检索结果-南通市图书馆

Ensemble learning of diffractive optical 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

Light(Science & Applications) 2021年第1期10卷 123-135页

作者： md Sadman sakib Rahman Jingxi Li Deniz Mengu Yair Rivenson Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCA 90095USA

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine ***,there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization,power efficiency and computation *** deep neural networks(D^(2)NNs)form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers.D^(2)NNs have demonstrated success in various tasks,including object classification,the spectral encoding of information,optical pulse shaping and ***,we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble *** independently training 1252 D^(2)NNs that were diversely engineered with a variety of passive input filters,we applied a pruning algorithm to select an optimized ensemble of D^(2)NNs that collectively improved the image classification *** this pruning,we numerically demonstrated that ensembles of N=14 and N=30 D^(2)NNs achieve blind testing accuracies of 61.14±0.23%and 62.13±0.05%,respectively,on the classification of GFAR-10 test images,providing an inference improvennent of>16%compared to the average performance of the individual D^(2)NNs within each *** results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.

关键词： networks collective successive

Universal linear intensity transformations using spatially incoherent diffractive processors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2023年第9期12卷 1830-1856页

作者： md Sadman sakib Rahman Xilin Yang Jingxi Li Bijie Bai Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCA 90095USA

Under spatially coherent light,a diffractive optical network composed of structured surfaces can be designed to perform any arbitrary complex-valued linear transformation between its input and output fields-of-view(FOVs)if the total number(N)of optimizable phase-only diffractive features is≥~2N_(i)N_(o),where Ni and No refer to the number of useful pixels at the input and the output FOVs,*** we report the design of a spatially incoherent diffractive optical processor that can approximate any arbitrary linear transformation in time-averaged intensity between its input and output *** spatially incoherent monochromatic light,the spatially varying intensity point spread function(H)of a diffractive network,corresponding to a given,arbitrarily-selected linear intensity transformation,can be written as H(m,n;m′,n′)=|h(m,n;m′,n′)|^(2),where h is the spatially coherent point spread function of the same diffractive network,and(m,n)and(m′,n′)define the coordinates of the output and input FOVs,*** numerical simulations and deep learning,supervised through examples of input-output profiles,we demonstrate that a spatially incoherent diffractive network can be trained to all-optically perform any arbitrary linear intensity transformation between its input and output if N≥~2N_(i)N_(o).We also report the design of spatially incoherent diffractive networks for linear processing of intensity information at multiple illumination wavelengths,operating ***,we numerically demonstrate a diffractive network design that performs all-optical classification of handwritten digits under spatially incoherent illumination,achieving a test accuracy of>95%.Spatially incoherent diffractive networks will be broadly useful for designing all-optical visual processors that can work under natural light.

关键词： spatially intensity arbitrary

Analysis of Clinicians' Subjective Approach Based on Three-way Mental Disorders Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Analysis of Clinicians' Subjective Approach Based on Three-w...

作者： md sakib Ullah Sourav 山东财经大学

学位级别：硕士

The traditional psychiatric diagnosis process is based on psychiatric nosology or mental disorders classification that follows a data-driven objective approach which implies an internal information-based analysis that is found unable in solving many complex *** construct a unified framework while in the psychiatric diagnosis process,as well as with other criteria,similar importance should be imposed on practitioners' external analysis consisting of culture-specific knowledge along with domain knowledge,through attained expertise and experience with a subjective *** on the principles of three-way decision,this thesis concentrated on the subjective approach from the clinician and proposed a model for the clinician's subjective approach(CSA)analysis with two *** first step is qualitative and quantitative *** the qualitative approach,we talked about the property of trichotomy,which plays an essential role in representing user *** building a structure using the TAO model,we can rank a set of disorders concerning their *** the quantitative approach,the three-level computing model is *** weights are assigned to disorders using the eigenvector *** second step is utilizing the evaluation-based three-way decision to categorize a disorder set into three classes of different importance in *** use three-way decision theory as our fundamental framework to examine CSA to classify mental disorders in psychiatric *** CSA model might be integrated with the traditional psychiatric diagnosis set up as an effective tool to make the whole diagnostic process more robust and powerful.

