| viXra.org > Artificial Intelligence > 2110 |
 |
 |
| viXra.org > Artificial Intelligence > 2110 |
|
|
[6] viXra:2110.0138 [pdf] submitted on 2021-10-23 19:28:00
Authors: Yan Li, Chenchen Lin, Huizi Cui, Bingyi Kang
Comments: 46 Pages. [Corrections to title made by viXra Admin]
Classic Dempster combination rule may result in illogical results when combining highly conflict evidence. How to deal with highly conflict evidence and get a reasonable result is critical. Modifying the evidence is one of significant strategies according to the importance of each evidence (e.g. similarity matrix). However, the dispersion of evidence similarity is rarely taken into consideration, which is also an important feature to distinguish the conflict evidence and normal evidence. In this paper, a new method based on similarity matrix and dispersion of evidence similarity is proposed to evaluate the importance of evidence in Dempster-Shafer theory (DST). The proposed method enhances to weaken the influence of the conflict evidence. Robustness of the proposed method is verified through the sensitivity analysis the changes of degree of conflict and amount of credible evidence changes in DST. Some numerical examples are used to show the effectiveness of the proposed method.
Category: Artificial Intelligence
[5] viXra:2110.0085 [pdf] submitted on 2021-10-17 15:51:55
Authors: Kai Gangi
Comments: 5 Pages.
Automating steps of the animation production process
using AI-based tools would ease the workload of Japanese animators. Although there have been recent advances in the automatic animation of still images, the majority of these models have been trained on human data and thus are tailored to images of humans. In this work, I propose a semi-automatic and scalable assembling pipeline to create a large-scale dataset containing clips of anime characters’
faces. Using this assembling strategy, I create AniVid, a novel anime video dataset consisting of 34,221 video clips. I then use a transfer learning approach to train a first order motion model (FOMM) on a portion of AniVid, which effectively animates still images of anime characters. Extensive experiments and quantitative results show that FOMM trained on AniVid outperforms other trained versions of FOMM when evaluated on my test set of anime videos.
Category: Artificial Intelligence
[4] viXra:2110.0055 [pdf] submitted on 2021-10-12 09:24:46
Authors: Abdurrahim Yilmaz, Mucahit Kalebasi, Yegor Samoylenko, Mehmet Erhan Guvenilir, Huseyin Uvet
Comments: 4 page for manuscript with 3 page supplementary that includes ROC curves of models.
Skin cancer is one of the deadly types of cancer and is common in the world. Recently, there has been a huge jump in the rate of people getting skin cancer. For this reason, the number of studies on skin cancer classification with deep learning are increasing day by day. For the growth of work in this area, the International Skin Imaging Collaboration (ISIC) organization was established and they created an open dataset archive. In this study, images were taken from ISIC 2017 Challenge. The skin cancer images taken were preprocessed and data augmented. Later, these images were trained with transfer learning and fine-tuning approach and deep learning models were created in this way. 3 different mobile deep learning models and 3 different batch size values were determined for each, and a total of 9 models were created. Among these models, the NASNetMobile model with 16 batch size got the best result. The accuracy value of this model is 82.00%, the precision value is 81.77% and the F1 score value is 0.8038. Our method is to benchmark mobile deep learning models which have few parameters and compare the results of the models.
Category: Artificial Intelligence
[3] viXra:2110.0036 [pdf] replaced on 2021-12-30 11:44:46
Authors: Ait-Taleb Nabil
Comments: 29 Pages.
In this paper, we propose a directed dependency graph learned from a continuous data matrix in order to extract the hidden oriented dependencies from this matrix.
For each of the dependency graph's node, we will assign a random variable as well as a conditioning percentage linking parents and children nodes of the graph.
Among all the dependency graphs learned from the continuous data matrix, we will choose the one using the highest successive conditionings method.
Category: Artificial Intelligence
[2] viXra:2110.0030 [pdf] submitted on 2021-10-07 21:49:52
Authors: Saarang Srinivasan
Comments: 18 Pages. [Corrections made by viXra Admin to conform with scholarly norm]
The aim of this project is to detect the motion in a video and accordingly follow
the motion. This program uses background elimination and contour detection to find the moving
objects in the video and determine which direction we must move in order to
follow the motion. We move the camera in the direction of the motion in order to
follow it.
Category: Artificial Intelligence
[1] viXra:2110.0026 [pdf] submitted on 2021-10-06 05:44:45
Authors: Amey Thakur, Mega Satish
Comments: 4 pages, 4 figures, Volume 8, Issue 9, International Research Journal of Engineering and Technology (IRJET), 2021.
We propose to implement a house price prediction model of Bangalore, India. It’s a Machine Learning model which integrates Data Science and Web Development. We have deployed the app on the Heroku Cloud Application Platform. Housing prices fluctuate on a daily basis and are sometimes exaggerated rather than based on worth. The major focus of this project is on predicting home prices using genuine factors. Here, we intend to base an evaluation on every basic criterion that is taken into account when establishing the pricing. The goal of this project is to learn Python and get experience in Data Analytics, Machine Learning, and AI.
Category: Artificial Intelligence
| Third-Party Links: |
|