检索结果-内蒙古大学图书馆

Assistive technology with device for self-inflating bag in neonatology

学校读者我要写书评

暂无评论

Research on Biomedical engineering 2025年第2期41卷

作者： Marcelino, Ana Carolina Rodovanski, Giovana Pascoali Bonetti, Karoline Panes, Caio Rabinovich de Almeida Martins, Fernando Moran, Cristiane Aparecida Araranguá Brazil Graduate Program in Neurosciences and Behavior Department of Experimental Psychology of the Institute of Psychology-University of São Paulo Sao Paulo Brazil Araranguá Brazil Computer Engineering Instituto Mauá de Tecnologia São Caetano do Sul Brazil Electronic Engineering and Computing with Emphasis on Electronic Devices and Systems at Instituto Tecnológico de Aeronáutica–ITA São Caetano do Sul Brazil Department of Physiotheraphy and at the Postgraduate Program in Rehabilitation Science of the Federal University of Santa Catarina-UFCS Ararangua Brazil

Purpose: The objectives of this study were to create a device with technological development of the self-inflating bag (SIB) equipment to measure the variables tidal volume, peak inspiratory pressure, and inspiratory flow and to evaluate the knowledge of undergraduate students in handling the SIB. To reduce the risks of mortality, length of hospital stay, and infections, SIB is a resource used to ventilate the patient through the inflation of the device, but it is not capable of measuring the ventilatory parameters. Excess ventilation and incorrect handling of the bag can cause lung injury in newborns. Therefore, measuring these parameters can prevent lung injury resulting from inadequate ventilation. Method: This is a cross-sectional and experimental study, with the development of a device SIB that allows the evaluation of variables of neonatal respiratory mechanics that were tested with an artificial lung. It was approved by the Research Ethics Committee and the research was developed in three stages: the first represents the search for scientific articles for the consensus of neonatal ventilatory variables for the construction of the SIB parameters;the second stage depicts the technological development of a device capable of monitoring such variables through the SIB. In the third stage, the content validation of the device with the handling of the SIB was carried out by students of medicine and physiotherapy courses of Brazil. Results: In this work, a device that analyzes the values of the main ventilatory parameters in neonatology was developed and to generate a safety range for the use of the device, curves with a tolerance of 10% up and down were created. All electronic components were coupled to the equipment, with a display that transmits the parameter values. The web page can be used on a cell phone, tablet, computer, or SmartTv, as long as it is connected to the "RespiratorIoT_AP" network. Among the 29 participants in the study, 8 said they were familiar w

关键词： Students

A Genetic Algorithm approach for optimization of geothermal power plant production: Case studies of direct steam cycle in Kamojang

学校读者我要写书评

暂无评论

South African Journal of Chemical engineering 2023年 45卷 1-9页

作者： Rudiyanto, Bayu Birri, Mochammad Syahrul Widjonarko Avian, Cries Kamal, Dianta Mustofa Hijriawan, Miftah Energy Engineering Laboratory Department of Renewable Energy Engineering Politeknik Negeri Jember Jl. Mastrip No.164 Krajan Timur Jember 68121 Indonesia Graduate School of Department of Renewable Energy Engineering Politeknik Negeri Jember Jl. Mastrip No.164 Krajan Timur Jember 68121 Indonesia Department of Electrical Engineering Universitas Jember Jl. Kalimantan 37 Tegalboto Jember 68121 Indonesia Departement of Electronic and Computer Engineering National Taiwan University of Science and Technology No.43 Keelung Rd. Sec.4 Da'an Dist. Taipei City 106335 Taiwan Department of Mechanical Engineering Politeknik Negeri Jakarta Jl. Prof. Dr. G. A. Siwabessy Depok 16425 Indonesia Graduate Program of Mechanical Engineering Universitas Sebelas Maret Jl. Ir. Sutami 36 Surakarta 57126 Indonesia

