检索结果-南通市图书馆

Deep Learning Framework for Precipitation Prediction Using Cloud Images

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8期72卷 4201-4213页

作者： Mirza Adnan Baig Ghulam Ali Mallah Noor Ahmed Shaikh shah abdul latif university Khairpur77150Pakistan

Precipitation prediction(PP)have become one of the significant research areas of deep learning(DL)and machine vision(MV)techniques are frequently used to predict the weather variables(WV).Since the climate change has left significant impact upon weather variables(WV)and continuously changes are observed in temperature,humidity,cloud patterns and other *** cloud images contain sufficient information to predict the precipitation pattern but due to changes in climate,the complex cloud patterns and rapid shape changing behavior of clouds are difficult to consider for rainfall *** of rainfall would provide more meticulous assistance to the farmers to know about the weather conditions and to care their cash *** research proposes a framework to classify the dark cloud patterns(DCP)for prediction of *** framework consists upon three steps to classify the cloud images,first step tackles noise reduction operations,feature selection and preparation of *** step construct the decision model by using convolutional neural network(CNN)and third step presents the performance visualization by using confusion matrix,precision,recall and accuracy *** research contributes(1)real-world clouds datasets(2)method to prepare datasets(3)highest classification accuracy to predict estimated as 96.90%.

关键词： Machine vision SIFT features dark cloud patterns precipitation agriculture

A Framework for e-Voting System Based on Blockchain and Distributed Ledger Technologies

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7期72卷 417-440页

作者： shahid Hussain Danwar Javed Ahmed Mahar Aneela Kiran Institute of Computer Science Shah Abdul Latif UniversityKhairpur66020SindhPakistan

Election allows the voter of a country to select the most suitable group of candidates to run the *** in Pakistan is simply paper-based method but some certain political and socio-economic issues turn that simple process in complicated and disputes *** of such problems are consisting of many methods including the e-voting *** e-voting system facilitates the voters to cast their votes by electronic means with very easy and convenient *** also allows maintaining the security and secrecy of the voter along with election *** voting reduces the human-involvement throughout the process from start to the *** system is not established yet in ***,every election is disputed *** this paper we proposed the framework of an e-voting system and simulation with the use of blockchain ledger *** proposed framework owns the capacity to deal with ballots in *** novelty of the framework is that the e-voting system is linked to National Database and Registration Authority(NADRA)database which assures voter’s *** fundamental requirements were kept in consideration during the performance evaluation of the *** results are processed and depicted specially with reference to the number of voters and voting stations,real time of vote casting,network bandwidth and controlling *** results support the decision makers and guide them in the foundation and customization of an e-voting system in Pakistan.

关键词： Simulation modeling e-voting system blockchain technology distributed ledger

Decision Support System for Diagnosis of Irregular Fovea

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6期71卷 5343-5353页

作者： Ghulam Ali Mallah Jamil Ahmed Muhammad Irshad Nazeer Mazhar Ali Dootio Hidayatullah Shaikh Aadil Jameel shah abdul latif university Khairpur77150Pakistan Sukkur IBA university Sukkur7720Pakistan shaheed Benazir university Layari Karachi77202Pakistan

Detection of abnormalities in human eye is one of the wellestablished research areas of Machine *** Learning techniques are widely used for the diagnosis of RetinalDiseases(RD).Fovea is one of the significant parts of retina which would be prevented before the involvement of Perforated Blood Vessels(PBV).Retinopathy Images(RI)contains sufficient information to classify structural changes incurred upon PBV but Macular Features(MF)and Fovea Features(FF)are very difficult to detect because features ofMFand FF could be found with Similar Color Movements(SCM)with minor *** paper presents novel method for the diagnosis of Irregular Fovea(IF)to assist the doctors in diagnosis of irregular *** considering all above problems this paper proposes a three-layer decision support system to explore the hindsight knowledge of RI and to solve the classification problem of *** first layer involves data preparation,the second layer builds the decision model to extract the hidden patterns of fundus images by using Deep Belief Neural Network(DBN)and the third layer visualizes the results by using confusion *** paper contributes a data preparation algorithm for irregular fovea and a highest estimated classification accuracy measured about 96.90%.

