This study is dedicated to evaluate the effectiveness of utilizing artificial intelligence (AI) and drone technology for the detection and management of stray dog issues worldwide. By combining the aerial photography ...
详细信息
ISBN:
(纸本)9798350386851;9798350386844
This study is dedicated to evaluate the effectiveness of utilizing artificial intelligence (AI) and drone technology for the detection and management of stray dog issues worldwide. By combining the aerial photography advantages of drones with deep learning techniques, the aim is to enhance the accuracy and efficiency of estimating stray dog populations and their locations. This provides animal management departments with a highly efficient tool for monitoring and quantity control. Through the collection of extensive aerial image data and the use of deep learning algorithms, such as YOLO, for the training of AI models, we optimize the identification and tracking capabilities for stray dogs. This study also leverages the flight data and real-time streaming images returned by drones to provide the detection system with immediate and accurate positioning capabilities. The results demonstrate that integrating AI and drone technology in the management and control of stray dogs can improve the accuracy of detection and tracking. It also enhances the efficiency of animal management tasks and the protection of public safety and animal welfare.
Advancements in memory technology have positioned memristors at the forefront of non-volatile memory applications, necessitating precise control mechanisms to accurately program memristor cells to their respective sta...
详细信息
ISBN:
(纸本)9798350377217;9798350377200
Advancements in memory technology have positioned memristors at the forefront of non-volatile memory applications, necessitating precise control mechanisms to accurately program memristor cells to their respective states. This study delves into the utilization of a RISC-V processor and PWM generators to configure registers for analog conductance control of crossbar memristor array architecture for accurate voltage and current mode operations. The core contribution is the development of a flexible and efficient control algorithm specifically designed for RISC-V. A Universal Verification Methodology Framework (UVMF) testbench is employed to validate control signals, ensuring their accuracy prior to hardware implementation. Results indicate significant enhancements in control efficiency, underlining the potential for integrating RISC-V with memristor technology.
This paper presents an isolated single-phase onboard charger used for BEV/PHEV using active power decoupling (APD) technology. The proposed circuit consists of an isolated SEPIC circuit and a totem pole PFC circuit an...
详细信息
For many space applications, traditional control methods are often used during operation. However, as the number of space assets continues to grow, autonomous operation can enable rapid development of control methods ...
详细信息
ISBN:
(纸本)9798350384529;9798350384512
For many space applications, traditional control methods are often used during operation. However, as the number of space assets continues to grow, autonomous operation can enable rapid development of control methods for different space related tasks. One method of developing autonomous control is Reinforcement Learning (RL), which has become increasingly popular after demonstrating promising performance and success across many complex tasks. While it is common for RL agents to learn bounded continuous control values, this may not be realistic or practical for many space tasks that traditionally prefer an on/off approach for control. This paper analyzes using discrete action spaces, where the agent must choose from a predefined list of actions. The experiments explore how the number of choices provided to the agents affects their measured performance during and after training. This analysis is conducted for an inspection task, where the agent must circumnavigate an object to inspect points on its surface, and a docking task, where the agent must move into proximity of another spacecraft and "dock" with a low relative speed. A common objective of both tasks, and most space tasks in general, is to minimize fuel usage, which motivates the agent to regularly choose an action that uses no fuel. Our results show that a limited number of discrete choices leads to optimal performance for the inspection task, while continuous control leads to optimal performance for the docking task.
This survey paper provides an in-depth survey of the application of eXtended Reality (XR) technology in the fields of commerce, management, and business edutainment. XR is a collective term that encompasses Virtual Re...
详细信息
ISBN:
(纸本)9798350373141;9798350373158
This survey paper provides an in-depth survey of the application of eXtended Reality (XR) technology in the fields of commerce, management, and business edutainment. XR is a collective term that encompasses Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR), and it is poised to transform how businesses operate, engage with consumers, and educate their employees. This survey examines the current state of XR technology in these areas, highlighting its impact, challenges, and future potential. It explores case studies and real-world applications, revealing the diverse ways in which XR is being utilized in commerce, management, and business edutainment.
