检索结果-南通市图书馆

Prediction of Covid-19 Based on Chest X-Ray Images Using Deep Learning with CNN

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 Systems Science & Engineering 2022年第6期41卷 1223-1240页

作者： Anika Tahsin Meem mohammad monirujjaman khan Mehedi Masud Sultan Aljahdali Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka1229Bangladesh Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia

The COVID-19 pandemic has caused trouble in people’s daily lives andruined several economies around the world, killing millions of people thus far. Itis essential to screen the affected patients in a timely and cost-effective manner inorder to fight this disease. This paper presents the prediction of COVID-19 withChest X-Ray images, and the implementation of an image processing systemoperated using deep learning and neural networks. In this paper, a Deep Learning,Machine Learning, and Convolutional Neural Network-based approach for predicting Covid-19 positive and normal patients using Chest X-Ray pictures is proposed. In this study, machine learning tools such as TensorFlow were used forbuilding and training neural nets. Scikit-learn was used for machine learning fromend to end. Various deep learning features are used, such as Conv2D, Dense Net,Dropout, Maxpooling2D for creating the model. The proposed approach had aclassification accuracy of 96.43 percent and a validation accuracy of 98.33 percentafter training and testing the X-Ray pictures. Finally, a web application has beendeveloped for general users, which will detect chest x-ray images either as covidor normal. A GUI application for the Covid prediction framework was run. Achest X-ray image can be browsed and fed into the program by medical personnelor the general public.

关键词： Covid-19 prediction covid-19 coronavirus normal deep learning convolutional neural network image processing chest x-ray

Comparative Design and Study of A 60 GHz Antenna for Body-Centric Wireless Communications

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 Systems Science & Engineering 2021年第4期37卷 19-32页

作者： Kaisarul Islam Tabia Hossain mohammad monirujjaman khan Mehedi Masud Roobaea Alroobaea Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka-1229Bangladesh Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia

In this paper performance of three different designs of a 60 GHz highgain antenna for body-centric communication has been evaluated. The basic structure of the antenna is a slotted patch consisting of a rectangular ring radiator withpassive radiators inside. The variation of the design was done by changing theshape of these passive radiators. For free space performance, two types of excitations were used—waveguide port and a coaxial probe. The coaxial probe signifi-cantly improved both the bandwidth and radiation efficiency. The centerfrequency of all the designs was close to 60 GHz with a bandwidth of more than5 GHz. These designs achieved a maximum gain of 8.47 dB, 10 dB, and 9.73 dBwhile the radiation efficiency was around 94%. For body-centric applications,these antennas were simulated at two different distances from a human torsophantom using a coaxial probe. The torso phantom was modeled by taking threelayers of the human body—skin, fat, and muscle. Millimeter waves have lowpenetration depth in the human body as a result antenna performance is lessaffected. A negligible shift of return loss curves was observed. Radiation efficiencies dropped at the closest distance to the phantom and at the furthest distance, theefficiencies increased to free space values. On the three layers human body phantom, all three different antenna designs show directive radiation patterns towards offthe body. All three designs exhibited similar results in terms of center frequency andefficiency but varied slightly by either having better bandwidth or maximum gain.

关键词： Body-centric communication coaxial probe high gain millimeterwave 60 GHz on-body patch compact antenna antenna performance

Miniaturized Novel UWB Band-Notch Textile Antenna for Body Area Networks

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 Systems Science & Engineering 2022年第3期40卷 1183-1198页

作者： mohammad monirujjaman khan Arifa Sultana Mehedi Masud Gurjot Singh Gaba Hesham A.Alhumyani Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka1229Bangladesh Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia School of Electronics&Electrical Engineering Lovely Professional UniversityPunjabIndia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

