检索结果-南通市图书馆

Enhancing ChatGPT’s Querying Capability with Voice-Based Interaction and CNN-Based Impair Vision Detection model

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 2024年第3期78卷 3129-3150页

作者： Awais Ahmad sohail Jabbar Sheeraz Akram Anand Paul umar Raza Nuha mohammed Alshuqayran College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudia Arabia 2 School of Computer Science and EngineeringKyungpook National UniversityDaegu41566South Korea 3 Department of EngineeringManchester Metropolitan UniversityManchesterM156BHUK

This paper presents an innovative approach to enhance the querying capability of ChatGPT,a conversational artificial intelligence model,by incorporating voice-based interaction and a convolutional neural network(CNN)-based impaired vision detection *** proposed system aims to improve user experience and accessibility by allowing users to interact with ChatGPT using voice ***,a CNN-based model is employed to detect impairments in user vision,enabling the system to adapt its responses and provide appropriate *** research tackles head-on the challenges of user experience and inclusivity in artificial intelligence(AI).It underscores our commitment to overcoming these obstacles,making ChatGPT more accessible and valuable for a broader *** integration of voice-based interaction and impaired vision detection represents a novel approach to conversational ***,this innovation transcends novelty;it carries the potential to profoundly impact the lives of users,particularly those with visual *** modular approach to system design ensures adaptability and scalability,critical for the practical implementation of these ***,the solution places the user at its *** responses for those with visual impairments demonstrates AI’s potential to not only understand but also accommodate individual needs and preferences.

关键词： Accessibility in conversational AI CNN-based impair vision detection ChatGPT voice-based interaction recommender system

Deep Learning-Based ECG Classification for Arterial Fibrillation Detection

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 2024年第6期79卷 4805-4824页

作者： muhammad sohail Irshad Tehreem masood Arfan Jaffar muhammad Rashid Sheeraz Akram Abeer Aljohani Faculty of Computer Science&Information Technology The Superior UniversityLahore54000Pakistan Intelligent Data Visual Computing Research(IDVCR) Lahore54000Pakistan Department of Computer Science National University of TechnologyIslamabad45000Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Computer Science Applied CollegeTaibah UniversityMedina42353Saudi Arabia

The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant *** and timely diagnosis increases the patient’s chances of ***,issues like overfitting and inconsistent accuracy across datasets remain *** a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib *** aim was to create a robust detection mechanism that consistently performs *** such as loss,accuracy,precision,sensitivity,and Area under the Curve(AuC)were utilized for *** findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated *** demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib *** insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG *** comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib ***,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.

关键词： Convolution neural network atrial fibrillation area under curve ECG false positive rate deep learning classification

Cost-Efficient medium Frequency Propagation Research with Software Defined Radio

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Engineering and Technology 2024年第1期12卷 158-169页

作者： Casey m. Hess sohail Anwar Division of Business Engineering and Information Sciences and Technology Department of Electromechanical Engineering Technology Pennsylvania State University Altoona Campus Altoona Pennsylvania USA Division of Business Engineering and Information Sciences and Technology Department of Engineering Pennsylvania State University Altoona Campus Altoona Pennsylvania USA

medium Frequency radio holds significance in modern society as it supports broadcasting and individual communications in the public, government, and military sectors. Enhancing the availability and quality of these communications is only possible by enhancing the understanding of medium frequency propagation. While traditional methods of radio wave propagation research can have a high material demand and cost, software defined radio presents itself as a versatile and low-cost platform for medium frequency signal reception and data acquisition. This paper details a research effort that utilizes software defined radio to help characterize medium frequency signal strength in relation to ionospheric and solar weather propagation determinants. Signal strength data from seven medium frequency stations of unique transmission locations and varying transmission powers were retrieved in 24-hour segments via a receiving loop antenna, Airspy HF+ Discovery software defined radio, and SDR Sharp software interface network. Retrieved data sets were visualized and analyzed in mATLAB for the identification of signal strength trends, which were subsequently compared to historical ionospheric and space weather indices in pursuit of a quantifiable correlation between such indices and medium frequency signal strengths. The results of the investigation prove that software defined radio, when used in conjunction with a receiving antenna and data analysis program, provides a versatile mechanism for cost-efficient propagation research.

关键词： Ionosphere Space Weather Airspy SDR SDR Sharp mATLAB Analysis

metamaterial terahertz device with temperature regulation function that can achieve perfect absorption and complete reflection conversion of ultrawideband

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2024年第7期76卷 123-133页

作者： Hao Sun Zao Yi Can ma Shubo Cheng Bin Tang Qingdong Zeng sohail Ahmad School of mathematics and Science Joint Laboratory for Extreme Conditions Matter PropertiesState Key Laboratory of Environment-Friendly Energy MaterialsTianfu Institute of Research and InnovationSouthwest University of Science and TechnologyMianyang 621010China Department of Oncology Sichuan Science City HospitalMianyangSichuan Province621000China School of Chemistry and Chemical Engineering Jishou UniversityJishou 416000China School of Physics and Optoelectronic Engineering Yangtze UniversityJingzhouHubei 434023China School of microelectronics and Control Engineering Changzhou UniversityChangzhou 213164China School of Physics and Electronic Information Engineering Hubei Engineering UniversityXiaogan 432000China Institute of Physics Bahauddin Zakariya UniversityMultan 66000Pakistan

