检索结果-内蒙古大学图书馆

A multimodal machine learning model for bipolar disorder mania classification: Insights from acoustic, linguistic, and visual cues

引用

Intelligence-Based Medicine 2025年 11卷 100223-100223页

作者： Murugavel, Kiruthiga devi r, Parthasarathy Mathivanan, Sandeep Kumar Srinivasan, Saravanan Shivahare, Basu dev Shah, Mohd Asif Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai 600026 India Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India School of Computing Science and Engineering Galgotias University Greater Noida 203201 India Department of Economics Kardan University Parwane Du Kabul 1001 Afghanistan Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh 174103 India Division of Research and Development Lovely Professional University Punjab Phagwara 144001 India

Mood fluctuations that can vary from manic to depressive states are a symptom of a disease known as bipolar disorder, which affects mental health. Interviews with patients and gathering information from their families are essential steps in the diagnostic process for bipolar disorder. Automated approaches for treating bipolar disorder are also being explored. In mental health prevention and care, machine learning techniques (ML) are increasingly used to detect and treat diseases. With frequently analyzed human behaviour patterns, identified symptoms, and risk factors as various parameters of the dataset, predictions can be made for improving traditional diagnosis methods. In this study, A Multimodal Fusion System was developed based on an auditory, linguistic, and visual patient recording as an input dataset for a three-stage mania classification decision system. deep denoising Autoencoders (ddAEs) are introduced to learn common representations across five modalities: acoustic characteristics, eye gaze, facial landmarks, head posture, and Facial Action Units (FAUs). This is done in particular for the audio-visual modality. The distributed representations and the transient information during each recording session are eventually encoded into Fisher Vectors (FVs), which capture the representations. Once the Fisher Vectors (FVs) and document embeddings are integrated, a Multi-Task Neural Network is used to perform the classification task, while mitigating overfitting issues caused by the limited size of the bipolar disorder dataset. The study introduces deep denoising Autoencoders (ddAEs) for cross-modal representation learning and utilizes Fisher Vectors with Multi-Task Neural Networks, enhancing diagnostic accuracy while highlighting the benefits of multimodal fusion for mental health diagnostics. Achieving an unweighted average recall score of 64.8 %, with the highest AUC-rOC of 0.85 & less interface time of 6.5 ms/sample scores the effectiveness of integrating mult

关键词： Audio-visual modality Bipolar disorder deep denoising autoencoders (ddAEs) Fisher vectors (FVs) Multimodal

来源：评论

学校读者我要写书评

暂无评论

Comparison and optimization of an air cooling design for lithium-ion battery packs by using an electrochemical-thermal coupled model

Comparison and optimization of an air cooling design for lit...

引用

New Energy and Energy Storage System Control Summit Forum (NEESSC)

作者： Zhuomin Zhou Jian Liang Aiqin Yu Zhengbin Qin Haotian Liu Yanchao Sheng Wei Guo Development Planning Department State Grid Hunan Electric Power Company Limited Changsha China Institute of Economic Research State Grid Hunan Electric Power Company Limited Changsha China Institute of Economic Research State Grid Xiangtan Electric Power Company Limited Changsha China R&D Department Three Gorges Intelligent Industrial Control Technology Co. Ltd. Wuhan China

Compared with other ways of heat dissipation, the capability of the air cooling heavily depends on the geometric forms of the cells’ cases, the arrangements of the cells and the boundary conditions, since the air flow is more arbitrary than other phases. A comprehensive study of the relationship between the cooling effect of the air and the factors lacks fairly until now. An electrochemical-thermal coupled model is proposed to design an air cooling system for lithium-ion cells packs in this study. The temperature, pressure and air velocity distributions are simulated, and the thermal and fluid kinetic behaviors in cells or packs are optimized by using the model. different schemes of geometric forms, air’s velocity and arrangements of cells are compared and analyzed in the process of the heat dissipation. results show that the uniformity of cell temperature throughout the pack was significantly affected by the geometry of cooling ducts. The capability of the heat dissipation in the battery packs is gradually improved when the inlet velocity increases, conversely, if the velocity exceeds 8 m s-1, the heat dissipation capability is not significantly improved. The heat dissipation capability is better in the staggered arrangement of the cells than in aligned arrangement, and the parallel arrangement of batteries is better than the series-wound arrangement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thermal Experiments and Chemical Kinetic Modeling of the in Situ Conversion of Shale Oil and Gas at different Pressures and Heating rates: Significance for Shale Oil Energy

SSRN

引用

SSrN 2022年

作者： Hou, Lianhua Han, Wenxue He, Kun Luo, Xia Lin, Senhu Research Institute of Petroleum Exploration & Development PetroChina Beijing100083 China National Energy Tight Oil & Gas R&D Center Beijing100083 China College of Earth Science and Engineering Shandong University of Science and Technology Qingdao266590 China School of Geosciences China University of Petroleum Shandong Qingdao266580 China

