检索结果-内蒙古大学图书馆

An Efficient Probabilistic Solution to Mapping Errors in LiDAR-Camera Fusion for Autonomous Vehicles

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Dan Zhang, Zhengming Tian, Renran Chen, Yaobin Sherony, Rini The Department of Electrical and Computer Engineering Indiana University Purdue University Indianapolis IndianapolisIN46202 United States The School of Industrial Engineering Purdue University West LafayetteIN47906 United States The Department of Computer Information & Graphics Technology Indiana University Purdue University Indianapolis IndianapolisIN46202 United States The Collaborative Safety Research Center Toyota Motor Engineering and Manufacturing North America Inc. Ann ArborMI United States

LiDAR-camera fusion is one of the core processes for the perception system of current automated driving systems. The typical sensor fusion process includes a list of coordinate transformation operations following system calibration. Although a significant amount of research has been done to improve the fusion accuracy, there are still inherent data mapping errors in practice related to system synchronization offsets, vehicle vibrations, the small size of the target, and fast relative moving speeds. Moreover, more and more complicated algorithms to improve fusion accuracy can overwhelm the onboard computational resources, limiting the actual implementation. This study proposes a novel and low-cost probabilistic LiDAR-Camera fusion method to alleviate these inherent mapping errors in scene reconstruction. By calculating shape similarity using KL-divergence and applying RANSAC-regression-based trajectory smoother, the effects of LiDAR-camera mapping errors are minimized in object localization and distance estimation. Designed experiments are conducted to prove the robustness and effectiveness of the proposed strategy. © 2023, CC BY.

关键词： Cameras

Using AI and Natural Language Processing to Enhance Consumer Banking Decision-Making

学校读者我要写书评

暂无评论

Using AI and Natural Language Processing to Enhance Consumer...

E-mobility, Power Control and Smart Systems (ICEMPS), International Conference on

作者： Sheetal Temara Sagar Varma Samanthapudi Piyush Rohella Ketan Gupta Ashokkumar S. R Dept of Computer & Information Sciences University of the Cumberlands Williamsburg KY USA Applied Data Science The Polis Center at Indiana University Purdue University Indianapolis Indianapolis Indiana USA Payments & Commerce GoDaddy Edmonds Washington USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of Computer and Communication Engineering Centre for Blockchain and Cyber security Sri Eshwar College of Engineering Coimbatore Tamil Nadu INDIA

ISBN: (数字)9798350394399

ISBN: (纸本)9798350394405

This technical summary outlines the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) to beautify patron banking decision-making. AI-based banking systems can autonomously identify patterns in consumer information and generate insights from a number of sources, including but not restricted to purchaser 360 profiles, 1/3-party statistics, and transactional statistics. With the assistance of AI and NLP, this gadget can answer customer questions relating to their banking wishes and offer personalized recommendations. AI-based monetary decision-making systems also permit banks to offer computerized customer service with information on clients' needs, respond speedily to purchaser requests, and offer quick acclaim for loans and other banking merchandise. Moreover, AI and NLP enhance patron engagement via chatbot-like solutions and purchaser sentiment analysis. The extraordinary AI and NLP-based services being presented by using banks are mentioned in this technical abstract. In conclusion, AI and NLP technology are giving banks the capacity to meet the desires of their customers and improve typical purchaser pleasure.

关键词： Sentiment analysis IEEE merchandise Customer services Decision making Power control Customer satisfaction Process control

Overcome IT Lab Challenge in COVID-19 with Windows-To-Go 11

学校读者我要写书评

暂无评论

Overcome IT Lab Challenge in COVID-19 with Windows-To-Go

11th Annual IEEE information technology, Electronics and Mobile Communication Conference, IEMCON 2020

作者： Yang, Changshi Wang, Xianping Luo, Ying Stefanek, George Purdue University Northwest Dept of Computer Information Technology and Graphics HammondIN46323 United States

