检索结果-南通市图书馆

An Improved SPSA Algorithm for System Identification Using Fuzzy Rules for Training Neural Networks

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2011年第3期8卷 333-339页

作者： Ahmad T.Abdulsadda kamran iqbal Smart Micro-Systems Laboratory Electrical and Computer Engineering Michigan State University Department of Systems Engineering University of Arkansas at Little Rock

Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.

关键词： Nonlinear system identification simultaneous perturbation stochastic approximation (SPSA) neural networks (NNs),fuzzy rules multi-layer perceptron (MLP).

Automatic seizure detection with different time delays using SDFT and time-domain feature extraction

在线全文

学校读者我要写书评

暂无评论

The Journal of Biomedical Research 2022年第1期36卷 58-67页

作者： Amal S.Abdulhussien Ahmad T.AbdulSaddaa kamran iqbal Communication Technical Engineering College Al-Furat Al-Awsat Technical UniversityAl-Najaf 54001Iraq Department of System Engineering University of Arkansas at Little RockLittle RockAR 72204USA.

Automatic seizure detection is important for fast detection of the seizure because the way that the expert denotes and searches for seizure in the long signal takes time. The most common way to detect seizures automatically is to use an electroencephalogram(EEG). Many studies have used feature extraction that needs time for calculation. In this study, sliding discrete Fourier transform(SDFT) was applied for conversion to a frequency domain without using a window, which was compared with using window for feature selection. SDFT was calculated for each time series sample directly without any delay by using a simple infinite impulse response(IIR)structure. The EEG database of Bonn University was used to test the proposed method, and two cases were defined to examine a two-classifier feedforward neural network and an adaptive network-based fuzzy inference system. Results revealed that the maximum accuracies were 93% without delay and 99.8% with a one-second delay. This delay accrued because the average was taken for the results with a one-second window.

关键词： EEG seizure detection machine learning sliding discrete Fourier transform

DNA Fingerprinting of Essential Commercialized Medicinal Plants from Pakistan

在线全文

学校读者我要写书评

暂无评论

American Journal of Plant Sciences 2017年第9期8卷 2119-2132页

作者： Waqar Ahmad Khushi Muhammad Altaf Hussain Habib Ahmad Khalid Kahn iqbal Ahmed Qarshi kamran iqbal Shinwari Muhammad Shahid Nadeem Youxiong Que Ayaz Khan Javed iqbal Department of Genetics Hazara University Mansehra Pakistan Qarshi University Lahore and Qarshi Industries Hattar Pakistan School of Biological Sciences University of the Punjab Lahore Pakistan Key Lab of Sugarcane Biology and Genetic Breeding Ministry of Agriculture Fujian Agriculture and Forestry University Fuzhou China Department of Biochemistry Faculty of Science King Abdulaziz University Jeddah Saudi Arabia Women University Swabi Pakistan

Development of fingerprints based on DNA markers is necessary for proper identification and standardization of plant species. These techniques are widely used to develop an unquestionable method of plant identification to protect the patents and quality control for industry. In this study, fifteen commercially important medicinal plants of Pakistan were collected from botanical garden of Qarshi Industries (Pvt.) Ltd, Pakistan. The objective was to optimize the extraction of genomic DNA for use in a PCR-based random amplified polymorphic DNA marker approach. The initial protocol used 60 decamers to amplify scorable amplicons;only nine markers produced significant bands in genomic DNA of medicinal plants. These markers generated 51 bands ranging between 250 and 1600 bp. The most important property of genomic markers is polymorphism to enable specific identification;all the used markers showed 100% polymorphism across 15 different plants. Further, six decamers amplified specific bands to reliably identify 8 species. The amplified bands were arranged in a binary matrix and analyzed by DNAMAN version 5.2.2 statistical software. A homology tree was constructed using binary data for nine markers, and four major clusters/clades were observed. The Rose, Mentha and Stevia accessions had shown clear clustering and grouped in major clusters/clads I, II and III respectively. Sixty decamers amplified 51 polymorphic loci in the genomes of 15 commercially valuable accessions. Moreover clear phylogenetic construction was observed in the generation of homolog tree. This protocol could therefore be useful to provide a baseline to authenticate, identify and perform phylogenetic analysis of important medicinal plants used in the Pakistani herbal medicine industry.