We conducted thermal experiments of hydrocarbon generation under different pressure conditions (7, 14, and 32 MPa). In addition, the geochemical characteristics of the in situ conversion process of shale at different pressures and heating rates were determined. Based on mass balance calculations, hydrocarbon generation kinetic modeling of hydrocarbon generation at different pressures and conversion rates was undertaken to investigate the in situ formation of shale oil and gas. Our study shows that pressure affects the reaction rate constant (ki), which in turn affects the in situ conversion rate of shale oil and gas. At the same heating rate, a higher pressure retards the in situ formation of shale oil and gas, and reduces the oil and gas yield. Under the same pressure conditions, a lower heating rate enhances the in situ formation rate of shale oil and gas. Our study suggests that low pressures and heating rates enhance the in situ formation rate of shale oil and gas. © 2022, The Authors. All rights reserved.

关键词： Heating rate

来源：评论

学校读者我要写书评

暂无评论

Study on the reaction Mechanism of the Khco3 Alkali Activation Process in Black Liquor

SSRN

引用

SSrN 2022年

作者： Lee, Jeong Han Cha, Young Lok Kang, Yong-Mook roh, Kwang Chul Emerging Materials R&D Division Korea Institute of Ceramic Engineering & Technology Jinju-si52851 Korea Republic of Bioenergy Crop Research Institute National Institute of Crop Science Rural Development Administration Muan58545 Korea Republic of Department of Materials Science and Engineering Korea University Seoul02841 Korea Republic of

The alkaline hydrothermal separation of cellulose is a crucial step in biofuel generation, wherein black liquor containing lignin and alkali is formed as a by-product. This study explored the reaction mechanism of the residual alkali during the activation process. In this reaction, the impregnated K reagent showed unusual behavior owing to its bonding with the lignin structure, which was confirmed by the K 2P peak shift in X-ray photoelectron spectra. This behavior resulted in the formation of a microporous and mesoporous substance with a high surface area of 2146 m 2 g −1 without the requirement for any additional chemical reagents. Furthermore, the activated carbon derived from black liquor possessed outstanding properties, allowing its use in supercapacitors. This work shows that giant-miscanthus-derived black liquor has potential for use as an activated carbon precursor for application in electric double-layer capacitors owing to its superior electrochemical capabilities. © 2022, The Authors. All rights reserved.

关键词： Activated carbon

来源：评论

学校读者我要写书评

暂无评论

Haloscope searching for dark photons in the Q band with a novel coupling tuning structure

引用

Physical review d 2025年第9期111卷 095022-095022页

作者： Yue Yin runqi Kang Man Jiao Xing rong Laboratory of Spin Magnetic Resonance School of Physical Sciences Anhui Province Key Laboratory of Scientific Instrument Development and Application University of Science and Technology of China Hefei 230026 China Hefei National Laboratory University of Science and Technology of China Hefei 230088 China Institute for Advanced Study in Physics Zhejiang University Hangzhou 310027 China Institute of Quantum Sensing and School of Physics Zhejiang University Hangzhou 310027 China Zhejiang Key Laboratory of R&D and Application of Cutting-edge Scientific Instruments Zhejiang University Hangzhou 310027 China

Laboratory searching for dark matter is crucial for understanding several fundamental conundrums in physics and cosmology. Most cavity-based haloscope searches focus on the frequency range below 10 GHz, while the parameter space with higher frequency remains rarely explored, due to the challenges lying in the fabrication of microwave cavities. Here we report the first Q band haloscope searching for dark photons with a 33.141 GHz cavity. A novel coupling tuning structure separated from the cavity was designed so as not to degrade the quality factor of the cavity. We have established the most stringent constraints χ<2.5×10−12 at a confidence level of 90% in the frequency range from 33.139 to 33.143 GHz, corresponding to the mass of dark photons ranging from 137.05 to 137.07 μeV. The results surpass the previous astronomical constraints by nearly three orders of magnitude. This work has demonstrated the feasibility of dark matter haloscopes in the Q band. In the future, the constraints can be further improved by more than one order of magnitude through low-temperature experiments, and the setup can be extended to search for axions, axion-like particles, and high-frequency gravitational waves.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning with deep Learning Approach for Cyber Security Threats Prevention Model

Machine Learning with Deep Learning Approach for Cyber Secur...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： S. Jagan rajesh Pokhariyal Kirti Mahajan Ch L N deepika P. deva Sudha Abhradita dutta Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Information Technology Institute of Management & Entrepreneurship Development Bharati Vidyapeeth Deemed University Pune Department : SOCC Kluniversity Department of Computer Science and Engineering St. Martins Engineering College Secunderabad Telangana Department of Mechanical Engineering New Horizon College of Engineering Bangalore