The field of terahertz devices is important in terahertz ***,most of the current devices have limited functionality and poor *** improve device performance and achieve multifunctionality,we designed a terahertz device based on a combination of VO_(2)and *** device can be tuned using the phase-transition characteristics of VO_(2),which is included in the triple-layer structure of the device,along with SiO_(2)and *** terahertz device exhibits various advantageous features,including broadband coverage,high absorption capability,dynamic tunability,simple structural design,polarization insensitivity,and incidentangle *** simulation results showed that by controlling the temperature,the terahertz device achieved a thermal modulation range of spectral absorption from 0 to *** 313 K,the device exhibited complete reflection of terahertz *** the temperature increased,the absorption rate also *** the temperature reached 353 K,the device absorption rate exceeded 97.7%in the range of 5-8.55 *** study used the effective medium theory to elucidate the correlation between conductivity and temperature during the phase transition of VO_(2).Simultaneously,the variation in device performance was further elucidated by analyzing and depicting the intensity distribution of the electric field on the device surface at different ***,the impact of various structural parameters on device performance was examined,offering valuable insights and suggestions for selecting suitable parameter values in real-world *** characteristics render the device highly promising for applications in stealth technology,energy harvesting,modulation,and other related fields,thus showcasing its significant potential.

关键词： terahertz perfect absorption complete reflection temperature regulation ultrawideband smart device

Effects of Supplementing Various Linoleic to α-linolenic Acid Ratios and Vitamin A on Production Performance and Egg Characteristics of Laying Hens during Summer months

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Zoological Research 2019年第1期1卷 1-9页

作者： S.Ahmad m.Yousaf Z.Kamran m.u.sohail m.N.Tahir K.C.Koutoulis A.manzoor 无 university College of Veterinary and Animal Sciences The Islamia University of Bahawalpur-63100Pakistan Institute of Animal Sciences University of AgricultureFaisalabad-38040Pakistan Department of Physiology GC UniversityFaisalabad-38000Pakistan Department of Avian medicine School of Health SciencesUniversity of ThessalyKarditsa-43100Greece Department of meat Science and Technology University of Veterinary and Animal SciencesLahore-54000Pakistan Poultry Production Division Al-Watania Poultry Institute of TechnologyAl-Bukayriyah51941Saudi Arabia

In the present feeding trial,responses of laying hens that were kept at high ambient temperature and Fed with various dietary ratios of linoleic acid(LNA)toα-linolenic acid(ALA)and vitamin A levels on production performance and egg quality traits were evaluated.A total of 360 Leghorn laying hens at 40th week of age(average initial body weight;1.79±0.23 kg)were fed with various combinations of canola oil and linseed oil containing diets to achieve LNA to ALA dietary ratios of 20:1,10:1,4:1,2:1,1:1 and 1:2,each supplemented with 3000 or 10000 Iu of vitamin A/kg of *** experiment was designed as a 6×2 factorial Completely Randomized Design that continued for 12 *** intake,body weight gain,egg production and egg quality traits were recorded during the *** dietary LNA to ALA ratio or increasing poly unsaturated fatty acids(PuFA)in the diet decreased(Pused egg production,feed conversion ratio(FCR)per dozen of eggs and shell quality remained unaffected(P>0.05)by dietary *** conversion ratio per kg eggs,egg weight and egg-shell thickness showed a curvilinear(Puld produce eggs by the hens with desirable quantities of n-6 and n-3 PuFA–that are characteristics of functional diets–the performance of laying hens in terms of body weight gain and egg-yolk percentage was slightly ***,a 4:1 or 2:1 LNA to ALA combination can make a borderline between the production traits and the feed economics.

关键词： Egg quality Fatty acids Hot climate Layers performance Vitamin A

In search of a pan-coronavirus vaccine:next-generation vaccine design and immune mechanisms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cellular & molecular Immunology 2024年第2期21卷 103-118页

作者： S.Cankat m.u.Demael L.Swadling Division of Infection and Immunity Institute of Immunity and TransplantationUniversity College LondonPears BuildingLondon NW32PPUK

members of the coronaviridae family are endemic to human populations and have caused several epidemics and pandemics in recent *** this review,we will discuss the feasibility of and progress toward the ultimate goal of creating a pan-coronavirus vaccine that can protect against infection and disease by all members of the coronavirus *** will detail the unmet clinical need associated with the continued transmission of SARS-CoV-2,mERS-CoV and the four seasonal coronaviruses(HCoV-OC43,NL63,HKu1 and 229E)in humans and the potential for future zoonotic *** will highlight how first-generation SARS-CoV-2 vaccines and natural history studies have greatly increased our understanding of effective antiviral immunity to coronaviruses and have informed next-generation vaccine *** will then consider the ideal properties of a pan-coronavirus vaccine and propose a blueprint for the type of immunity that may offer ***,we will describe a subset of the diverse technologies and novel approaches being pursued with the goal of developing broadly or universally protective vaccines for coronaviruses.