Indonesia has enormous geothermal potential, but it only contributes 5% to Indonesia's energy matrix. During 37 years of operation, PT. Pertamina Geothermal Energy Kamojang area has been operating to produce electricity and is currently capable of supplying and distributing electricity to the Java-Bali area with a capacity of 60 MWe. However, this can run into a decrease in the efficiency and effectiveness of system performance due to energy losses in several geothermal power plant components during energy conversion. In this case, exergy analysis at PT. Pertamina Geothermal Energy Kamojang area Unit 4 direct-dry steam cycle was done on each component and state. This aims to know the energy and exergy stream and where it happened irreversibly at the component. The biggest irreversibility value occurred at the turbine and main condenser, with a value of 21,693.890 kW and 21,688.148 kW. The total irreversibility of all systems is 58,326.201 kW, while the total exergy inlet systems is 119,308.457 kW, so the value efficiency exergy obtained is 51.13%. Based on the environment as dead state analysis, an efficiency exergy value is inversely proportional to the irreversibility value and ascending environment temperature. System optimization was done with the genetic algorithm method, with variable values at the pressure wellhead and inlet turbine for the overall exergy efficiency value. The value obtained from optimization is 11.98 bar at the wellhead and 10.023 bar at the inlet turbine, and the overall efficiency exergy increased by 51.22%. © 2023 The Author(s)

关键词： Dry steam cycle Exergy Genetic Algorithm Geothermal power plant Optimization

Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Guangyuan Du, Hongyang Wang, Jiacheng Niyato, Dusit Kim, Dong In College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments. © 2025, CC BY.

关键词： Mobile edge computing

Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yu Qiao, Pengchong Liu, Chang Song, Guoli Zheng, Xiawu Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China -Preferred Program Peking University Shenzhen Graduate School China

Recent advances in robust semi-supervised learning (SSL) typically filterout-of-distribution (OOD) information at the sample level. We argue that anoverlooked problem of robust SSL is its corrupted information on semanticlevel, practically limiting the development of the field. In this paper, wetake an initial step to explore and propose a unified framework termed OODSemantic Pruning (OSP), which aims at pruning OOD semantics out fromin-distribution (ID) features. Specifically, (i) we propose an aliasing OODmatching module to pair each ID sample with an OOD sample with semanticoverlap. (ii) We design a soft orthogonality regularization, which firsttransforms each ID feature by suppressing its semantic component that iscollinear with paired OOD sample. It then forces the predictions before andafter soft orthogonality decomposition to be consistent. Being practicallysimple, our method shows a strong performance in OOD detection and IDclassification on challenging benchmarks. In particular, OSP surpasses theprevious state-of-the-art by 13.7% on accuracy for ID classification and 5.9%on AUROC for OOD detection on TinyImageNet dataset. The source codes arepublicly available at https://***/rain305f/OSP. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cui, Jiaxi Ning, Munan Li, Zongjian Chen, Bohua Yan, Yang Li, Hao Ling, Bin Tian, Yonghong Yuan, Li School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China Law School Peking University Beijing China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China

AI legal assistants based on Large Language Models (LLMs) can provide accessible legal consulting services, but the hallucination problem poses potential legal risks. This paper presents Chatlaw, an innovative legal assistant utilizing a Mixture-of-Experts (MoE) model and a multi-agent system to enhance the reliability and accuracy of AI-driven legal services. By integrating knowledge graphs with artificial screening, we construct a high-quality legal dataset to train the MoE model. This model utilizes different experts to address various legal issues, optimizing the accuracy of legal responses. Additionally, Standardized Operating Procedures (SOP), modeled after real law firm workflows, significantly reduce errors and hallucinations in legal services. Our MoE model outperforms GPT-4 in the Lawbench and Unified Qualification Exam for Legal Professionals by 7.73% in accuracy and 11 points, respectively, and also surpasses other models in multiple dimensions during real-case consultations, demonstrating our robust capability for legal consultation. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jin, Peng Li, Hao Cheng, Zesen Huang, Jinfa Wang, Zhennan Yuan, Li Liu, Chang Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What’s worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address the partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSRVTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

