|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Numerical and experimental investigations of liquid mixing in two-stage micro-impinging stream reactors显示文摘A two-stage micro-impinging stream reactor(TS-MISR) that combined a first pre-mixing stage with a second micro-impinging stream reacting stage for continuous multi-component reacting systems has been built from commercial T-junctions and steel micro-capillaries. Both of operating parameters and reactor configurations,such as jet Reynolds number(Rej), volumetric flow ratio(R), the first-stage junction angle(φ), the connecting capillary length(Lc) and connecting capillary diameter(dc), had significant effects on the micromixing efficiency of the reactor. Such effects were investigated for both of the two stage structures, respectively, by experimental and CFD methods and were optimized for the best micromixing performance. Intensified micromixing among at least three reacting components can be achieved in a continuous mode by using TS-MISR; therefore, it is expected that the TS-MISR will produce products of higher quality with more uniform and stable element distribution. | Tianyu Guo Bin Ruan Zhiwei Liu Muhammad Ali Jamal Lixiong Wen Jianfeng Chen | 2017 | Chinese Journal of Chemical Engineering2017，25，4： | 6 |
| 2 | Mango Leaf Disease Identification Using Fully Resolution Convolutional Network显示文摘Due to the high demand for mango and being the king of all fruits,it is the need of the hour to curb its diseases to fetch high returns.Automatic leaf disease segmentation and identification are still a challenge due to variations in symptoms.Accurate segmentation of the disease is the key prerequisite for any computer-aided system to recognize the diseases,i.e.,Anthracnose,apicalnecrosis,etc.,of a mango plant leaf.To solve this issue,we proposed a CNN based Fully-convolutional-network(FrCNnet)model for the segmentation of the diseased part of the mango leaf.The proposed FrCNnet directly learns the features of each pixel of the input data after applying some preprocessing techniques.We evaluated the proposed FrCNnet on the real-time dataset provided by the mango research institute,Multan,Pakistan.To evaluate the proposed model results,we compared the segmentation performance with the available state-of-the-art models,i.e.,Vgg16,Vgg-19,and Unet.Furthermore,the proposed model’s segmentation accuracy is 99.2%with a false negative rate(FNR)of 0.8%,which is much higher than the other models.We have concluded that by using a FrCNnet,the input image could learn better features that are more prominent and much specific,resulting in an improved and better segmentation performance and diseases’identification.Accordingly,an automated approach helps pathologists and mango growers detect and identify those diseases. | Rabia Saleem Jamal Hussain Shah Muhammad Sharif Ghulam Jillani Ansari | 2021 | Computers, Materials & Continua2021，，12： | 2 |
| 3 | Quality and Crop Yield Potential of Moderately Degraded Alfisols Under Different Nutrient Inputs and Cropping Patterns显示文摘Crop performance on degraded soil needs special management practices to overcome soil quality limitations. In a 2-year(from summer 2006 to winter 2007–2008) field trial on a moderately degraded Alfisol in Swabi District(34°7′12′′N, 72°28′20′′E), Pakistan,the effects of three cropping patterns, cereal-cereal(CC), cereal-legume(CL), and cereal-cereal and legume intercrop(CLI), were tested in main plots under four fertilization treatments in sub-plots, including no fertilization(control), farmers' practice(FP, 60:45 kg ha^(-1) N:P_2O_5), recommended dose(RD, 120:90:60 kg ha^(-1) N:P_2O_5:K_2O), and integrated nutrient management(INM, 20 t ha^(-1) farmyard manure integrated with 50% N, 100% P, and K of recommended dose), using a split-plot randomized complete block design. The performance of CL was superior than CC in plant height, leaf area index(LAI), cob length, grain yield, biological yield, and grain protein(8%, 26%, 8%, 5%, 10%, and 8% increases, respectively), while CLI confirmed significant improvement only in LAI(25%) over CC. Response to nutrient inputs from all sources was in the order of INM > RD > FP > control, and the maximum net economic return by INM(23% and 2.5 times higher than RD and FP, respectively) indicated severe deficiency of both macro-and micro-nutrients in the soil as well as degraded physical properties. Increases in soil organic matter, total N, total mineral N, available P and K, total porosity, and available water-holding capacity by 6%, 34%, 24%, 50%, 13%, 5%, and 7%, respectively, and decrease in soil bulk density by 4% after four crop seasons indicated optimistic changes in soil quality as a result of the combined effects of fertilization from organic and inorganic sources and legumes within crop rotation. This study suggests that keeping the soil covered under cereal-legume rotation crops all year round and treatment with INM(50% N from organic source and 50% from inorganic source) are the best management practice for sustained production on degraded Alfisols. | Wiqar AHMAD Farmanullah KHAN Zahir SHAH Muhammad Jamal KHAN | 2019 | Pedosphere2019，29，2： | 2 |