关键词： Data-driven decision making Three-way decisions Psychiatric diagnosis Mental disorder classification the Trisecting-Acting-Outcome (TAO) model

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第2期7卷 294-314页

作者： Shahriar Kaisar md Mamunur Rashid Abdullahi Chowdhury sakib Shahriar Shafin Joarder Kamruzzaman Abebe Diro Department of Information Systems and Business Analytics RMIT UniversityMelbourne 3000Australia School of Engineering and Technology Central Queensland UniversityRockhampton 4700Australia Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide 5005Australia Centre for Smart Analytics Federation University AustraliaBallarat 3350Australia School of Accounting Information Systems and Supply ChainRMIT UniversityMelbourne 3000Australia

Telemarketing is a well-established marketing approach to offering products and services to prospective *** effectiveness of such an approach,however,is highly dependent on the selection of the appropriate consumer base,as reaching uninterested customers will induce annoyance and consume costly enterprise resources in vain while missing interested *** introduction of business intelligence and machine learning models can positively influence the decision-making process by predicting the potential customer base,and the existing literature in this direction shows promising ***,the selection of influential features and the construction of effective learning models for improved performance remain a ***,from the modelling perspective,the class imbalance nature of the training data,where samples with unsuccessful outcomes highly outnumber successful ones,further compounds the problem by creating biased and inaccurate ***,customer preferences are likely to change over time due to various reasons,and/or a fresh group of customers may be targeted for a new product or service,necessitating model retraining which is not addressed at all in existing works.A major challenge in model retraining is maintaining a balance between stability(retaining older knowledge)and plasticity(being receptive to new information).To address the above issues,this paper proposes an ensemble machine learning model with feature selection and oversampling techniques to identify potential customers more accurately.A novel online learning method is proposed for model retraining when new samples are available over *** newly introduced method equips the proposed approach to deal with dynamic data,leading to improved readiness of the proposed model for practical adoption,and is a highly useful addition to the *** experiments with real-world data show that the proposed approach achieves excellent results in all cases(e.g.,98.6

关键词： machine learning online learning oversampling telemarketing imbalanced dataset ensemble model

LDNet: A Robust Hybrid Approach for Lie Detection Using Deep Learning Techniques

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11期81卷 2845-2871页

作者： Shanjita Akter Prome md Rafiqul Islam md.Kowsar Hossain sakib David Asirvatham Neethiahnanthan Ari Ragavan Cesar Sanin Edward Szczerbicki School of Computer Science Taylor’s UniversitySubang Jaya47500Malaysia Information Systems Australian Institute of Higher EducationSydneyNSW 2000Australia Faculty of Social Sciences&Leisure Management Taylor’s UniversitySubang Jaya47500Malaysia Faculty of Management and Economics Gdansk University of TechnologyGdansk80-233Poland

Deception detection is regarded as a concern for everyone in their daily lives and affects social *** human face is a rich source of data that offers trustworthy markers of *** deception or lie detection systems are non-intrusive,cost-effective,and mobile by identifying facial *** the last decade,numerous studies have been conducted on deception detection using several advanced *** have focused their attention on inventing more effective and efficient solutions for the detection of ***,it could be challenging to spot trends,practical approaches,gaps,and chances for ***,there are still a lot of opportunities for innovative deception detection ***,we used a variety of machine learning(ML)and deep learning(DL)approaches to experiment with this *** research aims to do the following:(i)review and analyze the current lie detection(LD)systems;(ii)create a dataset;(iii)use several ML and DL techniques to identify lying;and(iv)create a hybrid model known as *** combining layers from Vgg16 and DeneseNet121,LDNet was developed and offered the best accuracy(99.50%)of all the *** developed hybrid model is a great addition that significantly advances the study of *** findings from this research endeavor are expected to advance our understanding of the effectiveness of ML and DL techniques in ***,it has significant practical applications in diverse domains such as security,law enforcement,border control,organizations,and investigation cases where accurate lie detection is paramount.

