Search

High-altitude platforms (HAPs) are autonomous airships or airplanes that fly beyond 20 kilometers in the ozone to build a telecommunications network or do remote sensing. Several initiatives were started in the 1990s and 2000s, but only a handful have been completed. In 2014, two major Internet corporations such as Google and Facebook announced new HAP initiatives to give Net access in areas where there is no network system (terrestrial or satellite), reviving interest in HAP development. The goal of this review is to review the history of HAPs, as well as the present state-of-the-art, technological developments, and problems. This analysis will concentrate on technology directly connected to the aircraft control system and inserted into the field of aviation, rather than on features of telecommunication services. [ABSTRACT FROM AUTHOR]

In modern era, road traffic density has been increasing requiring a smart traffic system in managing traffic. Traffic congestion management has been a challenge nowadays as there is sharp increase in the number of vehicles. Real-time vehicle monitoring techniques play an important part in prevention of recurring traffic jams, managing traffic on roads, and deadly accidents. The most notable challenges are operating the system in real time to accurately identify and classify vehicles in active traffic flows without obstructing the vehicle. Factors such as weather environment and video quality can become objectives in vehicle detection using traditional machine learning algorithms leading to poor detection results. Recently, for better application in traffic control systems for vehicles, there has been a move towards deep learning architectures. In this paper, YOLOv2 (You Only Look Once) principle is utilized for real-time detection and counting of vehicles. The working of proposed strategy is carried out in two phases where vehicle detection is done at first phase and then counting of moving vehicles during second phase. This method provides strong object positioning functionality and high frames per second (FPS). The test results confirm that higher detection accuracy can be achieved with the proposed method, even when detecting small vehicles. This mechanism of YOLO based system provided an average detection of 95.75% and counting accuracy of 96.85%. The implications of these results help in intelligent transport planning. [ABSTRACT FROM AUTHOR]

Stress is typically characterized as a disruption in emotional homeostasis. Stress awareness is an essential study subject in bioengineering because good stress detection may easily avoid many psychophysiological disorders such as heart rhythm irregularities or arrhythmias. There are various bio-signals accessible (for example, EEG, ECG, EMG, breathing rate, GSR, and so on) that may be used to determine stress levels since these signals exhibit typical changes when stressed. For this project, we will analyse the ECG signal. The key candidate's ECG signal, available recording (i.e., various mobile effective functioning recorders are currently on the market), and ECG extracting features algorithms. Additional benefit of ECG is that breathing signal characteristics may be identified from it, which is termed as EDR (ECG derived Respiration), without the need for a separate various sensor for expiratory measurements. The characteristics of ECG signals are unique, and signal collection is cost-effective. A number of machine learning models such as SVM, NB, RF, DTC, and KNN are used to predict, and each classification algorithm is fine-tuned by model parameters before predicting if the data is stressing or healthy. Google Collab may be used for the whole development. [ABSTRACT FROM AUTHOR]

In this modem age, the use of biometrics is an important aspect in the lives of people in all areas. Iris recognition is now a trustworthy method of personal recognition due to the outstanding requirements for security and reliable types of identification in biometric systems. It is a main and challenging field of study because of its advantages of high precision and non-contact recognition technology. In automatic identification, iris recognition technology plays a vital role. This paper introduces a new concept of optimal security where the proposed system is trained using Convolutional Neural Networks (CNN) incorporated with softmax classifier. The model is trained on a dataset for iris recognition where only a small number of images were trained for each set and showed an enhancement in the results over earlier methods. It focuses on a systematic approach for iris recognition, even when the images have noise, obstructions and various levels of illuminations. Experiments with standard datasets have shown that the put forward approach can attain high performance than competing with other deep learning-based methods. The efficiency gained from iris recognition based on performance evaluation is accurate, achieving a total of 99%. [ABSTRACT FROM AUTHOR]