Marketing Data Refined Push Algorithm Analysis Under the Background of Artificial Intelligence

279 Background: Immunofluorescence (IF) performed on tissue microarrays (TMA) is used for biomarker discovery but is limited by the arduous and subjective human visual assessment with an IF microscope. We aim to implement deep learning-based artificial intelligence (AI) models to automate and speed up the analysis of numerous biomarkers and generate prediction models of recurrence and metastasis after surgery. Methods: A TMA was constructed consisting of 648 samples (424 tumors, 224 normal tissue) generated from prostatectomy specimens. IF staining was performed on the TMA using anti Ki-67, ERG antibodies and analyzed for differential expression using “gold standard” manual microscopy and using an AI algorithm. Analysis was done blinded to any clinicopathological data. For manual microscopy, relative mean fluorescence intensity of cancerous versus normal tissue was determined. The AI algorithm was generated using a training cohort of digitized images. To do so the Otsu method thresholding algorithm combined with mean shift clustering was employed to find cell centers, followed by a level-set algorithm, to compute cell boundaries.These predictions were then combined with pixel predictions of a fully convolutional deep model to refine the regions of overlapping epithelium, stroma, and artifact. The algorithm was then validated using a separate cohort. Results from the algorithm were then compared to the data from manual microscopy. Results: Ki-67 and ERG expression levels generated by the algorithm showed only a 5% variance compared to the manually generated results. The algorithm was able to pick out which tumor were positive for ERG with 100% accuracy in spite of variance from artifacts. The algorithm also had the ability to improve its accuracy after each iteration of modifications and feedback through the training cohort. Conclusions: The AI algorithm produced similar outcomes than manual quantification with high accuracy but with more efficiency, cost effectiveness and objectivity. We are now developing more complex algorithms that will include the differential pattern of expression of PTEN, MYC and others with the objectives of streamlining biomarker discovery.

Download Full-text

Key Technologies of Photonic Artificial Intelligence Chip Structure and Algorithm

Applied Sciences ◽

10.3390/app11125719 ◽

2021 ◽

Vol 11 (12) ◽

pp. 5719

Author(s):

Li Pei ◽

Zeya Xi ◽

Bing Bai ◽

Jianshuai Wang ◽

Xiaoyan Zuo ◽

...

Keyword(s):

Artificial Intelligence ◽

Integrated Circuits ◽

Data Processing ◽

Electromagnetic Interference ◽

Critical Role ◽

Structure Design ◽

Algorithm Analysis ◽

Design Algorithm ◽

Data Services ◽

Silicon Waveguide

Artificial intelligence chips (AICs) are the intersection of integrated circuits and artificial intelligence (AI), involving structure design, algorithm analysis, chip fabrication and application scenarios. Due to their excellent ability in data processing, AICs show a long-term industrial prospect in big data services, cloud centers, etc. However, with the conceivable exhaustion of Moore’s Law, the size of traditional electronic AICs (EAICs) is gradually approaching the limit, and an architectural update is highly required. Photonic artificial intelligence chips (PAIC) utilize light beam propagation in the silicon waveguide, contributing to a high parallelism configuration, fast calculation speed and low latency. Due to light manipulation, PAICs perform well in anti-electromagnetic interference and energy conservation. This invited paper summarized the recent research on PAICs. The characteristics of different hardware structures are discussed. The current widely used training algorithm is given and the Photonic Design Automatic (PDA) simulation platform is introduced. In addition, the authors’ related work on PAICs is presented and we believe that PAICs may play a critical role in the deployment of data processing technology.

Download Full-text

APPLICATION OF ARTIFICIAL INTELLIGENCE-BASED IMAGE ANALYSIS IN BIOINFORMATICS

10.46793/iccbi21.047c ◽

2021 ◽

Author(s):

Zlatan Car ◽

◽

Nikola Anđelić ◽

Ivan Lorencin ◽

Jelena Musulin ◽

...

