scholarly journals Aiding Grasp Synthesis for Novel Objects Using Heuristic-Based and Data-Driven Active Vision Methods

2021 ◽  
Vol 8 ◽  
Author(s):  
Sabhari Natarajan ◽  
Galen Brown ◽  
Berk Calli
Keyword(s):  
Real World ◽  
Active Vision ◽  
Extensive Study ◽  
Data Driven ◽  
Future Research ◽  
Grasp Planning ◽  
Synthesis Algorithm ◽  
Novel Objects ◽  
Grasp Synthesis ◽  
Research Show

In this work, we present several heuristic-based and data-driven active vision strategies for viewpoint optimization of an arm-mounted depth camera to aid robotic grasping. These strategies aim to efficiently collect data to boost the performance of an underlying grasp synthesis algorithm. We created an open-source benchmarking platform in simulation (https://github.com/galenbr/2021ActiveVision), and provide an extensive study for assessing the performance of the proposed methods as well as comparing them against various baseline strategies. We also provide an experimental study with a real-world two finger parallel jaw gripper setup by utilizing an existing grasp planning benchmark in the literature. With these analyses, we were able to quantitatively demonstrate the versatility of heuristic methods that prioritize certain types of exploration, and qualitatively show their robustness to both novel objects and the transition from simulation to the real world. We identified scenarios in which our methods did not perform well and objectively difficult scenarios, and present a discussion on which avenues for future research show promise.

6. The Communicative Pragmatics of Data-Use for Equity: A Theoretical and Methodological Framework

2020 ◽  
Vol 2 (1) ◽  
pp. 117-149
Author(s):  
Mary B. Ziskin
Keyword(s):  
Critical Race Theory ◽  
Communicative Action ◽  
Educational Equity ◽  
Data Use ◽  
College Faculty ◽  
Postsecondary Institutions ◽  
Data Driven ◽  
Future Research ◽  
Education Data ◽  
Critical Qualitative Research

<?page nr="117"?>Abstract Calls for higher education institutions to implement improvements guided by “data-driven” processes are prevalent and widespread. Despite the pervasiveness of this turn toward data, research on how data-use works on the ground in postsecondary institutions—that is, how individuals within institutions make sense of education data and use it to inform practice—is still developing.Drawing on Habermas’ Theory of Communicative Action (TCA), critical-race theory, and methodological guidance on critical-qualitative research methods, this paper synthesizes methodological and substantive insights from P–12 data-use research, with an eye to applying these insights to critical questions on postsecondary educational equity. The result of the review and analysis is a theoretical framework and a set of methodological recommendations for future research on the perceptions and experiences of college faculty, administrators, and practitioners, regarding their data-use and its implications for equity.

scholarly journals Data-Driven Intelligent 3D Surface Measurement in Smart Manufacturing: Review and Outlook

Machines ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 13
Author(s):  
Yuhang Yang ◽  
Zhiqiao Dong ◽  
Yuquan Meng ◽  
Chenhui Shao
Keyword(s):  
High Resolution ◽  
High Performance ◽  
Sampling Design ◽  
Three Dimensional ◽  
Measurement Data ◽  
Data Driven ◽  
Surface Measurement ◽  
Smart Manufacturing ◽  
Future Research ◽  
3D Surface

High-fidelity characterization and effective monitoring of spatial and spatiotemporal processes are crucial for high-performance quality control of many manufacturing processes and systems in the era of smart manufacturing. Although the recent development in measurement technologies has made it possible to acquire high-resolution three-dimensional (3D) surface measurement data, it is generally expensive and time-consuming to use such technologies in real-world production settings. Data-driven approaches that stem from statistics and machine learning can potentially enable intelligent, cost-effective surface measurement and thus allow manufacturers to use high-resolution surface data for better decision-making without introducing substantial production cost induced by data acquisition. Among these methods, spatial and spatiotemporal interpolation techniques can draw inferences about unmeasured locations on a surface using the measurement of other locations, thus decreasing the measurement cost and time. However, interpolation methods are very sensitive to the availability of measurement data, and their performances largely depend on the measurement scheme or the sampling design, i.e., how to allocate measurement efforts. As such, sampling design is considered to be another important field that enables intelligent surface measurement. This paper reviews and summarizes the state-of-the-art research in interpolation and sampling design for surface measurement in varied manufacturing applications. Research gaps and future research directions are also identified and can serve as a fundamental guideline to industrial practitioners and researchers for future studies in these areas.

