|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Nat Med:靶向两分子或有助于彻底治愈白血病显示文摘科学家在癌细胞内发现两个信号蛋白能够让癌细胞抵抗化疗。研究表明阻断这两种蛋白能够增强化疗对人类白血病小鼠模型的治疗效果。相关研究结果发表在国际学术期刊NatureMedicine上。研究人员发现在治疗中阻断c-Fos和Dusp1这两个蛋白能够治愈一些受激酶驱动且抵抗治疗的白血病和实体瘤。 | Meenu Kesarwani, Zachary Kincaid, Ahmed Gomaa, Erika Huber, Sara Rohrabaugh, Zain Siddiqui, Muhammad F Bouso, Kakajan Komurov, James C Mulloy, Jose A Cancelas, H Leighton Grimes Mohammad Azam Tahir Latif Ming Xu H Leighton Grimes Mohammad Azam | 2017 | 现代生物医学进展2017，17，17： | 4 |
| 2 | Vertical axis wind turbine – A review of various configurations and design techniques显示文摘 | Muhammad Mahmood Aslam Bhutta Nasir Hayat Ahmed Uzair Farooq Zain Ali Sh. Rehan Jamil Zahid Hussain | 2011 | Renewable and Sustainable Energy Reviews2011，，4： | 3 |
| 3 | Reconfigurable intelligent surface-aided wireless communications: An overview显示文摘The reconfigurable intelligent surface(RIS)is an emerging technology,which will hopefully bring a new revolution in wireless communications.The RIS technology can be deployed in an indoor/outdoor environment to dynamically manipulate the propagation environment.The RIS consists of a large number of independently controllable passive elements,and these elements are involved in realizing high passive beamforming gain.Different from the conventional active phased antenna array,there is no dedicated radio-frequency(RF)chain installed at the RIS to perform complex signal processing operations.Therefore,it does not incur additional noise while retransmitting the incident wave,which is substantially a unique feature from the conventional wireless communication systems.Taking advantage of its working principle,RIS has been deployed in various practical scenarios.In this tutorial,at first we will review the latest advances in RIS,including the application scenarios such as the system and channel model,the information theoretic analysis,the physical realization and design,key signal processing techniques such as precoding and channel estimation,and prototyping.Finally,we discuss interesting future research problems for the RIS-aided communications. | Muhammad Zain Siddiqi Talha Mir | 2022 | Intelligent and Converged Networks2022，3，1： | 3 |
| 4 | Week Ahead Electricity Power and Price Forecasting Using Improved DenseNet-121 Method显示文摘In the Smart Grid(SG)residential environment,consumers change their power consumption routine according to the price and incentives announced by the utility,which causes the prices to deviate from the initial pattern.Thereby,electricity demand and price forecasting play a significant role and can help in terms of reliability and sustainability.Due to the massive amount of data,big data analytics for forecasting becomes a hot topic in the SG domain.In this paper,the changing and non-linearity of consumer consumption pattern complex data is taken as input.To minimize the computational cost and complexity of the data,the average of the feature engineering approaches includes:Recursive Feature Eliminator(RFE),Extreme Gradient Boosting(XGboost),Random Forest(RF),and are upgraded to extract the most relevant and significant features.To this end,we have proposed the DensetNet-121 network and Support Vector Machine(SVM)ensemble with Aquila Optimizer(AO)to ensure adaptability and handle the complexity of data in the classification.Further,the AO method helps to tune the parameters of DensNet(121 layers)and SVM,which achieves less training loss,computational time,minimized overfitting problems and more training/test accuracy.Performance evaluation metrics and statistical analysis validate the proposed model results are better than the benchmark schemes.Our proposed method has achieved a minimal value of the Mean Average Percentage Error(MAPE)rate i.e.,8%by DenseNet-AO and 6%by SVM-AO and the maximum accurateness rate of 92%and 95%,respectively. | Muhammad Irfan Ali Raza Faisal Althobiani Nasir Ayub Muhammad Idrees Zain Ali Kashif Rizwan Abdullah Saeed Alwadie Saleh Mohammed Ghonaim Hesham Abdushkour Saifur Rahman Omar Alshorman Samar Alqhtani | 2022 | Computers, Materials & Continua2022，，9： | 2 |
