Voice assistants can interpret what the user is most likely to want by deciphering questions that have been framed in a variety of different ways. Natural language interfaces are the predominant emphasis of voice assistants using AWS. The product category has come to be defined by the personal assistants that can communicate in own language and on a human level. The distribution of assistants to various computer devices has been affected by this emphasis on natural language interface. Finally, there are countless opportunities to enhance the Software. The proposed work conducted thorough a review of recent literature for this paper. This study looked at a number of articles from the past three years that discuss the use of voice assistants in the healthcare industry. Finally, the paper presented a web application called “Medico” which is a smart voice assistant with its applications in the medical sciences. It is an application created with Neo4j and AWS services connected. The primary motivation for creating this application was to use a smart voice assistant to help patients with their questions. While doctors can inquire about patients' medical history, including past ICU visits, diagnoses, and treatments received, individuals can only access their own medical information and not those of others. In addition, using the Neo4j Graph Data Science Library, “Medico” may make basic treatment recommendations for specific patients. 

Development of Cloud based Smart Voice Assistant using Amazon Web Services

Communication has been a part and parcel of our daily life. The advent of technology has bolstered the quality of communication and thus made it effective. Consequently, chat applications have become the primary method of connecting and socializing with people. However, the rise of these applications has also led people to question the confidentiality of their services. In this paper, we are proposing a secure chat application along with a unique authentication system while simultaneously providing a methodology for End-to-End Encryption. Our solution fulfills a set of requirements that are required for a safe chatting experience. We will be presenting an in-depth procedure of our alternative approach for developing a well-rounded and end-to-end encrypted chat application. 

Unique Authentication System in End-To-End Encrypted Chat Application

In a globalized world at the present epoch of generative intelligence, most of the manual labour tasks are automated with increased efficiency. This can support businesses to save time and money. A crucial component of generative intelligence is the integration of vision and language. Consequently, image captioning become an intriguing area of research. There have been multiple attempts by the researchers to solve this problem with different deep learning architectures, although the accuracy has increased, but the results are still not up to standard. This study buckles down to the comparison of Transformer and LSTM with attention block model on MS-COCO dataset, which is a standard dataset for image captioning. For both the models we have used pretrained Inception-V3 CNN encoder for feature extraction of the images. The Bilingual Evaluation Understudy score (BLEU) is used to checked the accuracy of caption generated by both models. Along with the transformer and LSTM with attention block models,CLIP-diffusion model, M2-Transformer model and the X-Linear Attention model have been discussed with state of the art accuracy.

Comparative study of Transformer and LSTM Network with attention mechanism on Image Captioning

Conversation-based learning technology is playing important role in adaptive instructional systems (AIS). As a part of the adaptivity of an instructional system it would be ideal to incorporate a human tutor to deal with conversation that is beyond the capability of a chat-bot or virtual tutor. Moreover, it is possible to answer many research questions if experiments are performed with a blended human tutor. In this research we have implemented a prototype that blends a human tutor with a virtual tutor in a typical conversation-based tutoring system (i.e., AutoTutor). We performed R&D with server-based and serverless implementations. Additionally, we have implemented audio-visual blending through WebRTC so that the conversation between students and teachers can take place through spoken language with video. We found that the serverless chat blending with AutoTutor is fast, easy to implement, and reliable. We made the so-called serverless implementation possible by using some very powerful features of a learning record store (LRS).

Enhance Conversation-Based Tutoring System with Blended Human Tutor

Voice assistants can interpret what the user is most likely to want by deciphering questions that have been framed in a variety of different ways. Natural language interfaces are the predominant emphasis of voice assistants using AWS. The product category has come to be defined by the personal assistants that can communicate in own language and on a human level. The distribution of assistants to various computer devices has been affected by this emphasis on natural language interface. Finally, there are countless opportunities to enhance the Software. The proposed work conducted thorough a review of recent literature for this paper. This study looked at a number of articles from the past three years that discuss the use of voice assistants in the healthcare industry. Finally, the paper presented a web application called “Medico” which is a smart voice assistant with its applications in the medical sciences. It is an application created with Neo4j and AWS services connected. The primary motivation for creating this application was to use a smart voice assistant to help patients with their questions. While doctors can inquire about patients' medical history, including past ICU visits, diagnoses, and treatments received, individuals can only access their own medical information and not those of others. In addition, using the Neo4j Graph Data Science Library, “Medico” may make basic treatment recommendations for specific patients.

Cloud computing in recent times has unfolded as the most popular and efficient standard for managing and delivering useful services over the Internet. Out of various cloud services and techniques, serverless computing represents an evolution of cloud-based programming technologies and is an attestation to the growth and large-scale adoption of cloud concepts. In this era of increasing technological advancements, large Internet companies like Amazon, Netflix and LinkedIn deploy big multistage applications in the cloud which can be developed, tested, deployed, scaled, operated and upgraded independently. However, aside from gaining agility and scalability, infrastructure costs are a major hindrance for companies following this pattern due to the increasing server loads and the need to increase server space. This is where serverless computing and services like AWS Lambda comes into picture. The paper delves into the functioning of AWS Lambda along with other existing AWS services through the development of a serverless chat application which supports scalability without the addition of new servers. The paper further explores the connection of different existing services in AWS like S3, DynamoDB, CloudWatch, etc. with serverless technologies like Lambda.

Case Study: Use of AWS Lambda for Building a Serverless Chat Application

While designing huge systems based on data access, storage, and retrieval, there are lot of problems faced by developers including ensuring portability, cross-platform support, scalable design, secure platforms, and reduced latency and redundancy. These problems need to be discussed and tackled in order to increase performance and efficiency for the benefit of the end-user. This study makes use of one such data-driven problem involving huge quantities of astronomical data to demonstrate the advantages of using umpteen efficient technologies and services in order to achieve significant improvement in results. Further sections compare and analyse the pros and cons of different technologies and protocols in use in order to derive fruitful conclusions.

Comparative Analysis for an Optimized Data-Driven System

Satellites all around the globe generate huge quantities of data periodically on a daily basis. The management of such large quantities of data poses significant problems ranging from data storage, retrieval and manipulation. The current scenario of managing Indian Space Research Organisation's (ISRO) ASTROSAT-CZTI satellite data involves an elementary and unsophisticated approach which causes a lot of delay in data retrieval and further causes noticeable data portability issues. The evaluation and research on the above mentioned complication paved a way for us to introduce a new architectural system to solve this complex optimization problem. We propose the creation of an independent application server and an underlying Django REST API based web service which would facilitate the efficient management and retrieval of this data. This also extends the scope, making the system more dynamic and helps in load balancing. The application server helps the system to regulate the turbulent flow of huge data quantities. The Django web framework provides feature distribution which helps manage unorganised data cost effectively. Thus, it removes the possible causes of deterioration of response in the existing system. The REST API extends the scope of the system by providing umpteen useful features which makes universal interfacing of our system possible. The techniques used in the development of our proposed system including data migration, prefetching of data and minimizing the time trade-off, address all existing challenges and show a significant improvement in the overall performance of the system.

Brijesh Choudhary

Papers

Case Study: Use of AWS Lambda for Building a Serverless Chat Application

Comparative Analysis for an Optimized Data-Driven System

Architectural Optimization of Large Scale Astronomical Data