检索结果-南通市图书馆

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

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 *** increase of 3.3%in consumption is predicted from 2024 to *** 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 ***,tomatoes are globally important due to their widespread usage and nutritional *** face the high demand for tomatoes,it is mandatory to investigate the causes of crop loss and minimize *** are one of the major causes that adversely affect crop yield and degrade the quality of the tomato *** leads to financial losses and affects the livelihood of ***,automatic disease detection at any stage of the tomato plant is a critical *** 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 ***,most of the models proposed so far work efficiently for images with plain backgrounds where a clear demarcation exists between the background and leaf ***,the existing techniques lack in recognizing multiple diseases on the same *** address these concerns,we introduce a customized deep learning-based convolution vision transformer *** achieves an accuracy of 93.51%for classifying tomato leaf images with plain as well as complex backgrounds into 13 *** 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,*** training time of 44 min is 51.12%,74.12%,and 57.7%lower than the above-mentioned ***,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 *** p

关键词： Tomato disease transformer deep learning mobile devices

PETG:Applications in Modern Medicine

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineered Regeneration 2024年第1期5卷 45-55页

作者： Catherine Yan Corinne Kleiner Aaron Tabigue veer Shah Gregory Sacks Darshi Shah Vincent DeStefano Renaissance School of Medicine at Stony Brook University Stony BrookNYUSA Department of Biology Niagara UniversityLewistonNYUSA Stony Brook University Stony BrookNYUSA Department of Mechanical and Industrial Engineering Northeastern UniversityBostonMAUSA

Polyethylene terephthalate glycol,PETG,is a miscible,transparent thermoplastic known to have strong tensile properties,high ductility,as well as resistance to heat and chemical *** may be manufactured in several ways,most notably 3D printing *** such,PETG has emerged as a viable biomaterial for a variety of medical applications such as tissue engineering,dentistry,optometry,vascular health,cardiology,orthopedics,neurology,gynecology,and *** also serves a valuable role in biomedical research and engineering by offering improvements in cell studies,drug carriers,and anti-bacterial *** medical research and innovation utilizing PETG will better characterize its value as an inexpensive and versatile biomaterial.

关键词： Polyethylene terephthalate glycol Tissue Engineering 3D Printing Clinical Applications Biomedical Research

Amyloid-beta and tau protein beyond Alzheimer's disease

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2024年第6期19卷 1262-1276页

作者： Morteza Abyadeh Vivek Gupta Joao A.Paulo Arezoo Gohari Mahmoudabad Sina Shadfar Shahab Mirshahvaladi veer Gupta Christine T.O.Nguyen David I.Finkelstein Yuyi You Paul A.Haynes Ghasem H.Salekdeh Stuart L.Graham Mehdi Mirzaei ProGene Technologies Pty Ltd. 2. Department of Clinical Medicine Faculty of Medicine Health and Human Sciences Macquarie Medical School Macquarie University Department of Cell Biology Harvard Medical School School of Medicine Deakin University Department of Optometry and Vision Sciences School of Health Sciences Faculty of Medicine Dentistry and Health Sciences University of Melbourne The Florey Institute of Neuroscience and Mental Health The University of Melbourne School of Natural Sciences Macquarie University

The aggregation of amyloid-beta peptide and tau protein dysregulation are implicated to play key roles in Alzheimer’s disease pathogenesis and are considered the main pathological hallmarks of this devastating disease. Physiologically, these two proteins are produced and expressed within the normal human body. However, under pathological conditions, abnormal expression, posttranslational modifications, conformational changes, and truncation can make these proteins prone to aggregation, triggering specific disease-related cascades. Recent studies have indicated associations between aberrant behavior of amyloid-beta and tau proteins and various neurological diseases, such as Alzheimer’s disease, Parkinson’s disease, and amyotrophic lateral sclerosis, as well as retinal neurodegenerative diseases like Glaucoma and age-related macular degeneration. Additionally, these proteins have been linked to cardiovascular disease, cancer, traumatic brain injury, and diabetes, which are all leading causes of morbidity and mortality. In this comprehensive review, we provide an overview of the connections between amyloid-beta and tau proteins and a spectrum of disorders.

