Heart rate (HR) and Heart rate variability (HRV) have received a great deal of attention that promises to change the dimension of awareness of health and fitness while swimming. HRV is very useful to understand physiological and psychological status of an individual. The variation in HR, provides a reliable information about the role of Autonomic Nervous System (ANS). HRV is very convenient to understand the overall physiological status of an individual. Due to individuality of the HRV, regular monitoring HRV is useful to understand training adaptation, load, recovery, overtraining. The study provides a brief concept on HR and HRV in swimming individual. Although RR intervals are highly individual centric but due to same practice pattern or same type of physical activity, the swimmer group has very small quartile range. A significance difference in RR intervals between control group and swimmer group may come from two different effects of the nervous system. Either it indicates a significant increase in parasympathetic tone due to normal training adaptation or a sign of overtraining that has caused increase in parasympathetic tone. High HRV denotes good indication of positive adaptation, good cardiovascular efficiency. Low HRV score indicates deterioration in VO2max.
Load forecasting plays a vital role in generation and distribution sectors in the power system. This helps to obtain optimum load scheduling which helps to predict future consumption to increase reliability in the system. The demand side management helps to optimize the consumption of energy based upon the priority of the consumers. The load forecasting helps to predict the usage of power through the priority scheduling of the loads which helps to minimize and maximize the operating cost. The optimization technique plays a versatile role in the load scheduling based on demand side management in the industrial sectors. The combination of advanced technologies with communication infrastructure makes the system more reliable and smarter. The demand side management is achieved through shifting the loads from peak hours to non-peak hours. Thus, to enhance the automatic scheduling of loads in the industrial sector is achieved by the neuro-fuzzy controller and deep learning techniques.
Wireless network and Communication engineers have a query that when, where and how mmWave will be used in volte+ network? The future generation network depends on multiple speed Radio Access Technology (RAT), but it makes use of different access in downlink with multipoint transmission in the presence of multilink distributed wireless channel information. Context awareness means that systems can sense and react their environment based on location which is capable of identifying nearest network locator. The location of particular system in a distributed network can be determined by Navigational Network Locator (NNL). Next, Vehicular Systems demand high data transfer links of mmWave communication. By the Convolution Neural Networks, it passes the result to the upcoming vehicular signal and multiple links shares the data to all mobile networks. The Enhanced Location Awareness Machine Learning (ELAML) combined with Mobile Edge Computing (MEC) technologies to enable multiple links ultra-high speed data downloads. The real-world implementations of Location based machine learning network architecture using traffic patterns are identified. The main aim of this research paper is about implementing multiple ultra-high data rate with volte+ mmWave vehicular network.
A power, delay efficient error acquiescent adder is proposed. In recent VLSI expertise, the manifestation of all categories of faults has developed foreseeable. By embracing an emergent perception in VLSI strategy, fault-tolerant adder (FTA) is suggested. The FTA is talented to comfort the harsh constraint on exactitude, and at the identical period accomplish marvelous enhancements in together the power ingestion and speediness enactment. For any transportable uses anywhere the power ingestion and speed are the utmost significant limit, one must diminish the power feeding and upsurge the speed as ample as probable. In this technique certain amendments are suggested to predictable adders to significantly decrease its power feeding. The amendments to the conservative building comprise the elimination of carry generation from LSB to MSB. With this the adder works at high speed with low power consumption.
Recent developments in internet of things technology created a way for various innovative applications are developed in embedded field. In spite of reducing the manual process in shopping malls, smart shopping system is employed. The smart shopping systems are keep on increasing in various shopping malls, supermarkets on considering the elderly people to have the hassle free purchasing of product based on the selections. The presented approach considers Smart Service for elderly people in shopping mall to have a smart purchase using customised products selected by them. The products are uniquely coded with RFID tag and identified by the RF ID Reader. Embedded Arduino UNO is utilized for the purpose of providing reprogrammable instructions. The interfacing of smart Supermarket system connected with automated billing in which the cloud server can receive the data and make the automated building according to the selection of the consumers system.