| 5 | Epidemiology and immunodiagnostics of Strongyloides stercoralis infections among migrant workers in Malaysia显示文摘Objective: To investigate the status of Strongyloides(S.) stercoralis infections among migrant workers in Malaysia for the first time and identify risk factors.Methods: Four diagnostic methods were employed for the detection of S. stercoralis including microscopy, enzyme-linked immunosorbent assay(ELISA) using a commercial kit, ELISA using the rSs1a antigen and polymerase chain reaction(PCR). Low and semi-skilled workers from five working sectors(i.e. manufacturing, food service, agriculture and plantation, construction and domestic service) were tested on a voluntary basis. Results: The overall seroprevalence of S. stercoralis from 483 workers employing the ELISA commercial kit for IgG was 35.8%(n=173;95% CI: 31.5%-40.1%) whereas seroprevalence using the rSs1a-ELISA was 13.0%(n=63;95% CI: 10.0%-16.0%). Cross tabulation between the ELISA commercial kit and rSs1a-ELISA showed that only 6.4%(n=31;95% CI: 4.2%-8.6%) of the samples were positive in both tests. Microscopic examination of all 388 fecal samples were negative;however subsequent testing by a nested PCR against DNA from the same samples successfully amplified DNA from three male subjects(0.8%;3/388). Male workers, India and Myanmar nationality, food service occupation and those living in the hostel were statistically significant with seroprevalence(P<0.005). Conclusion: This is the first report on the epidemiology of S. stercoralis infections among the migrant workers in Malaysia. Our results highlight the importance of using appropriate diagnostic tools for detection. The presence of anti-S. stercoralis antibodies in the study population calls for improvements in personal hygiene and sanitation standards among migrant workers in Malaysia through control strategies including health education campaigns and programs aimed at increasing awareness and healthy behaviors. | Norhidayu Sahimin Yvonne A.L.Lim Rahmah Noordin Muhammad Hafiznur Yunus Norsyahida Arifin Jerzy Marian Behnke Siti Nursheena Mohd Zain | 2019 | Asian Pacific Journal of Tropical Medicine2019，12，6： | 1 |
| 6 | Prevalence of Type 2 Dia- betes Mellitusin Hepatitis C Virus Infected Population: A Southeast Asian Study 显示文摘 | Muhammad SM Zain IA Farukh NR | 2000 | Journal of Diabetes Rsesearch2000，14，： | 1 |
| 7 | Tectonic Imprints of the Hazara Kashmir Syntaxis on the Mesozoic Rocks Exposed in Munda, Mohmand Agency, Northwest Pakistan显示文摘Two well-developed mesoscopic folds, D_2 and D_3, which postdate the middle amphibolite metamorphism, were recognized in the western hinterland zone of Pakistan. NW–SE trending D_2 folds developed during NE–SW horizontal bulk shortening followed by NE–SW trending D_3 folds, which developed during SE–NW shortening. Micro- to mesoscopically the NW–SE trending S2 crenulation cleavage, boudins and mineral stretching lineations are overprinted by D_3. The newly established NW–SE trending micro- to mesoscopic structures in Munda termed D_2, which postdated F_1/F_2, is synchronously developed with F3 structures in the western hinterland zone of Pakistan. We interpret that D_2 and D_3 folds are counterclockwise rotated in the tectonic event that has evolved the Hazara Kashmir Syntaxis after the main phase Indian plate and Kohistan Island Arc collision. Chlorite replacement by biotite in the main matrix crenulation cleavages indicates prograde metamorphism related with D_2. The inclusion of muscovite and biotite in garnet porphyroblasts and the presence of staurolite in these rocks indicate that the Barrovian metamorphic conditions predate D_2 and D_3. We interpret that garnet, staurolite and calcite porphyroblasts grew before D_2 because the well developed S2 crenulation cleavage wraps around these porphyroblasts. | Asghar ALI Umer HABIB Atta Ur REHMAN Noor ZADA Zain Ul ABIDIN Muhammad ISMAIL | 2016 | Acta Geologica Sinica(English Edition)2016，90，2： | 1 |