关键词： Artificial intelligence deception/lie detection deep learning facial expression machine learning

Low Altitude Satellite Constellation for Futuristic Aerial-Ground 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 Modeling in Engineering & Sciences 2023年第8期136卷 1053-1089页

作者： Saifur Rahman Sabuj Mohammad Saadman Alam Majumder Haider md Akbar Hossain Al-sakib Khan Pathan Department of Electronic Engineering Hanbat National UniversityDaejeon34158South Korea Department of Electrical and Electronic Engineering Brac UniversityDhaka1212Bangladesh School of Business and Digital Technologies Manukau Institute of TechnologyManukau2241New Zealand Department of Computer Science and Engineering United International UniversityDhaka1212Bangladesh

This paper discusses the significance and prospects of low altitude small satellite aerial vehicles to ensure smooth aerial-ground communications for next-generation broadband *** achieve the generic goals of fifthgeneration and beyondwireless networks,the existing aerial network architecture needs to be *** detailed architecture of low altitude aerial networks and the challenges in resource management have been illustrated in this ***,we have studied the coordination between promising communication technologies and low altitude aerial networks to provide robust network *** talk about the techniques that can ensure userfriendly control and monitoring of the low altitude aerial networks to bring forth wireless broadband connectivity to a new *** the end,we highlight the future research directions of aerial-ground communications in terms of access technologies,machine learning,compressed sensing,and quantum communications.

关键词： Aerial-terrestrial network cognitive radio network cooperative communication high altitude platform low altitude platform low earth orbit satellite constellation unmanned aerial vehicle

Physics and artificial intelligence: illuminating the future of optics and photonics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advanced Photonics 2024年第5期6卷 7-12页

作者： md Sadman sakib Rahman Aydogan Ozcan University of California Electrical and Computer Engineering Department University of California Bioengineering Department University of California California Nano Systems Institute

1 Introduction The artificial intelligence （AI） revolution is upon us,transforming not just our daily lives with smart assistants,personalized recommendations,and autonomous systems but also profoundly altering the landscape of scientific research and knowledge *** revolution is characterized by the integration of AI into every domain of human activity,from healthcare and finance to education and *** transformative effects are also being felt in the world of scientific research,e.g.,in the physical sciences,where AI is not just assisting in data analysis1but is also driving new discoveries2and pushing the boundaries of knowledge and applied *** interplay between AI and physics has reached a point where advancements in one field are catalyzing progress in the other,creating feedback loops of innovations that are reshaping our understanding of the universe and the tools we use to explore it.

关键词： physics artificial intelligence optics photonics

OAM-based diffractive all-optical classification

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Advanced Photonics 2024年第1期6卷 6-7页

作者： md Sadman sakib Rahman Aydogan Ozcan University of California Electrical and Computer Engineering DepartmentLos AngelesCaliforniaUnited States University of California Bioengineering DepartmentLos AngelesCaliforniaUnited States University of California California NanoSystems Institute(CNSI)Los AngelesCaliforniaUnited States

Object classification is an important aspect of machine *** practices in object classification entail the digitization of object information followed by the application of digital algorithms such as deep neural *** execution of digital neural networks is power-consuming,and the throughput is *** existing von Neumann digital computing paradigm is also less suited for the implementation of highly parallel neural network architectures.^(1)

关键词： consuming digit neural

Advances in coamorphous drug delivery systems

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

Acta Pharmaceutica Sinica B 2019年第1期9卷 19-35页

作者： Qin Shi sakib M.Moinuddin Ting Cai State Key Laboratory of Natural Medicines Department of Pharmaceutics School of Pharmacy China Pharmaceutical University

In recent years, the coamorphous drug delivery system has been established as a promising formulation approach for delivering poorly water-soluble drugs. The coamorphous solid is a single-phase system containing an active pharmaceutical ingredient(API) and other low molecular weight molecules that might be pharmacologically relevant APIs or excipients. These formulations exhibit considerable advantages over neat crystalline or amorphous material, including improved physical stability, dissolution profiles, and potentially enhanced therapeutic efficacy. This review provides a comprehensive overview of coamorphous drug delivery systems from the perspectives of preparation, physicochemical characteristics,physical stability, in vitro and in vivo performance. Furthermore, the challenges and strategies in developing robust coamorphous drug products of high quality and performance are briefly discussed.

关键词： Coamorphous Preparation Characterization Physical stability Dissolution Bioavailability