检索结果-南通市图书馆

Neural Machine Translation Models with Attention-Based Dropout Layer

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas Khan muhammad Ali tahir muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

Synthesis, Crystal Structure and Antimicrobial Activity of {[Bis(pyridine-κN)bis(3,5-dinitrosalicylato κ-O,O')Zn(Ⅱ)][bis(pyridine-κN)Zn(Ⅱ)]}

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 Structural Chemistry 2016年第5期35卷 705-712页

作者： CHANG Fouzia MEMON Najma AHMED muhammad Naeem tahir muhammad Nawaz MEMON Shahabuddin CHANG Abdul Sattar BHANGER muhammad Iqbal CHANDIO Anwer National Centre of Excellence in Analytical Chemistry University of Sindh Department of Chemistry The University of Azad Jammu and Kashmir Department of Physics University of Sargodha HEJ Research Institute of Chemistry ICCBS University of Karachi

A novel {[bis（pyridine-κN）bis（3,5-dinitrosalicylato κ-O,O＇）Zn（Ⅱ）][bis（pyridine-κN）Zn（Ⅱ）]}（C_（34）H_（24）N_8O_（14）Zn_2） was synthesized by a self-assemble method at room temperature. The molecular structure was determined by single-crystal X-ray analysis. The compound crystallizes in the monoclinic system, space group P2_1/n with a = 12.2156, b = 13.5696, c = 22.5602 A, β = 90.061o, Z = 4 and V = 3739.6（3）A^3. The new 1D binuclear coordination polymer {[bis（py-κN）bis（3,5-dinitrosal κ-O,O′） Zn（Ⅱ）][bis（py-κN）Zn（Ⅱ）]} resulted from two different types of moieties. The polymer [bis（py-κN）bis（3,5-dinitrosal κ-O,O′）Zn（Ⅱ）] unit is connected with [bis（py-κN） Zn（Ⅱ）] by zigzag topology. One zinc（Ⅱ） cation has a six-fold coordination environment, in which the metal atom is connected with four oxygen atoms of two 3,5-dinitrosalicylic acids to form equatorial bonds and two nitrogen atoms of pyridine to generate the axial bonds. Other four-fold nucleus contain two Zn-O bonds from different 3,5-dinitrosalicylic acids and two bonds with the Natom of pyridine. Antimicrobial assay results indicated that the compound showed moderate activities against different bacterial and fungal strains.

关键词： crystal structure antimicrobial pyridine C-H…π interactions

Towards Cache-Assisted Hierarchical Detection for Real-Time Health Data Monitoring in IoHT

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第11期77卷 2529-2544页

作者： muhammad tahir Mingchu Li Irfan Khan Salman AAl Qahtani Rubia Fatima Javed Ali Khan muhammad Shahid Anwar School of Software Technology Dalian University of Technology(DUT)Dalian116621China School of Software Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning ProvinceDalian116650China Department of Computer Engineering King Saud UniversityRiyadh11543Saudi Arabia School of Software Tsinghua UniversityBeijing100084China Department of Software Engineering University of Science and TechnologyBanu28100Pakistan Department of AI and Software Gachon UniversitySeongnamsi13120Korea

Real-time health data monitoring is pivotal for bolstering road services’safety,intelligence,and efficiency within the Internet of Health Things(IoHT)***,delays in data retrieval can markedly hinder the efficacy of big data awareness detection *** advocate for a collaborative caching approach involving edge devices and cloud networks to combat *** strategy is devised to streamline the data retrieval path,subsequently diminishing network *** an adept cache processing scheme poses its own set of challenges,especially given the transient nature of monitoring data and the imperative for swift data transmission,intertwined with resource allocation *** paper unveils a novel mobile healthcare solution that harnesses the power of our collaborative caching approach,facilitating nuanced health monitoring via edge *** system capitalizes on cloud computing for intricate health data analytics,especially in pinpointing health *** the dynamic locational shifts and possible connection disruptions,we have architected a hierarchical detection system,particularly during *** system caches data efficiently and incorporates a detection utility to assess data freshness and potential lag in response ***,we introduce the Cache-Assisted Real-Time Detection(CARD)model,crafted to optimize *** the inherent complexity of the NP-hard CARD model,we have championed a greedy algorithm as a *** reveal that our collaborative caching technique markedly elevates the Cache Hit Ratio(CHR)and data freshness,outshining its contemporaneous benchmark *** empirical results underscore the strength and efficiency of our innovative IoHT-based health monitoring *** encapsulate,this paper tackles the nuances of real-time health data monitoring in the IoHT landscape,presenting a joint edge-cloud caching strategy paired with a hierarchical detection *** methodology yields enh

