FriendBookmark.com New BlogU Posts (RITChennai) RSS Feed

Rajalakshmi Group of Institutions develop unique AI software to detect COVID-19

*Students and faculty team of Rajalakshmi Group behind this breakthrough innovation.[/SIZE][/FONT]* Software has 95.4% accuracy[/SIZE][/FONT]In the aftermath of the World Health OrganizationÃââs designation of the novel coronavirus as a pandemic, several measures have been put in place by various Governments to minimise the spread of the infection. But still, COVID-19 continues to spread rapidly across the world snatching away the lives of many.[/SIZE][/FONT]Hence, in a bid to help the Central and the State Governments and also the people, a team of students and faculty from Rajalakshmi Group of Institutions, has developed a breakthrough software to detect COVID-19.[/SIZE][/FONT]The AI (Artificial Intelligence) tool is based on neural network to detect COVID-19, CAP (Community-Acquired Pneumonia) and normal condition from chest X-Ray images.A whopping number of 14148 images were used in the training process and the tool has testing accuracy of 95.4 percent.[/SIZE][/FONT]The highlights of the tool are:[/SIZE][/FONT]* No installation required. It is a simple website which can be accessed from anywhere.[/SIZE][/FONT]* As simple as uploading a photo on social media.[/SIZE][/FONT]* The result will come within a second of uploading.[/SIZE][/FONT]Dr. S. Rajkumar, Professor & Head,Department of Biomedical Engineering; [/SIZE][/FONT]Dr. V. Sapthagirivasan, Professor,[/SIZE][/FONT]BME; Mr.V.Rajaraman, Assistant Professor, CSE;[/SIZE][/FONT]Mr. Ashwin Ramesh III Year CSE ( student )[/SIZE][/FONT]are the members of the team that developed the unique software. All the above are part of Centre of Medical Imaging of Rajalakshmi Group of Institutions.Read more : [/SIZE][/FONT]

Development of Artificial Intelligence (AI) tool to detect COVID-19 condition from a chest X-ray image

Rajalakshmi group of educational institutions in Chennai is familiar for their versatility of academic excellence and research activities. In the group, Centre for Medical Imaging is formed with the objective of creating proficient solutions in medical imaging applications. The centre has members from faculty fraternity, students, and medical imaging professionals.[/SIZE][/FONT]Ever since the onset of the pandemic COVID-19, the members of the centre discusses the research progress across global in the aspect of medical imaging to detect COVID-19 through various imaging modalities like X-Ray. Ultrasound and CT scan. Initially, we were thinking to use ultrasound images but due to some technical issues, we couldnÃâât follow it up.[/SIZE][/FONT]Later we decided to use chest X-ray images and incidentally, we were able to get around 100 COVID-19 affected subjectsÃââ chest X-ray images through open-source Canadian research forum. With the acquired images we planned to develop an Artificial Intelligence (AI) tool to detect COVID-19 condition from the test chest X-ray image.[/SIZE][/FONT]We decided to add the provision for detecting CAP (Community-Acquired Pneumonia) besides to COVID-19 in the proposed tool. The reason for the inclusion of CAP is that there is a relatively high possibility of getting this condition. We have decided to detect the normal conditions also. Hence, we decided to develop a three-class classifier using that we can detect COVID-19, CAP and normal condition from the test X-ray image.[/SIZE][/FONT]We acquired the necessary CAP & normal chest X-ray images through RSNA (Radiological Society of North America) for training the AI tool. We used 14,148 chest X-ray images of all these three classes for rigorously training the neural network inbuilt in the AI tool. The training process underwent different iterations until we reach a training accuracy of 99.9. In the testing process, 1661 images were used and by adopting different strategies we are able to get a testing accuracy of 95.4.[/SIZE][/FONT]Confusion Matrix[/SIZE][/FONT]

[IMG]http://rajalakshmi.org/blog/wp-content/uploads/2020/04/unnamed.png" alt="" class="wp-image-59" style="box-sizing: border-box; margin: 0px; padding: 0px; border: 0px; vertical-align: middle; max-width: 100%; height: auto;[/IMG][/SIZE][/FONT]Result Parameters:Precision: 97.18%Sensitivity/Recall: 94.51%Specificity: 99.65%Accuracy: 95.4%Read More : [/SIZE][/FONT]

GO ……go and learn GO!!

