Efficient Design of Engine Mount Characteristics Using Feature Extraction to Predict Vehicle Vibration and Bayesian Active Learning

Headnotes are the precise explanation and summary of legal points in an issued judgment. Law journals hire experienced lawyers to write these headnotes. These headnotes help the reader quickly determine the issue discussed in the case. Headnotes comprise two parts. The first part comprises the topic discussed in the judgment, and the second part contains a summary of that judgment. In this thesis, we design, develop and evaluate headnote prediction using machine learning, without involving human involvement. We divided this task into a two steps process. In the first step, we predict law points used in the judgment by using text classification algorithms. The second step generates a summary of the judgment using text summarization techniques. To achieve this task, we created a Databank by extracting data from different law sources in Pakistan. We labelled training data generated based on Pakistan law websites. We tested different feature extraction methods on judiciary data to improve our system. Using these feature extraction methods, we developed a dictionary of terminology for ease of reference and utility. Our approach achieves 65% accuracy by using Linear Support Vector Classification with tri-gram and without stemmer. Using active learning our system can continuously improve the accuracy with the increased labelled examples provided by the users of the system.

Download Full-text

An Efficient Technique for Design of Hydraulic Engine Mount via Design Variable-Embedded Damping Modeling

Journal of Vibration and Acoustics ◽

10.1115/1.1855930 ◽

2005 ◽

Vol 127 (1) ◽

pp. 93-99 ◽

Cited By ~ 9

Author(s):

Jun-Hwa Lee ◽

Kwang-Joon Kim

Keyword(s):

Dynamic Characteristics ◽

Low Frequency ◽

High Amplitude ◽

Nonlinear Damping ◽

Efficient Design ◽

Equivalent Viscous Damping ◽

Damping Characteristics ◽

Design Variables ◽

Engine Mount ◽

Stiffness And Damping

For an efficient design of hydraulic mounts, it is most important to have a good mathematical model available, which must be simple yet capable of representing dynamic characteristics of the hydraulic mounts accurately. Under high amplitude excitations in the low-frequency range, the hydraulic mounts show strongly frequency-dependent stiffness and damping characteristics, which are related with so-called inertia track dynamics. Since nonlinear damping models based on fluid mechanics are typically used to predict the dynamic characteristics of the hydraulic mounts, relations between various design variables, such as geometry of the inertia track, and resultant stiffness and damping characteristics are understood only by tedious numerical computations. In this paper, the use of an equivalent viscous damping model—derived from a nonlinear model and represented in terms of design variables in an explicit manner—is proposed and, based on the equivalent linear model, are presented simple as well as very useful formulas for an efficient design of the hydraulic mounts.

Download Full-text

THE IMPACT OF THE CLASSROOM ENVIRONMENT ON THE TRANSITION FROM THE TRADITIONAL MODEL TO THE FLIPPED CLASSROOM IN A UNIT OPERATION COURSE

Proceedings of the Canadian Engineering Education Association (CEEA) ◽

10.24908/pceea.vi0.13754 ◽

2019 ◽

Author(s):

Clémence Fauteux-Lefebvre

Keyword(s):

Active Learning ◽

Classroom Environment ◽

Flipped Classroom ◽

Learning Experience ◽

Deep Understanding ◽

Entire Group ◽

Unit Operation ◽

Efficient Design ◽

Design Skills ◽

The Impact

The learning objectives of the Unit Operation course are to learn, understand and apply the operational and design principles of various separation units. For each unit, students must learn the process principles, how to apply mass and energy balances and how to use solving procedures in various contexts to design units, based on given parameters and operating objectives. The main challenges for the students are to develop the general design skills and the necessary knowledge of the theory principles, with a deep understanding of the various concepts and procedures specific to each unit. The traditional format of the course leads students to solve problems mostly during their study time, while the help of the teacher is not direct. A flipped classroom approach would allow students to revise, explore and acquire significant part of the knowledge online or on their own rather than during the lectures and then to benefit from more efficient design problem-solving sessions. It, however, requires adaptation and engagement from both the students and the instructors for a successful learning experience. In this course, the transformation is gradually implemented with the use of active learning classrooms and the development of a blended learning format of the course, to obtain an entirely flipped classroom. The access to active learning classrooms is one of the tools that could impact the quality of the flipped classroom organization, but also change the student’s experience, and was the studied. Having the suitable space, tools and seating organization to easily work in team and share their work with the entire group efficiently could help them to be engaged and to develop these new skills. The assessment of the student’s experience during the unit operations course in the active learning classroom showed that it promotes collaboration and it was appreciated by the majority of students, with a clear preference for this classroom over a traditional one for the various learning activities. It could then help reducing some obstacles to engage students in cooperative learning.

Download Full-text

ALDOCX: Detection of Unknown Malicious Microsoft Office Documents Using Designated Active Learning Methods Based on New Structural Feature Extraction Methodology

IEEE Transactions on Information Forensics and Security ◽

10.1109/tifs.2016.2631905 ◽

2017 ◽

Vol 12 (3) ◽

pp. 631-646 ◽

Cited By ~ 28

Author(s):

Nir Nissim ◽

Aviad Cohen ◽

Yuval Elovici

Keyword(s):

Feature Extraction ◽

Active Learning ◽

Structural Feature ◽

Learning Methods ◽

Microsoft Office

Download Full-text

Multi-class active learning for video semantic feature extraction

2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763) ◽

10.1109/icme.2004.1394127 ◽

2005 ◽

Cited By ~ 1

Author(s):

Rong Yan ◽

A. Hauptmann

Keyword(s):

Feature Extraction ◽

Active Learning ◽

Semantic Feature ◽

Semantic Feature Extraction

Download Full-text

An Improved Quantitative Image Analyser

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100078663 ◽

1977 ◽

Vol 35 ◽

pp. 226-227

Author(s):

J.P. Fallon ◽

P.J. Gregory ◽

C.J. Taylor

Keyword(s):

Feature Extraction ◽

Quantitative Analysis ◽

Frequency Content ◽

General Sense ◽

Physical Measurements ◽

Quantitative Image ◽

Image Analyser ◽

Automatic Methods ◽

Quantitative Results

Quantitative image analysis systems have been used for several years in research and quality control applications in various fields including metallurgy and medicine. The technique has been applied as an extension of subjective microscopy to problems requiring quantitative results and which are amenable to automatic methods of interpretation.Feature extraction. In the most general sense, a feature can be defined as a portion of the image which differs in some consistent way from the background. A feature may be characterized by the density difference between itself and the background, by an edge gradient, or by the spatial frequency content (texture) within its boundaries. The task of feature extraction includes recognition of features and encoding of the associated information for quantitative analysis.Quantitative Analysis. Quantitative analysis is the determination of one or more physical measurements of each feature. These measurements may be straightforward ones such as area, length, or perimeter, or more complex stereological measurements such as convex perimeter or Feret's diameter.

Download Full-text