关键词： amyloid-beta cancer cardiovascular diseases diabetes neurodegeneration Tau traumatic brain injury

Spectral and mathematical evaluation of electromyography signals for clinical use

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Biomathematics 2016年第6期9卷 263-272页

作者： Karan veer Electrical and Instrumentation Engineering Department Thapar University Patiala 174001 India

The surface electromyography （SEMG） is a complicated biomedical signal, generated during voluntary or involuntary muscle activities and these muscle activities are always controlled by the nervous system. In this paper, the processing and analysis of SEMG signals at multiple muscle points for different operations were carried out. Myoelectric signals were detected using designed acquisition setup which consists of an instrumenta- tion amplifier, filter circuit, an amplifier with gain adjustment. Fhrther, Labview^-based data programming code was used to record SEMG signals for independent activities. The whole system consists of bipolar noninvasive electrodes, signal acquisition protocols and signal conditioning at different levels. This work uses recorded SEMG signals generated by biceps and triceps muscles for four different arm activities. Feature extraction was done on the recorded signal for investigating the voluntary muscular contraction relationship for exercising statistic measured index method to evaluate distance between two independent groups by directly addressing the quality of signal in separability class for different arm movements. Thereafter repeated factorial analysis of variance technique was implemented to evaluate the effectiveness of processed signal. From these results, it demonstrates that the proposed method can be used as SEMG feature evaluation index.

关键词： Electromyogram muscle movements ANOVA noninvasive electrode statis-tics upper arm.

Thickness Dependent Physical Properties of Thermally Evaporated Nanocrystalline CdSe Thin Films

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2015年第10期28卷 1299-1304页

作者： Anuradha Purohit Subhash Chander Satya Pal Nehra Mahendra Singh dhaka Department of Physics Mohanlal Sukhadia University Centre of Excellence for Energy and Environmental Studies Deenbandhu Chhotu Ram University of Science and Technology Microelectronics Research Center Iowa State University of Science and Technology

This paper presents a study on thickness dependent physical properties of cadmium selenide thin films. The films of thickness 445, 631 and 810 nm were deposited employing thermal evaporation technique on glass and ITO-coated glass substrates followed by thermal annealing in air atmosphere at 200 °C. These films were subjected to X-ray diffractometer, UV-Vis spectrophotometer, scanning electron microscopy（SEM） and electrometer for structural, optical,surface morphological and electrical analysis respectively. The structural analysis reveals that the films are nanocrystalline in nature with cubic phase and preferred orientation（111）. The crystallographic parameters such as lattice constant, interplanar spacing, grain size, internal strain, dislocation density, number of crystallites per unit area and texture coefficient are calculated and discussed. The optical band gap is found in the range 1.75-1.92 e V and observed to increase with *** SEM study shows that the annealed films are uniform, fully covered and well defined. The electrical analysis shows that the conductivity is varied with film thickness and found within the order of semiconductor behavior.

关键词： Thin films X-ray diffraction Optical properties Electrical properties Evaporation

Artificial intelligence and machine learning in drug discovery and development

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

Intelligent Medicine 2022年第3期2卷 134-140页

作者： veer Patel Manan Shah Ahmedabad International School AhmedabadGujaratIndia Department of Chemical Engineering School of TechnologyPandit Deendayal Energy UniversityGandhinagarGujaratIndia

The current rise of artificial intelligence and machine learning has been *** has reduced the human workload improved quality of life *** article describes the use of artificial intelligence and machine learning to augment drug discovery and development to make them more efficient and *** this study,a systematic evaluation of studies was carried out;these were selected based on prior knowledge of the authors and a keyword search in publicly available databases which were filtered based on related context,abstract,methodology,and full *** body of work supported the roles of machine learning and artificial intelligence in facilitating drug development and discovery processes,making them more cost-effective or altogether eliminating the need for clinical trials,owing to the ability to conduct simulations using these *** also enabled researchers to study different molecules more extensively,without any *** results of this paper demonstrate the prevalent application of machine learning and artificial intelligence methods in drug discovery,and indicate a promising future for these technologies;these results should enable researchers,students,and pharmaceutical industry to dive deeper into machine learning and artificial intelligence in a drug discovery and development context.