| 8 | Energy Theft Identification Using Adaboost Ensembler in the Smart Grids显示文摘One of the major concerns for the utilities in the Smart Grid(SG)is electricity theft.With the implementation of smart meters,the frequency of energy usage and data collection from smart homes has increased,which makes it possible for advanced data analysis that was not previously possible.For this purpose,we have taken historical data of energy thieves and normal users.To avoid imbalance observation,biased estimates,we applied the interpolation method.Furthermore,the data unbalancing issue is resolved in this paper by Nearmiss undersampling technique and makes the data suitable for further processing.By proposing an improved version of Zeiler and Fergus Net(ZFNet)as a feature extraction approach,we had able to reduce the model’s time complexity.To minimize the overfitting issues,increase the training accuracy and reduce the training loss,we have proposed an enhanced method by merging Adaptive Boosting(AdaBoost)classifier with Coronavirus Herd Immunity Optimizer(CHIO)and Forensic based Investigation Optimizer(FBIO).In terms of low computational complexity,minimized over-fitting problems on a large quantity of data,reduced training time and training loss and increased training accuracy,our model outperforms the benchmark scheme.Our proposed algorithms Ada-CHIO andAda-FBIO,have the low MeanAverage Percentage Error(MAPE)value of error,i.e.,6.8%and 9.5%,respectively.Furthermore,due to the stability of our model our proposed algorithms Ada-CHIO and Ada-FBIO have achieved the accuracy of 93%and 90%.Statistical analysis shows that the hypothesis we proved using statistics is authentic for the proposed technique against benchmark algorithms,which also depicts the superiority of our proposed techniques. | Muhammad Irfan Nasir Ayub Faisal Althobiani Zain Ali Muhammad Idrees Saeed Ullah Saifur Rahman Abdullah Saeed Alwadie Saleh Mohammed Ghonaim Hesham Abdushkour Fahad Salem Alkahtani Samar Alqhtani Piotr Gas | 2022 | Computers, Materials & Continua2022，，7： | 1 |
| 9 | Prediction of laser beam welding - induced distortions and residual stresses by numerical simulation for aeronautic application显示文摘 | Muhammad Zain - ul - Abdeina Daniel Neliasa Jean - Franc | 2009 | Journal of materials pro- cessing technology2009，，209： | 1 |
| 10 | Correlations among oligonucleotide repeats, nucleotide substitutions, and insertion-deletion mutations in chloroplast genomes of plant family Malvaceae显示文摘The co-occurrence of mutational events including substitutions and insertions—deletions(InDels)with oligonucleotide repeats has previously been reported for a limited number of prokaryotic,eukaryotic,and organelle genomes.In this study,the correlations among these mutational events in chloroplast genomes of species in the eudicot family Malvaceae were investigated.This study also reported chloroplast genome sequences of Hibiscus mutabilis,Malva parvifJora,and Malvastrum coromandelianum.These three genomes and 16 other publicly available chloroplast genomes from 12 genera of Malvaceae were used to calculate the correlation coefficients among the mutational events at干amily,subfamily,and genus levels.In these comparisons,chloroplast genomes were pairwise aligned to record the substitutions and the InDels in mutually exclusive,250 nucleotide long bins.Taking one among the two genomes as a reference,the coordinate positions of oligonucleotide repeats in the reference genome were recorded.The extent of correlations among repeats,substitutions,and InDels was calculated and categorized as follows:very weak(0.1-0.19),weak(0.20-0.29),moderate(0.30-0.39),and strong(0.4-0.69).The extent of correlations ranged 0.201-0.6 between^InDels and single-nucleotide polymorphism(SNP),'0.182-0.513 between“InDels and repeat,”and 0.055-0.403 between“SNPs and repeats.”At family-and subfamily-level comparisons,88%-96%of the repeats showed co-occurrence with SNPs,whereas at the genus level,23%-86%of the repeats co-occurred with SNPs in same bins.Our findings support the previous hypothesis suggesting the use of oligonucleotide repeats as a proxy for finding the mutational hotspots. | Abdullah Furrukh Mehmood Iram Shahzadi Zain Ali Madiha Islam Muhammad Naeem Bushra Mirza Peter JLockhart Ibrar Ahmed Mohammad Tahir Waheed | 2021 | Journal of Systematics and Evolution2021，59，2： | 1 |
