This paper describes a pulse-width modulated (PWM)-SAR A/D converter (ADC), in 22 nm FD-SOI technology, for mixed-signal accelerators and Machine Learning applications. The ADC integrates an asynchronous control unit ...
详细信息
This paper presents a preliminary study on sideslip angle estimation for autonomous vehicles (AVs) based on the Transformer architecture. Specifically, considering the decisive role of the dataset in the network's...
详细信息
ISBN:
(纸本)9798331540845;9789887581598
This paper presents a preliminary study on sideslip angle estimation for autonomous vehicles (AVs) based on the Transformer architecture. Specifically, considering the decisive role of the dataset in the network's inference results, a highcoverage dataset is constructed from three inputs: vehicle speed, steering wheel angle, and road surface coefficient, which is used for offline training of the network. Additionally, the model-based Extended Kalman Filter (EKF) algorithm and data-driven Long Short-Term Memory (LSTM) network are designed as baseline methods for comparison. Co-simulation results under varying vehicle speeds demonstrate that the neural network-based approach achieves significantly higher accuracy in sideslip angle estimation compared to the model-based method. Furthermore, the Transformer-based approach exhibits lower mean absolute error (MAE) and root mean square error (RMSE) in sideslip angle estimation compared to LSTM. These preliminary results validate the effectiveness of using the Transformer for solving vehicle state estimation problems.
The Fintech industry is currently experiencing a major shift as Artificial Intelligence (AI) becomes more integrated, fundamentally changing how financial services are provided, overseen, and enhanced. This study expl...
详细信息
ISBN:
(纸本)9798350351491;9798350351484
The Fintech industry is currently experiencing a major shift as Artificial Intelligence (AI) becomes more integrated, fundamentally changing how financial services are provided, overseen, and enhanced. This study explores the ever-evolving landscape of AI in Fintech, examining the most recent advancements and impactful applications. As AI technologies continue to evolve, they find their way into the core operations of Fintech, encompassing risk assessment, fraud prevention, customer service, and investment strategies. This paper provides a detailed examination of these cutting-edge applications, highlighting their significance and potential. Notable trends discussed in this research encompass Explainable AI, the increasing emphasis on data security and privacy, and the global proliferation of AI-powered financial solutions. Furthermore, the paper investigates the intricate landscape of regulations and ethical considerations governing AI in Fintech and the strategies in place to navigate them. This comprehensive analysis of AI's impact on Fintech aims to provide a holistic view of the current landscape while offering insights into the future trajectories of this symbiotic relationship. It serves as a valuable resource for industry practitioners, policymakers, and researchers interested in harnessing the transformative potential of AI within the financial technology domain.
Proportional integral derivative (PID) algorithm control is the most common control method in robot control, and agricultural harvesting robots have been a very popular robot application in recent years. This algorith...
详细信息
This paper explores the technology and strategies of using drones for external equipment surveying in the renovation of old pig farms in South China. Without interfering with production, drone aerial photography techn...
详细信息
In anticipation of future extensive lunar surface operations, lunar rovers are required to advance towards higher speeds and improved energy conservation. When traveling at high speeds on the lunar surface, the vehicl...
详细信息
Currently, there are numerous vehicle detection algorithms available. However, in real-world road scenes, factors such as difficult-to-identify features, low resolution, and complex environments often lead to situatio...
详细信息
In millimeter-wave communication networks, sidelobe leakage of phased array antennas can cause mutual interference to receiving devices, resulting in reduced network throughput. By optimizing the weights of antenna el...
详细信息
ISBN:
(纸本)9798350329285
In millimeter-wave communication networks, sidelobe leakage of phased array antennas can cause mutual interference to receiving devices, resulting in reduced network throughput. By optimizing the weights of antenna elements, nulls can be created to suppress the interference. However, commercial low-cost millimeter-wave phased arrays often not only lack amplitude control but also offer limited bits control. Therefore, interference suppression with highly quantized phase control is of great significance for practical applications of millimeter-wave communications. Existing algorithms for null steering and generation mainly consider continuous phase control which cannot adapt well to the quantized phase tuning for multi-user communications over the downlink. Moreover, the optimization of multiple nulls is inherently a discrete programming which is generally intractable. The authors propose a null generation algorithm for sole phase control based on the Levenberg-Marquardt algorithm. The algorithm takes into account phase quantization, making it convenient to implement wide and multiple nulls. Simulation results show that the algorithm can generate deep and wide nulls even with low phase resolution. Moreover, the algorithm is validated with Commercial Off-The-Shelf low-cost 60 GHz communication devices. Experimental results demonstrate that the algorithm achieves interference suppression up to 22.93 dB with a 4-bit phased array.
The reliability of modern industrial systems is rigid;therefore, it is mandatory to monitor the system status and detect anomalies accurately. A long short-term memory (LSTM) network can be used to predict the trend o...
详细信息
ISBN:
(纸本)9798350380903;9798350380910
The reliability of modern industrial systems is rigid;therefore, it is mandatory to monitor the system status and detect anomalies accurately. A long short-term memory (LSTM) network can be used to predict the trend of single-dimensional system test data and implement anomaly detection based on the prediction result. However, the structure of the modern system is complex, and strong dependencies may exist between different variables. The LSTM-based detection method cannot capture this dependency, and some anomalies can be ignored. Therefore, an anomaly detection framework based on the LSTM autoencoder is proposed in this paper. The autoencoder is applied to find the hidden dependency among variables by minimizing the reconstruction error of normal data, while the LSTM is used to capture the temporal dependencies in the time series. Moreover, a new dynamic error threshold selection strategy based on extreme value theory (EVT-DTS) is presented, which can avoid estimating the error distribution beforehand. The EVT-DTS method can dynamically adjust the error threshold according to the current input data error so that the overall optimal detection result can be obtained. Finally, we implement experiment on two industrial applications using the proposed method, which demonstrate its effectiveness in finding complex anomaly states in the system.
An area of robotics, assistive robotics, has been growing rapidly with recent advances in computing, control systems and instrumentation. Physio therapeutic procedures like gait rehabilitation and learning are often u...
详细信息
暂无评论