ISBN: (纸本)9781728184166

In the transition of courses from face-To-face to distance learning during the COVID-19 pandemic, students doing labs at home becomes a major challenge. In this paper, we proposed a feasible solution of building a low-cost portable IT laboratory with Windows-To-Go installed on a USB 3.1 flash drive. To verify the feasibility and usability of this portable IT laboratory, we setup two systems on a single test computer for performance comparison-Windows-To-Go installed on a USB 3.1 flash drive and Windows 10 installed on an internal SSD. Focusing on the needs of IT discipline, we manually compared the performance of installing, executing normal IT software and other common IT tasks on both systems. We also compared their performance benchmarks by PassMark. The experiment results show that this low-cost portable IT laboratory can be used as a candidate solution for students doing labs at home. © 2020 IEEE.

关键词： COVID-19

The Study of the Classic Producer-consumer Problem in a Series of IT Courses 20

学校读者我要写书评

暂无评论

The Study of the Classic Producer-consumer Problem in a Seri...

21st Annual Conference of the Special Interest Group in information technology Education, SIGITE 2020

作者： Luo, Ying Wang, Xianping Purdue University Northwest Dept. of Computer Information Technology and Graphics HammondIN United States

ISBN: (纸本)9781450370455

It is a time-consuming task for the instructors to design the examples, assignments, and projects to meet the requirement of learning outcomes. Luckily, most of the courses in information technology major are relevant and some are closely related to each other. Therefore, we propose to take advantage of the same problem which can be analyzed from different aspects under a series of IT courses. It will not only reduce the burden of the instructors to design the brand-new exercises but also help students quickly understand the foundation of the problem from what they studied and embark on exploring the high-level topics in new courses. In this paper, we use the classic producer-consumer problem as an example to present our proposition. This problem is generally shown up in operating systems course to illustrate the multi-process synchronization. We expand this problem from different angels and motivate the students to further explore other relevant topics: The objects? datatypes, properties, functions are declared in programming course and the built-in thread feature in some specific language like Java can also be demonstrated by this problem's solution. The design of data structure of the producer, the consumer, and the buffer can be discussed in data structure course. The collaboration between the producer and the consumer can be used for explaining the cause of deadlock in database course. Finally, the producer-consumer problem is used to clarify different application architectures in application/software design course. We expect that our methodology on IT education can illumine other educators looking to the similar mode in their program. © 2020 ACM.

关键词： Data structures

Significance of Strategic Outsourcing in IT Project Management

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Ravi, Akash Donawa, Nazim Dept of Computer and Information Technology Purdue University West Lafayette United States

Outsourcing refers to the concept of delegating certain tasks to an external team. It can be a differentiating factor that can aid an organization gain a competitive advantage. Consultants can bring valuable experience on domain knowledge, interdisciplinary applications, and benefits from economies of scale. From ensuring effective use of resources to venturing into uncharted sectors, outsourcing can have a myriad of benefits for a project team. Similar to most business processes, there is an inherent trade-off that needs to be made when outsourcing. Risk management protocols are required when outsourcing, to balance execution control and collaborate effectively. Within the scope of IT projects, this research aims to survey the various methods of strategic outsourcing and the contexts in which they operate. Further sections attempt to analyze case studies based on the aforementioned aspects. Based on the available literature, the research consolidates best practices in outsourcing and presents recommendations on aligning them with project goals. Finally, the potential concerns that need to be addressed when trying to outsource activities are presented. Therefore, the research to be done within this analysis will look to dissect existing literature to assess current outsourcing practices. Additionally, the research will look for reasons why outsourcing was/is not as successful as it could be, as well as evaluate how outsourcing in IT has changed with the occurrence of the COVID-19 pandemic. © 2021, CC BY.

关键词： Outsourcing

"If we didn’t solve small data in the past, how can we solve big data today?"