关键词： Machine learning deep belief neural network eye disease fovea

A Secure and Efficient Information Authentication Scheme for E-Healthcare System

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 3877-3896页

作者： Naveed Khan Jianbiao Zhang Ghulam Ali Mallah Shehzad Ashraf Chaudhry Faculty of Information Technology Beijing University of TechnologyBeijing100124China Department of Computer Science Shah Abdul Latif UniversityKhairpur66111Pakistan Department of Computer Engineering Faculty of Engineering ArchitectureNisantasi UniversityIstanbul34398Turkey

The mobile cellular network provides internet connectivity for heterogeneous Internet of Things(IoT)*** cellular network consists of several towers installed at appropriate locations within a smart *** cellular towers can be utilized for various tasks,such as e-healthcare systems,smart city surveillance,traffic monitoring,infrastructure surveillance,or sidewalk *** is a primary concern in data broadcasting,particularly authentication,because the strength of a cellular network’s signal is much higher frequency than the associated one,and their frequencies can sometimes be aligned,posing a significant *** a result,that requires attention,and without information authentication,such a barrier cannot be ***,we design a secure and efficient information authentication scheme for IoT-enabled devices tomitigate the flaws in the e-healthcare *** proposed protocol security shall check formally using the Real-or-Random(ROR)model,simulated using ProVerif2.03,and informally using pragmatic *** comparison,the performance phenomenon shall tackle by the already result available in the MIRACL cryptographic lab.

关键词： IoT-enable device e-healthcare authentication edge computing

AN AGENT BASED FRAMEWORK FOR INSIDER THREAT,PRIVACY AND ADAPTABILITY MANAGEMENT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

AN AGENT BASED FRAMEWORK FOR INSIDER THREAT,PRIVACY AND ADAP...

Suppressed response to hormonal contraceptives in women of Khairpur, Sindh, Pakistan

The 2nd Session of 2010 Workshop of Pakistan Academy of Sciences

作者： Ghulam Ali Mallah Noor Ahmed Shaikh Zubair Ahmed Shaikh Department of Computer Science Shah Abdul Latif UniversityKhairpurPakistan

This paper targets Network Security and more specifically deals with Insider *** Agents have been used as a technology in this *** literature survey shows that FIPA（Foundation for Intelligent Physical Agents） and MASIF（Mobile System Interoperability Facility） agent standards have many limitations,therefore their combination or a new standard is proposed for a true agent *** milestones were set and bottom-up approach is used to achieve the overall *** based vulnerability assessment model has been developed in which various practical issues have been identified and appropriate solutions have been ***-dependent and platform-independent approaches were used to achieve the task and results of both approaches are *** is the key source of identifying insider threat therefore an Agentbased Profiling model has been developed that considers an individual’s personality profile to identify real personality.A FIPAcompliant agent framework（ACENET） for profiling has been developed to achieve the *** framework allows identifying,online and offline,anomalies in user *** ACENET（Agent collaborative Environment ***） scores every user of the organization and maintains a detailed profile of whether a legitimate user is doing any malicious *** framework checks out whether user activities are in accordance with organization’s policy or *** is adaptable to deploy in any organization where agents are designed as services on the top layers of the *** threats have been categorized in various classes and for each category agents have been *** privacy as a major concern,the professional issues were studied and it is proposed that the organization may announce in advance what can be monitored and what cannot be monitored through a user monitoring *** framework has been tested on real data and the performance has also been evaluated on the basis of specified paramete

关键词： Insider threat software agents privacy agent framework .NET framework network security

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Health 2013年第11期5卷 1848-1852页

作者： Yasmeen Faiz Kazi Sobia Saleem Nasreen Kazi Department of Microbiology Shah Abdul Latif University Khairpur Pakistan Department of Pharmacology Liaqat University of Medical and Health Sciences Jamshoro Pakistan

Objective: Contraception has gained gradual popularity in many parts of the developing world including Pakistan. Despite this increase in acceptance, the birth rate remains high. Failure of contraception has been reported in the literature, which made us aim to conduct this study. The efficiency of hormonal contraceptives in the study area was assessed and this is the first report from Pakistan. Methods: A total of 200 women (aged 20-30 and 31-40 years;n = 100 each) with minimum consistent use of hormonal contraceptives in the form of pills (Combined oral contraceptives) for 12 months were enrolled in this study. Blood samples were collected from women of each age group and corresponding control groups (n = 100) from local hospitals and reproductive health service center. Serum levels of the fertility hormones viz leutinizing and follicle stimulating hormones were measured through ELISA technique. Results: Our data revealed that over all in the both age groups, 72% women had normal, 16% increased and 12% showed decreased levels of leutinizing hormone (p > 0.05) and 67% women showed normal, 33% showed decreased and no increased levels were found for follicle stimulating hormone (p > 0.05). No age-wise significant difference in response was observed among both the age groups tested. Conclusion: Statistically insignificant difference in serum leutinizing hormone and follicle stimulating hormone seen among both the age groups of hormonal contraceptive users and control group indicates less effective hormonal contraception response in the study area.