Computer vision is nothing but a concept in which a computer or any other machine analyzes a scene like a human eye and performs some tasks accordingly. In the past few years, the research in the area of computer vision has increased on a very large scale due to its numerous applications in video analysis, scene detection, self - driving systems etc. The process of object detection is getting faster and better with development in the fields of neural networks and deep learning domains. In this paper, a comprehensive study is carried out on deep learning and its major component named convolution neural networks (CNN) that are largely used for object detection. At last paper shed lights on the various methods for object detection such as R-CNN, Fast R-CNN and Faster R-CNN and their applications in real world. The object detection applications has leads the world to digital revolution..
Approximately 962,000,000 persons worldwide are 60 or older. Despite the widespread adoption of techniques for human activity detection, there has been a dearth of study into the specific challenge of identifying the tasks performed by the elderly. Given the proliferation of wearable and mobile devices, the Internet of Healthcare Things is assuming a larger role in Human Activity Recognition (HAR). This article focuses on assisting the elderly by tracking their movements in both indoor and outdoor settings. The dataset includes human actions like sitting, walking, ascending and descending stairs, standing, and lying down. Here, how deep learning might improve HAR in Internet of Home Things settings has been examined. For better HAR results, a semi-supervised deep learning framework has been developed that makes effective use of the imperfectly labelled sensor data in order to fine-tune the classifier learning model. An intelligent auto-labelling system is built on top of Deep Q-Network to enhance learning performance in Internet of Things (IoT) environment and address the issue of insufficient labelled samples. Finally, real-world data is used in trial and evaluation to prove the method’s utility and efficacy.
Managing energy costs is crucial because rapid urbanization increases energy demand, which affects existing energy resources. Load disaggregation is a promising non-intrusive tool for better demand management and power grid development. In this regard, feature selection and characterization are important. The paper represents a comparati ve analysis of the Indian Energy Dataset with Low-frequency (IEDL) using four different supervised machine learning models in a classification context. Five different appliances (ten years older) opted for the energy disaggregation purpose. The comparison between Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB), and k-Nearest Neighbor (k-NN) classifiers was observed and assessed for performance on accuracy, precision, recall, and f-score. Furthermore, grid search is performed on RF and k-NN to prevent loss of accuracy.
Battery life of EV (electric vehicles) depends on various factors. These factors include temperature of the battery, duration of use or the type and condition of the road traversed by the vehicle. This may cause the battery to discharge faster than it used to. Understanding what may cause the battery life to shorten can help us alleviate the given problem and can preserve the battery for longer time. This research focuses on the effects road conditions have on battery life to be able to recommend the favourable conditions to extend it. It proposes to find the routes taken by the vehicles and classifying them based on their battery health upon reaching the destination. In this paper, an attempt has been made to predict the category of the routes by employing Transfer learning via a pre-trained model VGG-16. Observations indicate that paths which have more turns and curves are generally worse for battery life as compared to straight and narrow paths. Another model which is an artificial neural network has been developed to predict the based on the average vehicle speed and the distance covered by the vehicle. The VGG-16 model predicts the data with which it is validated with an accuracy of 84.29% and the testing data with an accuracy of 83.56%. The artificial neural network model predicts the category of the data with an accuracy of 88.02%.
Air-drawing for authentication or gesture recognition is vastly studied such that new methods for the character drawn can be identified with better accuracy and be independent of any hardware components such as gloves to detect the fingertip movement or any wearable sensor or using any external pen. This article surveys how air-writing is done. Some of them include using fingertips as a pen and having the trained CNN model against it using the techniques DNST and Bi-LSTM for the regression and hand gesture identification and classification. This system had an overall accuracy of 88 percentage. Another system solves the air-writing issue by using deep learning architecture, by executing it on 3D space where the next evolution is numerical digits structured into multiple dimensions time-series extracted from a sensor called LMC. In another system, wi-write recognizes hand writing mainly to overcome blurred vision and neurological diseases in people, this will use COTS WiFi but is a device-free handwriting recognition system. In many other systems deep learning models are used and those parameters can be used to achieve higher recognition rate for example 98 percentage above.