关键词： Artificial intelligence Machine learning Drug discovery

A neural network-based electromyography motion classifier for upper limb activities

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 Innovative Optical Health Sciences 2016年第6期9卷 77-84页

作者： Karan veer Tanu Sharma Ravinder Agarwal Electrical and Instrumentation Engineering Department Thapar University Computer Science Engineering Department GCET Ropar 174001India

The objective of the work is to investigate the classifcation of different movements based on the surface electromyogram(SEMG)pattern recognition *** testing was conducted for four arm movements using several experiments with artificial neural network class fication *** time domain features were extracted and consequently dlassification was implemented using back propagation neural dassifier(BPNC).Further,the realization of projected network was verified using cross validation(CV)process;hence ANOVA algorithm was carried *** of the network is analyzed by considering mean square error(MSE)value.A comparison was performed between the extracted feat ures and back propagation network results reported in the *** concurrent result indicates the significance of proposed network with classification accuracy(CA)of 100%recorded from two channels,while analysis of variance technique helps in investigating the effectiveness of classified sigmal for recognition tasks.

关键词： ANN SEMG arm recognition statistics classification RMS upper arm activities

Development of prosthetic arm using body actioned SEMG signals

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 Innovative Optical Health Sciences 2016年第6期9卷 58-65页

作者： Karan veer Tanu Sharma Amod Kumar EIED Department Thapar UniversityPatialaIndia CSED Department Global College of EngineeringKhanpur KuiIndia Chief Scientist CSIO-CSIRChandigarhIndia

People's working capability is badly affected when they sufer an amputated *** replacements with prosthetic devices to get a satisfactory level of performance for essential functions with the currently available prosthetic technology are very *** arm prostheses are becoming popular because they are operated by a natural contraction of intact ***,SEMG based artifdal arm was *** system cousists of diferent electronic and mechanical assemblies for operation of hand utilizing microcontroller in order to have minimum signal loss during its *** the hep of relay switching connected to low power DC motor,system is capable of opening and closing of grip according to individual wish.

关键词： SEMG electrodes variable gripping myoelectric controls electronic interface signals processing.

Machine learned interatomic potentials using random features

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2022年第1期8卷 48-57页

作者： Gurjot Dhaliwal Prasanth B.Nair Chandra veer Singh Department of Mechanical and Industrial Engineering University of Toronto5 King’s College RdTorontoM5S 3G8ONCanada Institute for Aerospace Studies University of Toronto4925 Dufferin StTorontoM3H 5T6ONCanada Department of Materials Science and Engineering University of Toronto184 College StTorontoM5S 3E4ONCanada

We present a method to model interatomic interactions such as energy and forces in a computationally efficient *** proposed model approximates the energy/forces using a linear combination of random features,thereby enabling fast parameter estimation by solving a linear least-squares *** discuss how random features based on stationary and non-stationary kernels can be used for energy approximation and provide results for three classes of materials,namely two-dimensional materials,metals and *** and energy predictions made using the proposed method are in close agreement with density functional theory calculations,with training time that is 96%lower than standard kernel *** Dynamics calculations using random features based interatomic potentials are shown to agree well with experimental and density functional theory *** frequencies as computed by random features based interatomic potentials are within 0.1%of the density functional theory ***,the proposed random features-based potential addresses scalability issues encountered in this class of machine learning problems.

关键词： random stationary interatomic