Human communication plays a vital role; without communicating, day-to-day tasks seem difficult to complete. And the world has an almost 5% population that struggles with hearing or speaking disability, which contributes to 430 million people worldwide, and this will grow up to 900million just in the next 25 to 30 years. With the increasing noise pollution, hearing capacity degrades, leading to various hearing problems. The WHO statistics show that 32million kids are acoustically impaired. With disabilities, there are multiple issues these people face, such as lack of learning facilities, job opportunities, communication platforms, etc. These people need a cooperative environment to express, learn at their pace and level of understanding. This paper focuses on developing an application that bridges the gap between these acoustically disabled people and people unknown to their way of communication. The proposed research is an edge device application provides features like a gesture to text, speech to text, e-learning platform, and Alert mechanism. This paper majorly focuses on developing a friendly all in one platform for mute and deaf community for communication, learning and emergency alerts. The research was conducted with two approaches the traditional CNN and Tensorflow lite Efficient Net model to train the ASL (American Sign Language) dataset for the communication platform, where we obtained accuracy of 98.91% and 98.82% respectively. To overcome the computational barriers of traditional CNN approach, Tensorflow lite Efficient Net model was brought into the picture. The proposed methodology would help build a platform for the deaf and mute community to express themselves better and gain wider exposure to the world.
A study was conducted to find out caliber of validation of rubrics by Bayesian theorem to finding out importance of rubrics through complete repertory. Complete repertory by Robert Von Zandvoort is largest among all the repertories with all particulars and continuous confirmation it contain all rubrics and remedies. This study was single arm non randomized study total of 30 patents age group between 45-80yr both gender are considered and both acute and chronic cases was considered.
Learning to rank arises in many data mining applications, ranging from web search engine, online advertising to recommendation system. In learning to rank, the performance of a ranking model is strongly affected by the number of labeled examples in the training set; on the other hand, obtaining labeled examples for training data is very expensive and time-consuming. This presents a great need for the active learning approaches to select most informative examples for ranking learning; however, in the literature there is still very limited work to address active learning for ranking. In this paper, we propose a general active learning framework, expected loss optimization (ELO), for ranking. The ELO framework is applicable to a wide range of ranking functions. Under this framework, we derive a novel algorithm, expected discounted cumulative gain (DCG) loss optimization (ELO-DCG), to select most informative examples. Then, we investigate both query and document level active learning for raking and propose a two-stage ELO-DCG algorithm which incorporate both query and document selection into active learning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.