Are you confident in Python Programming? Can you create AI applications using Python? YesÃâÂ. ItÃââs wonderful and great. Also, be ready to learn the ÃâËGoÃââ Programming Language which is chasing Python to win the race![/SIZE][/FONT]ÃâËGoÃââ also called Golang is a general-purpose language developed by Google a decade ago. Though AI application developers and Data scientists are crazy with the features of Python, there are certain issues and challenges in Python that can slow up the process of developing AI applications in the near future.[/SIZE][/FONT]Few major issues are:[/SIZE][/FONT]Slow executionLack of support to concurrency The dynamic allocation of data types further reduces the speed in Python[/SIZE][/FONT][/SIZE][/FONT]The Go Programming language overcomes these issues. Go is a procedural and open source programming language developed by Robert Griesemer, Rob Pike, Ken Thompson at Google in 2007. It is statically typed and compiled, fast executing language like C++ and Java.Go provides a wide range of powerful tools that helps to develop highly efficient products.Few of them are:[/SIZE][/FONT]Gofmt Ãââ automatically format the Go code[/SIZE][/FONT]Gorun Ãââ Experiment and test a similar code [/SIZE][/FONT]Goget Ãââ Helps to download libraries from GitHub[/SIZE][/FONT]Godoc Ãââ Parses the source code and create document[/SIZE][/FONT]The excellent testing capabilities and garbage collection are the added advantages of the Go programming language. The syntax of the language is similar to C and C++ and it is extremely helpful to build cross-platform applications.[/SIZE][/FONT]Go is in use for different development activities like WebApp, Full Stack Development, Mobile applications, embedded systems, data science. Major companies like Google, IBM, Apple, Facebook, Twitter,BBC, PayPal, American Express are developing products using Go programming language.Read More : [/SIZE][/FONT]

Cloud Computing….?

Cloud Computing can be defined as delivering computing power (CPU, RAM, Network Speeds, Storage OS software) service over a network (usually on the internet) rather than physically having the computing resources at the customer location.Example: AWS, Azure, Google Cloud[/SIZE][/FONT]Essential Characteristics[/SIZE][/FONT]

[IMG]https://ritchennai.org/blog/wp-content/uploads/2020/12/image3.png" alt="Essential Characteristics" class="wp-image-69" srcset="https://ritchennai.org/blog/wp-content/uploads/2020/12/image3.png 662w, https://ritchennai.org/blog/wp-content/uploads/2020/12/image3-300x140.png 300w" sizes="(max-width: 662px) 100vw, 662px" style="box-sizing: border-box; margin: 0px; padding: 0px; border: 0px; vertical-align: middle; max-width: 100%; height: auto;[/IMG][/SIZE][/FONT]ÃâÂ On-demand self-service. A consumer can unilaterally provision computing capabilities, such as server time and network storage, as needed automatically without requiring human interaction with each service provider.[/SIZE][/FONT]ÃâÂ Broad network access. Capabilities are available over the network and accessed through standard mechanisms that promote use by heterogeneous thin or thick client platforms (e.g., mobile phones, tablets, laptops, and workstations).[/SIZE][/FONT]ÃâÂ Resource pooling. The providerÃââs computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically assigned and reassigned according to consumer demand. There is a sense of location independence in that the customer generally has no control or knowledge over the exact location of the provided resources but may be able to specify location at a higher level of abstraction (e.g., country, state, or datacenter). Examples of resources include storage, processing, memory, and network bandwidth.[/SIZE][/FONT]ÃâÂ Rapid elasticity. Capabilities can be elastically provisioned and released, in some cases automatically, to scale rapidly outward and inward commensurate with demand. To the consumer, the capabilities available for provisioning often appear to be unlimited and can be appropriated in any quantity at any time.Read More : https://ritchennai.org/blog/2020/12/09/cloud-computing/[/SIZE][/FONT]