| 4 | A Comparative Study on Hemp(Cannabis sativa)Essential Oil Extraction Using Traditional and Advanced Techniques显示文摘A comparative study of Cannabis sativa(Hemp)essential constituents obtained by using Supercritical Fluid Extraction(SCFE),Steam Distillation(SD)and Hydrodistillation(HD)is presented here.The optimized extraction temperatures were 130,110and 50℃for hydrodistillation,steam distillation and supercritical fluid extraction respectively.The essential oil of C.sativa was analyzed by using Gas chromatography mass spectrometry(GC-MS).A total of 33,30and 31components have been identified in HD,SD and SCFE respectively.Yield of essential oil using SCFE(0.039%)was more than HD(0.025%)and SD(0.035%)extraction respectively.The main component of sesquiterpenes obtained by hydrodistillation at 130℃with their percentages included caryophyllene(40.58%),trans-α-bergamotene(5.41%),humulene(10.97%),cis-β-farnesene(8.53%)and monoterpenes includedα-pinene(2.13%),d-limonene(6.46%),p-cymol(0.65%)and cineole(2.58%)respectively.The main component of sesquiterpenes obtained by SD steam distillation at110℃including caryophyllene(38.60%)trans-α-bergamotene(4.22%),humulene(10.26%),cis-β-farnesene(6.67%)and monoterpenes includedα-pinene(3.21%),d-limonene(7.07%),p-cymol(2.59%)and cineole(3.88%)whereas the more percentages of major components were obtained by SCFE at 50℃included caryophyllene(44.31%),trans-α-bergamotene(6.79%),humulene(11.97%)cis-β-farnesene(9.71%)and monoterpenes includedα-pinene(0.45%),d-limonene(2.13%)p-cymol(0.19%)and cineole(1.38%)respectively.We found yield/efficiency,chemical composition,quality of the essential oils by supercritical fluid extraction superior in terms of modern,green,saving energy and a rapid approach as compared to traditional techniques. | Saima naz Muhammad Asif Hanif Tariq Mahmood Ansari Jamal Nasar Al-Sabahi | 2017 | 光谱学与光谱分析2017，37，1： | 1 |
| 5 | Classification of Citrus Plant Diseases Using Deep Transfer Learning显示文摘In recent years,the field of deep learning has played an important role towards automatic detection and classification of diseases in vegetables and fruits.This in turn has helped in improving the quality and production of vegetables and fruits.Citrus fruits arewell known for their taste and nutritional values.They are one of the natural and well known sources of vitamin C and planted worldwide.There are several diseases which severely affect the quality and yield of citrus fruits.In this paper,a new deep learning based technique is proposed for citrus disease classification.Two different pre-trained deep learning models have been used in this work.To increase the size of the citrus dataset used in this paper,image augmentation techniques are used.Moreover,to improve the visual quality of images,hybrid contrast stretching has been adopted.In addition,transfer learning is used to retrain the pre-trainedmodels and the feature set is enriched by using feature fusion.The fused feature set is optimized using a meta-heuristic algorithm,the Whale Optimization Algorithm(WOA).The selected features are used for the classification of six different diseases of citrus plants.The proposed technique attains a classification accuracy of 95.7%with superior results when compared with recent techniques. | Muhammad Zia Ur Rehman Fawad Ahmed Muhammad Attique Khan Usman Tariq Sajjad Shaukat Jamal Jawad Ahmad Iqtadar Hussain | 2022 | Computers, Materials & Continua2022，，1： | 1 |