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ravi, Akash Dept of Computer and Information Technology Purdue University West Lafayette United States

Data is a critical aspect of the world we live in. With systems producing and consuming vast amounts of data, it is essential for businesses to digitally transform and be equipped to derive the most value out of data. Data analytics techniques can be used to augment strategic decision-making. While this overall objective of data analytics remains fairly constant, the data itself can be available in numerous forms and can be categorized under various contexts. In this paper, we aim to research terms such as ‘small’ and ‘big’ data, understand their attributes, and look at ways in which they can add value. Specifically, the paper probes into the question "If we didn’t solve small data in the past, how can we solve Big Data today?". Based on the research, it can be inferred that, regardless of how small data might have been used, organizations can still leverage big data with the right technology and business vision. © 2021, CC BY.

关键词： Data Analytics

A novel data encryption method inspired by adversarial attacks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fernando, Praveen Wei-Kocsis, Jin Department of Computer and Information Technology Purdue University West LafayetteIN United States

Due to the advances of sensing and storage technologies, a tremendous amount of data becomes available and, it supports the phenomenal growth of artificial intelligence (AI) techniques especially, deep learning (DL), in various application domains. While the data sources become valuable assets for enabling the success of autonomous decision-making, they also lead to critical vulnerabilities in privacy and security. For example, data leakage can be exploited via querying and eavesdropping in the exploratory phase for black-box attacks against DL-based autonomous decision-making systems. To address this issue, in this work, we propose a novel data encryption method, called AdvEncryption, by exploiting the principle of adversarial attacks. Different from existing encryption technologies, the AdvEncryption method is not developed to prevent attackers from exploiting the dataset. Instead, our proposed method aims to trap the attackers in a misleading feature distillation of the data. To achieve this goal, our AdvEncryption method consists of two essential components: 1) an adversarial attack-inspired encryption mechanism to encrypt the data with stealthy adversarial perturbation, and 2) a decryption mechanism that minimizes the impact of the perturbations on the effectiveness of autonomous decision making. In the performance evaluation section, we evaluate the performance of our proposed AdvEncryption method through case studies considering different scenarios. Copyright © 2021, The Authors. All rights reserved.

关键词： Cryptography

Tracing Topic Transitions with Temporal Graph Clusters

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jing, Xiaonan Hu, Qingyuan Zhang, Yi Rayz, Julia Taylor Department of Computer and Information Technology Purdue University West LafayetteIN United States

Twitter serves as a data source for many Natural Language Processing (NLP) tasks. It can be challenging to identify topics on Twitter due to continuous updating data stream. In this paper, we present an unsupervised graph based framework to identify the evolution of sub-topics within two weeks of real-world Twitter data. We first employ a Markov Clustering Algorithm (MCL) with a node removal method to identify optimal graph clusters from temporal Graph-of-Words (GoW). Subsequently, we model the clustering transitions between the temporal graphs to identify the topic evolution. Finally, the transition flows generated from both computational approach and human annotations are compared to ensure the validity of our framework. © 2021, CC BY-NC-ND.

关键词： Clustering algorithms

Predicting Simplified Thematic Progression Pattern for Discourse Analysis

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第4期63卷 163-181页

作者： Xuefeng Xi Victor S.Sheng Shuhui Yang Baochuan Fu Zhiming Cui School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou215009China Department of Computer Science University of Central ArkansasConwayAR 72035USA Department of Mathematics Statisticsand Computer SciencePurdue University NorthwestHammondIN 46323USA

The pattern of thematic progression,reflecting the semantic relationships between contextual two sentences,is an important subject in discourse *** introduce a new corpus of Chinese news discourses annotated with thematic progression information and explore some computational methods to automatically extracting the discourse structural features of simplified thematic progression pattern(STPP)between contextual sentences in a ***,these features are used in a hybrid approach to a major discourse analysis task,Chinese coreference *** novel approach is built up via heuristic sieves and a machine learning method that comprehensively utilizes both the top-down STPP features and the bottom-up semantic *** results on the intersection of the CoNLL-2012 task shared dataset and the CDTC corpus demonstrate the effectiveness of our proposed approach.

关键词： Discourse topic theme-rheme theory thematic progression