| 11 | LexDeep:Hybrid Lexicon and Deep Learning Sentiment Analysis Using Twitter for Unemployment-Related Discussions During COVID-19显示文摘The COVID-19 pandemic has spread globally,resulting in financialinstability in many countries and reductions in the per capita grossdomestic product.Sentiment analysis is a cost-effective method for acquiringsentiments based on household income loss,as expressed on social media.However,limited research has been conducted in this domain using theLexDeep approach.This study aimed to explore social trend analytics usingLexDeep,which is a hybrid sentiment analysis technique,on Twitter to capturethe risk of household income loss during the COVID-19 pandemic.First,tweet data were collected using Twint with relevant keywords before(9 March2019 to 17 March 2020)and during(18 March 2020 to 21 August 2021)thepandemic.Subsequently,the tweets were annotated using VADER(lexiconbased)and fed into deep learning classifiers,and experiments were conductedusing several embeddings,namely simple embedding,Global Vectors,andWord2Vec,to classify the sentiments expressed in the tweets.The performanceof each LexDeep model was evaluated and compared with that of a supportvector machine(SVM).Finally,the unemployment rates before and duringCOVID-19 were analysed to gain insights into the differences in unemploymentpercentages through social media input and analysis.The resultsdemonstrated that all LexDeep models with simple embedding outperformedthe SVM.This confirmed the superiority of the proposed LexDeep modelover a classical machine learning classifier in performing sentiment analysistasks for domain-specific sentiments.In terms of the risk of income loss,the unemployment issue is highly politicised on both the regional and globalscales;thus,if a country cannot combat this issue,the global economy will alsobe affected.Future research should develop a utility maximisation algorithmfor household welfare evaluation,given the percentage risk of income lossowing to COVID-19. | Azlinah Mohamed Zuhaira Muhammad Zain Hadil Shaiba Nazik Alturki Ghadah Aldehim Sapiah Sakri Saiful Farik Mat Yatin Jasni Mohamad Zain | 2023 | Computers, Materials & Continua2023，，4： | 0 |
| 12 | Reimagining safe lithium applications in the living environment and its impacts on human,animal,and plant system显示文摘Lithium's(Li)ubiquitous distribution in the environment is a rising concern due to its rapid proliferation in the modern electronic industry.Li enigmatic entry into the terrestrial food chain raises many questions and uncertainties that may pose a grave threat to living biota.We examined the leverage existing published articles regarding advances in global Li resources,interplay with plants,and possible involvement with living organisms,especially humans and animals.Globally,Li concentration(<10 e300 mg kg1)is detected in agricultural soil,and their pollutant levels vary with space and time.High mobility of Li results in higher accumulation in plants,but the clear mechanisms and specific functions remain unknown.Our assessment reveals the causal relationship between Li level and biota health.For example,lower Li intake(<0.6 mM in serum)leads to mental disorders,while higher intake(>1.5 mM in serum)induces thyroid,stomach,kidney,and reproductive system dysfunctions in humans and animals.However,there is a serious knowledge gap regarding Li regulatory standards in environmental compartments,and mechanistic approaches to unveil its consequences are needed.Furthermore,aggressive efforts are required to define optimum levels of Li for the normal functioning of animals,plants,and humans.This review is designed to revitalize the current status of Li research and identify the key knowledge gaps to fight back against the mountainous challenges of Li during the recent digital revolution.Additionally,we propose pathways to overcome Li problems and develop a strategy for effective,safe,and acceptable applications. | Noman Shakoor Muhammad Adeel Muhammad Arslan Ahmad Muhammad Zain Usman Waheed Rana Arsalan Javaid Fasih Ullah Haider Imran Azeem Pingfan Zhou Yuanbo Li Ghulam Jilani Ming Xu Jorg Rinklebe Yukui Rui | 2023 | Environmental Science and Ecotechnology2023，，3： | 0 |
| 13 | Multi-omics insights into neuronal regeneration and re-innervation显示文摘The regeneration of peripheral nervous system and central nervous system(CNS)neurons after injury remains challenging.We have come a long way since the identification of a 37 k Da protein specific for regenerating peripheral nervous system and CNS nerves(Muller et al.,1985). | Muhammad Zain Chauhan Sanjoy K.Bhattacharya | 2021 | Neural Regeneration Research2021，16，2： | 0 |
