With the proliferation of artificial intelligence, computer-aideddesign (CAD) is being transformed into computer-Automated design (CAutoD). In this paper, the advent of Large Language Models (LLMs) introduces new opp...
详细信息
The valve-side single-phase-to-ground (SPG) fault is one of the key challenges for the MMC-based bipolar HVdc system. In this article, a grounded thyristor loop (GTL)-based hybrid MMC (HMMC) is proposed to protect the...
详细信息
The valve-side single-phase-to-ground (SPG) fault is one of the key challenges for the MMC-based bipolar HVdc system. In this article, a grounded thyristor loop (GTL)-based hybrid MMC (HMMC) is proposed to protect the bipolar HVdc system under valve-side SPG faults. In the GTL-HMMC, the thyristor branches are proposed to connect the different arm inductors and the ground. The operation for the GTL-HMMC in case of valve-side SPG faults is also proposed, where the GTL-HMMC can handle the faults with the advantages of short-fault current interruption time, low capacitor overvoltage, low arm overcurrent, low semiconductor cost, and low power loss. Electromagnetic transient (EMT) simulation studies using Power systemcomputeraideddesign / electromagnetic transients including DC (PSCAD/EMTDC) tool and experimental studies with a laboratory scaled hardware prototype are conducted to confirm the effectiveness of the proposed technique.
The proceedings contain 331 papers. The topics discussed include: research on computeraided French audiovisual intelligence system;feature extraction and intelligent generation of spatial environment design combined ...
ISBN:
(纸本)9798350373646
The proceedings contain 331 papers. The topics discussed include: research on computeraided French audiovisual intelligence system;feature extraction and intelligent generation of spatial environment design combined with deep learning;a federated learning algorithm based on combination of prototype and comparative learning;research on the optimization of wind-solar energy storage systems in park microgrids based on mixed integer linear programming and Monte Carlo simulation;deep learning in biometric recognition: applications and challenges;design and research of virtual human based on deep learning and paddle model;a fault diagnosis method based on TCN-LSTM-SE neural networks for distributed PV systems;and research on real-time image data transmission system of UAV in fault location of distribution network.
According to the cold state and operation parameters of diesel generator set, the operation and excitation of the generator are controlled, and the fault protection is implemented. The monitoring system including the ...
详细信息
The proceedings contain 229 papers. The topics discussed include: research on passive localization techniques for UAV formations based on the law of sines;text-driven image editing based on diffusion models;research o...
ISBN:
(纸本)9798350350760
The proceedings contain 229 papers. The topics discussed include: research on passive localization techniques for UAV formations based on the law of sines;text-driven image editing based on diffusion models;research on the application of electromechanical automation control software architecture to production line inspection under cloud computing platform;Bayesian optimization based LSTM model for time series forecasting problems;research on digital system of collaborative cycle integration information transformation in electric power enterprises;research on network intrusion detection method based on CNN;stereo matching algorithm based on DACVNet;a study on the thermal deformation prediction model of a motorized spindle based on swarm intelligence optimization algorithms;and study on the constraints of output and frequency fluctuations of offshore wind turbines.
In the scenario of multi-user access in smart homes, the platform's access control mechanism is crucial in ensuring that users can legitimately and appropriately access devices. However, we have found that the per...
详细信息
ISBN:
(纸本)9798350348439;9798350384611
In the scenario of multi-user access in smart homes, the platform's access control mechanism is crucial in ensuring that users can legitimately and appropriately access devices. However, we have found that the permission management mechanisms provided by smart home platforms and the solutions proposed in academic research are insufficient to fully meet the new requirements of access control. This can result in issues such as unauthorized access, inability to coordinate access conflicts, and lack of support for black-box platforms. In this paper, we present SHPAC, a new smart home access control scheme based on Policy-Based Access control. This scheme not only provides fine-grained permission management, but also supports users in submitting their personalized access preferences, as well as automatic conflict resolution and multi-platform support. We also implemented a prototype system and evaluated the system from the perspectives of black-box platform support, access control performance, and policy management effectiveness. The results show that our design can address the shortcomings of existing solutions, enhancing the flexibility and effectiveness of smart home access control.
Intelligent system have a significant impact in the realm of sports and fitness, but there exists an issue with incomplete applications. Standard deep learning methods are insufficient to tackle these application chal...
详细信息
The field of computer-aided diagnosis (CAD) of brain tumors has been transformed by developments in medical imaging and artificial intelligence. The accuracy and interpretability of brain tumor classification are impr...
详细信息
In this paper, a remote video conferencing system based on cloud video is proposed and implemented. The system uses a mesh transfer card for MV-440 single channel high definition MPEG4 images. This paper introduces th...
详细信息
With increasing computation of various applications, dynamic voltage and frequency scaling (DVFS) is gradually deployed on FPGAs to improve performance and save energy. However, its reliability and security have not b...
详细信息
With increasing computation of various applications, dynamic voltage and frequency scaling (DVFS) is gradually deployed on FPGAs to improve performance and save energy. However, its reliability and security have not been sufficiently evaluated, which incurs quite many concerns. In this article, we propose an evaluation framework for deep investigation of stealthy DVFS fault injection attacks on the state-of-the-art deep neural networks (DNNs) deployed on modern FPGAs. The evaluation framework mainly consists of a DVFS attack striker and a time-to-digital converter (TDC)-based hardware profiler. Two modes of evaluation are derived, and their effectiveness is demonstrated on a platform composed of a SkyNet accelerator and three ImageNet models built on a Xilinx deep learning processor unit (DPU). Experimental results show that more than 99% detection accuracy loss can be measured targeting at all tested DNN models under prospective operation mode but without any performance degradation in frame per second (FPS). In our investigation of sensitive layer mode, more than 93% average accuracy loss with 84.7% fault probability can be measured on a single bundle of the SkyNet. We characterize the vulnerabilities of different DNN layers subject to DVFS attacks through leveraging the TDC-based hardware profiler to precisely control the timing of fault injection.
暂无评论