检索结果-南通市图书馆

Cybersecurity 2024年第2期7卷 13-27页

作者： B S Sharmila Rohini Nagapadma Depatment of Electronics and communication Engineering The National Institute of EngineeringMysoreKarnataka 570008India

In recent years,many researchers focused on unsupervised learning for network anomaly detection in edge devices to identify attacks.The deployment of the unsupervised autoencoder model is computationally expensive in resource-constrained edge devices.This study proposes quantized autoencoder(QAE)model for intrusion detection systems to detect anomalies.QAE is an optimization model derived from autoencoders that incorporate pruning,clustering,and integer quantization techniques.Quantized autoencoder uint8(QAE-u8)and quantized autoencoder float16(QAE-f16)are two variants of QAE built to deploy computationally expensive Al models into Edge devices.First,we have generated a Real-Time Internet of Things 2022 dataset for normal and attack traffic.The autoencoder model operates on normal traffic during the training phase.The same model is then used to reconstruct anomaly traffic under the assumption that the reconstruction error(RE)of the anomaly will be high,which helps to identify the attacks.Furthermore,we study the performance of the autoencoders,QAE-u8,and QAE-f16 using accuracy,precision,recall,and F1 score through an extensive experimental study.We showed that QAE-u8 outperforms all other models with a reduction of 70.01%in average memory utilization,92.23%in memory size compression,and 27.94%in peak CPU utilization.Thus,the proposed QAE-u8 model is more suitable for deployment on resource-constrained IoT edge devices.

关键词： IoT constrained system

Cross-Modal Consistency with Aesthetic Similarity for Multimodal False Information Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2723-2741页

作者： Weijian Fan Ziwei Shi State Key Laboratory of Media Convergence and communication Communication University of ChinaBeijing100024China Software Research institute China United Network Communication Group Co.Ltd.Beijing100024China

With the explosive growth of false information on social media platforms, the automatic detection of multimodalfalse information has received increasing attention. Recent research has significantly contributed to multimodalinformation exchange and fusion, with many methods attempting to integrate unimodal features to generatemultimodal news representations. However, they still need to fully explore the hierarchical and complex semanticcorrelations between different modal contents, severely limiting their performance detecting multimodal falseinformation. This work proposes a two-stage detection framework for multimodal false information detection,called ASMFD, which is based on image aesthetic similarity to segment and explores the consistency andinconsistency features of images and texts. Specifically, we first use the Contrastive Language-Image Pre-training(CLIP) model to learn the relationship between text and images through label awareness and train an imageaesthetic attribute scorer using an aesthetic attribute dataset. Then, we calculate the aesthetic similarity betweenthe image and related images and use this similarity as a threshold to divide the multimodal correlation matrixinto consistency and inconsistencymatrices. Finally, the fusionmodule is designed to identify essential features fordetectingmultimodal false information. In extensive experiments on four datasets, the performance of the ASMFDis superior to state-of-the-art baseline methods.

关键词： Social media false information detection image aesthetic assessment cross-modal consistency

Whispering-gallery-mode barcode-based broadband sub-femtometer-resolution spectroscopy with an electro-optic frequency comb

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advanced Photonics 2024年第1期6卷 115-125页

作者： Bingxin Xu Yangyang Wan Xinyu Fan Zuyuan He Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and NetworksDepartment of Electronic EngineeringShanghaiChina Max-Planck institute of Quantum Optics Hans-Kopfermann-Straûe 185748 GarchingGermany

Spectroscopy is the basic tool for studying molecular physics and realizing biochemical sensing.However,it is challenging to realize sub-femtometer resolution spectroscopy over broad bandwidth.Broadband and high-resolution spectroscopy with calibrated optical frequency is demonstrated by bridging the fields of speckle pattern and electro-optic frequency comb.A wavemeter based on a whispering-gallery-mode barcode is proposed to link the frequencies of a probe continuous-wave laser and an ultrastable laser.The ultrafine electro-optic comb lines are generated from the probe laser to record spectrum of sample with sub-femtometer resolution.Measurement bandwidth is a thousandfold broader than comb bandwidth,by sequentially tuning the probe laser while its wavelength is determined.This approach fully exploits the advantages of two fields to realize 0.8-fm resolution with a fiber laser and 80-nm bandwidth with an external cavity diode laser.The spectroscopic measurements of an ultrahigh Q-factor cavity and gas molecular absorption are experimentally demonstrated.The compact system,predominantly constituted by few-gigahertz electronics and telecommunication components,shows enormous potential for practical spectroscopic applications.

关键词： frequency comb reconstructive wavemeter spectroscopy

Emergence of machine language: towards symbolic intelligence with neural networks

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第4期11卷 27-30页

作者： Yuqi Wang Xu-Yao Zhang Cheng-Lin Liu Tieniu Tan Zhaoxiang Zhang State Key Laboratory of Multimodal Artificial Intelligence systems Institute of AutomationChinese Academy of Sciences

Representation learning is a core issue in artificial intelligence (AI). Currently,there exists a disparity in the choice of representation between humans and machines. Humans rely on discrete language for communicati...

