A Smart Sensing Technologies-Based Intelligent Healthcare System for Diabetes Patients.

An Artificial Intelligence (AI)-enabled human-centered smart healthcare monitoring system can be useful in life saving, specifically for diabetes patients. Diabetes and heart patients need real-time and remote monitoring and recommendation-based medical assistance. Such human-centered smart healthcare systems can not only provide continuous medical assistance to diabetes patients but can also reduce overall medical expenses. In the last decade, machine learning has been successfully implemented to design more accurate and precise medical applications. In this paper, a smart sensing technologies-based architecture is proposed that uses AI and the Internet of Things (IoT) for continuous monitoring and health assistance for diabetes patients. The designed system senses various health parameters, such as blood pressure, blood oxygen, blood glucose (non-invasively), body temperature, and pulse rate, using a wrist band. We also designed a non-invasive blood sugar sensor using a near-infrared (NIR) sensor. The proposed system can predict the patient's health condition, which is evaluated by a set of machine learning algorithms with the support of a fuzzy logic decision-making system. The designed system was validated on a large data set of 50 diabetes patients. The results of the simulation manifest that the random forest classifier gives the highest accuracy in comparison to other machine learning algorithms. The system predicts the patient's condition accurately and sends it to the doctor's portal.

Railway Track Inspection Using Deep Learning Based on Audio to Spectrogram Conversion: An on-the-Fly Approach.

The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks' faults, which is cumbersome, laborious, and error-prone. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Contrary to traditional acoustic-based systems where the spectrogram dataset is generated before the model training, the proposed approach uses on-the-fly feature extraction by generating spectrograms as a deep learning model's layer. Different lengths of audio samples are used to analyze their performance with each model. Each audio sample of 17 s is split into 3 variations of 1.7, 3.4, and 8.5 s, and all 3 deep learning models are trained and tested against each split time. Various combinations of audio data augmentation are analyzed extensively to investigate models' performance. The results suggest that the LSTM with 8.5 split time gives the best results with the accuracy of 99.7%, the precision of 99.5%, recall of 99.5%, and F1 score of 99.5%.

Integration of 5G and Block-Chain Technologies in Smart Telemedicine Using IoT.

The Internet of Health Thing (IoHT) has various applications in healthcare. Modern IoHTintegrates health-related things like sensors and remotely observed medical devices for the assessment and managment of a patient's record to provide smarter and efficient health diagnostics to the patient. In this paper, we proposed an IoT with a cloud-based clinical decision support system for prediction and observation of disease with its severity level with the integration of 5G services and block-chain technologies. A block-chain is a system for storing and sharing information that is secure because of its transparency. Block-chain has many applications in healthcare and can improve mobile health applications, monitoring devices, sharing and storing of the electronic media records, clinical trial data, and insurance information storage. The proposed framework will collect the data of patients through medical devices that will be attached to the patient, and these data will be stored in a cloud server with relevant medical records. Deployment of Block-chain and 5G technology allows for sending patient data securely at a fast transmission rate with efficient response time. Furthermore, a Neural Network (NN) classifier is used for the prediction of diseases and their severity level. The proposed model is validated by employing different classifiers. The performance of different classifiers is measured by comparing the values to select the classifier that is the best for the dataset. The NN classifier attains an accuracy of 98.98. Furthermore, the NN is trained for the dataset so that it can predict the result of the dataset class that is not labeled. The trained Neural Network predicts and intelligently shows the results with more accuracy than other classifiers.

A Neural Network-Inspired Approach for Improved and True Movie Recommendations.

In the last decade, sentiment analysis, opinion mining, and subjectivity of microblogs in social media have attracted a great deal of attention of researchers. Movie recommendation systems are the tools, which provide valuable services to the users. The data available online are growing gradually because the online activities of users or viewers are increasing day by day. Because of this, big data, analytics, and computational issues have raised. Therefore, we have to improve recommendations services upon the traditional one to make the recommendation system significant and efficient. This article presents the solution for these issues by producing the significant and efficient recommendation services using multivariates (ratings, votes, Twitter likes, and reviews) of movies from multiple external resources which are fetched by the web bot and managed by the Apache Hadoop framework in a distributed manner. Reviews are analyzed by a deep semantic analyzer based on the recurrent neural network (RNN/LSTM attention) with user movie attention (UMA) to produce the emotion. The proposed recommender evaluates multivariates and produces a more significant movie recommendation list according to the taste of the user on a mobile app in an efficient way.

An Intelligent Fire Warning Application Using IoT and an Adaptive Neuro-Fuzzy Inference System.

In the recent past, a few fire warning and alarm systems have been presented based on a combination of a smoke sensor and an alarm device to design a life-safety system. However, such fire alarm systems are sometimes error-prone and can react to non-actual indicators of fire presence classified as false warnings. There is a need for high-quality and intelligent fire alarm systems that use multiple sensor values (such as a signal from a flame detector, humidity, heat, and smoke sensors, etc.) to detect true incidents of fire. An Adaptive neuro-fuzzy Inference System (ANFIS) is used in this paper to calculate the maximum likelihood of the true presence of fire and generate fire alert. The novel idea proposed in this paper is to use ANFIS for the identification of a true fire incident by using change rate of smoke, the change rate of temperature, and humidity in the presence of fire. The model consists of sensors to collect vital data from sensor nodes where Fuzzy logic converts the raw data in a linguistic variable which is trained in ANFIS to get the probability of fire occurrence. The proposed idea also generates alerts with a message sent directly to the user's smartphone. Our system uses small size, cost-effective sensors and ensures that this solution is reproducible. MATLAB-based simulation is used for the experiments and the results show a satisfactory output.