An efficient cardio vascular disease prediction using multi-scale weighted feature fusion-based convolutional neural network with residual gated recurrent unit.

The cardiovascular disease (CVD) is the dangerous disease in the world. Most of the people around the world are affected by this dangerous CVD. In under-developed countries, the prediction of CVD remains the toughest job and it takes more time and cost. Diagnosing this illness is an intricate task that has to be performed precisely to save the life span of the human. In this research, an advanced deep model-based CVD prediction and risk analysis framework is proposed to minimize the death rate of humans all around the world. The data required for the prediction of CVD is collected from online data sources. Then, the input data is preprocessed using data cleaning, data scaling, and Nan and null value removal techniques. From the preprocessed data, three sets of features are extracted. The three sets of features include deep features, Principal Component Analysis (PCA), and Support Vector Machine (SVM)-based features. A Multi-scale Weighted Feature Fusion-based Deep Structure Network (MWFF-DSN) is developed to predict CVD. This structure is composed of a Multi-scale weighted Feature fusion-based Convolutional Neural Network (CNN) with a Residual Gated Recurrent Unit (GRU). The retrieved features are given as input to MWFF-DSN, and for optimizing weights, a Modernized Plum Tree Algorithm (MPTA) is developed. From the overall analysis, the developed model has attained an accuracy of 96% and it achieves a specificity of 95.95%. The developed model takes minimum time for the CVD and it gives highly accurate detection results.

IoT-Enabled Classification of Echocardiogram Images for Cardiovascular Disease Risk Prediction with Pre-Trained Recurrent Convolutional Neural Networks.

Cardiovascular diseases currently present a key health concern, contributing to an increase in death rates worldwide. In this phase of increasing mortality rates, healthcare represents a major field of research, and the knowledge acquired from this analysis of health information will assist in the early identification of disease. The retrieval of medical information is becoming increasingly important to make an early diagnosis and provide timely treatment. Medical image segmentation and classification is an emerging field of research in medical image processing. In this research, the data collected from an Internet of Things (IoT)-based device, the health records of patients, and echocardiogram images are considered. The images are pre-processed and segmented, and then further processed using deep learning techniques for classification as well as forecasting the risk of heart disease. Segmentation is attained via fuzzy C-means clustering (FCM) and classification using a pretrained recurrent neural network (PRCNN). Based on the findings, the proposed approach achieves 99.5% accuracy, which is higher than the current state-of-the-art techniques.

Active Volume Control in Smart Phones Based on User Activity and Ambient Noise.

To communicate efficiently with a prospective user, auditory interfaces are employed in mobile communication devices. Diverse sounds in different volumes are used to alert the user in various devices such as mobile phones, modern laptops and domestic appliances. These alert noises behave erroneously in dynamic noise environments, leading to major annoyances to the user. In noisy environments, as sounds can be played quietly, this leads to the improper masked rendering of the necessary information. To overcome these issues, a multi-model sensing technique is developed as a smartphone application to achieve automatic volume control in a smart phone. Based on the ambient environment, the volume is automatically controlled such that it is maintained at an appropriate level for the user. By identifying the average noise level of the ambient environment from dynamic microphone and together with the activity recognition data obtained from the inertial sensors, the automatic volume control is achieved. Experiments are conducted with five different mobile devices at various noise-level environments and different user activity states. Results demonstrate the effectiveness of the proposed application for active volume control in dynamic environments.

Wireless sensing system for the welfare of sewer labourers.

There is a growing demand for the environmental pollution monitoring and control systems. In the view of ever increasing sources of toxic chemicals, these systems should have the facilities to detect and calibrate the source quickly. Toxic gases are the ones that cause health impact but humans are being exposed to it in various situations. These gases have to be monitored such that increase in the normal level of them could be known and proper precaution measures can be undertaken. So, an embedded system is designed using a microcontroller with internet of things, for the purpose of detecting and monitoring the hazardous gas leakage, which aids in the evasion of endangering of human lives. The hazardous gases can be sensed and displayed each and every second, in proximity to one more sensor for tracking heart beats which help to monitor the condition of the sewer labourers. If both the gases along with a pulse detector exceeds the normal level then an alarm is generated immediately and also an alert warning message can be sent to the authorised administrator and as well to the nearest health center to make the sewer labourers feel comfortable with necessary first aid and possibilities with the treatment in the case of emergency. Once the message is received by the health center, they enforce their team with necessary first aid to the current location to save the sewer labourer. Once this system is established for a particular user this will completely become fully automated and does not need any other additional people for monitoring and alerting purpose. It has an advantage over the manual method in offering quick response time and accurate detection of an emergency.