In the current world, more confidential information on untrusted repositories is maintained such that it is important to encrypt data on these pages. New encryption methods are being developed and improved from time t...
详细信息
Traditional sensor-based fire detection systems cannot be alerted until the heat actually reach to the sensors. Therefore, it is evident to make a fast, robust and reliable system which can detect fire at an early sta...
详细信息
Vehicular networks rely on periodic broadcast of each vehicle39;s state information to track its surrounding vehicles and therefore, to predict potential collisions. However, in a scenario of high vehicle density, a...
Vehicular networks rely on periodic broadcast of each vehicle's state information to track its surrounding vehicles and therefore, to predict potential collisions. However, in a scenario of high vehicle density, a large number of vehicles compete to access the shared channel and transmit their beacons, inevitably leading to channel congestion. In order to avoid channel congestion and guarantee the vehicle safety requirements for each vehicle, in this paper, we propose a multi-agent coordinated channel resource allocation method based on multi-agent deep reinforcement learning method. In this method, each vehicle acts as an agent and interacts with communication environments to a learn channel congestion control strategy through updating deep Q-network (DQN). Experimental results show that with the designed reward and training procedure, the proposed method can achieve fair and efficient channel resource allocation for each vehicle under varying traffic conditions.
The paper is devoted to solving the problem of analyzing and forecasting the parameters of traffic flows in the network of a large urban agglomeration. As one of these parameters, the average travel time for public tr...
详细信息
ISBN:
(数字)9798350353099
ISBN:
(纸本)9798350353105
The paper is devoted to solving the problem of analyzing and forecasting the parameters of traffic flows in the network of a large urban agglomeration. As one of these parameters, the average travel time for public transport vehicles along a selected segment of the Baku transport network is considered. The initial data is formed by processing and filtering the readings of the speed sensors of the Technical (computer) vision System of the city Intelligent Transport Management Centre, which monitors traffic in real time (every second during the day). The solution to the problem of short-term forecasting of the travel time is proposed, which is considered using both traditional methods of analysis, for example, the exponential smoothing method, and using neural network and fuzzy modeling methods. As the basic object of subsequent analysis, the corresponding time series is considered, reflecting the dynamics of changes in the time parameter for vehicles to travel through a limited segment of a transport network of the fixed length for a full day.
In the past decade, various haze removal techniques have been widely reported for object recognition. But hitherto little has been identified on the use of single image dehazing using transfer learning approach for ob...
In the past decade, various haze removal techniques have been widely reported for object recognition. But hitherto little has been identified on the use of single image dehazing using transfer learning approach for object detection. Single image dehazing is an emerging computervision technology which offers some of the extreme benefits over the existing techniques such as consumes less processing time, requires less space for real time dehaze purpose, etc. In this study, we combine both the object detection and image dehazing methods for real time applications such as-remote sensing, video surveillances, driverless automatic vehicles, etc. This paper presents an effective and efficient image dehazing method using transfer learning which helps to recognize objects in real time with more clarity and that can automatically detect objects with a high recognition rate and lesser probability of error. Our tests show that object detection becomes less accurate as the haze intensity increases; yet, under all haze circumstances (low, medium, or heavy), our jointly trained model AOD-net +YOLO v3 consistently outperforms non-joint and naïve YOLO v3 techniques.
Waste management has become a critical requirement to maintain a green environment in Sri Lanka as well as other countries. Town councils have to regularly collect different types of wastes to clean cities/towns. Henc...
详细信息
In the process of rod pump lifting, the study on the movement law of rod pump and the distribution of liquid pressure and velocity in the valve barrel of the rod pump is an important basis for judging whether the oil ...
详细信息
Based on the lateral vibration control of bogie frame for improving hunting stability in high-speed trains, three control strategies including linear quadratic regulator (LQR) control, Fuzzy Proportional-Integral (Fuz...
详细信息
ISBN:
(数字)9798331529505
ISBN:
(纸本)9798331529512
Based on the lateral vibration control of bogie frame for improving hunting stability in high-speed trains, three control strategies including linear quadratic regulator (LQR) control, Fuzzy Proportional-Integral (Fuzzy-PI) control and Particle Swarm Optimization Proportional-Integral-Derivative (PSO-PID) control are compared in this study. For the simplified linear lateral dynamics model of single bogie, the control parameters under the three control strategies are acquired, then they are applied to the vehicle dynamics model co-simulated by the SIMPACK and MATLAB codes. The different train operating conditions are taken into account and the improvement of dynamics indexes under the three control strategies are evaluated from the aspects of lateral riding quality of the car body and lateral force of wheelsets. The results show that the three control strategies lead to obvious mitigation on lateral vibration, and the improvement of PSO-PID control is the most obvious, but the LQR control effect is the worst.
The recent development of blockchain technology has accelerated innovation across several areas, with far-reaching ramifications for the field of marketing. This disruptive platform marks a shift from traditional mark...
详细信息
ISBN:
(数字)9798350375190
ISBN:
(纸本)9798350375206
The recent development of blockchain technology has accelerated innovation across several areas, with far-reaching ramifications for the field of marketing. This disruptive platform marks a shift from traditional marketing paradigms, encouraging accountability and trust among key stakeholders such as advertisers, influencers, content suppliers, and consumers. This platform empowers consumers while providing marketers with more chances to efficiently exploit targeted audience engagement by emphasizing data protection through the sophisticated encryption mechanisms inherent in the blockchain. Furthermore, the use of Artificial Intelligence (AI) improves marketing techniques by allowing for the delivery of individualized experiences and increasing conversion rates. Positioned at the forefront of the Web3 era, this innovative Web3 Marketing Suite encompasses a vision for a more inclusive and simplified marketing environment, establishing the framework for a new era of digital marketing innovation.
The mathematical model of a two-wheeled robotic machine (TWRM) with five degrees of freedom (DOF) is utilized in this paper to enlarge the workspace and enhance the robot’s flexibility. The suggested machine features...
The mathematical model of a two-wheeled robotic machine (TWRM) with five degrees of freedom (DOF) is utilized in this paper to enlarge the workspace and enhance the robot’s flexibility. The suggested machine features five degrees of freedom (DOFs), which makes it suitable for pick-and-place, material handling, and packing tasks in the workplace. The proposed architecture will make it more difficult to control the system to account for the center of mass’ (COM) location changing as a result of managing tasks that must be performed in multiple directions. The state space model was created by linearizing the non-linear modeling equations at the equilibrium point using the Lagrangian modeling. Numerous controllers, including the proportional-integral-derivative (PID), linear-quadratic regulator (LQR), and PID with LQR methods, were tested in order to stabilize the robot. The PID with LQR technique, where PID was used as a feedforward to control the intermediate body (IB) and end-effector and LQR was used as state feedback to regulate all states. These controllers were evaluated while taking into account a variety of circumstances (disturbance signals, tracking pathways, and moving actuators). In terms of least overshoot, rising time, and applied input forces, simulation results showed that PID with LQR controller tuned performed better than the other two control systems.
暂无评论