| 14 | Medical therapy vs early revascularization in diabetics with chronic total occlusions:A meta-analysis and systematic review显示文摘BACKGROUND Management of chronic total occlusions(CTO)in diabetics is challenging,with a recent trend towards early revascularization[ER:Percutaneous coronary intervention(PCI)and bypass grafting]instead of optimal medical therapy(OMT).We hypothesize that ER improves morbidity and mortality outcomes in diabetic patients with CTOs as compared to OMT.AIM To determine the long term clinical outcomes and to compare morbidity and mortality between OMT and ER in diabetic patients with CTOs.METHODS Potentially relevant published clinical trials were identified in Medline,Embase,chemical abstracts and Biosis(from start of the databases till date)and pooled hazard ratios(HR)computed using a random effects model,with significant P value<0.05.Primary outcome of interest was all-cause death.Secondary outcomes included cardiac death,prompt revascularization(ER)or repeat myocardial infarction(MI).Due to scarcity of data,both Randomized control trials and observational studies were included.4 eligible articles,containing 2248 patients were identified(1252 in OMT and 1196 in ER).Mean follow-up was 45-60 mo.RESULTS OMT was associated with a higher all-cause mortality[HR:1.70,95%confidence interval(CI):0.80-3.26,P=0.11]and cardiac mortality(HR:1.68,95%CI:0.96-2.96,P=0.07).Results were close to significance.The risk of repeat MI was almost the same in both groups(HR:0.97,95%CI:0.61-1.54,P=0.90).Similarly,patients assigned to OMT had a higher risk of repeat revascularization(HR:1.62,95%CI:1.36-1.94,P<0.00001).Sub-group analysis of OMT vs PCI demonstrated higher all-cause(HR:1.98,95%CI:1.36-2.87,P=0.0003)and cardiac mortality(HR:1.87,95%CI:0.96-3.62,P=0.06)in the OMT group.The risk of repeat MI was low in the OMT group vs PCI(HR:0.53,95%CI:0.31-0.91,P=0.02).Data on repeat revascularization revealed no difference between the two(HR:1.00,95%CI:0.52-1.93,P=1.00).CONCLUSION In diabetic patients with CTO,there was a trend for improved outcomes with ER regarding all-cause and cardiac death as compared to OMT.These findings were reinforced with statistical significance on subgroup analysis of OMT vs PCI. | Muhammad Shayan Khan Farhad Sami Hemindermeet Singh Waqas Ullah Ma'en Al-Dabbas Khalid Hamid Changal Tanveer Mir Zain Ali Ameer Kabour | 2020 | World Journal of Cardiology2020，12，11： | 0 |
| 15 | Software Defect Prediction Harnessing on Multi 1-Dimensional Convolutional Neural Network Structure显示文摘Developing successful software with no defects is one of the main goals of software projects.In order to provide a software project with the anticipated software quality,the prediction of software defects plays a vital role.Machine learning,and particularly deep learning,have been advocated for predicting software defects,however both suffer from inadequate accuracy,overfitting,and complicated structure.In this paper,we aim to address such issues in predicting software defects.We propose a novel structure of 1-Dimensional Convolutional Neural Network(1D-CNN),a deep learning architecture to extract useful knowledge,identifying and modelling the knowledge in the data sequence,reduce overfitting,and finally,predict whether the units of code are defects prone.We design large-scale empirical studies to reveal the proposed model’s effectiveness by comparing four established traditional machine learning baseline models and four state-of-the-art baselines in software defect prediction based on the NASA datasets.The experimental results demonstrate that in terms of f-measure,an optimal and modest 1DCNN with a dropout layer outperforms baseline and state-of-the-art models by 66.79%and 23.88%,respectively,in ways that minimize overfitting and improving prediction performance for software defects.According to the results,1D-CNN seems to be successful in predicting software defects and may be applied and adopted for a practical problem in software engineering.This,in turn,could lead to saving software development resources and producing more reliable software. | Zuhaira Muhammad Zain Sapiah Sakri Nurul Halimatul Asmak Ismail Reza M.Parizi | 2022 | Computers, Materials & Continua2022，，4： | 0 |
