The global energy landscape is evolving, with distributed generation (DG) playing a key role. This study assesses the applicability of EnergyPLAN, a simulation tool, for a high renewable energy source (RES) system, fo...
详细信息
The transportation industry is currently facing a significant challenge with overloading, which not only poses safety risks but also leads to higher operational costs. One potential solution involves the implementatio...
详细信息
In the contemporary world, artificial intelligence and machine learning algorithms are an important driver for decision-making, by leveraging real-world data for future predictions. Despite clearly improving efficienc...
详细信息
ISBN:
(纸本)9798350384048;9798350384031
In the contemporary world, artificial intelligence and machine learning algorithms are an important driver for decision-making, by leveraging real-world data for future predictions. Despite clearly improving efficiency, the lack of transparency in their predictions raises concerns about the degree of fairness of machine learning models, well highlighted by recent instances of algorithmic unfairness, from automated decisions on criminal recidivism to disease prediction. Increased user awareness of algorithmic fairness is met with a deficiency in systems guiding data analysts and practitioners in comprehending the implications of their outputs. To tackle the challenge of fairness interpretability, we propose FairnessFriend, a chatbot solution that combines data science with a human-computer interaction perspective. Given a dataset and a trained machine learning model with established fairness metrics, our system facilitates users in understanding these metrics and their significance in the context of the training data. FairnessFriend provides meanings for various statistical fairness metrics, and presents the resulting metrics values with detailed explanations, offering specific insights into their implications.
This paper investigates optimization strategies for fog and edge computing systems, focusing on the key challenges of resource allocation, load balancing, latency minimization, and power efficiency. We analyze the res...
详细信息
With the continuous advancement of human-computer interaction (HCI) technology, traditional interaction methods are increasingly unable to meet the growing complexity of application requirements. Human gesture recogni...
详细信息
ISBN:
(纸本)9798350377040;9798350377033
With the continuous advancement of human-computer interaction (HCI) technology, traditional interaction methods are increasingly unable to meet the growing complexity of application requirements. Human gesture recognition, as a natural and intuitive interaction method, has been widely applied in fields such as smart devices and virtual reality due to its convenience and flexibility. In recent years, the emergence of deep learning technology has provided new solutions for improving the performance of gesture recognition systems. This study designs a human gesture recognition and interaction system based on deep learning methods, aiming to enhance recognition accuracy and real-time responsiveness. First, the paper reviews the development of gesture recognition technology and provides a detailed analysis of deep learning-based gesture recognition methods. Subsequently, a gesture recognition model combining Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) is proposed, along with the overall system architecture. Through the processes of gesture image data collection, preprocessing, and model training, experimental results demonstrate that the proposed system exhibits significant advantages in recognition accuracy, robustness, and response speed. Finally, the paper discusses optimization strategies for the system and envisions the broad application prospects of deep learning technology in future HCI systems.
Object detection is an important computer vision task in digital images for a specific class of phenomena (such as people, animals or ball-type objects). To improve the accuracy of small object detection for high-spee...
详细信息
ISBN:
(纸本)9798350391961;9798350391954
Object detection is an important computer vision task in digital images for a specific class of phenomena (such as people, animals or ball-type objects). To improve the accuracy of small object detection for high-speed moving balls in sports fields, we researched and tested a small object detection model based on the YOLOv8 algorithm. The YOLO algorithm based on deep learning is fast and accurate in operation, making it suitable for real-time systems. On the basis of the original algorithm, we carried out algorithm fusion and parameter adjustments, added a small object detection head to enhance the capability for detecting small objects, incorporated an attention mechanism to increase the precision of object detection, and achieved ball detection in complex backgrounds on the sports field, which played a guiding role in the switching of broadcast camera angles.
This study describes a novel way for improving automatic license plate recognition (ALPR) systems, with a focus on addressing obstacles associated with indistinct license plate photos. The suggested method combines ad...
详细信息
The advancements in information technology and computer-aided design have paved the way for virtual modeling and exploration of real-life objects. In the realm of CAD systems, there are subgroups of specialized softwa...
详细信息
The hand gesture-based computer Screen Control approach has had a lot of popularity in these years. This article examines recent advancements in hand gesture recognition technology and its applications across diverse ...
详细信息
Autonomous systems rely on artificial intelligence to perform their tasks more effectively. With the increasing complexity of tasks, it is essential to provide a structured way to define tasks. This paper explores a n...
详细信息
暂无评论