The increase in population, climate change, urbanisation and growing usage of technological gadgets all contribute to rising electricity demand. A device which enables effective use of electrical energy have been made possible by the Internet of Things. However, majority of developed techniques addressing this issue only monitor energy usage of the device without concentrating on their switching condition. Therefore, the development of a smart metre with load control becomes more essential on home automation. Hence, this work formulated a novel smart meter which monitors RMS current and voltage, active and reactive power and apparent energy usage data along with load control. Thus, it can be utilized in smart grids.
At present, the signal detection principle of the ultrasonic flowmeter can be roughly divided into propagation velocity difference method, the beam shift method, the Doppler method, correlation method, spatial filtering method and noise method, and hence, the proper selection of the methods will be essential for the success of the modelling. This paper then studies the optimal feedback loop algorithm for the automatic control of ultrasonic gas flowmeter. Firstly, the ultrasonic gas flow measurement principle is introduced, considering that the time difference measurement principle will use the movement time difference of ultrasonic waves in the case of forward flow and reverse flow to measure gas flow. Secondly, realization of the intelligent ultrasonic gas flow measuring system is studied. Here, the Butterworth filters are considered to maintain the useful ultrasonic signal in a proper frequency range by removing high and low frequency noise. Finally, the optimal feedback loop is considered to finalize the model. The proposed experiment will provide the high-speed comparison of signal waveform simulation to show the visualized performance and then, the error comparison analysis in conducted to test the performance under different flow rate.
cardiovascular diseases have been the primary reason for the increasing fatal rate in the recent years. Early detection of heart diseases, as well as constant clinical supervision, can reduce the death rate. To recognize coronary disease using machine learning approaches, a theoretical structure of cloud-based coronary disease evidence and a gauge system was developed. For the specific recognition of the coronary disease, and numerous backslides for the assumption of cardiovascular disease, a useful AI approach has been developed.The proposed method is used to predict respiratory failure by considering various autonomous factors. A hybrid model that incorporates multiple regressions with RNN to predict coronary diseases and IoT devices that use the cloud platform to remind the individual of cardiovascular failure. The final result demonstrates that the proposed learning model essentially predicts the pulse by using accumulated heartbeat data and alternative web of things to locate the coronary disease.
The purpose of this study is to predict the flood at the dams and alerting the authorities to make them the people who are living their lives in remote areas i.e., near to the dam to the safer place, so that to reduce the mortality rate due to unprecedented flood. This study predicts the flood by using sensor-based networking system. Here, two ultrasonic sensors are connected to determine the level of water; waterflow sensor is used to know the speed of water; rainfall sensor is used to determine the rainfall. After measuring all the factors, the data is processed to the NodeMCU, which will act as a transmitter and it will transfer the data through the wireless communication to the another NodeMCU, which was situated at the office present at the dam and it will act as a receiver. After analyzing all the values, if the values exceed the limit, an alert will be sent to the authorities and then automatically the dam gates will get open.
The most plentiful form of renewable energy is solar energy. Windstorms and constant soling significantly impair effectiveness. Consequently, it is crucial to clean the panel on a regular basis and properly. The majority of the components require hand cleaning. This kind of cleaning is inconsistent and might harm the workers' health. Solar panel cleaning systems that are permanently installed and fully automated with or without water can address this issue. It contains a brush to remove the dust and water/ chemical solution in addition to have gentle cleaning on the solar panels. In solar power plants, business buildings, and homes, the proposed technique may be installed directly onto the panels. This technique allows a multiple row cleaning. By eliminating any type of dust, this approach aims to boost the efficiency of solar panels. The proposed work comprises a cloud server powered by the internet of things (IoT) to enable online status tracking from anywhere in the world.
