检索结果-内蒙古大学图书馆

Large margin deep embedding for aesthetic image classification

science China(information sciences) 2020年第1期63卷 229-231+259-264页

作者： Guanjun GUO Hanzi WANG Yan YAN Liming ZHANG Bo LI Fujian Key Laboratory of Sensing and Computing for Smart City School of Information Science and EngineeringXiamen University Faculty of Science and Technology University of Macau Beijing Key Laboratory of Digital Media School of Computer Science and EngineeringBeihang University

Dear editor,The problem of aesthetic image classification has attracted much attention during the past few years. The recently proposed methods [1–4] based on the deep convolutional neural network (CNN)[5,6]have achi... 详细信息

关键词： net CNN image Large margin deep embedding for aesthetic image classification

来源：评论

学校读者我要写书评

暂无评论

SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network

arXiv

引用

arXiv 2024年

作者： Guo, Weiyu Sun, Ying Xu, Yijie Qiao, Ziyue Yang, Yongkui Xiong, Hui Artificial Intelligence Thrust HKUST Guangzhou China School of Computing and Information Technology Great Bay University China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Department of Computer Science and Engineering HKUST Hong Kong Guangzhou HKUST Fok Ying Tung Research Institute China

Surface electromyography (sEMG) based gesture recognition offers a natural and intuitive interaction modality for wearable devices. Despite significant advancements in sEMG-based gesture recognition models, existing methods often suffer from high computational latency and increased energy consumption. Additionally, the inherent instability of sEMG signals, combined with their sensitivity to distribution shifts in real-world settings, compromises model robustness. To tackle these challenges, we propose a novel SpGesture framework based on Spiking Neural Networks, which possesses several unique merits compared with existing methods: (1) Robustness: By utilizing membrane potential as a memory list, we pioneer the introduction of Source-Free Domain Adaptation into SNN for the first time. This enables SpGesture to mitigate the accuracy degradation caused by distribution shifts. (2) High Accuracy: With a novel Spiking Jaccard Attention, SpGesture enhances the SNNs’ ability to represent sEMG features, leading to a notable rise in system accuracy. To validate SpGesture’s performance, we collected a new sEMG gesture dataset which has different forearm postures, where SpGesture achieved the highest accuracy among the baselines (89.26%). Moreover, the actual deployment on the CPU demonstrated a latency below 100ms, well within real-time requirements. This impressive performance showcases SpGesture’s potential to enhance the applicability of sEMG in real-world scenarios. The code is available at https://***/guoweiyu/SpGesture/. © 2024, CC BY-NC-ND.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

IoT based Monitoring of Mushroom

IoT based Monitoring of Mushroom

引用

Sustainable computing and Data Communication Systems (ICSCDS), International Conference on

作者： J. Lysa Eben Chamandeep Kaur Mathews T Thelly Parimita Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Information Technology Jazan University Jazan Saudi Arabia Department of Botany Kuriakose Elias College Mannanam India Agricultural Engineering Sam Higginbottom University of Agriculture Technology & Sciences Prayagraj India

Most of India’s population relies on farming for their livelihood. Every year brings new advances in agricultural technology. The use of wireless sensors in contemporary agriculture is crucial. The employment of wireless sensors across a wide range of agricultural applications has a profoundly favourable effect on crop productivity and economic efficiency. The mushroom business is still relatively young and modest compared to other sectors of India’s agricultural market. The white button mushroom is India’s most commercially significant fungus and is a global favourite. It may be grown anywhere with a suitable climate and soil, but most of the world’s supply comes from North India in the winter. For mycelia to flourish, the ideal temperature range is between 22 and 25 degrees Celsius. In contrast, the sweet spot for developing fruit bodies is between 14 and 18 degrees Celsius with high relative humidity. Equipment for maintaining a steady temperature and pasteurising the mushrooms, should be present in the rooms used for growing. The primary objective of this study is to automate the mushroom production plant and keep track of the crop room’s environmental state to reduce the amount of human care required for the mushroom plant. The Internet of Things has also modernized agriculture industries, creating an environmental monitoring and regulating system that is used in the mushroom farm in this work. Using the Speak internet platform, users may monitor ecological conditions in a mushroom farm on their Android mobile, including the ambient temperature, relative humidity, carbon dioxide level, and light intensity. The Arduino prototype platform is employed as the sensors station’s controller, ensuring that the plant parameters are within the user-specified range. Using a pair of low-power ESP8266 as Wi-Fi modems, the current parameter status is relayed to a distant monitoring station. The integrated Arduino uses the programming environment to write the controller’s cod