| 6 | First report on molecular characterization of Leishmania species from cutaneous leishmaniasis patients in southern Khyber Pakhtunkhwa province of Pakistan显示文摘Objective: To report presence of Leishmania major in Khyber Pakhtunkhwa of Pakistan, where cutaneous leishmaniasis(CL) is endemic and was thought to be caused by Leishmania tropica only. Methods: Biopsy samples from 432 CL suspected patients were collected from 3 southern districts of Khyber Pakhtunkhwa during years 2011–2016. Microscopy on Giemsa stained slides were done followed by amplification of the ribosomal internal transcribed spacer 1 gene. Results: Leishmania amastigotes were detected by microscopy in 308 of 432 samples(71.3%) while 374 out of 432 samples(86.6%) were positive by ribosomal internal transcribed spacer 1 PCR. Subsequent restriction fragment length polymorphism confirmed Leishmania tropica in 351 and Leishmania major in 6 biopsy samples. Conclusions: This study is the first molecular characterization of Leishmania species in southern Khyber Pakhtunkhwa. It confirmed the previous assumptions that anthroponotic CL is the major CL form present in Khyber Pakhtunkhwa province. Furthermore, this is the first report of Leishmania major from a classical anthroponotic CL endemic focus identified in rural areas of Kohat district in southern Khyber Pakhtunkhwa. | Mubbashir Hussain Shahzad Munir Sultan Ayaz Bahar Ullah Khattak Taj Ali Khan Niaz Muhammad Muhammad Anees Hazir Rahman Muhammad Qasim Muhammad Ameen Jamal Irfan Ahmed Kashif Rahim Humaira Mazhar Noha Watanay Mohamed Kasbari | 2017 | Asian Pacific Journal of Tropical Medicine2017，10，7： | 1 |
| 7 | Distribution, toxicity level, and concentration of polycyclic aromatic hydrocarbons (PAHs) in surface soil and groundwater of Rawalpindi, Pakistan显示文摘 | Beenish Saba Imran Hashmi Muhammad Ali Awan Habib Nasir Sher Jamal Khan | 2012 | 2012 (1-3)2012，，1： | 1 |
| 8 | Job Stress,Type-A Behavior,and Well-Being:A Cross-Cultural Examination显示文摘 | Muhammad Jamal | | 0，，01： | 1 |
| 9 | Exploring multi-level risk factors and post-war burdens of trachomatous trichiasis among displaced population in Raya Kobo districts, implication for urgent action显示文摘AIM:To estimate post-war burdens of trachomatous trichiasis(TT)and multi-level risk factors among displaced population in Raya Kobo districts,implication for urgent action.METHODS:A community-based cross-sectional study was conducted among 603 participants from randomly selected 14 displaced slums in the Raya Kobo district.The data was collected from February 16th to March 30th,2023.Study participants were selected using the multistage sampling technique.A structured questionnaire and ophthalmic loupe with×2.5 magnificence were used to collect from participants.Multi-level binary logistic regression was used to determine associated factors with TT infection.Adjusted odds ratio(AOR)with 95%confidence interval(CI)were claimed for the strength of association at P<0.05.RESULTS:We recruited 602(99.9%)participants for the final analysis.From the total,126(20.9%)and 98(16.3%,95%CI:13.5%-19.4%)participants were diagnosed with active trachoma&TT infection,respectively.Being age≥45y(AOR=7.9,95%CI:2.4-25.3),having multiple eye infections(AOR=2.73,95%CI:1.47-5.29),poor wealth index(AOR=9.2;95%CI:2.7-23.7)and twice face washing per day(AOR=0.082,95%CI:0.03-0.21)has identified as individual as factors for TT infection.Whereas,distance between clean water source≥10 km(AOR=6.5,95%CI:3.9-31.3),and latrine availability(AOR=0.35,95%CI:0.21-0.58)were the two community-level factors associated with TT infections.CONCLUSION:The high prevalence of TT infection post-war throughout the study districts indicates a need for urgent clinical intervention in addition to rapid scaling up surgery,antibiotics,facial cleanliness,and environmental improvement(SAFE)strategies,strategy for high-risk population.Age≥45y,distance from the clean water source,poor wealth indexes,and eye infection are identified to be risk factors for TT infection.Furthermore,community-level preventative factors for TT infection are found as latrine availability and face washing practice. | Muhammad Jamal Fassikaw Kebede | 2023 | International Journal of Ophthalmology(English edition)2023，16，8： | 0 |