To feed the world’s population of 7.9 billion people, preventing crop failure through early disease detection is essential. Various bacterial, viral, or fungal diseases affect the rice leaf and these diseases drastically lower rice yield. Therefore, identifying rice leaf diseases is essential to meeting the demand for rice from an extensive worldwide population. However, the ability to identify rice leaf disease is constrained by the image backgrounds and the circumstances under which the images were captured. When tested on independent rice leaf diseased data, the performance of deep learning models for automated detection of rice leaf diseases suffers substantially. This stusy examines the results of well-known and widely used transfer learning models to detect the rice leaf disease. This can be done in two ways: frozen layers and fine-tuning. It was observed that the results of the freeze layers, the DenseNet169, achieved a good testing accuracy of 99.66%, and when the results of the fine-tuned transfer learning models were examined, Xception performed well and achieved 99.99% of testing accuracy.
Internet of Things (IoT) devices and user input will accelerate healthcare delivery and reduce errors to an unparalleled degree. The spread of healthcare in remote locations is driving the development of Wi-Fi equipment. Future EHR prototypes give clinicians a holistic view of a patient’s health. This study investigates medical care in rural India and suggests the Rural Smart Healthcare System (RSHS) for the elderly. Internet of Things lets patients' vitals talk to one other and to clinic staff. It introduces cost-effective, high-quality patient care methods to the healthcare business. Cloud computing and big data have ushered in a new age in healthcare technology. Scale, rapidity, and dependability are key cloud computing qualities. Cloud computing and the Internet of Things are being used to produce smarter linked devices and goods. Clinical equipment with record-keeping software is also widespread. Continuous engineering helps healthcare firms build a strong future. They're connected to Internet-enabled devices worldwide. All healthcare facilities, clinics, and health clubs strive for the best patient outcomes. The Internet of Things (IoT) in healthcare drives innovation, cost savings, enhanced precision, and service expansion. Healthcare stakeholders have recently moved their focus from establishing automated scientific methods and digitising medical records to big data analysis. Cloud-based data could help healthcare organisations provide better care to providers. IoT healthcare devices collect medical signals and/or photos. Accurate diagnosis requires analysing IoT cloud computing. This gives precise statistics for health management. Smart systems provide extraordinary real-time data collection. Cloud computing uses open-source technologies with varied degrees of safety.
In modern communication systems there are heterogeneous service request from the applications like mobile devices, virtual reality, automatic driving cars, IoT devices. These devices have different QoS requirements in which network slicing enabler plays a vital role in 5G. Network Slicing unfolds a new paradigm for the providers as well as for the users. In this context the resource management has gained importance in the field of networking. Since a huge data is been generated by these devices, it is very difficult to deliver high performance with resource utilization. In such situation these traditional monitoring techniques will not be able to handle such a huge data. Towards this, the researchers have started applying with Deep learning techniques with the network monitoring system. This paper focuses on the work done towards one of the key components of network analysis (i.e.) traffic prediction. This study has reviewed the articles, which have proposed the deep learning techniques for traffic prediction towards resource management in network slicing.*CRITICAL: Do Not Use Symbols, Special Characters, Footnotes, or Math in Paper Title or Abstract. (Abstract)
This paper describes a machine learning model for predicting earthquakes on the basis of past earthquake data. In particular, this study uses the Long Short Term Memory (LSTM) model, a neural network model designed to operate on time-series data with long-term dependencies. Here, the instrumental earthquake data is considered from three selected locations in Indonesia. First, the dataset is pre-processed by segmenting it into time intervals and space grids. The multi-dimensional time-series data is then fed into the network to output the probability of an earthquake in the next interval. This method was originally introduced by Wang et al. [1] and achieved an accuracy close to 85% on a dataset from Mainland China (1966–2016). To the best of our knowledge, no subsequent works have attempted to reproduce their results on different datasets, or introduce enhancements. This research work has implemented the same model on three different datasets. Further, the softmax activation function is replaced with the sigmoid activation function. This ensures that the probability values of earthquakes occurring in the segmented grids are independent of each other and are not rendered mutually exhaustive or exclusive events. Finally, a failure mode of this model is mentioned by showing that it performs poorly to predict large earthquakes.