关键词： Temperature measurement Temperature sensors Wireless communication Temperature distribution Wireless sensor networks Soil moisture Crops

来源：评论

学校读者我要写书评

暂无评论

DE3-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks

arXiv

引用

arXiv 2024年

作者： He, Jianing Zhang, Qi Ding, Weiping Miao, Duoqian Zhao, Jun Hu, Liang Cao, Longbing The School of Computer Science Tongji University Shanghai201804 China The School of Information Science and Technology Nantong University Nantong226019 China The National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The DataX Research Centre School of Computing Macquarie University SydneyNSW2109 Australia

Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. However, most existing early exiting methods only consider local information from an individual test sample to determine their exiting indicators, failing to leverage the global information offered by sample population. This leads to suboptimal estimation of prediction correctness, resulting in erroneous exiting decisions. To bridge the gap, we explore the necessity of effectively combining both local and global information to ensure reliable early exiting during inference. Purposefully, we leverage prototypical networks to learn class prototypes and devise a distance metric between samples and class prototypes. This enables us to utilize global information for estimating the correctness of early predictions. On this basis, we propose a novel Distance-Enhanced Early Exiting framework for BERT (DE3-BERT). DE3-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions. Extensive experiments on the GLUE benchmark demonstrate that DE3-BERT consistently outperforms state-of-the-art models under different speed-up ratios with minimal storage or computational overhead, yielding a better trade-off between model performance and inference efficiency. Additionally, an in-depth analysis further validates the generality and interpretability of our method. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Crypto Bank: Cryptocurrency Wallet Based on Blockchain 6th

Crypto Bank: Cryptocurrency Wallet Based on Blockchain

引用

6th International Conference on Recent Trends in Image Processing and Pattern Recognition, RTIP2R 2023

作者： Tripathi, Ashish Choudhary, Arjun Arora, Sandeep Kumar Arora, Gautam Shakya, Gargi Rajwanshi, Bhavya School of Computing Science and Engineering Galgotias University Greater Noida India Centre for Cyber Security Sardar Patel University of Police Security and Criminal Justice Jodhpur India Lovely Professional University Punjab India Department of Information Technology GL Bajaj Institute of Technology and Management Greater Noida India

ISBN: (纸本)9783031530845

Cryptocurrency is a type of money that only exists in digital form and is protected by encryption. It is sometimes referred to as digital cash or virtual currency. It is decentralized, meaning it runs without a central bank, and transactions are recorded on a public ledger called a blockchain. Bitcoin, which Satoshi Nakamoto developed in 2009 using his renowned whitepaper on blockchain technology, was the first cryptocurrency ever. The genuine identity of Nakamoto or the organization using this alias is still unknown to us. However, Bitcoin was not the very first cryptocurrency. The development of a digital form of money has been the subject of numerous projects and attempts in the late 1980s and early 1990s. One illustration is Blinded Cash. Developed in 1989 by an American named David Chaum, Blinded Cash is a gambling game. Due to his thorough contributions to the subject of cryptography, Chaum established a solid professional reputation. The goal of the scientific discipline of cryptography is to create methods that would only allow the message’s sender and recipient to read it. The present issue with bitcoin transactions is that consumers do not have complete control over their own cryptocurrency instead it is stored in the wallet’s smart contract so the wallet has control over the consumer’s currency. With the ability to hold cryptocurrencies within your own account, the proposed work concentrates on streamlining cryptocurrency payments. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Augmented reality-based solar system for e-magazine with 3-D audio effect

引用

International Journal of Simulation and Process Modelling 2020年第6期15卷 524-534页

作者： Martin Sagayam, K. Timothy, Alex J. Ho, Chiung Ching Henesey, Lawrence Edward Bestak, Robert Department of Electronics and Communication Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India Department of Computing and Information Systems School of Science and Technology Sunway University Malaysia School of Computing Blekinge Institute of Technology Sweden Department of Telecommunication Engineering Czech Technical University in Prague Prague Czech Republic