| 10 | A Machine Learning Approach for Expression Detection in Healthcare Monitoring Systems显示文摘Expression detection plays a vital role to determine the patient’s condition in healthcare systems.It helps the monitoring teams to respond swiftly in case of emergency.Due to the lack of suitable methods,results are often compromised in an unconstrained environment because of pose,scale,occlusion and illumination variations in the image of the face of the patient.A novel patch-based multiple local binary patterns(LBP)feature extraction technique is proposed for analyzing human behavior using facial expression recognition.It consists of three-patch[TPLBP]and four-patch LBPs[FPLBP]based feature engineering respectively.Image representation is encoded from local patch statistics using these descriptors.TPLBP and FPLBP capture information that is encoded to find likenesses between adjacent patches of pixels by using short bit strings contrary to pixel-based methods.Coded images are transformed into the frequency domain using a discrete cosine transform(DCT).Most discriminant features extracted from coded DCT images are combined to generate a feature vector.Support vector machine(SVM),k-nearest neighbor(KNN),and Naïve Bayes(NB)are used for the classification of facial expressions using selected features.Extensive experimentation is performed to analyze human behavior by considering standard extended Cohn Kanade(CK+)and Oulu–CASIA datasets.Results demonstrate that the proposed methodology outperforms the other techniques used for comparison. | Muhammad Kashif Ayyaz Hussain Asim Munir Abdul Basit Siddiqui AaqifAfzaal Abbasi Muhammad Aakif Arif Jamal Malik Fayez Eid Alazemi Oh-Young Song | 2021 | Computers, Materials & Continua2021，，5： | 0 |
| 11 | Bioinformatics Analysis of the Relationship between Lifestyle and Prostate Cancer显示文摘In this study,we assessed the relationship between lifestyle and prostate cancer.We selected the Gene Expression Omnibus(GEO)dataset GSE10306 to analyze the expression levels of ataxin10(ATXN10),interferon related developmental regulator 1(IFRD1),formin-binding protein 1 like(FNBP1 L)and THO complex 2(THOC2)in prostate biopsies pre and post intensive nutrition and lifestyle intervention.Following a three-month intervention of nutrition and lifestyle,these genes showed a significant down-regulation.ONCOMINE database analysis showed that the four genes exhibited high expression in prostate cancer tissues compared with normal prostate tissues,which indicated that comprehensive lifestyle changes may modify the progression of prostate cancer mediated by altering the expression of ATXN10,FNBP1 L,THOC2 and IFRD1.Among the four genes,the high expression of IFRD1 was found to indicate a worse overall survival(OS)and disease-free survival(DFS).FNBP1 L and THOC2 were associated with CD8+T cell infiltration of prostate cancer.We also speculated a possible regulatory network for lifestyle to influence miRNA,subsequently influencing the expression of relevant genes.Our findings suggested that these genes may be used as potential target sites for the treatment of prostate cancer. | XIONG Youming YIN Qian YUAN Wen WANG Meng XIE Tian SUN Jiaxinq JAMAL Muhammad SONG Tianbao CHEN Bei HONG Zixi QIN Caiqin | 2020 | Wuhan University Journal of Natural Sciences2020，25，3： | 0 |
| 12 | Influencing factors on the accuracy of local geoid model显示文摘Different modification methods and software programs were developed to obtain accurate local geoid models in the past two decades.The quantitative effect of the main factors on the accuracy of local geoid modeling is still ambiguous and has not been clearly diagnosed yet.This study presents efforts to find the most influential factors on the accuracy of the local geoid model,as well as the amount of each factor’s effect quantitatively.The methodology covers extracting the quantitative characteristics of 16 articles regarding local geoid models of different countries.The Statistical Package of Social Sciences(SPSS)software formulated a strong multiple regression model of correlation coefficient r = 0.999 with a high significance coefficient of determination R^2 = 0.997 and adjusted R^2 = 0,98 for the required effective factors.Then,factor analysis is utilized to extract the dominant factors which include:accuracy of gravity data(40%),the density of gravity data(25%)(total gravity factors is 65%),the Digital Elevation Model(DEM)resolution(16%),the accuracy of GPS/leveling points(10%)and the area of the terrain of the country/state under the study(9%).These results of this study will assist in developing more accurate local geoid models. | Shazad Jamal Jalal Tajul Ariffin Musa Ami Hassan Md Din Wan Anom Wan Aris WenBin Shen Muhammad Faiz Pa’suya | 2019 | Geodesy and Geodynamics2019，10，6： | 0 |