The need for effective cybersecurity solutions has never been greater than in today's world of constant digitalization and interconnection. This study explores the use of deep learning to the creation of a model for preventing cyber security threats using machine learning. The model is meant to successfully identify and prevent cyber-attacks by analysing network traffic and system behaviour using a convolutional neural network (CNN) linked with variationalautoencoders (VAEs). This study's findings illustrate the model's competency in threat recognition with a high degree of accuracy, precision, and recall. Actively monitoring and evaluating network data, providing automatic threat identification and response, further demonstrates its usefulness when used in the real world. This work sets the path for future developments in quantum-resistant encryption, adversarial machine learning studies, deep learning architectures, autonomous cybersecurity systems, explainable AI, and global threat intelligence cooperation. These new approaches have great potential for paving the way towards a more secure and resilient cyber future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Safety Assessment of Algae Protein from Picochlorum for Human Consumption

引用

regulatory toxicology and pharmacology : rTP 2024年 162卷 105753页

作者： Tomal dattaroy Manish r Shukla Synthetic Biology Research and Development Group Reliance Industries Limited Reliance Technology Group R&D Centre Reliance Corporate Park Ghansoli Navi Mumbai Maharashtra 400701 India. Electronic address: Tomal.dattaroy@***. Synthetic Biology Research and Development Group Reliance Industries Limited Reliance Technology Group R&D Centre Reliance Corporate Park Ghansoli Navi Mumbai Maharashtra 400701 India. Electronic address: Manish.R.Shukla@***.

The current trend happens to be that consumers are seeking nourishing, high quality sustainable protein sources to meet their nutritional needs, thus establishing a clear intent to broaden their protein horizon. Microalgae protein holds great promise in becoming the next vegan protein option. In the present study, protein extracted from the microalga Picochlorum maculatum has been thoroughly evaluated for its safety for human consumption through a battery of in-vivo and in-vitro tests. Bacterial reverse mutation assay indicates that the test substance is non-mutagenic and studies comprising of in-vitro chromosomal aberration test and the in-vivo mammalian micronucleus test showed that the test item is non-clastogenic, and therefore, lacks genotoxicity. Based the results of an acute oral toxicity study, the test item can be classified as "Category 5" as designated in a globally harmonized system for classification of chemicals. Further, 28-day and 90-day repeated dose oral toxicity studies did not result in any mortality or morbidity throughout the experimental period; none of the animal groups used in the study showed any abnormal clinical signs, establishing a "No Observed Adverse Effect Level" of Algae Protein Powder at 3000 mg kg bw. Moreover, the test item exhibited a positive impact on growth in test animals. Computational studies established extremely low allergenic potential of the test item.

关键词： Picochlorum maculatum algae protein genotoxicity oral toxicity safety

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Security in IoT using Secure Hash Cryptography Algorithm with double Encryption (SHCA-dE)

Enhancement of Security in IoT using Secure Hash Cryptograph...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： G. Uganya d. rajalakshmi ramarao Vangapandu M. dinesh Jayant Giri Mahmoud Odeh Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai Department of Computer Science and Engineering Vignan's Institute of Engineering for Women Vishakhapatnam Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur Division of Research and Development Lovely Professional University Phagwara India Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The “Internet of things” is the developing technology to transfer the world into smart innovation. “IoT” security is the most problematic issue in recent applications due to its properties including ‘centralized architecture’, ‘limited capacity devices’, and ‘ambiguity’. So, blockchain with “IoT” applications provides secure data communication compared to traditional “IoT” applications. Blockchain is a recent growing technology that has features including ‘decentralized structure’, ‘transparency’, ‘immutable records’, ‘increased capacity’, and ‘quick backtracks’. The ‘cryptography hash algorithm’ is very important to provide secure data transmission. It converted the different size input to fixed-size unalterable output to enhance the security. But still, it needs efficient algorithm to secure data transmission with safeguard of private key. The objective of this paper is to propose a secure hash cryptography algorithm with double encryption (SHCA-dE) to protect the private key message. Then, this proposed algorithm has been analyzed with Md5, SHA-256, and SHA3-512. From this analysis, the SHA3-512 performs well with proposed algorithm.