scholarly journals Research on a novel data-driven aging estimation method for battery systems in real-world electric vehicles

2021 ◽  
Vol 13 (7) ◽  
pp. 168781402110277
Author(s):  
Yankai Hou ◽  
Zhaosheng Zhang ◽  
Peng Liu ◽  
Chunbao Song ◽  
Zhenpo Wang
Keyword(s):  
Electric Vehicles ◽  
Real World ◽  
Regression Models ◽  
Estimation Method ◽  
Recursive Least Squares ◽  
Data Driven ◽  
Accurate Estimation ◽  
Support Vector ◽  
Battery Degradation ◽  
Operational Data

Accurate estimation of the degree of battery aging is essential to ensure safe operation of electric vehicles. In this paper, using real-world vehicles and their operational data, a battery aging estimation method is proposed based on a dual-polarization equivalent circuit (DPEC) model and multiple data-driven models. The DPEC model and the forgetting factor recursive least-squares method are used to determine the battery system’s ohmic internal resistance, with outliers being filtered using boxplots. Furthermore, eight common data-driven models are used to describe the relationship between battery degradation and the factors influencing this degradation, and these models are analyzed and compared in terms of both estimation accuracy and computational requirements. The results show that the gradient descent tree regression, XGBoost regression, and light GBM regression models are more accurate than the other methods, with root mean square errors of less than 6.9 mΩ. The AdaBoost and random forest regression models are regarded as alternative groups because of their relative instability. The linear regression, support vector machine regression, and k-nearest neighbor regression models are not recommended because of poor accuracy or excessively high computational requirements. This work can serve as a reference for subsequent battery degradation studies based on real-time operational data.

scholarly journals Data-driven graph drawing techniques with applications for conveyor systems

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Simone Göttlich ◽  
Sven Spieckermann ◽  
Stephan Stauber ◽  
Andrea Storck
Keyword(s):  
Real World ◽  
Connected Graph ◽  
Stress Function ◽  
Graph Drawing ◽  
Point Of View ◽  
Data Driven ◽  
Challenging Problem ◽  
Conveyor System ◽  
System Graph ◽  
Real World Problems

AbstractThe visualization of conveyor systems in the sense of a connected graph is a challenging problem. Starting from communication data provided by the IT system, graph drawing techniques are applied to generate an appealing layout of the conveyor system. From a mathematical point of view, the key idea is to use the concept of stress majorization to minimize a stress function over the positions of the nodes in the graph. Different to the already existing literature, we have to take care of special features inspired by the real-world problems.

scholarly journals A Review of Remote Sensing Image Dehazing

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3926
Author(s):  
Juping Liu ◽  
Shiju Wang ◽  
Xin Wang ◽  
Mingye Ju ◽  
Dengyin Zhang
Keyword(s):  
Remote Sensing ◽  
Data Driven ◽  
Future Research ◽  
Research Focus ◽  
Image Dehazing ◽  
Surface Information ◽  
Haze Removal ◽  
Advantages And Disadvantages ◽  
Extra Information ◽  
Removal Technique

Remote sensing (RS) is one of the data collection technologies that help explore more earth surface information. However, RS data captured by satellite are susceptible to particles suspended during the imaging process, especially for data with visible light band. To make up for such deficiency, numerous dehazing work and efforts have been made recently, whose strategy is to directly restore single hazy data without the need for using any extra information. In this paper, we first classify the current available algorithm into three categories, i.e., image enhancement, physical dehazing, and data-driven. The advantages and disadvantages of each type of algorithm are then summarized in detail. Finally, the evaluation indicators used to rank the recovery performance and the application scenario of the RS data haze removal technique are discussed, respectively. In addition, some common deficiencies of current available methods and future research focus are elaborated.

scholarly journals Revisiting the CompCars Dataset for Hierarchical Car Classification: New Annotations, Experiments, and Results

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 596
Author(s):  
Marco Buzzelli ◽  
Luca Segantin
Keyword(s):  
Real World ◽  
High Performance ◽  
Ad Hoc ◽  
Future Research ◽  
Levels Of Detail ◽  
Excellent Starting Point ◽  
Starting Point ◽  
Hierarchical Nature ◽  
Multiple Levels ◽  
Entire Dataset