Augmented reality (AR) is the newest technology that can be applied to computer vision, audio, video and other sensor-based input projects into 3D vision. It is the backbone for all specialisation of science, medical and engineering concepts. Currently, the reading and learning method through AR-based approaches are quite highly intensive than the existing methods such as papers, books and magazines. This strategy is more expensive but it is more interactive to the user in understanding the root concepts in an effective manner. This paper explores the experiment on solar system revolution pattern along with 3D audio effect in spatial dimension. This novel idea inculcates more vibrancy in the current generation of students to understand the concepts with the clear illustrations and demonstrations. © 2020 Inderscience Enterprises Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Navigating Flood Prediction Complexities: Harnessing Fuzzy Expert Systems and Real-Time Sensor Integration 7

Navigating Flood Prediction Complexities: Harnessing Fuzzy E...

引用

7th International Conference on Image information Processing, ICIIP 2023

作者： Madasamy, Sridhar Praveena, K.V.S. Sreedevi, Vaitla Basi Reddy, A. Nirosha, Ch. Naik, S. K. Lokesh Cognizant Technology Solution 500 Frank W. Burr Boulevard TeaneckNJ07666 United States Vignan's Institute of Information Technology Department of Management Studies Andhra Pradesh Visakhapatnam India Department of Cse Maisammaguda Kompally Telagana State Secunderabad500100 India Mohan Babu University School of Computing Department of Computer Science And Engineering Andhra Pradesh Tirupati India St. Martin's Engineering College Department of Eee Secunderabad Telangana Dhulapally India Mlr Institute of Technology Department of Cse Hyderabad Dundigal India

ISBN: (纸本)9798350371406

Fuzzy Expert Systems (FESs) stand at the forefront as a pioneering amalgamation of fuzzy logic and expert systems, constituting a robust framework primed for intricate decision-making processes. Within this context, this work presents an innovative paradigm that harnesses the profound capabilities of FESs to elevate the precision of flood prediction through the seamless integration of real-time sensor data. The domain of flood prediction takes on paramount significance in the realm of disaster management, necessitating the timely and accurate identification of potential risks. By orchestrating the nuanced cognitive processes of fuzzy logic with the specialized knowledge inherent to expert systems, the methodology introduced herein serves as a tangible demonstration of FESs' potential to fundamentally reshape the landscape of flood prediction strategies. This pioneering approach, empowered by the dynamic fusion of disparate fields, stands as a testament to the evolving nature of predictive analytics. By effectively leveraging real-time sensor data, the developed system adeptly maneuvers through the intricate dynamics of flooding events, culminating in predictions that transcend traditional forecasts. The outcomes of these predictions, actionable in nature, engender a profound sense of empowerment in the realm of proactive decision-making, thereby minimizing the potential ramifications of impending flood disasters. Within this work, a thorough examination unfolds, encompassing the foundational underpinnings, the meticulous design, and the execution of the fuzzy expert system. Furthermore, the implications of this approach are rigorously tested through its application in real-world flood scenarios, providing tangible evidence of its efficacy. This holistic exploration thus unravels the transformative potential of FESs in the context of augmenting flood prediction precision, thus forming a cornerstone of disaster management frameworks that embrace resilience and adaptab

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Optimizing wastewater treatment plant operations: a machine learning approach for energy consumption and climate dynamics analysis

Optimizing wastewater treatment plant operations: a machine ...

引用

8th IET Smart Cities Symposium (SCS 2024)

作者： Mahmoud Elshabrawy Faris H. Rizk Ahmed Mohamed Zaki Marwa M. Eid Ali E. Takieldeen Abdelhameed Ibrahim Abdelaziz A. Abdelhamid Laith Abualigah El-Sayed M. El-kenawy Computer Science and Intelligent Systems Research Center Blacksburg 24060 Virginia USA Faculty of Artificial Intelligence Delta University for Science and Technology Mansoura 35111 Egypt School of ICT Faculty of Engineering Design and Information & Communications Technology (EDICT) Bahrain Polytechnic PO Box 33349 Isa Town Bahrain Department of Computer Science College of Computing and Information Technology Shaqra University 11961 Shaqra Saudi Arabia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan

