classification via a machine learning algorithm that can be executed on the Internet of Medical Things (IoMT). The study uses and analyses two benchmarking datasets, the PIMA Indian Diabetes Dataset (PIDD) and the Behavioral Risk Factor Surveillance System (BRFSS) diabetes dataset, to classify diabetes. The proposed model consists of the random oversampling method to balance the range of classes, the interquartile range technique-based outlier detection to eliminate outlier data, and the Boruta algorithm for selecting the optimal features from the datasets. The proposed approach considers ML algorithms such as random forest, gradient boosting models, light gradient boosting classifiers, and decision trees, as they are widely used classification algorithms for diabetes prediction. We evaluated all four ML algorithms via performance indicators such as accuracy, F1 score, recall, precision, and AUC-ROC. Comparative analysis of this model suggests that the random forest algorithm outperforms all the remaining classifiers, with the greatest accuracy of 92% on the BRFSS diabetes dataset and 94% accuracy on the PIDD dataset, which is greater than the 3% accuracy reported in existing research. This research is helpful for assisting diabetologists in developing accurate treatment regimens for patients who are diabetic.

A photoplethysmogram (PPG) is a plethysmogram which is optically obtained, a volumetric measurement of an organ. Two PPG signals are used here to estimate the blood pressure and heart rate. Blood pressure is the pressure exerted by circulating blood upon the walls of blood vessels. Nowadays the standard blood pressure is measured by using cuff based digital devices. In cuff based method, there will be an uncomfortable to the patient and cannot measure the blood pressure in a continuous manner. Blood pressure is in terms of the systolic (maximum) pressure over diastolic (minimum) pressure and is measured in millimeters of mercury. Pulse Transit Time (PTT) is playing the main role here. PTT is the time between peaks of the two PPG signal. Heart rate can be measured by counting the number of peaks for sixty seconds. Blood pressure will be vary based on situation, activity, and disease states. Heart rate is the speed of the heartbeat measured by the number of contractions of the beat per minute (bpm). Threshold method is used to find the total number of peaks. The signals are need to be filtered to remove any noises. A low pass filter is used here to remove the noises from the PPG signals. Then the Pulse Transit Time (PTT) is determined by detecting the peak location, peak time and peak time difference using LabVIEW. Using linear regression analysis in MATLAB the blood pressure is obtained. GSM is used here to send the averaged PTT values.

Objective: Gastrointestinal problems have claimed the lives of about two million individuals worldwide. Video endoscopy is one of the most important tools for detecting gastrointestinal diseases (GD). However, it has the disadvantage of producing a huge quantity of images that should be analysed by medical professionals, which demands more time. This makes manual diagnosis challenging, encouraging research on computer-assisted methods for accurately identifying all of the produced images in a short amount of time. The goal of this research is to develop an artificial intelligence technique to classify different gastrointestinal problems. Materials and Methods: In developing a framework for classifying gastrointestinal diseases, the proposed methodology is unique. VGG-19 and ResNet-50, two deep learning networks, were used to evaluate their ability to recognise a dataset of lower GD. To validate the proposed models, a Kvasir dataset of 3500 images was employed, comprising 500 images from each of the seven classes. Results: ResNet-50 had the greatest validation accuracy of 96.81%, recall of 95.28%, precision of 95%, and 94.85% of F1 score, whereas VGG-19 had the highest validation accuracy of 94.21%, recall of 94%, precision of 94.28%, and 94% of F1 score. Conclusion: The Convolutional Neural Network (CNN) was used to extract shape, colour, and texture features. Softmax assists in the classification of seven types of GD by passing these features into fully connected layers. Two models performed equally well and yielded promising results.

Water consumed is stored in several water bodies in and around us, out of which dams accommodate a major portion of water. The quantity and quality monitoring of water in dams is troublesome due to their large surface area and high depths. Although groundwater resources are the primary water source in India, dams plays a vital role in water distribution and storage network. The Central Water Commission in India has identified more than 5,000 dams of which a major portion is persistently consumed by the rural and urban populations for drinking and irrigation. The water quality of these reservoirs is of serious concern as it would not only affect the socio-economic status of the nation but the aquatic systems as well. Water quality control and management are vital for a delivering clean water supply to the general society. Because of their size, collecting, assessing, and managing a vast volume of water quality data are critical. Water quality data are primarily obtained through manual field sampling; however, real-time sensor monitoring is increasingly being used for more efficient data collection. The literature depicts that the methods involving remote sensing and image processing of water quality analysis consume time, and require sample collection at various depths, analysis of collected samples, and manual interpretations. The objective of this study was to propose a novel cost-effective method to monitor water quality devoid of considerable human intervention. Sensor-based online monitoring aids in assessing the sample with limited technology, at various depths of water in the dam to analyze turbidity which gives the major indication of pure water. The quality analysis of the dam water is suitable if the water is assessed at the distribution end before consumption. Hence, to enhance the water management system, other quality parameters like pH, conductivity, temperature are sensed and monitored in the distribution pipeline. An unstable pH can alter the chemical and microbiological aspects of water, resulting in a variation of other water quality parameters. Temperature variations affect the amount of dissolved oxygen in the water bodies and results in unstable quality parameters. The change in dissolved solvents and the ionic concentration alters the electrical conductivity of the water and the increased concentration of salts also results in turbidity. The data from all the sensors are processed by the microcontroller, transmitted, and displayed in a mobile application comprehensible to the layman.

Water, the primary source of human existence, vastly occurs in the earth, our home. The major share of water resource comes from ocean and sea which is saline in nature. The remaining constitutes the freshwater or surface water resources on which we depend for our day to day life for domestic uses and consumption. In this context it is very necessary that better quality water ensure for human population and the environmental protection. Among various quality indices, Total Dissolved Solvents are considered as predominant that accounts for hardness and salinity, for the salt organic and inorganic constituents present. The lack of knowledge about the contents prevents common man to use such water or ill treatment of water bodies results in misuse of water resources. The work focuses on an alternative by identifying the solvents present in the water body ensuring to desalinate the particular ionic compound or metal.