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Computer Vision ◽

Clinical Practice ◽

Image Data ◽

Algorithm Analysis ◽

Diagnostic Systems ◽

Common Procedure ◽

Magnetic Resonance Imaging Mri ◽

Standard Practices

The collection of image data is an extremely common procedure in clinical practice today. Many of the diagnostic approaches generate such data – computed tomography (CT), X-ray radiography, magnetic resonance imaging (MRI), and others. This data collection process allows for the use of computer vision approaches to be applied with the goal of analysis and diagnostics. Artificial Intelligence (AI) based algorithms have repeatedly been shown to be the best performing computer vision algorithms, in many fields including medicine. AI-based – or more precisely machine learning (ML) based, algorithms have capabilities which allow them to learn the patterns contained in the data from the data itself. Among the best performing algorithms are artificial neural networks (ANNs), or more precisely convolutional neural networks (CNNs). Their pitfall is the need for the large amounts of data – but as it has been previously mentioned, the amount of data collected in today’s clinical practice is large and ever increasing. This allows for the development of Smart Diagnostic systems which are meant to serve as support systems to the health professionals. In this paper first, the standard practices and review of the field is given – with the focus on challenges and best practices. Then, multiple examples of the research applying AI-based algorithm analysis are given – including diagnostics of various cancer types (bladder and oral) as well as COVID-19 severity diagnostics and image quality determination.

Download Full-text

New Framework of Digital Entrepreneurship Model Based on Artificial Intelligence and Cloud Computing

Mobile Information Systems ◽

10.1155/2021/3080160 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Jiahui Li ◽

Meifang Yao

Keyword(s):

Artificial Intelligence ◽

Cloud Computing ◽

Big Data ◽

Data Analysis ◽

Big Data Analysis ◽

Algorithm Analysis ◽

Model Based ◽

Artificial Intelligence Technology ◽

New Framework ◽

Digital Entrepreneurship

With the rapid development of entrepreneurial enterprises and the widespread application of emerging technologies, the commercialization of new technologies for entrepreneurial enterprises is particularly important. This research mainly discusses the new framework of digital entrepreneurship model based on artificial intelligence and cloud computing. Through artificial intelligence technology, the products provided by existing competitors only have the characteristics of one-way value; that is, data is only collected and displayed, and the application of artificial intelligence technology in products makes the value of products develop in two directions; that is, the machine can self-identify faults and errors are resolved and reported. Let customers experience the convenience, accuracy, and safety brought by technology through intelligent acquisition equipment hardware with artificial intelligence algorithm analysis and camera hardware with artificial intelligence image analysis. Customers can pay flexibly according to their needs. This model greatly enhances the high possibility of artificial intelligence companies landing. Use big data analysis and cloud computing technology to provide customers with a series of solutions such as warehouse management, sales forecasting, big data analysis, and financial management. In the SaaS market, in terms of market segmentation, there are no domestic enterprises with scale and brand effect; the incentive and welfare module will focus on the outsourcing and outsourcing of employee benefits. Relevant value-added services and derivative services are the core business, which can give play to the competitive advantages of specialization, scale, and platform. From 2018 to 2020, the cash paid to employees shows a gradual increase, and the taxes and fees paid are also increasing year by year. The cash paid for other operating activities reached a maximum of 12303 million yuan in 2018. This research will promote the innovation of new types of enterprises.

Download Full-text

On practice and dilemma of artificial intelligence in collaborative teaching of the ideological and political theory course in colleges and universities

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-219166 ◽

2021 ◽

pp. 1-12

Author(s):

Yuanmeng

Keyword(s):

Artificial Intelligence ◽

College Students ◽

Big Data ◽

Empirical Research ◽

Data Model ◽

Ideological And Political Education ◽

Political Education ◽

Algorithm Analysis ◽

New Paradigm ◽

Technical Data

Computational ideological and political education is the product of the high degree of integration of ideological and political education with computers, big data, artificial intelligence and other information technologies, and is a new paradigm of ideological and political education in the information age. Through intelligent data collection, data model construction, algorithm analysis, simulation and other links, ideological and political education can not only scientifically explain the various complex ideological and political education phenomena that have already occurred, but also accurately calculate and predict the future state of the ideological and political education system, so that the discipline of ideological and political education can be like natural science, engineering technology through data, model, calculation, simulation and other scientific means. Realize from empirical research to empirical research in order to achieve the political goal of ideological and political education in a more scientific, accurate and efficient way. However, there are still a series of conceptual, technical, data, legal and ethical problems in the construction of computational ideological and political education. Through efforts from various aspects, design practical and guiding program strategies, so as to make full use of big data as a carrier to implement the innovation of college students’ ideological and political education into practice, and enhance the effectiveness of college students’ ideological and political education in the era of big data as the ultimate goal.

Download Full-text