关键词： Vaccine Coronavirus Cross-reactive immunity Cross-protection universal

An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2024年第3期17卷 65-79页

作者： Jiahao Zhang Lan Cheng Zhile Yang Qinge Xiao sohail Khan Rui Liang Xinyu Wu Yuanjun Guo Taiyuan university of Technology TaiyuanShanxiChina Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhenGuangdongChina Guangdong Institute of Carbon Neutrality(Shaoguan) ShaoguanGuangdongChina Sino-Pak Center for Artificial Intelligence Pak-Austria Fachhochschule–Institute of Applied Sciences and TechnologyHaripurKhyber PakhtunkhwaPakistan Chengxi Company State Grid Tianjin Electric Power CompanyTianjinChina

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.

关键词： Power grid fault detection Semi-supervised learning Data driven Deep learning Smart grid

FlowBreakdown of Hybrid Nanofluid on a Rigid Surface with Power Law Fluid as Lubricated Layers

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer modeling in Engineering & Sciences 2024年第2期138卷 1485-1499页

作者： mirza Naveed Jahangeer Baig NadeemSalamat sohail Nadeem Naeemullah mohamed Bechir Ben Hamida Hassan Ali Ghazwani Sayed m.Eldin A.S.Al-Shafay Instituite of mathematics Khwaja Fareed University of Engineering and Information TechnologyRahim yar Khan64200Pakistan Department of mathematics Quaid-I-Azam UniversityIslamabad44000Pakistan Department of mathematics Wenzhou UniversityWenzhou325035China College of Engineering Department of Mechanical EngineeringImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11564Saudi Arabia Research Laboratory of Ionized Backgrounds and Reagents Studies(EmIR) Preparatory Institute for Engineering Studies of Monastir(IPEIM)University of MonastirMonastir5060Tunisia Higher School of Sciences and Technology of Hammam Sousse Department of PhysicsJazan82511Kingdom of Saudia Arabia Department of mechanical Engineering Faculty of engineeringJazan UniversityP.O.Box 45124JazanKingdom of Saudia Arabia Center of Research Faculty of EngineeringFuture University in EgyptNew Cairo11835Egypt Department of mechanical Engineering College of EngineeringPrince Sattam bin Abdulaziz UniversityAlkharj16436Saudi Arabia

Thiswork investigates an oblique stagnation point flowof hybrid nanofluid over a rigid surface with power lawfluidas lubricated layers. Copper (Cu) and Silver (Ag) solid particles are used as hybrid particles acting in water H2O asa base fluid. The mathematical formulation of flow configuration is presented in terms of differential systemthat isnonlinear in nature. The thermal aspects of the flow field are also investigated by assuming the surface is a heatedsurface with a constant temperature T. Numerical solutions to the governing mathematical model are calculatedby the RK45 algorithm. The results based on the numerical solution against various flow and thermal controllingparameters are presented in terms of line graphs. The specific results depict that the heat flux increases over thelubricated-indexed parameter.

关键词： Oblique stagnation point flow hybrid nanofluid lubricated layer magnetohydrodynamics

Deactivation mechanism for water splitting:Recent advances

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Carbon Energy 2024年第7期6卷 53-82页

作者： Yansong Jia Yang Li Qiong Zhang sohail Yasin Xinyu Zheng Kai ma Zhengli Hua Jianfeng Shi Chaohua Gu Yuhai Dou Shixue Dou Hydrogen Energy Institute Zhejiang UniversityHangzhouChina Institute of Process Equipment Zhejiang UniversityHangzhouChina Donghai Laboratory ZhoushanChina Department of mechanical Engineering Faculty of EngineeringUniversiti MalayaKuala LumpurMalaysia Institute of Energy materials Science University of Shanghai for Science and TechnologyShanghaiChina

Hydrogen(H2)has been regarded as a promising alternative to fossil-fuel *** H2 produced via water electrolysis(WE)powered by renewable energy could achieve a zero-carbon *** attention has been focused on developing highly active catalysts to facilitate the reaction kinetics and improve the energy efficiency of ***,the stability of the electrocatalysts hampers the commercial viability of *** studies have elucidated the origin of catalyst *** this review,we first discuss the WE mechanism,including anodic oxygen evolution reaction(OER)and cathodic hydrogen evolution reaction(HER).Then,we provide strategies used to enhance the stability of *** that,the deactivation mechanisms of the typical commercialized HER and OER catalysts,including Pt,Ni,RuO_(2),and IrO_(2),are ***,the influence of fluctuating energy on catalyst degradation is highlighted and in situ characterization methodologies for understanding the dynamic deactivation processes are described.

关键词： deactivation mechanism hydrogen evolution in situ characterization oxygen evolution water splitting