关键词：

Dielectric barrier discharge plasma-assisted catalytic ammonia synthesis:synergistic effect of Ni-MOF-74 catalyst and nanosecond pulsed plasma

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Plasma Science and Technology 2024年第6期26卷 40-49页

作者：徐晓芳孙萌宋勤龙吴璇陈冲冲陈强张海宝 Laboratory of Plasma Physics and Materials Beijing Institute of Graphic CommunicationBeijing 102600People’s Republic of China

Ammonia is one of the most important chemical raw materials in both manufacture and life of human.Traditionally Haber-Bosch method for ammonia synthesis involves high temperature and high pressure conditions,leading to significant energy consumption and environmental pollution.Non-thermal plasma(NTP) is a promising alternative approach to ammonia synthesis at low temperature and atmospheric pressure.In this study,the synergistic effect of nanosecond pulsed dielectric barrier discharge(np-DBD) and Ni-MOF-74 catalyst was investigated in ammonia synthesis by utilizing nitrogen and hydrogen as feedstock.The results demonstrated that the plasma catalytic-synthesis process parameters play a crucial role in the synthesis process of ammonia.The highest ammonia synthesis rate of 5145.16 μmol·g^(-1)·h^(-1)with an energy efficiency of 1.27 g·kWh^(-1)was observed in the presence of the Ni-MOF-74 catalyst,which was3.7 times higher than that without Ni-MOF-74 catalyst.The synergistic effect of Ni-MOF-74catalyst and nanosecond pulsed plasma was explored by in-situ plasma discharge diagnostics.

关键词： ammonia synthesis low-temperature plasma nanosecond pulsed power source Ni-MOF-74

Preparation of palladium-based catalyst by plasma-assisted atomic layer deposition and its applications in CO_(2) hydrogenation reduction

在线全文

学校读者我要写书评

暂无评论

Plasma Science and Technology 2024年第6期26卷 31-39页

作者：唐守贤田地李筝王正铎刘博文程久珊刘忠伟 Laboratory of Plasma Physics and Materials Beijing Institute of Graphic CommunicationBeijing 102600People’s Republic of China

Supported Pd catalyst is an important noble metal material in recent years due to its high catalytic performance in CO_(2)hydrogenation.A fluidized-bed plasma assisted atomic layer deposition(FP-ALD) process is reported to fabricate Pd nanoparticle catalyst over γ-Al_(2)O_(3)or Fe_(2)O_(3)/γ-Al_(2)O_(3)support,using palladium hexafluoroacetylacetonate as the Pd precursor and H_(2)plasma as counter-reactant.Scanning transmission electron microscopy exhibits that highdensity Pd nanoparticles are uniformly dispersed over Fe_(2)O_(3)/γ-Al_(2)O_(3)support with an average diameter of 4.4 nm.The deposited Pd-Fe_(2)O_(3)/γ-Al_(2)O_(3)shows excellent catalytic performance for CO_(2)hydrogenation in a dielectric barrier discharge reactor.Under a typical condition of H_(2)to CO_(2)ratio of 4 in the feed gas,the discharge power of 19.6 W,and gas hourly space velocity of10000 h^(-1),the conversion of CO_(2)is as high as 16.3% with CH_(3)OH and CH4selectivities of 26.5%and 3.9%,respectively.

关键词： atomic layer deposition CO_(2)hydrogenation palladium based catalyst

Time and Space Efficient Multi-Model Convolution Vision Transformer for Tomato Disease Detection from Leaf Images with Varied Backgrounds

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 117-142页

作者： Ankita Gangwar Vijaypal Singh Dhaka Geeta Rani Shrey Khandelwal Ester Zumpano Eugenio Vocaturo Department of Computer and communication Engineering Manipal University JaipurJaipurIndia Department of IoT and Intelligent systems Manipal University JaipurJaipurIndia Department of Computer Engineering ModellingElectronics and Systems(DIMES)University of CalabriaRende(Cosenza)Italy National Research Council Institute of Nanotechnology(NANOTEC)Rende(Cosenza)Italy