| 16 | Anti-obesity effect and UHPLC-QTOF-MS/MS based metabolite profiling of Solanum nigrum leaf extract显示文摘Objective:To evaluate the antioxidant potential and pancreatic lipase inhibitory action of optimized hydroethanolic extracts of Solanum nigrum.Methods:Optimized extraction for maximum recovery of metabolites was performed using a combination of freeze-drying and ultrasonication followed by determination of antioxidant and antiobesity properties.The ultra-high performance liquid chromatography equipped with mass spectrometry was used to analyze metabolite profiling of Solanum nigrum.Computational studies were performed using molecular docking and electrostatic potential analysis for individual compounds.The hypolipidemic potential of the most potent extract was assessed in the obese mice fed on fat rich diet.Results:The 80%hydroethanolic extract exhibited the highest extract yield,total phenolic contents,total flavonoid contents along with the strongest 2,2-diphenyl-1-picrylhydrazyl scavenging activity,total antioxidant power,and pancreatic lipase inhibitory properties.The 80%hydroethanolic extract not only regulated the lipid profile of obese mice but also restricted the weight gain in the liver,kidney,and heart.The 80%hydroethanolic extract also reduced alanine transaminase and aspartate transaminase concentrations in serum.The effects of plant extract at 300 mg/kg body weight were quite comparable with the standard drug orlistat.Conclusions:Solanum nigrum is proved as an excellent and potent source of secondary metabolites that might be responsible for obesity mitigation. | Zain Ul Aabideen Muhammad Waseem Mumtaz Muhammad Tayyab Akhtar Muhammad Asam Raza Hamid Mukhtar Ahmad Irfan Syed Ali Raza Muhammad Nadeem Yee Soon Ling | 2022 | Asian Pacific Journal of Tropical Biomedicine2022，12，4： | 0 |
| 17 | Angiotensin converting enzyme inhibitor associated spontaneous herniation of liver mimicking a pleural mass:A case report显示文摘BACKGROUND Spontaneous diaphragmatic herniation of the liver is a rare entity.It may mimic pulmonary mass especially in the absence of trauma.Cough is a common side effect of angiotensin converting enzyme(ACE)inhibitors that may cause diaphragmatic rupture due to a sudden increase in trans-diaphragmatic pressure.We present a case of ACE-inhibitor associated spontaneous herniation of the liver mimicking pleural mass.CASE SUMMARY An 80-year-old woman presented with dry cough for 1 mo and sudden onset of cramping abdominal pain for 1 d.She denied history of trauma,prior surgeries,smoking,alcohol or illicit drug use.She has a history of diabetes and was started on an ACE inhibitor 6 mo ago for the management of hypertension.Examination was remarkable for right upper quadrant tenderness.Lab work-up was unremarkable.Chest X-ray showed a right lower lung opacity suspecting right pleural mass.Chest computed tomography scan ruled out pleural mass,however,revealed herniated right lobe of the liver(3.9 cm×3.6 cm×3.4 cm)into the thoracic cavity through the posterolateral diaphragmatic defect.Laparoscopic repair of the diaphragmatic defect was performed and the ACE inhibitor was stopped.Patients’symptoms had completely resolved on follow-up.CONCLUSION ACE inhibitor-associated cough may cause diaphragmatic liver herniation mimicking pleural mass.Early diagnosis,surgical repair and addressing the triggering factors improve patients’outcomes. | Sameer Saleem Tebha Zain Ali Zaidi Sehrish Sethar Muhammad Asif Abbas Virk Muhammad Nadeem Yousaf | 2022 | World Journal of Hepatology2022，14，4： | 0 |