| 13 | Heat Transfer Enhancement of an Automobile Engine Radiator using ZnO Water Base Nanofluids显示文摘In this research paper, the forced convective heat transfer enhancement of a Suzuki Mehran(VXR) 2016 radiator(heat exchanger) along with pressure drop and friction factor by utilizing Zinc oxide(Zn O) water based nanofluids has been experimentally studied. Three types of nanofluids with different volumetric concentrations of Zn O nanoparticles(0–0.3%) were employed in order to understand its effect on heat transfer enhancement. The experimental setup was completely designed as closely as possible to the car cooling system. The experimentation has been done under laminar flow conditions(186≤Re≤1127) at different fluid volume flow rates(2–12 L/min) and constant fluid inlet temperature(70°C) to the automobile radiator. A maximum enhancement in heat transfer rate, overall heat transfer coefficient and Nusselt number was obtained up to 41%, 50% and 31% by using nanofluid with 0.2% volumetric concentration of nanoparticles respectively. On the other hand, the mean enhancement in pressure drop and friction factor was obtained up to 47% and 46% by using nanofluid with the same volumetric concentration of nanoparticles i.e. 0.2% respectively. The experimental results also revealed that the heat transfer rate, overall heat transfer coefficient and Nusselt number of nanofluids increases by increasing the volume flow rates and volumetric concentration of nanoparticles. However, these thermal performance parameters of nanofluids started to decline when the volumetric concentration of nanoparticles was increased from 0.2% to 0.3%. Furthermore, pressure drop and friction factor of nanofluids increase by increasing the volumetric concentration of nanoparticles, while pressure drop increases and friction factor decreases by increasing the volume flow rate of nanofluids respectively. At the end, the thermal efficiency of automobile radiator with high cooling rates was obtained by using nanofluid with 0.2% volumetric concentration of nanoparticles. | Muhammad QASIM Muhammad SAJID KAMRAN Muhammad AMMAR Muhammad ALI JAMAL Muhammad YASAR JAVAID | 2020 | Journal of Thermal Science2020，29，4： | 0 |
| 14 | Detection of ROS and translocation of ERP-57 in apoptotic induced human neuroblastoma(SH-SY5Y)cells显示文摘Several toxic compounds are known to induce apoptosis in mammalian cell lines.The human neuroblastoma cells(SHSH-SY5Y)were exposed to the phosphatase inhibiting toxin okadaic acid(OA)or hydrogen peroxide(H2O2)to induce apoptosis as well as generate reactive oxygen species(ROS).Mitoxantrone(MXT)was used as a positive control for apoptosis.The SHSH-SY5Y cells were transfected with eukaryotic expression plasmid pHyPer-dMito encoding mitochondrial-targeted fluorescent or pHyPer-dCito encoding cytoplasmic-targeted fluorescent sensor for hydrogen peroxide(HyPer).The ERp57,also called GRP58(Glucose-regulated protein 58),is a stress protein induced in conditions like glucose starvation and viral infection.Recently ERp57 was shown to translocate from the endoplasmatic reticulum to the cell surface in anthracycline-induced apoptotic cells.ERp57 co-translocation together with calreticulin has been suggested to be crucial for recognizing tumor cells to induce immunogenic cell death.ERp57 translocation after exposure to okadaic acid was studied using immunofluorescence and confocal microscopy.These studies indicated that okadaic acid has induced the translocation of ERp57 to the cellular membrane. | ATIF KAMIL MUBARAK ALI KHAN MUHAMMAD AASIM NADIR ZAMAN KHAN RAHAM SHER KHAN MUHSIN JAMAL WAQAR AHMAD MIR AZAM KHAN FAZAL JALIL | 2019 | BIOCELL2019，43，3： | 0 |
| 15 | FPGA Implementation of Elliptic-Curve Diffie Hellman Protocol显示文摘This paper presents an efficient crypto processor architecture for key agreement using ECDH(Elliptic-curve Diffie Hellman)protocol over GF2163.The composition of our key-agreement architecture is expressed in consisting of the following:(i)Elliptic-curve Point Multiplication architecture for public key generation(DESIGN-I)and(ii)integration of DESIGN-I with two additional routing multiplexers and a controller for shared key generation(DESIGN-II).The arithmetic operators used in DESIGN-I and DESIGNII contain an adder,squarer,a multiplier and inversion.A simple shift and add multiplication method is employed to retain lower hardware resources.Moreover,an essential inversion operation is operated using the Itoh-Tsujii algorithm with similar hardware resources of used squarer and multiplier units.The proposed architecture is implemented in a Verilog HDL.The implementation results are given on a Xilinx Virtex-7 FPGA(field-programmable gate array)device.For DESIGN-I and DESIGN-II over GF2163,(i)the utilized Slices are 3983 and 4037,(ii)the time to compute one public key and a shared secret is 553.7μs and 1170.7μs and(iii)the consumed power is 29μW and 57μW.Consequently,the achieved area optimized and power reduced results show that the proposed ECDH architecture is a suitable alternative(to generate a shared secret)for the applications that require low hardware resources and power consumption. | Sikandar Zulqarnain Khan Sajjad Shaukat Jamal Asher Sajid Muhammad Rashid | 2022 | Computers, Materials & Continua2022，，10： | 0 |
