检索结果-南通市图书馆

U-Net Inspired Deep Neural Network-Based smoke Plume Detection in satellite Images

维普期刊数据库

同方期刊数据库评论

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 779-799页

作者： Ananthakrishnan Balasundaram Ayesha shaik Japmann Kaur Banga Aman Kumar singh Centre for Cyber Physical systems Vellore Institute of Technology(VIT)ChennaiTamil Nadu600127India school of Computer science and Engineering Vellore Institute of Technology(VIT)ChennaiTamil Nadu600127India

Industrial activities, through the human-induced release of Green House Gas (GHG) emissions, have beenidentified as the primary cause of global warming. Accurate and quantitative monitoring of these emissions isessential for a comprehensive understanding of their impact on the Earth’s climate and for effectively enforcingemission regulations at a large scale. This work examines the feasibility of detecting and quantifying industrialsmoke plumes using freely accessible geo-satellite imagery. The existing systemhas so many lagging factors such aslimitations in accuracy, robustness, and efficiency and these factors hinder the effectiveness in supporting timelyresponse to industrial fires. In this work, the utilization of grayscale images is done instead of traditional colorimages for smoke plume detection. The dataset was trained through a ResNet-50 model for classification and aU-Net model for segmentation. The dataset consists of images gathered by European space Agency’s sentinel-2 satellite constellation from a selection of industrial sites. The acquired images predominantly capture scenesof industrial locations, some of which exhibit active smoke plume emissions. The performance of the abovementionedtechniques and models is represented by their accuracy and IOU (Intersection-over-Union) *** images are first trained on the basic RGB images where their respective classification using the ResNet-50model results in an accuracy of 94.4% and segmentation using the U-Net Model with an IOU metric of 0.5 andaccuracy of 94% which leads to the detection of exact patches where the smoke plume has occurred. This work hastrained the classification model on grayscale images achieving a good increase in accuracy of 96.4%.

关键词： smoke plume ResNet-50 U-Net geo satellite images early warning global monitoring

Impact of Artificial Intelligence on Corporate Leadership

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第4期12卷 40-48页

作者： Daniel schilling Weiss Nguyen Mudassir Mohiddin shaik school of Business and Technology (sBT) Aspen University Phoenix Arizona USA Information Technology Indiana Wesleyan University Indianapolis Indiana USA

Artificial Intelligence (AI) is transforming organizational dynamics, and revolutionizing corporate leadership practices. This research paper delves into the question of how AI influences corporate leadership, examining both its advantages and disadvantages. Positive impacts of AI are evident in communication, feedback systems, tracking mechanisms, and decision-making processes within organizations. AI-powered communication tools, as exemplified by slack, facilitate seamless collaboration, transcending geographical barriers. Feedback systems, like Adobe’s Performance Management system, employ AI algorithms to provide personalized development opportunities, enhancing employee growth. AI-based tracking systems optimize resource allocation, as exemplified by studies like “AI-Based Tracking systems: Enhancing Efficiency and Accountability.” Additionally, AI-powered decision support, demonstrated during the COVID-19 pandemic, showcases the capability to navigate complex challenges and maintain resilience. However, AI adoption poses challenges in human resources, potentially leading to job displacement and necessitating upskilling efforts. Managing AI errors becomes crucial, as illustrated by instances like Amazon’s biased recruiting tool. Data privacy concerns also arise, emphasizing the need for robust security measures. The proposed solution suggests leveraging Local Machine Learning Models (LLMs) to address data privacy issues. Approaches such as federated learning, on-device learning, differential privacy, and homomorphic encryption offer promising strategies. By exploring the evolving dynamics of AI and leadership, this research advocates for responsible AI adoption and proposes LLMs as a potential solution, fostering a balanced integration of AI benefits while mitigating associated risks in corporate settings.