We address the task of classifying car images at multiple levels of detail, ranging from the top-level car type, down to the specific car make, model, and year. We analyze existing datasets for car classification, and identify the CompCars as an excellent starting point for our task. We show that convolutional neural networks achieve an accuracy above 90% on the finest-level classification task. This high performance, however, is scarcely representative of real-world situations, as it is evaluated on a biased training/test split. In this work, we revisit the CompCars dataset by first defining a new training/test split, which better represents real-world scenarios by setting a more realistic baseline at 61% accuracy on the new test set. We also propagate the existing (but limited) type-level annotation to the entire dataset, and we finally provide a car-tight bounding box for each image, automatically defined through an ad hoc car detector. To evaluate this revisited dataset, we design and implement three different approaches to car classification, two of which exploit the hierarchical nature of car annotations. Our experiments show that higher-level classification in terms of car type positively impacts classification at a finer grain, now reaching 70% accuracy. The achieved performance constitutes a baseline benchmark for future research, and our enriched set of annotations is made available for public download.

A Survey on Data-driven Network Intrusion Detection

2022 ◽  
Vol 54 (9) ◽  
pp. 1-36
Author(s):  
Dylan Chou ◽  
Meng Jiang
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Real World ◽  
Data Driven ◽  
Network Intrusion Detection ◽  
Large Network ◽  
Learning Models ◽  
Simulated Environments ◽  
Network Intrusion ◽  
Machine Learning Models

Data-driven network intrusion detection (NID) has a tendency towards minority attack classes compared to normal traffic. Many datasets are collected in simulated environments rather than real-world networks. These challenges undermine the performance of intrusion detection machine learning models by fitting machine learning models to unrepresentative “sandbox” datasets. This survey presents a taxonomy with eight main challenges and explores common datasets from 1999 to 2020. Trends are analyzed on the challenges in the past decade and future directions are proposed on expanding NID into cloud-based environments, devising scalable models for large network data, and creating labeled datasets collected in real-world networks.

Big data-driven strategic orientation in international marketing

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shahriar Akter ◽  
Md Afnan Hossain ◽  
Qiang (Steven) Lu ◽  
S.M. Riad Shams
Keyword(s):  
Big Data ◽  
Literature Review ◽  
Systematic Literature Review ◽  
International Marketing ◽  
Strategic Orientation ◽  
Data Driven ◽  
Future Research ◽  
Content Type ◽  
Strategic Orientations ◽  
Marketing Activities

PurposeBig data is one of the most demanding topics in contemporary marketing research. Despite its importance, the big data-based strategic orientation in international marketing is yet to be formed conceptually. Thus, the purpose of this study is to systematically review and propose a holistic framework on big data-based strategic orientation for firms in international markets to attain a sustained firm performance.Design/methodology/approachThe study employed a systematic literature review to synthesize research rigorously. Initially, 2,242 articles were identified from the selective databases, and 45 papers were finally reported as most relevant to propose an integrative conceptual framework.FindingsThe findings of the systematic literature review revealed data-evolving, and data-driven strategic orientations are essential for performing international marketing activities that contain three primary orientations such as (1) international digital platform orientation, (2) international market orientation and (3) international innovation and entrepreneurial orientation. Eleven distinct sub-dimensions reflect these three primary orientations. These strategic orientations of international firms may lead to advanced analytics orientation to attain sustained firm performance by generating and capturing value from the marketplace.Research limitations/implicationsThe study minimizes the literature gap by forming knowledge on big data-based strategic orientation and framing a multidimensional framework for guiding managers in the context of strategic orientation for international business and international marketing activities. The current study was conducted by following only a systematic literature review exclusively in firms' overall big data-based strategic orientation concept in international marketing. Future research may extend the domain by introducing firms' category wise systematic literature review.Originality/valueThe study has proposed a holistic conceptual framework for big data-driven strategic orientation in international marketing literature through a systematic review for the first time. It has also illuminated a future research agenda that raises questions for the scholars to develop or extend theory in this area or other related disciplines.

Sign in / Sign up

Export Citation Format

Share Document