This paper presents the design and analysis of a miniaturized and novel wearable ultra-wideband(UWB)band-notch textile antenna for Body Area Networks(BANs).The major goal of building the antenna for wearable applications with band notch in X-band is to reject the downlink band(7.25 to 7.75 GHz)of satellite communication in the UWB frequency ranges of 3.1–10.6 GHz to keep away from *** Simulation Technology(CST)TM Microwave Studio,which is user-friendly and reliable,was used to model and simulate the *** radiating element of the antenna is designed on Jeans’textile substrate,which has a relative permittivity of *** thickness of the jeans’fabric substrate has been considered to be 1 *** loss,gain,bandwidth,impedance,radiation,and total efficiency,and radiation patterns are presented and *** antenna is simulated placed on the three layers of the human body model,and the on-body results are summarized in comparison with free *** and analysis indicate that this antenna has good band-notch characteristics in the frequency range of 7.25 GHz to 7.75 *** parametric study varying the relative permittivity of Jeans’fabric substrate of this antenna is also *** addition,effects on the antenna parameters of variation of ground plane size have been *** antenna is 25 mm×16 mm×1.07 mm in total *** reveal that this antenna achieves the design goal and performs well both in free space and on the body.

关键词： UWB band notch textile antenna wearable antenna on-body BANs jeans X-band CST

Novel Compact UWB Band Notch Antenna Design for Body-Centric Communications

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 Systems Science & Engineering 2022年第2期40卷 673-689页

作者： Sk Raziul Ahasan Kaisarul Islam mohammad monirujjaman khan Mehedi Masud GurjotSingh Gaba Hesham A.Alhumyani Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka1229Bangladesh Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia School of Electronics&Electrical Engineering Lovely Professional UniversityPunjabIndia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia

This research analyzes and implements an innovative and tiny ultrawideband(UWB)antenna with band-notched features for body-centric *** shape of the designed antenna looks like a‘swan’with a slotted *** Simulation Technology(CST)is used to assess and investigate the performance of this *** a band notch,this antenna can prevent interference from Wireless Local Area Network(WLAN)(5.15–5.825 GHz)and Worldwide Interoperability for Microwave Access(WiMAX)(5.25–5.85 GHz)*** first,the performance parameters like return loss response,gain,radiation patterns,and radiation efficiency of this UWB antenna are *** that,the human body effects on the antenna performance of the antenna are also examined to place the antenna at various distances away from 3-layers of phantom body model at different *** the on-body performance parameter results are compared and analyzed with free space performance parameter ***,by changing patch slot length and ground plane length,parametric studies were done for performance *** to this research,it is noticed that the antenna is tiny and *** shows good performance in body case as ***,the antenna is very suitable for healthcare applications.

关键词： Band notch compact size ultra wide band antenna novel antenna on-body body-centric communications computer simulation technology(CST)

Machine Learning and Artificial Neural Network for Predicting Heart Failure Risk

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 Systems Science & Engineering 2023年第1期44卷 757-775页

作者： Polin Rahman Ahmed Rifat MD.IftehadAmjad Chy mohammad monirujjaman khan Mehedi Masud Sultan Aljahdali Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka1229Bangladesh Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia

Heart failure is now widely spread throughout the *** disease affects approximately 48%of the *** is too expensive and also difficult to cure the *** research paper represents machine learning models to predict heart *** fundamental concept is to compare the correctness of various Machine Learning(ML)algorithms and boost algorithms to improve models’accuracy for *** supervised algorithms like K-Nearest Neighbor(KNN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF),Logistic Regression(LR)are considered to achieve the best *** boosting algorithms like Extreme Gradient Boosting(XGBoost)and Cat-Boost are also used to improve the prediction using Artificial Neural Networks(ANN).This research also focuses on data visualization to identify patterns,trends,and outliers in a massive data *** and Scikit-learns are used for *** Flow and Keras,along with Python,are used for ANN model *** DT and RF algorithms achieved the highest accuracy of 95%among the ***,KNN obtained a second height accuracy of 93.33%.XGBoost had a gratified accuracy of 91.67%,SVM,CATBoost,and ANN had an accuracy of 90%,and LR had 88.33%accuracy.