ISBN: (数字)9781837243105

Treatment plant optimization plays an important role in the implementation of eco-problem solutions. This article is going to cover how machine learning algorithms can determine energy consumption, climate, and wastewater features of electricity at a wastewater treatment plant in eastern Melbourne from 2014 to 2019. This study uses data obtained from the Melbourne Water and Airport weather station, which are freely available to carry out MLPRegressor, SVM, Linear Regression, Decision Tree Regression, random forest regression, and Nearest Neighbor. Through customary measures like MSE, RMSE, EVS, and others, the best model is adequately identified, which is the Random Forest Regressor model, which has 0.889285. (Lowest MSE) With these results, the plant treatment optimization processes, such as sampling for environmental analysis and the control of energy consumption, have improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced adaptive distributed energy-efficient clustering (EADEEC) for wireless sensor networks

引用

Recent Advances in Computer science and Communications 2020年第2期13卷 168-172页

作者： Poluru, Ravi Kumar Praveen Kumar Reddy, M. Basha, Syed Muzamil Patan, Rizwan Kallam, Suresh School of Computing Science and Engineering VIT University VelloreTamilnadu India School of Computing Science and Engineering Galgotias University Greater NoidaUttar Pradesh India School of Information Technology and Engineering VIT University VelloreTamilnadu India

Background: Recently Wireless Sensor Network (WSN) is a composed of a full number of arbitrarily dispensed energy-constrained sensor nodes. The sensor nodes help in sensing the data and then it will transmit it to sink. The Base station will produce a significant amount of energy while accessing the sensing data and transmitting data. High energy is required to move towards base station when sensing and transmitting data. WSN possesses significant challenges like saving energy and extending network lifetime. In WSN the most research goals in routing protocols such as robustness, energy efficiency, high reliability, network lifetime, fault tolerance, deployment of nodes and latency. Most of the routing protocols are based upon clustering has been proposed using heter-ogeneity. For optimizing energy consumption in WSN, a vital technique referred to as clustering. Methods: To improve the lifetime of network and stability we have proposed an Enhanced Adaptive Distributed Energy-Efficient Clustering (EADEEC). Results: In simulation results describes the protocol performs better regarding network lifetime and packet delivery capacity compared to EEDEC and DEEC algorithm. Stability period and network lifetime are improved in EADEEC compare to DEEC and EDEEC. Conclusion: The EADEEC is overall Lifetime of a cluster is improved to perform the network oper-ation: Data transfer, Node Lifetime and stability period of the cluster. EADEEC protocol evidently tells that it improved the throughput, extended the lifetime of network, longevity, and stability compared with DEEC and EDEEC. © 2020 Bentham science Publishers.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Image Authentication Method Based on Phase-Only Hologram and Logistic Map

SSRN

引用

SSRN 2024年

作者： Liansheng, Sui Zishan, Jiang Haiwei, Lu Zhaolin, Xiao Tianyu, Zeng School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Hebei Normal University Shijiazhuang050024 China Hebei Provincial Key Laboratory of Information Fusion and Intelligent Control Shijiazhuang050024 China

An interesting security method for multiple-image authentication scheme is proposed based on computer-generated holograms and logistic map. First, each original image is encoded as the complex-valued hologram under the point light source model. The resulting hologram is then converted to a phase-only hologram using the Floyd-Steinberg dithering algorithm. Second, each phase-only hologram is randomly sampled by the aid of a binary mask. Through the catenation of all selected pixels, a phase-only pixel sequence is formed. Finally, a non-periodic and non-converging sequence generated with logistic map is used to scramble this sequence. After only preserving the phase data of the scrambled sequence, the real-valued ciphertext carrying the information of all original images is obtained. In the process of authentication, although no valid information can be discerned from noisy reconstructed images at a small sampling rate, the verification of original images can be efficiently accomplished using the nonlinear correlation maps. Besides binary masks, the parameters of logistic map are served as secret keys. Due to their high sensitivity, the security of the proposed method is greatly enhanced. The proposed authentication mechanism has been demonstrated to be effective and robust through experiments. To our best knowledge, it is first time to implement multiple-image authentication using phase-only holograms, which can provide a new perspective for optical information security. © 2024, The Authors. All rights reserved.

关键词： Holograms

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：