关键词： Artificial Intelligence (AI) Corporate Leadership Communication Feedback systems Tracking Mechanisms Decision-Making Local Machine Learning Models (LLMs) Federated Learning On-Device Learning Differential Privacy Homomorphic Encryption

Improving the operational stability of perovskite solar cells with cesium-doped graphene oxide interlayer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第9期96卷 483-490页

作者： Masaud Almalki Katerina Anagnostou Konstantinos Rogdakis Felix T.Eickemeyer Mostafa Othman Minas M.stylianakis Dimitris Tsikritzis Anwar Q.Alanazi Nikolaos Tzoganakis Lukas Pfeifer Rita Therisod Xiaoliang Mo Christian M.Wolff Aïcha Hessler-Wyser shaik M.Zakeeruddin Hong Zhang Emmanuel Kymakis Michael Grätzel Laboratory of Photonics and Interfaces École Polytechnique Fédérale de Lausanne(EPFL)Lausanne 1015Switzerland Department of Electrical and Computer Engineering Hellenic Mediterranean UniversityHeraklionCrete 71410Greece Institute of Electrical and Microengineering(IEM)Photovoltaics and Thin-Film Electronics Laboratory(PV-Lab) École Polytechnique Fédérale de Lausanne(EPFL)Neuchâtel 2000Switzerland Department of Nursing Faculty of Health SciencesHellenic Mediterranean UniversityCrete 71410Greece Centre Interdisciplinaire de Microscopie Electronique École Polytechnique Fédérale de Lausanne(EPFL)Lausanne 1015Switzerland Future Energy Technology Institute King Abdulaziz City for Science and Technology(KACST)P.O.Box 6086Riyadh 11442Saudi Arabia state Key Laboratory of Photovoltaic science and Technology Shanghai Frontiers Science Research Base of Intelligent Optoelectronics and PerceptionInstitute of OptoelectronicsDepartment of Materials ScienceFudan UniversityShanghai 200433China

Perovskite solar cells(PsCs)have made great advances in terms of power conversion efficiency(PCE),yet their subpar stability continues to hinder their *** interface between the perovskite layer and the charge-carrier transporting layers plays a crucial role in undermining the stability of *** this work,we propose a strategy to stabilize high-performance PsCs with PCE over 23%by introducing a cesium-doped graphene oxide(GO-Cs)as an interlayer between the perovskite and hole-transporting *** GO-Cs treated PsCs exhibit excellent operational stability with a projected T80(the time where the device PCE reduces to 80%of its initial value)of 2143 h of operation at the maximum powering point under one sun illumination.

关键词： Perovskite solar cells Doped graphene oxide Graphene related material Long-term operational stability

Deep Convolutional Neural Networks for south Indian Mango Leaf Disease Detection and Classification

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 2023年第12期77卷 3593-3618页

作者： shaik Thaseentaj s.sudhakar Ilango school of Computer science and Engineering VIT-AP UniversityAmaravatiVijayawada522237India

The south Indian mango industry is confronting severe threats due to various leaf diseases,which significantly impact the yield and quality of the *** management and prevention of these diseases depend mainly on their early identification and accurate *** central objective of this research is to propose and examine the application of Deep Convolutional Neural Networks(CNNs)as a potential solution for the precise detection and categorization of diseases impacting the leaves of south Indian mango *** study collected a rich dataset of leaf images representing different disease classes,including Anthracnose,Powdery Mildew,and Leaf *** maintain image quality and consistency,pre-processing techniques were *** then used a customized deep CNN architecture to analyze the accuracy of south Indian mango leaf disease detection and *** proposed CNN model was trained and evaluated using our collected *** customized deep CNN model demonstrated high performance in experiments,achieving an impressive 93.34%classification *** result outperformed traditional CNN algorithms,indicating the potential of customized deep CNN as a dependable tool for disease *** proposed model showed superior accuracy and computational efficiency performance compared to other basic CNN *** research underscores the practical benefits of customized deep CNNs for automated leaf disease detection and classification in south Indian mango *** findings support deep CNN as a valuable tool for real-time interventions and improving crop management practices,thereby mitigating the issues currently facing the south Indian mango industry.

关键词： south Indian mango tree customized deep CNN mango leaf disease classification accuracy

Deep Learning Based Face Detection and Identification of Criminal suspects

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 2023年第2期74卷 2331-2343页

作者： s.sandhya A.Balasundaram Ayesha shaik school of Computer science and Engineering Vellore Institute of Technology(VIT)Chennai600127India school of Computer science and Engineering Center for Cyber Physical SystemsVellore Institute of Technology(VIT)Chennai600127India

Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past *** of the most tedious tasks is to track a suspect once a crime is *** most of the crimes are committed by individuals who have a history of felonies,it is essential for a monitoring system that does not just detect the person’s face who has committed the crime,but also their ***,a smart criminal detection and identification system that makes use of the OpenCV Deep Neural Network(DNN)model which employs a single shot Multibox Detector for detection of face and an auto-encoder model in which the encoder part is used for matching the captured facial images with the criminals has been *** detection and extraction of the face in the image by face cropping,the captured face is then compared with the images in the *** comparison is performed by calculating the similarity value between each pair of images that are obtained by using the Cosine similarity *** plotting the values in a graph to find the threshold value,we conclude that the confidence rate of the encoder model is 0.75 and above.