关键词： Heart failure prediction data visualization machine learning k-nearest neighbors support vector machine decision tree random forest logistic regression xgboost and catboost artificial neural network

Novel Design of UWB Jeans Based Textile Antenna for Body-Centric Communications

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 Systems Science & Engineering 2022年第9期42卷 1079-1093页

作者： mohammad monirujjaman khan Bright Yeboah-Akowuah Kaisarul Islam Eric Tutu Tchao Sumanta Bhattacharyya Rajesh Dey Mehedi Masud Fahad Alraddady Department of Electrical and Computer Engineering North South UniversityDhaka1229Bangladesh Department of Computer Engineering Kwame Nkrumah University of Science and TechnologyKumasiGhana Electronics and Communication Engineering Cambridge Institute of TechnologyRanchiIndia Department of Electronics and Communication Engineering Brainware Group of Institutions-SDETKolkataIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

This research presents an ultra-wideband (UWB) textile antenna designfor body-centric applications. The antenna is printed on a 1 mm thick denim substrate with a 1.7 relative permittivity. The jeans substrate is sandwiched between apartial ground plane and a radiating patch with a Q-shaped slot. The slotted radiating patch is placed above the substrate and measures 27.8 mm × 23.8 mm. In freespace, the antenna covers the ultra-wideband spectrum designated by the FederalCommunication Commission (FCC). Various parameters of the antenna designwere changed for further performance evaluation. Depending on the operating frequency, the antenna's realized gain varied from 2.7 to 5 dB. The antenna achievedhigh radiation efficiency with an omnidirectional radiation pattern. A parametricstudy was performed in research on varying antenna substrates and other components of the antenna. The three outermost layers of the human body are used tomodel a human phantom for on-body simulation. After that, the antenna wasplaced at five different distances from the phantom. The findings demonstrate thatat close distances to the phantom, the antenna's gain and efficiency at lower frequencies are reduced. The antenna's radiation efficiency and gain were muchhigher at higher frequencies for distances greater than 6 mm. Compared to freespace, the antenna's radiation pattern was more omnidirectional, especially athigher frequencies. This antenna is novel, compact and has an ultra wide bandwidth, a maximum of 94.60% radiation efficiency and a 5 dBi gain that will makeit a good candidate for body-centric communications.

关键词： Ultra-wideband body-centric communication on-body textile jeans slotted-patch WBAN

Operation and Control of Microgrids Using IoT (Internet of Things)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Software Engineering and Applications 2021年第8期14卷 418-441页

作者： Dipta Voumick Prince Deb mohammad monirujjaman khan Department of Electrical and Computer Engineering North South University Dhaka Bangladesh

The current microgrid power management system is undergoing a significant and drastic overhaul. The integration of existing electrical infrastructure with an information and communication network is an inherent and significant need for microgrid classification and operation in this case. Microgrid technology’s most important features: 1) Full duplex communication;2) Advanced metering infrastructure;3) Renewable and energy resource integration;4) Distribution automation and complete monitoring, as well as overall power system control. A microgrid’s communication infrastructure is made up of several hierarchical communication networks. Microgrid applications can frequently be found in numerous aspects of energy consumption. Because it provides a spontaneous communicational network, the Internet of Things plays a fundamental and crucial role in Microgrid infrastructure. This paper covers the deployment of a comprehensive energy management system for microgrid communication infrastructure based on the Internet of Things (IoT). This paper discusses microgrid operations and controls using the Internet of Things (IoT) architecture. Microgrids make use of IoT-enabled technologies, in conjunction with power grid equipment, which are enabling local networks to provide additional services on top of the essential supply of electricity to local networks that operate in parallel with or independently of the regional grid. Local balancing, internal blockage management, and request for support marketplace or grid operator activities are examples of auxiliary services provided by the microgrid that can add value to each end-user and other true stakeholders. Different technologies, architectures, and applications that use IoT as a key element with the main purpose of preserving and regulating innovative smart microgrids in accordance with modern optimization features and regulations are designed to update and improve efficiency, resiliency, and economics.