关键词： Hash functions Technological innovation Accuracy Public key cryptography Blockchains Encryption Internet of Things data communication

来源：评论

学校读者我要写书评

暂无评论

dual-porous ZIF-8 heterogeneous catalysts with increased reaction sites for efficient PET glycolysis

引用

Chemosphere 2024年 364卷 143187页

作者： Han, Nara Lee, Kyunghan Lee, Jieun Jo, Jin Hui An, Eun Ji Lee, Gicheon Chi, Won Seok Lee, Chanmin School of Polymer Science and Engineering Chonnam National University 77 Yongbong-ro Buk-gu Gwangju61186 Korea Republic of 291 Daehak-ro Yuseong-gu Daejeon Korea Republic of Department of Polymer Engineering Graduate School Chonnam National University 77 Yongbong-ro Buk-gu Gwangju61186 Korea Republic of Green Circulation R&D Department Research Institute of Sustainable Development Technology Korea Institute of Industrial Technology 89 Yangdaegiro-gil Ipjan-myeon Seobuk-gu Chungcheongnam-do Cheonan-si31056 Korea Republic of Hydrogen·Fuel Cell Research Group Eco-friendly Power Lab Korea Construction Equipment Technology Institute 36 Sandan-ro Gunsan-si Jeollabuk-do54004 Korea Republic of

Poly (ethylene terephthalate) (PET) has been widely used for drink bottles, food packing, films, and fibers, resulting in millions of tons of waste PET. Less than 10% of that waste is recycled, and the rest is discarded or incinerated. Waste PET upcycling employs chemical recycling and particularly glycolysis to create the bis(2-hydroxyethyl) terephthalate (BHET) monomer. Herein, we report a dual-porous zeolitic imidazolate framework-8 nanoparticle (dPZIF-8) heterogeneous catalyst for efficient PET glycolysis. The dPZIF-8 nanoparticles were prepared using a triethylamine modulator, which can control the nucleation and growth mechanisms of the ZIF-8 nanoparticles. The dPZIF-8 nanoparticles include both intrinsic micropores and particle-particle adhesion-induced mesopores that can provide a larger external surface area of the zinc sites in the ZIF-8 architecture. The PET glycolysis catalyzed by dPZIF-8 at 180 °C and 1 atm for 4 h shows a PET conversion of 91.7% and a BHET yield of 76.1%, the latter particularly being much higher than with a traditional heterogeneous ZIF-8 catalyst. This dual-porous structure rational design strategy can be versatile for other metal–organic frameworks (MOFs) to increase the interfacial catalytic reaction sites between the metal–organic framework and the polymer, enhancing the PET depolymerization performance and efficiency. © 2024 Elsevier Ltd

关键词： Catalysis

来源：评论

学校读者我要写书评

暂无评论

Leveraging Augmented and Virtual reality in Conjunction with Artificial Intelligence, 5G, and Edge Computing to Transform Immersive Experiences

Leveraging Augmented and Virtual Reality in Conjunction with...

引用

Smart Technologies, Communication and robotics (STCr)

作者： G.Palanikumar V.Samuthira Pandi S.Banumathi G. Karthikeyan Jayant Giri Maram Y. Al-Safarini Department of Mathematics Sri Venkateswara College of Engineering (SVCE) Tamil Nadu Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of Computer Science Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Veltech University - Deemed to be University Chennai Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur. Division of Research and Development Lovely Professional University Phagwara India Computer Science Department Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

Ar, Vr, AI, 5G, and Edge Computing are converging to reshape immersive experiences across industries in terms of content creation, content delivery and content interaction. Ar and Vr have achieved remarkable progress so far in fields like the gaming industry, education, healthcare, and entertainment, and are already delivering immersive and realistic environments for users. Nonetheless, the real magic happens with their combination with AI, 5G and Edge Computing, which makes immersive experiences perform, scale and respond better to interactions. AI and Ar/Vr create a symbiotic relationship where AI designs intelligent interaction, personalizes user experience, and aids decision-making in Ar/Vr environments by analyzing user behaviors and context in real-time. Simultaneously, the rollout of 5G networks will provide ultra-low latency, high-speed data transfer, and immense connectivity, all of which are critical to rendering high-quality asynchronous immersive experiences. By processing data to the edge, close to the end-user, Edge Computing cuts latency to the minimal level and makes sure that interactions are fast and seamless enough to make immersive applications work. This paper discusses the convergence of Ar/Vr with the other digital technologies such as AI, 5G, and Edge computing and its impact on industries leading to more immersive, scalable and personalized experiences. In this report, we explore how these technologies make one another better, resulting in breakthroughs across fields like telemedicine, remote education, autonomous driving, and even virtual tourism. We also highlight the implications of this convergence in terms of data security, privacy considerations, and the requirements for computational resources. This paper encapsulates those concepts, discussing what comes next and what role immersive technologies will play in the next generation of human-computer interactions. Thus, the fusion of Ar/Vr, AI, 5G, and Edge Computing is enhancing user exp

关键词： 5G mobile communication Telemedicine Education Entertainment industry Medical services rendering (computer graphics) real-time systems Artificial intelligence Autonomous vehicles Edge computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：