关键词： Deep learning opencv deep neural network single shot multi-box detector auto-encoder cosine similarity

Neosporosis: An Overview of Its Molecular Epidemiology and Pathogenesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering 2020年第1期6卷 10-19页

作者： Asis Khan Jahangheer s.shaik Patricia sikorski Jitender P.Dubey Michael E.Grigg Molecular Parasitology section Laboratory of Parasitic DiseasesNational Institute of Allergy and Infectious DiseasesNational Institutes of HealthBethesdaMD 20892USA Animal Parasitic Disease Laboratory Beltsville Agricultural Research CenterAgricultural Research ServiceUS Department of AgricultureBeltsvilleMD 20705USA

Neospora caninum (N. caninum), a cyst-forming protozoan parasite, is a major cause of bovine abortions and neonatal mortality worldwide. N. caninum has a broad intermediate host range, and its sexual cycle occurs exclusively in canids. Another species of Neospora, Neospora hughesi (N. hughesi), has been identified and causes myeloencephalitis in horses. Although molecular epidemiology studies are in their infancy, the 18s ribosomal RNA (rRNA) and ITs1 regions within the small subunit ribosomal RNA (ssuRNA) and an N. caninum species-specific DNA probe (pNc5) have been used extensively to differentiate Neospora from other closely related apicomplexan parasites. While these repetitive regions have higher sensitivity and specificity than housekeeping or antigen genes, they suffer from low discriminatory power and fail to capture intra-species diversity. similarly, although multiple minisatellite or microsatellite marker studies have shown clear geographic substructures within Neospora, strains are often misclassified due to a convergence in the size of different alleles at microsatellite loci, known as homoplasy. Only one strain, N. caninum Liverpool (Nc-Liv), has been genome sequenced and compared with its closest relative, Toxoplasma gondii (T. gondii). Hence, detailed population genomics studies based on whole-genome sequences from multiple strains worldwide are needed in order to better understand the current population genetic structure of Neospora, and ultimately to determine more effective vaccine candidates against bovine neosporosis. The aim of this review is to outline our current understanding of the molecular epidemiology and genomics of Neospora in juxtaposition with the closely related apicomplexan parasites Hammondia hammondi and T. gondii.

关键词： Neosporosis Molecular epidemiology Population genetics Genomics Host response Vaccine

single-phase Thirteen-level Dual-boost Inverter Based shunt Active Power Filter Control Using Resonant and Fuzzy Logic Controllers

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

CsEE Journal of Power and Energy systems 2022年第3期8卷 849-863页

作者： shaik Gouse Basha Venkatesan Mani subbarao Mopidevi Vignan's Foundation for science Technology and Research Andhra Pradesh522213India Vignan's Lara Institute of Technology and science Vadlamudi522213India

This paper addresses the power quality improvement of a single-phase utility grid using a thirteen-level dualboost inverter(TLDBI)-shunt active filter(sAF).The TLDBI uses a single DC source of low voltage magnitude and five switched capacitor arrangement to achieve self-balanced thirteen level output ***,the charging and voltage balancing of the capacitor is achieved by proper switching sequence control in a series,through which boosted inverter output voltage levels are *** with the tradional H-bridge multilevel inverters(MLIs),all the elements in the proposed TLDBI are able to withstand a voltage stress which is equal to the input DC *** feature ensures the performance of the proposed TLDBI in high-frequency *** power at the electrical grid is highly affected by a wide range of non-linear *** proposed sAF is used for measuring and controlling the current flow from source to *** difference between the targeted and actual currents from the utility grid is measured by using the modified synchronous reference frame(sRF)*** estimated error current is used by the controllers to predict the optimum suitable switching angle and modulation index(MI)to the *** this paper,the traditional proportional-integral(PI)controller,fuzzy logic controller(FLC)and proportional resonant controller(PRC)are compared and the results are presented to validate the performance of *** stability and robustness of the proposed controller is evaluated using Bode,Root locus,and Nyquist *** modeling and analysis of the proposed system are done using MATLAB/simulink *** simulation results are presented in the various MI of TLDBI and also subjected to non-linear load *** results are also compared to the claim novelty of the proposed study.