关键词： RAPD Decamers Medicinal Plants DNA Fingerprinting

Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease

维普期刊数据库评论

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9期76卷 3763-3781页

作者： Sayyid kamran Hussain Ali Haider Khan Malek Alrashidi Sajid iqbal Qazi Mudassar Ilyas kamran Shah Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering Faculty of Computer ScienceLahore Garrison UniversityLahore54000Pakistan Department of Computer Science Applied CollegeUniversity of TabukTabukSaudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl Hofuf31982Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl HofufSaudi Arabia

As ocular computer-aided diagnostic(CAD)tools become more widely accessible,many researchers are developing deep learning(DL)methods to aid in ocular disease(OHD)*** eye diseases like cataracts(CATR),glaucoma(GLU),and age-related macular degeneration(AMD)are the focus of this study,which uses DL to examine their *** imbalance and outliers are widespread in fundus images,which can make it difficult to apply manyDL algorithms to accomplish this analytical *** creation of efficient and reliable DL algorithms is seen to be the key to further enhancing detection *** the analysis of images of the color of the retinal fundus,this study offers a DL model that is combined with a one-of-a-kind concoction loss function(CLF)for the automated identification of *** study presents a combination of focal loss(FL)and correntropy-induced loss functions(CILF)in the proposed DL model to improve the recognition performance of classifiers for biomedical *** is done because of the good generalization and robustness of these two types of losses in addressing complex datasets with class imbalance and *** classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy(ACU),recall(REC),specificity(SPF),Kappa,and area under the receiver operating characteristic curve(AUC)as the evaluation *** testing shows that the method is reliable and efficient.

关键词： Deep learning multi-classification focal loss CNN eye disease

A Genetic Based Leader Election Algorithm for IoT Cloud Data Processing

维普期刊数据库评论

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 2021年第8期68卷 2469-2486页

作者： Samira Kanwal Zeshan iqbal Aun Irtaza Rashid Ali kamran Siddique Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan School of Intelligent Mechatronics Engineering Sejong UniversitySeoulKorea School of Electrical and Computer Engineering Department of Information and Communication TechnologyXiamen University MalaysiaSepang43900Malaysia

In IoT networks,nodes communicate with each other for computational services,data processing,and resource *** of the time huge data is generated at the network edge due to extensive communication between IoT ***,this tidal data is transferred to the cloud data center(CDC)for efficient processing and effective data *** CDC,leader nodes are responsible for higher performance,reliability,deadlock handling,reduced latency,and to provide cost-effective computational services to the ***,the optimal leader selection is a computationally hard problem as several factors like memory,CPU MIPS,and bandwidth,etc.,are needed to be considered while selecting a leader amongst the set of available *** existing approaches for leader selection are monolithic,as they identify the leader nodes without taking the optimal approach for leader ***,for optimal leader node selection,a genetic algorithm(GA)based leader election(GLEA)approach is presented in this *** proposed GLEA uses the available resources to evaluate the candidate nodes during the leader election *** the first phase of the algorithm,the cost of individual nodes,and overall cluster cost is computed on the bases of available *** the second phase,the best computational nodes are selected as the leader nodes by applying the genetic operations against a cost function by considering the available *** GLEA procedure is then compared against the Bees Life Algorithm(BLA).The experimental results show that the proposed scheme outperforms BLA in terms of execution time,SLA Violation,and their utilization with state-of-the-art schemes.

关键词： IoT cloud computing datacenter leader election algorithm machine learning genetic algorithm

Design and Optimization of 3D Radial Slot Grain Configuration

维普期刊数据库评论

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 Journal of Aeronautics 2010年第4期23卷 409-414页

作者： Ali kamran School of Astronautics Beijing University of Aeronautics and Astronautics

Upper stage solid rocket motors （SRMS） for launch vehicles require a highly efficient propulsion system. Grain design proves to be vital in terms of minimizing inert mass by adopting a high volumetric efficiency with minimum possible sliver. In this arti- cle, a methodology has been presented for designing three-dimensional （3D） grain configuration of radial slot for upper stage solid rocket motors. The design process involves parametric modeling of the geometry in computer aided design （CAD） software through dynamic variables that define the complex configuration. Grain bum back is achieved by making new surfaces at each web increment and calculating geometrical properties at each step. Geometrical calculations are based on volume and change-in-volume calculations. Equilibrium pressure method is used to calculate the internal ballistics. Genetic algorithm （GA） has been used as the optimizer because of its robustness and efficient capacity to explore the design space for global optimum solution and eliminate the requirement of an initial guess. Average thrust maximization under design constraints is the objective function.

关键词： solid rocket motors 3D grains radial slot configuration internal ballistics computer aided design heuristic optimization genetic algorithm

Electro-optomechanical switch via tunable bistability and four-wave mixing

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2019年第11期28卷 193-203页

作者： kamran Ullah Department of Physics Quaid-i-Azam University

We investigate the tunable bistable behavior of a hybrid nano-electro-optomechanical system(NEOMS) composed of S-shaped in the presence of two-level atoms, trapped inside a Fabry–Pérot cavity, and driven by a strong driving field and a weak probe field. The bistable behavior of the steady-state photon number and the mechanical steady-state positions are discussed. Further, we tune bistability by tuning all the coupling frequencies involved in the system and amplitude of the driving field. The present study provides the possibility of realization of a controllable optical switch depending on atom-field coupling, optomechanical coupling, electrostatic Coulomb coupling, and threshold power. In addition, we discuss that the non-linear effect of the hybrid NEOMS generates the four-wave mixing(FWM) process. Moreover, we show that the FWM process can be suppressed by the atom-field detuning and cavity-field detuning, which exhibits low photon transmission.

