This research presents an innovative educational resource integration and intelligent Questions and Answers (Q&A) system for Sichuan University-Pittsburgh Institute (SCUPI), combining Retrieval-Augmented Generatio...
详细信息
ISBN:
(数字)9798331522216
ISBN:
(纸本)9798331522223
This research presents an innovative educational resource integration and intelligent Questions and Answers (Q&A) system for Sichuan University-Pittsburgh Institute (SCUPI), combining Retrieval-Augmented Generation (RAG) technology with Large Language Models (LLMs). Through controlled experiments with admission-related queries, our system demonstrates significant advantages over baseline models in three aspects: response accuracy through knowledge integration, information boundary management, and contextual awareness in multi-turn conversations. The findings provide valuable insights for implementing AI consultation systems in international higher education programs, particularly in managing admission inquiries.
Continuous operation of power systems is critical to modern society, even during unexpected or emergency situations. One method to evaluate the security of power systems is contingency analysis, a computationally-inte...
详细信息
Most of the research conducted in action recognition is mainly focused on general human action recognition, and most of the available datasets support studies in general human action recognition. In more specific cont...
详细信息
Efficient image processing architectures are consistently in demand across a multitude of applications, particularly those customized for resource-constrained systems-on-chip (SoC). The increasing need for high-perfor...
详细信息
ISBN:
(纸本)9798400709586
Efficient image processing architectures are consistently in demand across a multitude of applications, particularly those customized for resource-constrained systems-on-chip (SoC). The increasing need for high-performance image processing in various sectors has driven the development of specialized architectures. However, deploying such architectures on platforms with limited resources, such as SoCs, poses significant challenges. Furthermore, the implementation of complex algorithms to handle large datasets using software solutions often leads to slower response times, prompting exploration into hardware implementations. Field-Programmable Gate Arrays (FPGAs) are becoming popular for hardware implementations because of their attributes: low latency, connectivity, parallel computing capabilities, and flexibility. Consequently, the utilization of FPGA-based implementations has resulted in faster and more efficient performance of unique architectures tailored to specific requirements. This paper presents a novel hardware/software co-design approach to implement erosion, dilation, and neighborhood image processing operations on the FPGA development board, "Zedboard". In this approach, the FPGA is programmed by connecting it to a PC via USB, facilitating the transfer of an image pixel by pixel. The pixels are temporarily stored in on-chip DDR and accessed through DMA (Direct Memory Access) until they are requested by an interrupt signal from the Image Processing IP, at which point they are moved to line buffers for faster processing. Once processed, the image is transmitted back to the PC via UART, facilitating pixel-by-pixel transfer for verification, where it is compared with a reference image generated using Python. This comparison confirms a 99.22% match between the processed image and the reference image, with the discrepancy occurring at the image's edges due to initial padding. Additionally, the time required to process the entire image was measured and displayed
Since panoramic images provide a wide field of view of the surrounding environment, they offer a rich source of information that is increasingly utilized in fields like robotics and autonomous systems. With the applic...
详细信息
ISBN:
(数字)9798331522216
ISBN:
(纸本)9798331522223
Since panoramic images provide a wide field of view of the surrounding environment, they offer a rich source of information that is increasingly utilized in fields like robotics and autonomous systems. With the application of 360° cameras (i.e. panorama, omnidirectional cameras), robots are gaining 360°perception, enabling them to better understand and interact with their surroundings. However, the unique characteristics of panoramic images, such as geometric distortion and spatial discontinuity introduced by the panoramic projection, pose significant challenges for the application of conventional object detection methods, which are typically designed for perspective images. To address these challenges, current approaches often rely on repetitive overlapping detections to avoid object fragmentation caused by view cuts, but this leads to detection failures and inefficiencies. In this paper, we propose a novel method that explores region proposals within panoramic images to perform view projection. By reducing redundant detections, our approach improves detection efficiency and accuracy. We demonstrate through experiments that our method enhances object detection performance, providing a more effective solution for panoramic image object detection tasks in robotics and autonomous systems.
Expert systems (ES) rely heavily on effective control mechanisms to navigate complex problem-solving tasks. These mechanisms govern how ES utilizes knowledge and data to make decisions and execute actions. Optimizing ...
详细信息
Among the many software technologies around the world,there is no parallel to cloud computing(CC).Businesses use cloud computing for hosting *** cloud computing, tasks are distributed across a group of resources which...
详细信息
To address practical issues such as complex backgrounds, indistinct target features, and poor real-time performance in detecting and tracking small and weak targets at sea, this paper first designs a guided filter alg...
详细信息
ISBN:
(数字)9798331522216
ISBN:
(纸本)9798331522223
To address practical issues such as complex backgrounds, indistinct target features, and poor real-time performance in detecting and tracking small and weak targets at sea, this paper first designs a guided filter algorithm fused with a foggy day imaging model for image preprocessing. This aims to simplify the background complexity. Subsequently, the incremental YOLOv8 detection head algorithm is employed for detecting and tracking these targets, while integrating the ACmix hybrid model to enhance overall operational efficiency. Finally, simulation experiments are conducted to validate the effectiveness and feasibility of the proposed algorithm.
Legal firms face mounting pressure to adapt to technology-induced transformations in the corporate landscape. To address this challenge, we propose a strategic approach centered on a customized software-as-a-Service (...
详细信息
This paper proposes an artificial neural network (ANN)-based prediction model to accurately estimate green hydrogen production in the Dakhla Oued Ed-Dahab region, using detailed data ex-extracted from HOMER Pro softwa...
详细信息
暂无评论