检索结果-南通市图书馆

Weed Classification Using particle Swarm Optimization and Deep Learning models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第1期44卷 913-927页

作者： m.manikandakumar p.Karthikeyan Department of Computer Science and Engineering Thiagarajar College of EngineeringTamil NaduIndia Department of Information Technology Thiagarajar College of EngineeringTamil NaduIndia

Weed is a plant that grows along with nearly allfield crops,including rice,wheat,cotton,millets and sugar cane,affecting crop yield and *** and accurate identification of all types of weeds is a challenging task for farmers in earlier stage of crop growth because of *** address this issue,an efficient weed classification model is proposed with the Deep Convolutional Neural Network(CNN)that implements automatic feature extraction and performs complex feature learning for image *** this work,weed images were trained using the proposed CNN model with evolutionary computing approach to classify the weeds based on the two publicly available weed *** Tamil Nadu Agricultural University(TNAU)dataset used as afirst dataset that consists of 40 classes of weed images and the other dataset is from Indian Council of Agriculture Research–Directorate of Weed Research(ICAR-DWR)which contains 50 classes of weed *** effective particle Swarm Optimization(pSO)technique is applied in the proposed CNN to automa-tically evolve and improve its classification *** proposed model was evaluated and compared with pre-trained transfer learning models such as GoogLeNet,AlexNet,Residual neural Network(ResNet)and Visual Geometry Group Network(VGGNet)for weed *** work shows that the performance of the pSO assisted proposed CNN model is significantly improved the success rate by 98.58%for TNAU and 97.79%for ICAR-DWR weed datasets.

关键词： Deep learning convolutional neural network weed classification transfer learning particle swarm optimization evolutionary computing Algorithm 1:metrics Evaluation

A Secure IoT-Cloud Based Healthcare System for Disease Classification Using Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第4期41卷 95-108页

作者： m.Vedaraj p.Ezhumalai Department of Computer Science and Engineering R.M.D.Engineering CollegeKavaraipettai601206TamilnaduIndia

The integration of the Internet of Things(IoT)and cloud computing is the most popular growing technology in the IT *** integrated cloud com-puting technology can be used in smart cities,health care,smart homes,environ-mental monitoring,*** recent days,IoT integrated cloud can be used in the health care system for remote patient care,emergency care,disease prediction,pharmacy management,***,still,security of patient data and disease predic-tion accuracy is a major *** machine learning approaches were used for effective early disease ***,machine learning takes more time and less performance while classiﬁ*** this research work,the Attribute based Searchable Honey Encryption with Functional Neural Network(ABSHE-FNN)framework is proposed to analyze the disease and provide stronger security in IoT-cloud healthcare *** this work,the Cardiovascular Disease and pima Indians diabetes dataset are used for heart and diabetic disease classiﬁ***-ally,means-mode normalization removes the noise and normalizes the IoT data,which helps to enhance the quality of ***ﬁed Linear Unit(RLU)was applied to adjust the feature weight to reduce the training cost and error classiﬁ-*** proposed ABSHE-FNN technique provides better security and achieves 92.79%disease classiﬁcation accuracy compared to existing techniques.

关键词： Honey encryption functional neural network rectiﬁed linear unit feature selection classiﬁcation

THE SCENERY FLOW FOR GEOmETRIC STRUCTURES ON THE TORUS: THE LINEAR SETTING

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Annals of mathematics,Series B 2001年第4期22卷 427-470页

作者： p.ARNOUX A.m.FISHER InstitutdemathematiquesdeLuminy（UpR9016） 163AvenuedeLuminycase90713288MarseilleCedex9France. DeptmatImE-USp CaixaPostal66281CEP05315-970SaoPauloBrazil.

The authOrs define the scenery flow of the torus. The flow space is the union of all flat 2- dimensional tori of area 1 with a marked direction (or equivalently the union of all tori with a quadratic differential of norm 1). This is a 5-dimensional space, and the flow acts by following individual points under an extremal deformation of the quadratic differential. The authors define associated horocycle and translation flows; the latter preserve each torus and are the horizontal and vertical flows of the corresponding quadratic differential. The scenery flow projects to the geodesic flow on the modular surface, and admits, for each orientation preserving hyperbolic toral automorphism, an invariant 3-dimensional subset on which it is the suspension flow of that map. The authors first give a simple algebraic definition in terms of the group of affine maps of the plane, and prove that the flow is Anosov. They give an explicit formula for the first-return map of the flow on convenient cross-sections. Then, in the main part of the paper, the authors give several different models for the flow and its cross-sections, in terms of : stacking and rescaling periodic tilings of the plane; symbolic dynamics: the natural extension of the recoding of Sturmian sequences, or the S-adic system generated by two substitutions; zooming and subdividing quasi-periodic tilings of the real line, or aperiodic quasicrystals of minimal complexity; the natural extension of two-dimensional continued fractions; induction on exchanges of three intervals; rescaling on pairs of transverse measure foliations on the torus, or the Teichmuller flow on the twice-punctured torus.

