A significant shift towards autonomous and connected cars is currently expected in the automotive sector. This creates new risks in terms of privacy and the complexity of electrical and electronic systems. Although safety risk management is still in its infancy, it is encouraging that the auto industry has well-known and regulated safety risk management practices. They propose a showed improved risk assessment framework and show its validity with an actual use-case to make it easier to derive safety procedures & safety solutions for automotive integrated devices. The adequacy of functional safety to existing methods and accessibility for non-safety professionals are some of the important aspects. Risk analysis is an essential element of the methodology used to assess properties and capacity risks. The level of hazard and the level of effect are estimated in the next stage of the risk management process. This step uses several existing guidelines and requirements to make amendments as necessary. To create high-level security objectives, a level of security has finally been determined. This architecture should be well adapted to the requirements of the automobile industry due to its excellent convergence with current principles and specifications.

A Safety Assessment Model for Automotive Embedded Systems Networks

Lung cancer is one of the major causes of death in the world, according to radiologists. However, a constant flow of medical images to hospitals is forcing radiologists to focus on accurate early prediction of nodules. Recently, several image‐processing techniques have cooperated for the early prediction of lung nodules. However, it's hard to detect strong nodes because of lung node diversity and environmental complexity. This study presents a hybrid machine learning technique for predicting an early prognosis of lung nodules from clinical images using a learning‐based neural network classifier. First, we introduce an improved snake swarm optimization with a bat model (ISSO‐B) for lung nodule segmentation using statistical information. Second, we demonstrate a chaotic atom search optimization (CASO) algorithm to select the optimal best features among multiple features, which minimize the dimensionality problem. Third, we develop a hybrid learning‐based deep neural network classifier (L‐DNN) for nodule prediction and classification. Finally, we evaluate our proposed technique with different public datasets LIDC‐IDRI and FAH‐GMU. Then, performance can be compared with the latest technology in terms of accuracy, sensitivity, specificity, and area under curve (AUC).

A hybrid machine learning technique for early prediction of lung nodules from medical images using a learning‐based neural network classifier

A significant shift towards autonomous and connected cars is currently expected in the automotive sector. This creates new risks in terms of privacy and the complexity of electrical and electronic systems. Although safety risk management is still in its infancy, it is encouraging that the auto industry has well-known and regulated safety risk management practices. They propose a showed improved risk assessment framework and show its validity with an actual use-case to make it easier to derive safety procedures & safety solutions for automotive integrated devices. The adequacy of functional safety to existing methods and accessibility for non-safety professionals are some of the important aspects. Risk analysis is an essential element of the methodology used to assess properties and capacity risks. The level of hazard and the level of effect are estimated in the next stage of the risk management process. This step uses several existing guidelines and requirements to make amendments as necessary. To create high-level security objectives, a level of security has finally been determined. This architecture should be well adapted to the requirements of the automobile industry due to its excellent convergence with current principles and specifications. 

With the development of sensor technologies, Internet of Things (IoT) technologies for creating behavioral and physiological management systems, including IoT-based pupil medical management systems, have evolved quickly. It is now required to monitor the health function status of the increasing number of students who live alone and are dispersed across large geographic areas. An IoT based methodology of management student heath is put forth in this study to continually monitor students’ vital signs and identifies biological and behavioral changes using advanced medical technology. In this concept, critical data are gathered by the IoT module, & data evaluation is done using neural network models are used to analyze the data to determine the likely risks to kids' physiological and behavioral modifications. According to the experimental findings, the suggested model is effective and accurate in determining the state of the pupils. The support vector machine had a maximum performance of 99.1% after the suggested model had been evaluated, which is a good outcome for our objectives. Algorithms for multilevel perceptron neural systems, random forests & decision trees were also beaten by the results. 

Student Health Detection using a Machine Learning Approach and IoT

With the development of sensor technologies, Internet of Things (IoT) technologies for creating behavioral and physiological management systems, including IoT-based pupil medical management systems, have evolved quickly. It is now required to monitor the health function status of the increasing number of students who live alone and are dispersed across large geographic areas. An IoT based methodology of management student heath is put forth in this study to continually monitor students’ vital signs and identifies biological and behavioral changes using advanced medical technology. In this concept, critical data are gathered by the IoT module, & data evaluation is done using neural network models are used to analyze the data to determine the likely risks to kids' physiological and behavioral modifications. According to the experimental findings, the suggested model is effective and accurate in determining the state of the pupils. The support vector machine had a maximum performance of 99.1% after the suggested model had been evaluated, which is a good outcome for our objectives. Algorithms for multilevel perceptron neural systems, random forests & decision trees were also beaten by the results.

Human evolution has included the development of transportation systems. People are currently driving a significant number of fuel-powered automobiles. This resulted in an increase in the number of accidents as well as pollution in the environment. To address the disadvantages of gasolinebased vehicles, this study presents an IoT-based E-vehicle monitoring system (E-VMS) for early accident detection and to make the environment cleaner and greener by using alternative energy. E-VMS employs internet of things (IoT) technology to continuously monitor the vehicle as well as to access and control it remotely. The IoT devices installed in vehicles are built using an Arduino microcontroller and sensors to detect accidents quickly. When an accident occurs, the E-VMS recognizes it quickly and determines the severity of the incident. The machine will then promptly alert the authorities. The E-VMS is also familiar with the GPS system. This will allow the E-VMS to maintain track of the cars' location in real time. This information will be used to locate the car in the event of an accident or theft. The E-VMS system's results were promising in terms of accurately identifying accidents, determining the severity of the accident, and determining the position of the vehicle.

IoT based E-vehicle monitoring system using sensors and imaging processing algorithm

Computer tomography is an extensively used method for the detection of the disease in the subjects. Basically, computer-aided tomography depending on the artificial intelligence reveals its significance in smart health care monitoring system. Owing to its security and the private issue, analyzing the computed tomography dataset has become a tedious process. This study puts forward the convolutional autoencrypted deep learning neural network to assist unsupervised learning technique. By carrying out various experiments, our proposed method produces better results comparative to other traditional methods, which efficaciously solves the issues related to the artificial image description. Hence, the convolutional autoencoder is widely used in measuring the lumps in the bronchi. With the unsupervised machine learning, the extracted features are used for various applications.

/pdf/development-of-deep-learning-technique-of-features-for-the-49azd41p.pdf

Development of Deep Learning Technique of Features for the Analysis of Clinical Images Integrated with CANN

A fifth-generation network is the need of the people in the year 2020 and it had been deployed all over the world. The drawbacks of the fifth-generation network include data rate, efficiency, reliability, processing, coverage globally, density. This has led to the progress of technology. There had been an increased need for a high-security system (RAT) has been developed. The next-generation wireless network is expected to have coverage globally, higher security along with intelligence, and improved efficiency in terms of energy, spectrum, and cost. Thus, this paper is intended in developing a novel radio technology for the seamless wireless network. The advent of the Radio Access Technology into the next-generation wireless network seems to include more users when compared to the existing system of networks. This technology has proven. In this paper, we have discussed the design scenario, expectations from the 6G networks, energy efficiency, bit error rate, and spectral efficiency. This paper also includes the primary technology used and an overview of the current project and researches that are being held. There had been an improved method for searching and automatically computing using artificial intelligence for convergence of the local optimal solution.

Prabakaran Kasinathan

Papers

IoT based E-vehicle monitoring system using sensors and imaging processing algorithm

Development of Deep Learning Technique of Features for the Analysis of Clinical Images Integrated with CANN

A Novel Wireless Radio Technology Paradigm for Next Generation Wireless Networks