| viXra.org > Artificial Intelligence > 2203 |
 |
 |
| viXra.org > Artificial Intelligence > 2203 |
|
|
[6] viXra:2203.0172 [pdf] submitted on 2022-03-29 20:28:39
Authors: Amey Thakur, Mega Satish
Comments: 13 Pages. 7 figures, Volume 10, Issue III, International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022. DOI: https://doi.org/10.22214/ijraset.2022.40861
Because of breakthroughs in machine learning and deep learning, which are causing a change in every industry area and managing various types of activities better than people. The majority of monotonous jobs that were formerly performed by humans are now replaced by AI. Every firm is aiming to replace the least skilled labour with AI robots that can do comparable tasks more efficiently, especially when it comes to chatbots. A chatbot is computer software that mimics human interaction by using voice instructions, text dialogues, or both. Chatbots are being employed to address consumer concerns or problems in food delivery app businesses such as Zomato and Swiggy, but are chatbots truly useful in that business model? This business model's target customers are those who don't have time to go outside to obtain food, prefer convenience at home, or are unwilling to endure discomfort, thus their concerns should be resolved in the most convenient way possible. To fulfil the user's request, a chatbot is employed. It is critical for the chatbot to plan how to carry out the task that the user has asked. New tools are available now to create and deploy chatbots; Amazon Lex by AWS is one of them. This project focuses on creating a Pizza Ordering Chatbot using Amazon Lex to help the user order pizza.
Category: Artificial Intelligence
[5] viXra:2203.0158 [pdf] submitted on 2022-03-27 12:21:30
Authors: Narayanan Arvind
Comments: 7 Pages. Presented at Samudramanthan 2022, Indian Institute of Technology Kharagpur
ID documents submitted for Maritime digital KYC processes can be skewed due to the
environment in which the photograph is taken or due to user preferences and/or errors. The
skewed image results in a low accuracy in downstream image processing tasks like optical
character recognition (OCR). ID document deskewing has been typically approached using deep
learning (MaskRCNN), regression, projection plans, Hough transforms, Fourier transforms and
other computer vision techniques. The aim of this study is to build a robust document deskewing
system based on keyword detection and coordinate geometry. The research is carried out by
analyzing skewed Indian PAN cards available with IN-D. The database has 50 Indian PAN card
images. These images are augmented to generate 150 images, with 50 images for each of the
+90, -90 and 180 degree skew cases. Google Vision API is used as the OCR engine for finding
the coordinates of the keyword in our study. The research employs Numpy, Pandas and OpenCV
open-source libraries for Python. The accuracy of the reported model is 95.33 %. The accuracy
of our present approach surpasses the accuracy of all the models available in literature.
Category: Artificial Intelligence
[4] viXra:2203.0150 [pdf] submitted on 2022-03-25 20:50:57
Authors: Shuvra Smaran Das
Comments: 11 Pages. 3 figures (Corrections made by viXra Admin to conform with the requirements on the Submission Form)
By using Artificial Intelligence (AI) called Deepfakes, clothes are stripped digitally from photographs of users and shared on social media. Deepfakes are computer-generated images and videos, often convincing, based on an existing template. Victims are already afraid and worried about these things. Moreover, the images are so realistic that most users believe that these images are authentic. These things can happen to us too. However, we cannot stop using these social platforms because these platforms are the only way to communicate with others and continue our daily work online. These types of crimes should be strictly prevented and let users know which of the images are real and not. Thus, victims and users may be able to know and assure the truth about this fraud. Here, we will be analyzed image-related paperwork, including the original and the duplicate images, to inform users about image forgery. So, users will no longer believe in these fake images.
Category: Artificial Intelligence
[3] viXra:2203.0145 [pdf] submitted on 2022-03-24 23:11:44
Authors: Arnav Dantuluri
Comments: 9 Pages. (Author's name added to article as required by the rules of viXra.org)
In this paper, I propose a simple and easily reproducible method to enhance and extend datasets from as few as 1000 images to as much as 10000 or in essence as many as the user requires. My approach combines a proper latent space modeling of the VAE which is then modified using a process called vector quantization. With these techniques along with enhancing model parameterization and training a simple convolutional neural network can achieve accuracies of up to 93% on synthetic data which proves extremely helpful especially when handling datasets with very few images.
Category: Artificial Intelligence
[2] viXra:2203.0144 [pdf] submitted on 2022-03-24 00:11:24
Authors: Deokjin Kim
Comments: 3 Pages.
In previous studies, the calculation of everything in physics through logarithmic elliptic equation was proposed. The calculation is very simple that only high school physics and high school mathematics are needed. Given the author's calculation methodology as preceding conditions, artificial intelligence will be able to discover the theory of everything in only one day. We propose to develop the artificial intelligence and call this natural intelligence.
Category: Artificial Intelligence
[1] viXra:2203.0004 [pdf] submitted on 2022-03-01 20:24:27
Authors: Siddhant Kumar Jha, Zhi Hua Zhou
Comments: 8 Pages.
Hypergraphs are a generalization of a graph in which an edge can join any number of vertices. In contrast, in an ordinary graph, an edge connects exactly two vertices.The applications of hypergraphs can range from analogical explainations such as social networks to
hard generalities in the case of collabarative game theory where they are known as simple games. The more abstract applications can be used in localized and global optimizations of radial function under computational geometry , and the optmizers generated could also be used to solve linear scheduling problems. The theoretical approach developed under these categories can be used in embedding . cluster-ing and classification which can be solved through the application of
spectral hypergraph clustering too.
Category: Artificial Intelligence
| Third-Party Links: |
|