关键词： modular surface Continued fractions Sturmian sequences plane tilings Teichmuller flow Substitution dynamical system

CNN Approaches for Classification of Indian Leaf Species Using Smartphones

在线全文

学校读者我要写书评

暂无评论

Computers, materials & Continua 2020年第3期62卷 1445-1472页

作者： m.Vilasini p.Ramamoorthy KpR Institute of Engineering and Technology Coimbatore641407India Adithiya Institute of Engineering and Technology Coimbatore641107India

Leaf species identification leads to multitude of societal *** is enormous research in the lines of plant identification using pattern *** the help of robust algorithms for leaf identification,rural medicine has the potential to reappear as like the previous *** paper discusses CNN based approaches for Indian leaf species identification from white background using *** of CNN models over the features like traditional shape,texture,color and venation apart from the other miniature features of uniformity of edge patterns,leaf tip,margin and other statistical features are explored for efficient leaf classification.

关键词： Deep learning CNN classification transfer learning prewitt edge detection

Spatial Variability of mass movements in the Satluj Valley,Himachal pradesh during 1990～2006

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 mountain Science 2008年第1期5卷 38-51页

作者： Vikram GUpTA m.p.SAH Wadia Institute of Himalayan Geology Dehra Dun-24 8 001 (Uttarakhand)

Satluj Valley is known to have a history of landslides and related mass movement activities since the geological times. Geological and geomorphological settings combined with anthropogenic activities constitute a propensity towards slope failure. During the last two decades,the area witnessed substantial increase in athropogenic pressure,mainly due to the exploitation of hydropower potential,changing landuse pattern and population growth. In addition,a shift of the climatic patterns in the form of larger area falling under the influence of rains was observed. These natural as well as anthropogenic changes in the area have resulted in increased spatial coverage of landslide in the area. This paper documents these changes during 1990～2006.

关键词： Landslides mass movement Satluj Valley Himachal pradesh India

Stimulated Raman Scattering in a Weakly polar Ⅲ-Ⅴ Semiconductor： Effect of dc magnetic Field and Free Carrier Concentration

在线全文

学校读者我要写书评

暂无评论

Chinese physics Letters 2007年第8期24卷 2245-2248页

作者： m. Singh p. Aghamkar p. K. Sen Department of Applied physics Guru Jambheshwar University of Science and Technology Hisar-125001 India Department of Applied physics S.G.S. Institute of Technology and Science 23-Park Road Indore-452003 India

Using the hydrodynamic model of semiconductor plasmas, we perform an analytical investigation of stimulated Raman scattering （SITS） of an electromagnetic pump wave in a transversely magnetized weakly polar semicon- ductor arising from electron-density perturbations and molecular vibrations of the medium both produced at the longitudinal optical phonon frequency. Assuming that the origin of SItS lies in the third-order susceptibility of the medium, we investigate the growth rate of Stokes mode. The dependence of stimulated Raman gain on the external dc magnetic field strength and free carrier concentration is reported. The possibility of the occurrence of optical phase conjugation via SItS is also studied. The steady-state Raman gain is found to be greatly enhanced by the presence of the strong external dc magnetic field.

关键词： Stimulated Raman Scattering Weakly polar Semiconductor

Invariance of specific mass increment in the case of non-equilibrium growth

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese physics B 2015年第9期24卷 139-141页

作者： L.m.martyushev A.p.Sergeev p.S.Terentiev Ural Federal University Institute of Industrial Ecology

The invariance of specific mass increments of crystalline structures that co-exist in the case of non-equilibrium growth is grounded for the first time by using the maximum entropy production principle. Based on the hypothesis of the existence of a universal growth equation, and through the dimensional analysis, an explicit form of the time-dependent specific mass increment is proposed. The applicability of the obtained results for describing growth in animate nature is discussed.

关键词： entropy production universal growth equation

Removal of fluoride from water using aluminium containing compounds

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2009年第11期21卷 1513-1518页

作者： m. Karthikeyan K. p. Elango Department of Chemistry Gandhigram Rural University

Batch adsorption studies were undertaken to assess the suitability of aluminium titanate （AT） and bismuth aluminate （BA） to remove fluoride ions from water. The effect of pH, dose of adsorbent, contact time, initial concentration, co-ions and temperature on fluoride removal efficiency were studied. The amounts of fluoride ions adsorbed, at 30°C from 4 mg/L of fluoride ion solution, by AT and BA were 0.85 and 1.55 mg/g, respectively. The experimental data fitted well to the Freundlich and Langmuir isotherms. Thermodynamic parameters such as △H0, △S 0 and △G0 indicated that the removal of fluoride ions by AT was exothermic and non-spontaneous while that by BA was endothermic and spontaneous. Fourier transform infrared （FT-IR） analysis and X-ray diffraction （XRD） patterns of the adsorbent before and after adsorption indicated that fluoride ions were chemisorbed by these adsorbents.

关键词： adsorption defluoridation isotherms aluminium titanate bismuth aluminate

pOLYmERIC SURFACTANT STRUCTURE

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of polymer Science 2001年第2期19卷 135-145页

作者： p.m.Saville J.W.White Research School of Chemistry The Australian National University Canberra ACT 0200 AustraliaResearch School of Chemistry The Australian National University Canberra ACT 0200 Australia

polymeric surfactants are amongst the most widespread of all polymers. In nature, proteins and polysaccharidescause self organization as a result of this surfactancy; in industry, polymeric surfactants play key roles in the food, explosivesand surface coatings sectors. The generation of useful nano- and micro-structures in films and emulsions as a result ofpolymer amphiphilicity and the application of mechanical stress is discussed. The use of X-ray and neutron small anglescattering and reflectivity to measure these structures and their dynamic properties will be described. New results on linear and dendritic polymer surfactants are presented.

关键词： polymeric Surfactant Structure X-ray Neutron Reflectivity Film