| 16 | Bacterial Spectrum and Antimicrobial Profile of Pediatric Blood Stream Infection at a Tertiary Care Hospital in Pakistan显示文摘Objectives Blood stream infections(BSIs)are the main cause of morbidity and mortality in children worldwide.The present study was carried out to determine the prevalence of BSI with a focus on the identification of the causative agent of BSI,and to further evaluate the antibiotic susceptibility profile of the causing bacterial pathogens.Methods A cross-section study was carried out at the tertiary care hospital in Peshawar,Pakistan from January to December,2018.Blood samples were collected in BACTEC™botdes and standard microbiological protocols were applied for the isolation and identification of bacterial strains.The antibiotic susceptibility tests were performed using disc diffusion method as per the 2014 guideline of Clinical Laboratory Standard Institute(CLSI).Results Of 567 blood cultures in total,111(19.6%)were positive for BSI.Male children were 64%(71/111)and female children were 36%(40/111).For the causative predominant group of microorganisms,Gramnegative bacteria were identified in 79(71.1%)isolates,and Gram-positive bacteria in 32(28.9%)isolates.The common bacteria of isolates were S.typhi(n=35,31.5%),E.coli(n=19,17.1%),S.aureus(n=18,16.2%),K.pneumonia(n=12,10.8%),and Enterococcus species(n=7,6.3%).The 36.7%(29/79)isolates of Gram-negative bacteria were ESBL producers,and 61.1%(11/18)of S.aureus isolates were methicillin resistant.Overall,72.9%isolates were multidrug resistant.Conclusions Gram-negative bacteria were the main cause of pediatric BSIs,where the predominant microorganism was S.卯hi.Remarkably,majority of the S.typhi isolates were resistant to ciprofloxacin. | Anees Muhammad Sadiq Noor Khan Tahir Jamal Irshad Ul Haq Abdul Jabbar Ihsan Ali | 2020 | Chinese Medical Sciences Journal2020，35，4： | 0 |
| 17 | An Empirical Analysis of Defense-Economic Growth Relationship显示文摘Most of the developing and developed countries try to make peace and promote it but still it is seen that large portion of the overall global GDP is spent on the defense sector. This study surveys defense-growth nexus by incorporating openness to trade, external debt, gross capital formation and labor force in production function. The study uses annual time series data over the period 1972-2016. For estimation purposes, the study employed ADF unit root test and P-P unit root test for testing stationarity properties, ARDL Bound test to cointegration used for testing long run relationship. The empirical evidence of the study reveals that Economic growth is positively affected by spending on defense sector, capital investments, labor force, and openness to trade in long run while external debt has a negative effect on economic growth. Apart from this, empirical evidence also suggests that in short run;there is positive imperative role of capital investment, defense spending, and openness to trade in growth process, while external debt retards the pace of economic growth. Results of the study indicates that defense spending could be used as a fiscal tool for achieving sustainable growth, government should invest high R&D in defense. | Muhammad Tayyab Sohail Qaiser Jamal Umair Shad | 2018 | Journal of Business Administration Research2018，1，1： | 0 |
| 18 | Can outer-to-outer diameter be used alone in diagnosing appendicitis on 128-slice MDCT?显示文摘AIM: To assess the frequency of visualization, position and diameter of normal appendix on 128-slice multidetector computed tomography(MDCT) in adult population.METHODS: Retrospective cross sectional study conducted at Radiology Department, Dallah Hospital, Riyadh, Saudi Arabia from March 2013 to October 2013. Non-enhanced computed tomography scans of abdomen and pelvis of 98 patients presenting with hematuria(not associated with abdominal pain, fever or colonic disease) were reviewed by two radiologists, blinded to patient history. The study group included 55 females and 43 males with overall mean age of 54.7 years(range 21 to 94 years). The coronal reformatted images were reviewed in addition to the axial