TG-VQA: Ternary Game of Video Question Answering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Hao Jin, Peng Cheng, Zesen Zhang, Songyang Chen, Kai Wang, Zhennan Liu, Chang Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Shanghai AI Laboratory Shanghai China -Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University China

Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them. However, since relying heavily on human instructions, i.e., annotations or priors, current contrastive learning-based VideoQA methods remains challenging to perform fine-grained visual-linguistic alignments. In this work, we innovatively resort to game theory, which can simulate complicated relationships among multiple players with specific interaction strategies, e.g., video, question, and answer as ternary players, to achieve fine-grained alignment for VideoQA task. Specifically, we carefully design a VideoQA-specific interaction strategy to tailor the characteristics of VideoQA, which can mathematically generate the fine-grained visual-linguistic alignment label without label-intensive efforts. Our TG-VQA outperforms existing state-of-the-art by a large margin (more than 5%) on long-term and short-term VideoQA datasets, verifying its effectiveness and generalization ability. Thanks to the guidance of game-theoretic interaction, our model impressively convergences well on limited data (104 videos), surpassing most of those pre-trained on large-scale data (107 videos). © 2023, CC BY.

关键词： Alignment

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jin, Peng Li, Hao Cheng, Zesen Li, Kehan Ji, Xiangyang Liu, Chang Yuan, Li Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-distribution data. To address this limitation, we creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates, query). This is accomplished through a diffusion-based text-video retrieval framework (DiffusionRet), which models the retrieval task as a process of gradually generating joint distribution from noise. During training, DiffusionRet is optimized from both the generation and discrimination perspectives, with the generator being optimized by generation loss and the feature extractor trained with contrastive loss. In this way, DiffusionRet cleverly leverages the strengths of both generative and discriminative methods. Extensive experiments on five commonly used text-video retrieval benchmarks, including MSRVTT, LSMDC, MSVD, ActivityNet Captions, and DiDeMo, with superior performances, justify the efficacy of our method. More encouragingly, without any modification, DiffusionRet even performs well in out-domain retrieval settings. We believe this work brings fundamental insights into the related fields. Code is available at https://***/jpthu17/DiffusionRet. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

DigitalLLaVA: Incorporating Digital Cognition Capability for Physical World Comprehension in Multimodal LLMs 39

学校读者我要写书评

暂无评论

DigitalLLaVA: Incorporating Digital Cognition Capability for...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Shiyu Wei, Pengxu Qiao, Pengchong Liu, Chang Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Pengcheng Laboratory Shenzhen China Sun Yat-Sen University Guangzhou China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Department of Automation and BNRist Tsinghua University Beijing China

ISBN: (纸本)157735897X

Multimodal Large Language Models (MLLMs) have shown remarkable cognitive capabilities in various cross-modal tasks. However, existing MLLMs struggle with tasks that require physical digital cognition, such as accurately reading an electric meter or pressure gauge. This limitation significantly reduces their effectiveness in practical applications like industrial monitoring and home energy management, where digital sensors are not feasible. For humans, physical digits are artificially defined quantities presented on specific carriers, which require training to recognize. As existing MLLMs are only pre-trained in the manner of object recognition, they fail to comprehend the relationship between digital carriers and their reading. To this end, referring to human behavior, we propose a novel DigitalLLaVA method to explicitly inject digital cognitive abilities into MLLMs in a two-step manner. In the first step, to improve the MLLM’s understanding of physical digit carriers, we propose a digit carrier mapping method. This step utilizes object-level text-image pairs to enhance the model’s comprehension of objects containing physical digits. For the second step, unlike previous methods that rely on sequential digital prediction or digit regression, we propose a 32 bit floating point simulation approach that treats digit prediction as a whole. Using digit-level text-image pairs, we train three float heads to predict 32-bit floating-point numbers using 0/1 binary classification. This step significantly reduces the search space, making the prediction process more robust and straightforward. Being simple but effective, our method can identify very precise metrics (i.e., accurate to ±0.001) and provide floating-point results, showing its applicability in digital carrier domains. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：