关键词： Contraceptive Women Response

Okra Leaves—Agricultural Waste for the Removal of Cr(III) and Cr(VI) from Contaminated Water

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

American Journal of Analytical Chemistry 2016年第4期7卷 395-409页

作者： Mazhar Iqbal Khaskheli Saima Qayyum Memon Zaheer Ahmed Chandio Wahid Bux Jatoi Mohammad Tariq Mahar Faiz Mohammad Khokhar M. A. Kazi Institute of Chemistry University of Sindh Jamshoro Pakistan Institute of Chemistry Shah Abdul Latif University Khairpur Sindh Pakistan

The present study demonstrates the sorptive efficiency of okra leaves for the Cr(III) and Cr(VI) in aqueous system. The batch dynamic sorption method was carried out as the function of the pH of the solution, sorbent doze, initial bulk concentration, shaking speed and contact time. The experimental data were examined by Langmuir and Freundlich isotherms. Cr(III) at pH-4.0 and Cr(VI) pH-2.0 showed a maximum sorption capacities 221.17 mg/g and 81.94 mg/g respectively. Kinetically experimental data of both chromium species were well fitted to pseudo second order rate, Elovich, Morris-Weber and Richenberg equations. Positive values of enthalpy change and negative values of Gibbs free energy indicated the endothermic and spontaneous nature of sorption reaction respectively. The developed method was applied to real ground water samples (affected by industrial wastewater). Up to 92.15% of chromium metal was removed from the real water samples.

关键词： Okra Leaves Chromium Pseudo Second Order

Floristic Composition of the Plants of the Cholistan Desert, Pakistan

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

American Journal of Plant Sciences 2013年第12期4卷 58-65页

作者： Hafiz Muhammad Wariss Muhammad Mukhtar Shazia Anjum Ghulam Raza Bhatti Saeed Ahmad Pirzada Khurshid Alam Cholistan Institute of Desert Studies The Islamia University of Bahawalpur Bahawalpur Pakistan Shakarpur Campus Shah Abdul-Latif University Khairpur Pakistan The Islamia university of Bahawalpur Pakistan

A floristic survey of Cholistan desert was carried out during 2009-2011 and total of 38 families, 106 genera and 154 species were documented from the area. Among families, 33 families belong to Dicotyledons of 79 genera and 115 species, while the 38 species of 26 genera belong to 4 families of Monocotyledons and 1 family of gymnosperms with 1 genus and 1 species. The largest family was Poaceae with 34 species followed by Papilionaceae and Zygophyllaceae with 10 species while Asteraceae with 9 species respectively. The life form of plant species was determined by following the Raunkier’s method. Therophytes comprised of 74 species (48%), Chamaephyte 40 species (26%), Hemicryptophyte 18 species (12%), Phanerophyte 19 species (12%) and Cryptophyte 3 species (2%) of the flroa of the area. It will be helpful and serve for the conservation and sustainable utilization of plant resources of the study area.

关键词： Floristic Composition Life Form Habit Cholistan Desert Pakistan

Extended Forgery Detection Framework for COVID-19 Medical Data Using Convolutional Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第9期68卷 3773-3787页

作者： Sajid Habib Gill Noor Ahmed Sheikh Samina Rajpar Zain ul Abidin N.Z.Jhanjhi Muneer Ahmad Mirza Abdur Razzaq Sultan S.Alshamrani Yasir Malik Fehmi Jaafar Department of Computer Science Shah Abdul Latif UniversityKhairpur66020SindhPakistan National College of Business Administration&Economics Lahore54000Pakistan School of Computer Science and Engineering SCETaylor’s UniversityMalaysia Department of Information Systems Faculty of Computer Science&Information TechnologyUniversiti MalayaMalaysia Department of Information Technology College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science College of Engineering&Computing SciencesNew York Institute of TechnologyVancouverCanada The Computer Research Institute of Montreal QuebecCanada

Medical data tampering has become one of the main challenges in the field of secure-aware medical data *** of normal patients’medical data to present them as COVID-19 patients is an illegitimate action that has been carried out in different ways ***,the integrity of these data can be *** detection is a method of detecting an anomaly in manipulated forged *** appropriate number of features are needed to identify an anomaly as either forged or non-forged data in order to find distortion or tampering in the original *** neural networks(CNNs)have contributed a major breakthrough in this type of *** has been much interest from both the clinicians and the AI community in the possibility of widespread usage of artificial neural networks for quick diagnosis using medical data for early COVID-19 patient *** purpose of this paper is to detect forgery in COVID-19 medical data by using CNN in the error level analysis(ELA)by verifying the noise pattern in the *** proposed improved ELA method is evaluated using a type of data splicing forgery and sigmoid and ReLU phenomenon *** proposed method is verified by manipulating COVID-19 data using different types of forgeries and then applying the proposed CNN model to the data to detect the data *** results show that the accuracy of the proposed CNN model on the test COVID-19 data is approximately 92%.

关键词： Data security data privacy medical-data forgery COVID-19 convolutional neural network machine learning deep learning