images. The frequency of visualization of appendix was recorded with assessment of position, diameter and luminal contents.RESULTS: The appendix was recorded as definitely visualized in 99% of patients and mean outer-to-outer diameter of the appendix was 5.6 ± 1.3 mm(range 3.0-11.0 mm).CONCLUSION: MDCT with its multiplanar reformation display is extremely useful for visualization of normal appendix. The normal appendix is very variable in its position and diameter. In the absence of other signs, the diagnosis of acute appendix should not be made solely on outer-to-outer appendiceal diameter. | Jamal Yaqoob Muhammad Idris Muhammad Shahbaz Alam Nazia Kashif | 2014 | World Journal of Radiology2014，6，12： | 0 |
| 19 | Improved Shark Smell Optimization Algorithm for Human Action Recognition显示文摘Human Action Recognition(HAR)in uncontrolled environments targets to recognition of different actions froma video.An effective HAR model can be employed for an application like human-computer interaction,health care,person tracking,and video surveillance.Machine Learning(ML)approaches,specifically,Convolutional Neural Network(CNN)models had beenwidely used and achieved impressive results through feature fusion.The accuracy and effectiveness of these models continue to be the biggest challenge in this field.In this article,a novel feature optimization algorithm,called improved Shark Smell Optimization(iSSO)is proposed to reduce the redundancy of extracted features.This proposed technique is inspired by the behavior ofwhite sharks,and howthey find the best prey in thewhole search space.The proposed iSSOalgorithmdivides the FeatureVector(FV)into subparts,where a search is conducted to find optimal local features fromeach subpart of FV.Once local optimal features are selected,a global search is conducted to further optimize these features.The proposed iSSO algorithm is employed on nine(9)selected CNN models.These CNN models are selected based on their top-1 and top-5 accuracy in ImageNet competition.To evaluate the model,two publicly available datasets UCF-Sports and Hollywood2 are selected. | Inzamam Mashood Nasir Mudassar Raza Jamal Hussain Shah Muhammad Attique Khan Yun-Cheol Nam Yunyoung Nam | 2023 | Computers, Materials & Continua2023，76，9： | 0 |
| 20 | A Two Stream Fusion Assisted Deep Learning Framework for Stomach Diseases Classification显示文摘Due to rapid development in Artificial Intelligence(AI)and Deep Learning(DL),it is difficult to maintain the security and robustness of these techniques and algorithms due to emergence of novel term adversary sampling.Such technique is sensitive to these models.Thus,fake samples cause AI and DL model to produce diverse results.Adversarial attacks that successfully implemented in real world scenarios highlight their applicability even further.In this regard,minor modifications of input images cause“Adversarial Attacks”that altered the performance of competing attacks dramatically.Recently,such attacks and defensive strategies are gaining lot of attention by the machine learning and security researchers.Doctors use different kinds of technologies to examine the patient abnormalities including Wireless Capsule Endoscopy(WCE).However,using WCE it is very difficult for doctors to detect an abnormality within images since it takes enough time while inspection and deciding abnormality.As a result,it took weeks to generate patients test report,which is tiring and strenuous for them.Therefore,researchers come out with the solution to adopt computerized technologies,which are more suitable for the classification and detection of such abnormalities.As far as the classification is concern,the adversarial attacks generate problems in classified images.Now days,to handle this issue machine learning is mainstream defensive approach against adversarial attacks.Hence,this research exposes the attacks by altering the datasets with noise including salt and pepper and Fast Gradient Sign Method(FGSM)and then reflects that how machine learning algorithms work fine to handle these noises in order to avoid attacks.Results obtained on the WCE images which are vulnerable to adversarial attack are 96.30%accurate and prove that the proposed defensive model is robust when compared to competitive existing methods. | Muhammad Shahid Amin Jamal Hussain Shah Mussarat Yasmin Ghulam Jillani Ansari Muhamamd Attique Khan Usman Tariq Ye Jin Kim Byoungchol Chang | 2022 | Computers, Materials & Continua2022，，11： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员