关键词： Real-time health data monitoring Cache-Assisted Real-Time Detection(CARD) edge-cloud collaborative caching scheme hierarchical detection Internet of Health Things(IoHT)

Infectious causes of fever of unknown origin in developing countries: An international ID-IRI study

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 Intensive Medicine 2024年第1期4卷 94-100页

作者： Hakan Erdem Jaffar AAl-Tawfiq Maha Abid Wissal Ben Yahia George Akafity Manar Ezzelarab Ramadan Fatma Amer Amani El-Kholy Atousa Hakamifard Bilal Ahmad Rahimi Farouq Dayyab Hulya Caskurlu Reham Khedr muhammad tahir Lysien Zambrano Mumtaz Ali Khan Aun Raza Nagwa Mostafa El-Sayed Magdalena Baymakova Aysun Yalci Yasemin Cag Umran Elbahr Aamer Ikram Department of Infectious Diseases&Clinical Microbiology Gulhane School of MedicineTurkish Health Sciences UniversityAnkaraTurkey Specialty Internal Medicine and Quality and Patient Safety Department Johns Hopkins Aramco HealthcareDhahranSaudi Arabia Division of Infectious Diseases Indiana University School of MedicineIndianapolisINUSA Department of Infectious Diseases Farhat Hached University HospitalIbn El Jazzar Medical SchoolUniversity of SousseSousseTunisia Internal Medicine Department Farhat Hached University HospitalIbn El Jazzar Medical SchoolUniversity of SousseSousseTunisia Cape Coast Teaching Hospital Cape CoastGhana Medical Parasitology Faculty of MedicineSuez UniversitySuezEgypt Department of Medical Microbiology and Immunology Faculty of MedicineZagazig UniversityZagazigEgypt Department of Clinical Pathology Faculty of MedicineCairo UniversityGizaEgypt Department of Infectious Diseases School of MedicineIsfahan University of Medical SciencesIsfahanIran Department of Infectious Diseases Kandahar University Medical FacultyTeaching HospitalKandaharAfghanistan Department of Infectious Diseases Mohammed Bn Khalifa Bn Salman Alkhalifa Specialist Cardiac CenterAwaliBahrain Department of Infectious Diseases and Clinical Microbiology Faculty of MedicineIstanbul Medeniyet UniversityIstanbulTurkey Department of Pediatric Oncology National Cancer Institute–Cairo UniversityChildren Cancer Hospital EgyptCairoEgypt Department of Medicine Federal General HospitalIslamabadPakistan Institute for Research in Medical Sciences and Right to Health(ICIMEDES) Scientific Research Unit(UIC)Faculty of Medical Sciences(FCM)National Autonomous University of Honduras(UNAH)TegucigalpaHonduras National Institute of Health IslamabadPakistan Shaukat Khanum Memorial Cancer Hospital and Research Center LahorePakistan Medical Parasitology Department Research Institute of OphthalmologyGizaEgypt Department of Infectious Diseases Military Medical AcademySofiaBulgaria Department of Infecti

Background:Fever of unknown origin(FUO)in developing countries is an important dilemma and further research is needed to elucidate the infectious causes of ***:A multi-center study for infectious causes of FUO in lower middle-income countries(LMIC)and lowincome countries(LIC)was conducted between January 1,2018 and January 1,*** total,15 participating centers from seven different countries provided the data,which were collected through the Infectious DiseasesInternational Research Initiative *** adult patients with confirmed infection as the cause of FUO were included in the *** severity parameters were quick Sequential Organ Failure Assessment(qSOFA)≥2,intensive care unit(ICU)admission,vasopressor use,and invasive mechanical ventilation(IMV).Results:A total of 160 patients with infectious FUO were included in the ***,148(92.5%)patients had community-acquired infections and 12(7.5%)had hospital-acquired *** most common infectious syndromes were tuberculosis(TB)(n=27,16.9%),infective endocarditis(n=25,15.6%),malaria(n=21,13.1%),brucellosis(n=15,9.4%),and typhoid fever(n=9,5.6%).Plasmodium falciparum,Mycobacterium tuberculosis,Brucellae,Staphylococcus aureus,Salmonella typhi,and Rickettsiae were the leading infectious agents in this study.A total of 56(35.0%)cases had invasive procedures for *** mean qSOFA score was 0.76±0.94{median(interquartile range[IQR]):0(0–1)}.ICU admission(n=26,16.2%),vasopressor use(n=14,8.8%),and IMV(n=10,6.3%)were not ***,38(23.8%)patients had at least one of the severity *** mortality rate was 15(9.4%),and the mortality was attributable to the infection causing FUO in 12(7.5%)***:In LMIC and LIC,tuberculosis and cardiac infections were the most severe and the leading infections causing FUO.

