| viXra.org > Artificial Intelligence > 2011 |
 |
 |
| viXra.org > Artificial Intelligence > 2011 |
|
|
[4] viXra:2011.0190 [pdf] submitted on 2020-11-27 10:32:47
Authors: Deval Srivastava, Saim Shaikh, Priyank Shah
Comments: 8 Pages.
In our day and age where the numbers of cars on the road are rapidly increasing, thereby causing traffic. Drivers are becoming more reckless and carefree as the burden on the current human and automated system grows. Drivers and bikers who may wish to save a few minutes may break red lights and avoid wearing helmets but these small actions can have a significant impact and can result in the loss of lives. We propose a system that will intelligently use deep learning-based object detection to identify traffic offenders and provide methods to penalize them by recognizing their number plate. Our system will be able to detect traffic light violators and bikers without helmets. It has been designed in such a way that it is robust enough to work in drastic conditions and intelligent enough to reduce human dependence.
Category: Artificial Intelligence
[3] viXra:2011.0179 [pdf] submitted on 2020-11-26 07:36:23
Authors: Chenchen Lin, Xiangjun Mi, Bingyi Kang
Comments: 17 Pages.
Conflict management is a key issue in D-S evidence theory(DST) and has been the focus of many related researchers. However, there has been a lack of discussion about whether the evidence should be fused. In this paper, in the frame of DST, inspired by the belief universal gravitation[1], we proposed a concept of belief Coulomb force (BCF) to focus on whether or not the evidence should be fused. It aims to discuss the elimination of conflicts in the information fusion process from the perspective of electricity, which may provide us with a new idea to solve the problem of conflict evidence. An application is used to show that the conflict management is solved better than previous methods by using the proposed BCF.
Category: Artificial Intelligence
[2] viXra:2011.0129 [pdf] submitted on 2020-11-16 18:11:19
Authors: Yannis Haralambous
Comments: 33 Pages.
In this paper we attempt to decrypt the sequence of digits given by Jonathan Safran Foer in his novel Extremely Loud & Incredibly Close. We create directed acyclic graphs that a human can follow to find potential solutions. Representations of these graphs are displayed in this paper. The Python code used to produce them is also provided, in the appendix.
Category: Artificial Intelligence
[1] viXra:2011.0068 [pdf] submitted on 2020-11-10 10:09:21
Authors: Mostafa Khalaji
Comments: 11 Pages. 17th Iran Media Technology Exhibition and Conference, Tehran, Iran, November 2020
With the growing data on the Internet, recommender systems have been able to predict users’ preferences and offer related movies. Collaborative filtering is one of the most popular algorithms in these systems. The main purpose of collaborative filtering is to find the users or the same items using the rating matrix. By increasing the number of users and items, this algorithm suffers from the scalability problem. On the other hand, due to the unavailability of a large number of user preferences for different items, there is a cold start problem for a new user or item that has a significant impact on system performance. The purpose of this paper is to design a movie recommender system named TRSM-RS using users’ demographic information (just users’ gender) along with the new weighted similarity measure. By segmenting users based on their gender, the scalability problem is improved and by considering the reliability of the users’ similarity as the weight in the new similarity measure (Tanimoto Reliability Similarity Measure, TRSM), the effect of the cold-start problem is undermined and the performance of the system is improved. Experiments were performed on the MovieLens dataset and the system was evaluated using mean absolute error (MAE), Accuracy, Precision and Recall metrics. The results of the experiments indicate improved performance (accuracy and precision) and system error rate compared to other research methods of the researchers. The maximum improved MAE rate of the system for men and women is 5.5% and 13.8%, respectively.
Category: Artificial Intelligence
| Third-Party Links: |
|