关键词： nano-electro-optomechanics nano-resonators two-level atom optical switch optical bistability four-wave mixing

The role of graveyards in species conservation and beta diversity:a vegetation appraisal of sacred habitats from Bannu,Pakistan

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2020年第4期31卷 1147-1158页

作者： Saqib kamran Shujaul Mulk Khan Zeeshan Ahmad Amjad Ur Rahman Majid iqbal Fazal Manan Zahoor Ul Haq Saif Ullah Department of Plant Sciences Quaid-i-Azam UniversityIslamabadPakistan

Graveyards or sacred groves are often places of natural vegetation protected by spiritual believers because of their sacred beliefs and indigenous culture.A study of graveyards was conducted to determine their role in species conservation,community formation,and associated indicators and species composition using multivariate statistical *** was hypothesized that variations in the age of graveyards would give rise to diverse plant communities under the impact of various edaphic and climatic *** ecological techniques were applied to determine various phytosociological *** the data were put in MS Excel for analysis in PCORD and CANOCO softwares for cluster analysis(CA),two-way cluster analysis(TWCA),indicator species analysis and canonical correspondence *** and TWCA through Sorenson distance measurements identified five major graveyard plant communities:(1)FicusBougainvillea-Chenopodium;(2)Acacia-Datura-Convolvulus;(3)Ziziphus-Vitex-Abutilon;(4)Acacia-Lantana-Salsola;and(5)*** such as Capparis decidua,Herniaria hirsuta,Salvadora oliedes and Populus euphratica were only present inside graveyards rather than outside and advocate the role of graveyards in species *** impact of different environmental and climatic variables plus the age of the graveyards were also assessed for comparison of plant communities and their respective indicator *** results indicate that higher chlorine concentration,age of graveyards,low soil electrical conductivity,lower anthropogenic activities,higher nitrogen,calcium and magnesium concentrations in the soil,and sandy soils were the strong environmental variables playing a significant role in the formation of graveyard plant communities,their associated indicators and species distribution *** results could further be utilized to evaluate the role of edaphic and climatic factors,indicator species and conservation management practices at a gr

关键词： Graveyards/Sacred groves Plant communities Multivariate statistical techniques Indicator species Edaphic factors Conservation PCORD software

Biosorption characteristics of unicellular green alga Chlorella sorokiniana immobilized in loofa sponge for removal of Cr(Ⅲ)

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2008年第2期20卷 231-239页

作者： AKHTAR Nasreen iqbal Muhammad ZAFAR Saeed iqbal iqbal Javed Department of Biology Government lslamia College for WomenCooper RoadLahore-54550Pakistan. Environment Biotechnology Group Biotechnology and Food Research CentrePCSIR Laboratories ComplexLahore-54600Pakistan. School of Biological Sciences University of PunjabLahore-54570Pakistan.

Loofa sponge （LS） immobilized biomass of Chlorella sorokiniana （LSIBCS）, isolated from industrial wastewater, was investigated as a new biosorbent for the removal of Cr（Ⅲ） from aqueous solution. A comparison of the biosorption of Cr（Ⅲ） by LSIBCS and free biomass of C. sorokiniana （FBCS） from 10-300 mg Cr（Ⅲ）/L aqueous solutions showed an increase in uptake of 17.79% when the microalgal biomass was immobilized onto loofa sponge. Maximum biosorption capacity for LSIBCS and FBCS was found to be 69.26 and 58.80 mg Cr（Ⅲ）/g biosorbent, respectively, whereas the amount of Cr（Ⅲ） ions adsorbed onto naked LS was 4.97 mg/g. The kinetics of Cr（Ⅲ） biosorption was extremely rapid and equilibrium was established in about 15 and 20 min by LSIBCS and FBCS, respectively. The biosorption equilibrium was well defined by Langmuir adsorption isotherm model. The biosorption kinetics followed the pseudo-second order kinetic model. The biosorption was found to be pH dependent and the maximum sorption occurred at the solution pH 4.0. Desorption studies showed that 98% of the adsorbed Cr（Ⅲ） could be desorbed with 0.1 mol/L HNO3, while other desorbing agents were less effective in the order： EDTA 〉 H2SO4 〉 CH3COOH 〉 HCl. The regenerated LSIBCS retained 92.68% of the initial Cr（Ⅲ） binding capacity up to five cycles of reuse in continuous flow-fixed bed columns. The study revealed that LSIBCS could be used as an effective biosorbent for the removal of Cr（Ⅲ） from wastewater.

关键词： biosorption immobilization loofa sponge Chlorella sorokiniana Cr(Ⅲ) desorption fixed bed column reactor