关键词： Developing countries Fever of unknown origin Infection

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional 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

Computers, Materials & Continua 2022年第3期70卷 5503-5518页

作者： Kanika Bhalla Deepika Koundal Surbhi Bhatia Mohammad Khalid Imam Rahmani muhammad tahir Department of Electrical Engineering National Taipei University of TechnologyTaipei10608Taiwan Department Virtualization School of Computer ScienceUniversity of Petroleum&Energy StudiesDehradunIndia College of Computer Science and Information technology King Faisal University36362Saudi Arabia College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared(IR)/visible(VS)*** in various kind of features in these images are vital to preserve in the single fused ***,simultaneous preservation of both the aspects at the same time is a challenging ***,most of the existing methods utilize the manual extraction of features;and manual complicated designing of fusion rules resulted in a blurry artifact in the fused ***,this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous ***,fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the ***,images have been learned by two parallel branches of the siamese convolutional neural network(CNN)to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image ***,the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixelwise strategy to result in fused *** parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information(MI),0.841 for entropy(EG),0.655 for edge information(EI),0.652 for human perception(HP),and 0.980 for image structural similarity(ISS).Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform(DCT),anisotropic diffusion&karhunen-loeve(ADKL),guided filter(GF),random walk(RW),principal component analysis(PCA),and convolutional neural network(CNN)methods.

关键词： Convolutional neural network fuzzy sets infrared and visible image fusion deep learning

Cartesian Product Based Transfer Learning Implementation for Brain Tumor 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 2022年第11期73卷 4369-4392页

作者： Irfan Ahmed Usmani muhammad tahir Qadri Razia Zia Asif Aziz Farheen Saeed Electronic Engineering Department Sir Syed University of Engineering&TechnologyKarachi75300Pakistan Department of Computer Science Bahria University Karachi CampusKarachi75260Pakistan Christus Trinity Clinic TexasUSA

Knowledge-based transfer learning techniques have shown good performance for brain tumor classification,especially with small ***,to obtain an optimized model for targeted brain tumor classification,it is challenging to select a pre-trained deep learning(DL)model,optimal values of hyperparameters,and optimization algorithm(solver).This paper first presents a brief review of recent literature related to brain tumor ***,a robust framework for implementing the transfer learning technique is *** the proposed framework,a Cartesian product matrix is generated to determine the optimal values of the two important hyperparameters:batch size and learning *** extensive exercise consisting of 435 simulations for 11 state-of-the-art pre-trained DL models was performed using 16 paired hyperparameters from the Cartesian product matrix to input the model with the three most popular solvers(stochastic gradient descent with momentum(SGDM),adaptive moment estimation(ADAM),and root mean squared propagation(RMSProp)).The 16 pairs were formed using individual hyperparameter values taken from literature,which generally addressed only one hyperparameter for optimization,rather than making a grid for a particular *** proposed framework was assessed using a multi-class publicly available dataset consisting of glioma,meningioma,and pituitary *** assessment shows that ResNet18 outperforms all other models in terms of accuracy,precision,specificity,and recall(sensitivity).The results are also compared with existing state-of-the-art research work that used the same *** comparison was mainly based on performance metric“accuracy”with support of three other parameters“precision,”“recall,”and“specificity.”The comparison shows that the transfer learning technique,implemented through our proposed framework for brain tumor classification,outperformed all existing *** the best of our knowledge,the proposed framework is a

关键词： Deep transfer learning Cartesian product hyperparameter optimization magnetic resonance imaging(MRI) brain tumor classification

Deep Learning Method to Detect the Road Cracks and Potholes for Smart Cities

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4期75卷 1863-1881页

作者： Hong-Hu Chu muhammad Rizwan Saeed Javed Rashid muhammad tahir Mehmood Israr Ahmad Rao Sohail Iqbal Ghulam Ali College of Civil Engineering Hunan UniversityChangsha410082China Department of CS University of OkaraOkara56310Pakistan Department of CS&SE Islamic International UniversityIslamabad44000Pakistan Department of IT Services University of OkaraOkara56310Pakistan Department of CS Government College UniversityFaisalabad38000Pakistan Department of Automation Science Beihang UniversityBeijing100191China

The increasing global population at a rapid pace makes road trafficdense;managing such massive traffic is challenging. In developing countrieslike Pakistan, road traffic accidents (RTA) have the highest mortality percentageamong other Asian countries. The main reasons for RTAs are roadcracks and potholes. Understanding the need for an automated system forthe detection of cracks and potholes, this study proposes a decision supportsystem (DSS) for an autonomous road information system for smart citydevelopment with the use of deep learning. The proposed DSS works in layerswhere initially the image of roads is captured and coordinates attached to theimage with the help of global positioning system (GPS), communicated tothe decision layer to find about the cracks and potholes in the roads, andeventually, that information is passed to the road management informationsystem, which gives information to drivers and the maintenance *** the decision layer, we projected a CNN-based model for pothole crackdetection (PCD). Aimed at training, a K-fold cross-validation strategy wasused where the value of K was set to 10. The training of PCD was completedwith a self-collected dataset consisting of 6000 images from Pakistani *** proposed PCD achieved 98% of precision, 97% recall, and accuracy whiletesting on unseen images. The results produced by our model are higher thanthe existing model in terms of performance and computational cost, whichproves its significance.

