With the purpose of increasing the security of physical access in restricted areas, the paper proposes the use of the Linqstat material for a touch sensor keyboard consisting of 19 keys with the possibility of expansi...
详细信息
ISBN:
(数字)9798350352078
ISBN:
(纸本)9798350352085
With the purpose of increasing the security of physical access in restricted areas, the paper proposes the use of the Linqstat material for a touch sensor keyboard consisting of 19 keys with the possibility of expansion for later versions, model that is missing from the specialized literature. The advantage of this type of sensor is that it can also be applied to a curved surface, with the necessary calibration. The construction method of the keyboard including the touch sensor is presented. First, a neural network (NN) is used to locate the touch on the keyboard, then a second method detects each pressed key individually.
Human detection for critical missions with unmanned aerial vehicle (UAV) support becomes more and more important in the actual context when tension at borders builds up for an increasing number of countries. Although ...
Human detection for critical missions with unmanned aerial vehicle (UAV) support becomes more and more important in the actual context when tension at borders builds up for an increasing number of countries. Although convolutional neural networks are continuously evolving, the required computational resources pose a great problem when implemented on portable embedded systems such as UAVs, with limited processing power and autonomy. This demand becomes even more drastic when running real-time human detection and tracking. This paper proposes an improved implementation of the YOLOv.7, trained on a custom dataset, for real-time human detection and tracking with confidence scores above 80% on NVIDIA Jetson TX2 neural processing unit equipped on DJI Matrice 100 UAV. The authors created a YOLOv.7 model running independently on an embedded system for real-time human detection and tracking.
During the last few years, there has been a growing interest in the topic of using natural or synthetic esters as an alternative to mineral oils in oil transformers due to the easier way to obtain them and their abili...
详细信息
With the recent advancements in drone technology, there has been an increase in the development of human detection and tracking techniques for various applications, especially near borders. In this research, we propos...
With the recent advancements in drone technology, there has been an increase in the development of human detection and tracking techniques for various applications, especially near borders. In this research, we propose methods to enhance people detection performance in diverse outdoor scenarios. Our dataset design includes a wide range of lighting and color changes, different target distances, angles, and postures. The experimental data consists of images taken in various environmental situations, such as changing the drone’s flight height and capturing pictures in intensive light. To evaluate the performance of our proposed method, we enhanced the generic YOLOv5 model using the gathered data, and calculated key performance indicators, including loss functions, recall, accuracy, and mAP50. We compared the performance of our enhanced model against the standard YOLOv5 model and its versions on the same testing set.
Image corruption due to noise disturbances severely decreases color image quality and therefore image enhancement is a vital step of the processing pipeline. Our approach modifies the standard Mean-Shift technique, so...
详细信息
Few studies address the challenge of minimizing energy consumption during trajectory generation, particularly in the context of multicopter dynamics, characterized by strong non-linearity. This paper introduces a nove...
详细信息
This paper describes the solutions submitted by the UPB team to the AuTexTification shared task, featured as part of IberLEF-2023. Our team participated in the first subtask, identifying text documents produced by lar...
详细信息
Longer training times pose a significant challenge in Artificial neural networks (ANNs) as it may leads to increasing the computational costs and decreasing the effectiveness of the model. Therefore, it is imperative ...
详细信息
Longer training times pose a significant challenge in Artificial neural networks (ANNs) as it may leads to increasing the computational costs and decreasing the effectiveness of the model. Therefore, it is imperative to reduce training times in ANNs to enhance the computational efficiency. The initialization of the weights between the layers in ANN plays a vital role in reducing training times. Appropriate weight initialization can help the network converge faster during the training by providing an optimum starting point for the network. Therefore, weight initialization techniques are essential for efficient training of ANNs. This paper revisits and implements different popular weight initialization techniques in ANNs and analyzes their impact on training time. Specifically, this paper implements Gaussian-based, Kaming-based, and Xavier-based weight initiation atop a popular DNN-based network. The experiments are conducted by employing a well-known dataset. The results show that the scenario when no weight initiation is applied consumed the highest training time, whereas different weight initiation techniques contribute in reducing the training times for the network.
This paper presents a refined complexity calculus model: r-Complexity, a new asymptotic notation that offers better complexity feedback for similar programs than the traditional Bachmann-Landau notation, providing sub...
详细信息
automatic guided vehicles are increasingly used in factories. It is obvious that wireless communication with this type of devices is necessary. By default, transmissions are not based on time-deterministic behavior. H...
详细信息
暂无评论