关键词： IoT Micro Grid Operation Control Smart Meter

Detecting Deepfake Images Using Deep Learning Techniques and Explainable AI Methods

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第2期35卷 2151-2169页

作者： Wahidul Hasan Abir Faria Rahman khanam Kazi Nabiul Alam Myriam Hadjouni Hela Elmannai Sami Bourouis Rajesh Dey mohammad monirujjaman khan Department of Electrical and Computer Engineering North South UniversityBashundharaDhaka1229Bangladesh Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Electronics and Communication Engineering Brainware Group of Institutions-SDETBarasatKolkata700124West BengalIndia

Nowadays,deepfake is wreaking havoc on *** content is created with the help of artiﬁcial intelligence and machine learning to replace one person’s likeness with another person in pictures or recorded *** visual media manipulations are not new,the introduction of deepfakes has marked a breakthrough in creating fake media and *** manipulated pic-tures and videos will undoubtedly have an enormous societal *** uses the latest technology like Artiﬁcial Intelligence(AI),Machine Learning(ML),and Deep Learning(DL)to construct automated methods for creating fake content that is becoming increasingly difﬁcult to detect with the human ***,automated solutions employed by DL can be an efﬁcient approach for detecting *** the“black-box”nature of the DL system allows for robust predictions,they cannot be completely *** is theﬁrst step toward achieving transparency,but the existing incapacity of DL to explain its own decisions to human users limits the efﬁcacy of these *** Explainable Artiﬁcial Intelligence(XAI)can solve this problem by inter-preting the predictions of these *** work proposes to provide a compre-hensive study of deepfake detection using the DL method and analyze the result of the most effective algorithm with Local Interpretable Model-Agnostic Explana-tions(LIME)to assure its validity and *** study identiﬁes real and deepfake images using different Convolutional Neural Network(CNN)models to get the best *** also explains which part of the image caused the model to make a speciﬁc classiﬁcation using the LIME *** apply the CNN model,the dataset is taken from Kaggle,which includes 70 k real images from the Flickr dataset collected by Nvidia and 70 k fake faces generated by StyleGAN of 256 px in *** experimental results,Jupyter notebook,TensorFlow,Num-Py,and Pandas were used as software,InceptionResnetV2,DenseNet201,Incep

关键词： Deepfake deep learning explainable artificial intelligence(XAI) convolutional neural network(CNN) local interpretable model-agnostic explanations(LIME)

Design and Investigation of Energy Harvesting System from Noise

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 Power Engineering 2021年第8期13卷 307-321页

作者： Junayed Hossain Nazmus Sadad Ovi mohammad monirujjaman khan Department of Electrical and Computer Engineering North South University Dhaka Bangladesh

In order to survive in this modern world, electricity is an essential thing. Electricity allows us to power the technology we use every day. Without electricity, people can’t imagine their lives. As a developing country, Bangladesh still lacks electricity every day. The electricity supply to the rural areas is very poor. It is known that energy can be converted from one form to another form. As noise is the energy, it can also be converted into various forms of energy. Noise can be represented as a sound that is loud or unpleasant and causes disturbances such as street traffic sounds, construction sounds, airports, etc. Using a suitable transducer, noise (sound) energy can be transferred into a viable source of electricity generation. This can be accomplished by employing a transducer and converting noise-induced vibrations into electrical energy. Our main goal is getting enough energy, reducing the pressure of the main grid of electricity and decreasing fossil fuel imports. This paper presents the design and investigation of an energy harvesting system from noise. In this paper, an application is designed to get energy from noise by using a speaker as a transducer. Voltage has been stepped up by using a transformer, a diode which gives DC value which can be tapped into a battery and provide energy from the battery when it is needed. The embedded device was initially tested by clapping hands and tested further by using car horns. The vibrations created by car horns and other noises have been converted into electrical energy through the principle of electromagnetic induction. In total, the application produced optimal results of 0.5 -

关键词： Electromagnetic Induction Electromotive Force Sound Energy Transducers Energy Harvest