关键词： FLC power quality PRC thirteen-level DBI shunt active filter single-phase utility grid sRF

In situ deposited cobalt-magnesium selenates as an advanced electrode for electrochemical energy storage

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2022年第12期10卷 3565-3575页

作者： Manchi Nagaraju s.Chandra sekhar Bhimanaboina Ramulu shaik Junied Arbaz Jae su Yu Department of Electronics and Information Convergence Engineering Kyung Hee University1732 Deogyeong-aeroGihung-guYongin-siGyeonggi-do 17104Republic of Korea

Currently,bimetallic selenates have attracted much attention as a prominent electrode composite material for supercapacitors owing to their higher redox chemistry and superior electrical ***,we synthesized cobalt-magnesium selenates (CoseO3-Mg se O4,CMs) via a facile hydrothermal process,followed by *** first,cobalt-magnesium oxide (Co2.32Mg0.68O4,CMO) was in situ prepared by a one-pot hydrothermal *** investigation on the morphological change was performed by synthesizing the same CMO samples at different growth times by keeping the temperature *** CMO electrode designed for 8 h of growth time (CMO-8 h)with an attractive morphology showed a higher areal capacity of 101.7μAh cm-2(at 3 m A cm-2) than the other CMO electrodes prepared for 6 and 10 *** exalted performance was achieved by the selenization of the CMO-8 h sample to form the CMs *** 3 m A cm-2,the resulted CMs exhibited nearly three times higher capacity,i.e.,385.4μAh cm-2,than the CMO-8 h ***,an asymmetric cell fabricated with CMs as a positive electrode also revealed good energy storage *** the applied voltage between 0 and 1.5 V,the asymmetric cell demonstrated maximum energy density of 0.159 m Wh cm-2(18.6 Wh kg-1) and maximum power density of 18.47 m W cm-2(1938 W kg-1),***,novel magnesium-based metal selenates can act as an efficient electrode for energy storage.

关键词： Co2.32Mg0.68O4 CoseO3–MgseO4 In situ formation Energy storage Asymmetric cell

Evoking robust immunogenic cell death by synergistic sonodynamic therapy and glucose depletion using Au clusters/single atoms modified TiO_(2)nanosheets

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Nano Research 2023年第7期16卷 9730-9742页

作者： Xiuxin Lu Kun Qiao Firdoz shaik Yang Zheng Zhaoyou Chu Haisheng Qian Xijun Liu Weiqing Zhang Department of Research Guangxi Medical University Cancer HospitalNanning 530021China Department of Breast surgery Harbin Medical University Cancer HospitalHarbin 150081China Department of Biotechnology Vignan’s Foundation for ScienceTechnology&ResearchGuntur 522213India Department of Breast surgery Guangxi Medical University Cancer HospitalNanning 530021China school of Biomedical Engineering Research and Engineering Center of Biomedical MaterialsAnhui Provincial Institute of Translational MedicineAnhui Medical UniversityHefei 230032China state Key Laboratory of Featured Metal Materials and Life-cycle safety for Composite structures School of ResourceEnvironments and MaterialsGuangxi UniversityNanning 530004China

Facilitated by reactive oxygen species(ROs)-involved therapies,tumor cells undergo immunogenic cell death(ICD)to stimulate long-term immunity ***,it is hard to trigger abundant and large-scale ICD for satisfactory cancer ***,a multifunctional sonosensitizer that consists of Au single atoms and clusters anchored on TiO_(2)nanosheets(named Au_(s/C)-TiO_(2))is reported for augmented sonodynamic therapy(sDT)and glucose depletion,which ultimately induce robust ICD due to the improved ROs generation and strong endoplasmic reticulum(ER)*** synergy effect between Au cluster/single atom with TiO_(2)nanosheets intensifies apoptosis and ICD pathways to inhibit 80%of tumor cells through in vivo ***,immune cells in vivo analyses verify the effectiveness of Au_(s/C)-TiO_(2)sonosensitizer towards the induction of antitumor *** study thus reveals that simultaneous presence of ROs generation and strong ER stress can efficiently evoke a strong ICD-mediated immune response.

关键词： single atom cluster titania sonodynamic therapy immunogenic cell death multifunctional