A consumption of 46.9 million tons of processed tomatoes was reported in 2022 which is merely 20%of the total consumption.An increase of 3.3%in consumption is predicted from 2024 to 2032.Tomatoes are also rich in iron,potassium,antioxidant lycopene,vitamins A,C and K which are important for preventing cancer,and maintaining blood pressure and glucose levels.Thus,tomatoes are globally important due to their widespread usage and nutritional value.To face the high demand for tomatoes,it is mandatory to investigate the causes of crop loss and minimize them.Diseases are one of the major causes that adversely affect crop yield and degrade the quality of the tomato fruit.This leads to financial losses and affects the livelihood of farmers.Therefore,automatic disease detection at any stage of the tomato plant is a critical issue.Deep learning models introduced in the literature show promising results,but the models are difficult to implement on handheld devices such as mobile phones due to high computational costs and a large number of parameters.Also,most of the models proposed so far work efficiently for images with plain backgrounds where a clear demarcation exists between the background and leaf region.Moreover,the existing techniques lack in recognizing multiple diseases on the same leaf.To address these concerns,we introduce a customized deep learning-based convolution vision transformer model.Themodel achieves an accuracy of 93.51%for classifying tomato leaf images with plain as well as complex backgrounds into 13 categories.It requires a space storage of merely 5.8 MB which is 98.93%,98.33%,and 92.64%less than stateof-the-art visual geometry group,vision transformers,and convolution vision transformermodels,respectively.Its training time of 44 min is 51.12%,74.12%,and 57.7%lower than the above-mentioned models.Thus,it can be deployed on(Internet of Things)IoT-enabled devices,drones,or mobile devices to assist farmers in the real-time monitoring of tomato crops.The periodicmonitoring promotes timely action to prev

关键词： Tomato disease transformer deep learning mobile devices

Tunable polarization holographic gratings obtained by varying the ratio of intensities of the recording beams

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Photonics Research 2024年第4期12卷 749-754页

作者： HONG CHEN ZIYAO LYU CHANGSHUN WANG State Key Laboratory of Advanced Optical communication systems and Networks School of Physics and AstronomyShanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Space-Ground Integrated Information Technology Beijing Institute of Satellite Information EngineeringBeijing 100095China

Polarization holography has been extensively applied in many fields, such as optical science, metrology, and biochemistry, due to its property of polarization modulation. However, the modulated polarization state of diffracted light corresponds strictly to that of incident light one by one. Here, a kind of tunable polarization holographic grating has been designed in terms of Jones matrices, and intensity-based polarization manipulation has been realized experimentally. The proposed tunable polarization holographic grating is recorded on an azobenzene liquid-crystalline film by a pair of coherent light beams with orthogonal polarization states and asymmetrically controlled intensities. It is found that the diffracted light can be actively manipulated from linearly to circularly polarized based on the light intensity of the recording holographic field when the polarization state of incident light keeps constant. Our work could enrich the field of light manipulation and holography.

关键词： holographic recording Polarization

LiDAR-based estimation of bounding box coordinates using Gaussian process regression and particle swarm optimization

在线全文

学校读者我要写书评

暂无评论

Biomimetic Intelligence & Robotics 2024年第1期4卷 24-35页

作者： Vinodha K. E.S.Gopi Tushar Agnibhoj Department of Electronics and communication Engineering National Institute of Technology TiruchirappalliTamil Nadu620015India

Camera-based object tracking systems in a given closed environment lack privacy and confidentiality.In this study,light detection and ranging(LiDAR)was applied to track objects similar to the camera tracking in a closed environment,guaranteeing privacy and confidentiality.The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios.In Scenario I,the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface,achieved by analyzing LiDAR data collected from several locations within the closed environment.Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single,fixed location.Real-time experiments are conducted with human subjects navigating predefined paths.Three individuals move within an environment,while LiDAR,fixed at the center,dynamically tracks and identifies their locations at multiple instances.Results demonstrate that a single,strategically positioned LiDAR can adeptly detect objects in motion around it.Furthermore,this study provides a comparison of various regression techniques for predicting bounding box coordinates.Gaussian process regression(GPR),combined with particle swarm optimization(PSO)for prediction,achieves the lowest prediction mean square error of all the regression techniques examined at 0.01.Hyperparameter tuning of GPR using PSO significantly minimizes the regression error.Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls,surveillance systems,and various Internet of Things scenarios.

关键词： LiDAR Data acquisition Bounding box Gaussian process regression Particle swarm optimization(PSO)

State-Based Opacity Verification of Networked Discrete Event systems Using Labeled Petri Nets

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1274-1291页

作者： Yifan Dong Naiqi Wu Zhiwu Li The authors are with the institute of systems Engineering Macao University of Science and TechnologyTaipa 999078MacaoChina

The opaque property plays an important role in the operation of a security-critical system,implying that pre-defined secret information of the system is not able to be inferred through partially observing its behavior.This paper addresses the verification of current-state,initial-state,infinite-step,and K-step opacity of networked discrete event systems modeled by labeled Petri nets,where communication losses and delays are considered.Based on the symbolic technique for the representation of states in Petri nets,an observer and an estimator are designed for the verification of current-state and initial-state opacity,respectively.Then,we propose a structure called an I-observer that is combined with secret states to verify whether a networked discrete event system is infinite-step opaque or K-step opaque.Due to the utilization of symbolic approaches for the state-based opacity verification,the computation of the reachability graphs of labeled Petri nets is avoided,which dramatically reduces the computational overheads stemming from networked discrete event systems.

关键词： infinite system symbolic