| 18 | A Transfer Learning Based Approach for COVID-19 Detection Using Inception-v4 Model显示文摘Coronavirus(COVID-19 or SARS-CoV-2)is a novel viral infection that started in December 2019 and has erupted rapidly in more than 150 countries.The rapid spread of COVID-19 has caused a global health emergency and resulted in governments imposing lock-downs to stop its transmission.There is a signifi-cant increase in the number of patients infected,resulting in a lack of test resources and kits in most countries.To overcome this panicked state of affairs,researchers are looking forward to some effective solutions to overcome this situa-tion:one of the most common and effective methods is to examine the X-radiation(X-rays)and computed tomography(CT)images for detection of Covid-19.How-ever,this method burdens the radiologist to examine each report.Therefore,to reduce the burden on the radiologist,an effective,robust and reliable detection system has been developed,which may assist the radiologist and medical specia-list in effective detecting of COVID.We proposed a deep learning approach that uses readily available chest radio-graphs(chest X-rays)to diagnose COVID-19 cases.The proposed approach applied transfer learning to the Deep Convolutional Neural Network(DCNN)model,Inception-v4,for the automatic detection of COVID-19 infection from chest X-rays images.The dataset used in this study contains 1504 chest X-ray images,504 images of COVID-19 infection,and 1000 normal images obtained from publicly available medical repositories.The results showed that the proposed approach detected COVID-19 infection with an overall accuracy of 99.63%. | Ali Alqahtani Shumaila Akram Muhammad Ramzan Fouzia Nawaz Hikmat Ullah Khan Essa Alhashlan Samar MAlqhtani Areeba Waris Zain Ali | 2023 | Intelligent Automation & Soft Computing2023，，2： | 0 |
| 19 | Neural Machine Translation Models with Attention-Based Dropout Layer显示文摘In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of alignment.NMT model has obtained state-of-the-art performance for several language pairs.However,there has been little work exploring useful architectures for Urdu-to-English machine translation.We 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 Transformer.Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen data.The trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,respectively.From 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 frequently.The 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 structure.Therefore,we considered refining the attention-based models by defining an additional attention-based dropout layer.Attention dropout fixes alignment errors and minimizes translation errors at the word level.After 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 score.The ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as well.We 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. | Huma Israr Safdar Abbas Khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain | 2023 | Computers, Materials & Continua2023，，5： | 0 |
| 20 | Multi-Attribute Group Decision-Making Method under Spherical Fuzzy Bipolar Soft Expert Framework with Its Application显示文摘Spherical fuzzy soft expert set(SFSES)theory blends the perks of spherical fuzzy sets and group decision-making into a unified approach.It allows solutions to highly complicated uncertainties and ambiguities under the unbiased supervision and group decision-making of multiple experts.However,SFSES theory has some deficiencies such as the inability to interpret and portray the bipolarity of decision-parameters.This work highlights and overcomes these limitations by introducing the novel spherical fuzzy bipolar soft expert sets(SFBSESs)as a powerful hybridization of spherical fuzzy set theory with bipolar soft expert sets(BSESs).Followed by the development of certain set-theoretic operations and properties of the proposed model,important problems,including the selection of non-powered dam(NPD)sites for hydropower conversion are discussed and solved under the proposed approach.These problems mainly focus on the need for an efficient tool capable of considering the bipolarity of parameters,complicated ambiguities,and multiple opinions.Supporting the new approach by a detailed comparative analysis,it is concluded that the proposed model is more comprehensive and reliable for multi-attribute group decisionmaking(MAGDM)than the previous tools,particularly considering the bipolarity of parameters under SFSES environment. | Mohammed M.Ali Al-Shamiri Ghous Ali Muhammad Zain Ul Abidin Arooj Adeel | 2023 | Computer Modeling in Engineering & Sciences2023，，11： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员