关键词： Road cracks and potholes CNN smart cities pothole crack detection decision support system

Discovery of human coronaviruses pan-papain-like protease inhibitors using computational approaches

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 Pharmaceutical Analysis 2020年第6期10卷 546-559页

作者： Mubarak A.Alamri muhammad tahir ul Qamar muhammad Usman Mirza Safar M.Alqahtani Matheus Froeyen Ling-Ling Chen Department of Pharmaceutical Chemistry College of PharmacyPrince Sattam Bin Abdulaziz UniversityAlkarjSaudi Arabia College of Life Science and Technology Guangxi UniversityNanningChina Department of Pharmaceutical and Pharmacological Sciences Rega Institute for Medical ResearchMedicinal ChemistryUniversity of LeuvenB-3000LeuvenBelgium Hubei Key Laboratory of Agricultural Bioinformatics College of InformaticsHuazhong Agricultural UniversityWuhan430070China

The papain-like protease(PLpro)is vital for the replication of coronaviruses(Co Vs),as well as for escaping innate-immune responses of the ***,it has emerged as an attractive antiviral *** this study,computational approaches were employed,mainly the structure-based virtual screening coupled with all-atom molecular dynamics(MD)simulations to computationally identify specific inhibitors of severe acute respiratory syndrome coronavirus 2(SARS-Co V-2)PLpro,which can be further developed as potential pan-PLprobased broad-spectrum antiviral *** sequence,structure,and functional conserveness of most deadly human Co Vs PLprowere explored,and it was revealed that functionally important catalytic triad residues are well conserved among SARS-Co V,SARS-Co V-2,and middle east respiratory syndrome coronavirus(MERS-Co V).The subsequent screening of a focused protease inhibitors database composed of^7,000 compounds resulted in the identification of three candidate compounds,ADM13083841,LMG15521745,and *** three compounds established conserved interactions which were further explored through MD simulations,free energy calculations,and residual energy contribution estimated by MM-PB(GB)SA *** these compounds showed stable conformation and interacted well with the active residues of SARS-Co V-2 PLpro,and showed consistent interaction profile with SARS-Co V PLproand MERS-Co V PLproas ***,the reported SARS-Co V-2 PLprospecific compounds could serve as seeds for developing potent pan-PLprobased broad-spectrum antiviral drugs against deadly human ***,the presented information related to binding site residual energy contribution could lead to further optimization of these compounds.

关键词： COVID-19 MERS-CoV Molecular dynamic simulation Pan-inhibitors Papain-like protease SARS-CoV SARS-CoV-2 Virtual screening

Synthesis, Crystal Structure and Antimicrobial Activity of Ethyl 2-(1-cyclohexyl-4-phenyl-1H-1,2,3-triazol-5-yl)-2-oxoacetate

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Structural Chemistry 2014年第11期33卷 1666-1672页

作者： muhammad Naeem Ahmed SHAHID Hameed KHAWAJA Ansar Yasin IFZAN Arshad IHSAN-ul-Haq SAFEENA Zafar muhammad Nawaz tahir Department of Chemistry The University of Azad Jammu and Kashmir Department of Chemistry Quaid-i-Azam University Department of Pharmacy Faculty of Biological SciencesQuaid-i-Azam University University of Sargodha Department of Physics

A novel 1,4,5-trisubstituted 1,2,3-triazole（C18H21N3O3） was synthesized by a one-pot three component reaction of 1-azidocyclohexane, 1-copper（I） phenylethyne and ethoxalyl chloride at room temperature. The molecular structure was determined by single-crystal X-ray analysis. The compound crystallizes in the monoclinic system, space group P21/n with a = 12.8167（9）, b = 8.0966（6）, c = 16.7079（9） A, β = 98.716（2）°, Z = 4 and V = 1713.8（2）. In the crystal, the molecules are related by inversion and paired into dimers via C–H…O and C–O…C interactions involving（oxo） acetate groups. Furthermore, X-ray analysis results are compared with the optimized structure computed by using B3 LYP method with 6-311 G basis set. The calculated results showed that optimized geometry can well reproduce the crystal structure parameters. The bioassay results indicate that the compound has good antibacterial and antifungal activities.

关键词： click chemistry triazole cyclohexyl oxoacetate XRD antimicrobial