Demand response (DR) has been regarded as one of the most effective manners to regulate power grids. Small power customers, such as households, offices, or classrooms, etc., can be assembled by an aggregator to partic...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
Demand response (DR) has been regarded as one of the most effective manners to regulate power grids. Small power customers, such as households, offices, or classrooms, etc., can be assembled by an aggregator to participate in the DR market, especially their air-conditioner (AC) loads. However, excessive reduction of the AC load may cause discomfort, adversely resulting in limited load curtailment. This paper proposes an AC temperature control model, which considers both users' comfort and load curtailment, for a group of air conditioners based on double deep Q-network (DDQN) reinforcement learning (RL). A recurrent neural network (RNN) is adopted to learn the indoor space thermal model such that the RNN model can estimate the indoor temperature response under a certain temperature setting point of AC. To achieve fair assignment of power curtailment target, the optimal temperature setting point schedule during DR events is determined to improve the comfort of indoor personnel on the premise of satisfying load shedding requirements. Furthermore, the reward mechanism is designed to constitute the learning objectives of the RL model: load curtailment and the maintenance of indoor comfort defined by the predicted mean vote (PMV) and predicted percentage dissatisfied (PPD) indices. A DR event for 20-room building equipped with individual ACs is simulated. The results reveal that the proposed model maintains a comfortable environment in various types of rooms and enables the aggregator to achieve the DR requirement.
People cannot handle the volume of data and the complexity of processes needed to secure cyberspace without significant automation. However, it is challenging to develop technologies and software with conventional fix...
详细信息
ISBN:
(纸本)9798350367607;9798350367591
People cannot handle the volume of data and the complexity of processes needed to secure cyberspace without significant automation. However, it is challenging to develop technologies and software with conventional fixed implementations ( hardwired decision-making logic) that successfully defend against security risks. AI learning techniques and machine simplicity can be used to treat this issue. Artificial intelligence (AI) approaches have been attempted to be used in a variety of cyber security applications recently. This paper gives an overview to the algorithms that might be used to have a better protection for our systems. This paper examines the crucial role that artificial intelligence plays in cybersecurity, as well as its benefits, drawbacks, and practical applications from the largest global corporations, such as PayPal and AWS. Also gives the benefits of using AI technology for Security.
A novel energy management strategy based on neural network (NN) and reinforcement learning is proposed to split the power of lithium battery and supercapacitor in the hybrid energy vehicle (HEV), which can meet the po...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
A novel energy management strategy based on neural network (NN) and reinforcement learning is proposed to split the power of lithium battery and supercapacitor in the hybrid energy vehicle (HEV), which can meet the power required by the vehicle driving, improve the battery lifetime. First, the NN state-action model is gained by using traditional energy management controller, it generates new data and combined with the original data to optimize the NN model. Then, the action sequences are generated randomly, which will be evaluated by NN model, here, only the first action is adopted. The next action is re-predicted after this action is executed, which reduces the cumulative error caused by the inaccurate model. Finally, four typical driving patterns are selected, and the comparison with Deep Q-network (DQN) method is carried out, which verifies the performance of energy management strategy based on NN and reinforcement learning.
The study deals with the human body's electromagnetic interferences (EMI). The preliminary fundamental theory is put on the designing and modelling small low-frequency inductive electromagnetic field sensors. The ...
详细信息
ISBN:
(纸本)9798350385236;9798350385243
The study deals with the human body's electromagnetic interferences (EMI). The preliminary fundamental theory is put on the designing and modelling small low-frequency inductive electromagnetic field sensors. The possibilities of printed circuit board (PCB) nanotechnology for applications in biophysics are also presented. The aim is to define the limits of this new principle in clinical research. This paper implies methods of modelling and simulation of the sensor concerning recent trends in electronic design.
Recent advancements in unmanned aerial vehicle (UAV) and multirotor technology have increased industrial applications, but safety and noise remain challenges. The aim is to devise a method to suppress thrust force vib...
详细信息
ISBN:
(纸本)9798350355376;9798350355369
Recent advancements in unmanned aerial vehicle (UAV) and multirotor technology have increased industrial applications, but safety and noise remain challenges. The aim is to devise a method to suppress thrust force vibration in cross-wind conditions that apply to small-sized multirotors. A higher harmonic rotational speed control method is proposed based on the position-dependent aerodynamic force model. Second-order harmonic thrust vibration under crosswind conditions is simply modeled, and higher harmonic input is designed only for use in the rotational speed and utilized high torque response performance of the electric motor. The effectiveness of the proposed method is validated through the wind tunnel experiment.
暂无评论