A novel multi-target multi-camera tracking approach based on feature grouping

Max/MSP/Jitter for Music

10.1093/oso/9780199777679.001.0001 ◽

2011 ◽

Author(s):

V. J Manzo

Keyword(s):

Video Game ◽

Music Technology ◽

Camera Tracking ◽

Instructional Tools ◽

Music Therapists ◽

Interactive Music ◽

Pitch Tracking ◽

Special Value ◽

And Performance ◽

Private Studio

In Max/MSP/Jitter for Music, expert author and music technologist V. J. Manzo provides a user-friendly introduction to a powerful programming language that can be used to write custom software for musical interaction. Through clear, step-by-step instructions illustrated with numerous examples of working systems, the book equips you with everything you need to know in order to design and complete meaningful music projects. The book also discusses ways to interact with software beyond the mouse and keyboard through use of camera tracking, pitch tracking, video game controllers, sensors, mobile devices, and more. This book will be of special value for everyone who teaches music at any level, from classroom instructors to ensemble directors to private studio instructors. Whether you want to create simple exercises for beginning performers or more complex programs for aspiring composers, this book will show you how to write customized software that can complement and even inspire your instructional objectives. No specialist foreknowledge is required to use this book to enliven your experience with music technology. Even musicians with no prior programming skills can learn to supplement their lessons with interactive instructional tools, to develop adaptive instruments to aid in composition and performance activities, and to create measurement tools with which to conduct research. This book allows you to: -Learn how to design meaningful projects for composition, performance, music therapy, instruction, and research -Understand powerful software through this accessible introduction, written for beginners -Follow along through step-by-step tutorials -Grasp the principles by downloading the extensive software examples from the companion website This book is ideal for: -Music educators at all levels looking to integrate software in instruction -Musicians interested in how software can improve their practice and performance -Music composers with an interest in designing interactive music -Music therapists looking to tailor programs to the needs of specific groups or individuals And all who are interested in music technology. Visit the companion website at www.oup.com/us/maxmspjitter

Download Full-text

Telecom Churn Prediction System Based on Ensemble Learning Using Feature Grouping

Applied Sciences ◽

10.3390/app11114742 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4742

Author(s):

Tianpei Xu ◽

Ying Ma ◽

Kangchul Kim

Keyword(s):

Ensemble Learning ◽

Machine Learning Algorithms ◽

Customer Relationship ◽

Prediction System ◽

Churn Prediction ◽

Customer Churn ◽

Feature Grouping ◽

Recognition Systems ◽

The Cost ◽

Better Than

In recent years, the telecom market has been very competitive. The cost of retaining existing telecom customers is lower than attracting new customers. It is necessary for a telecom company to understand customer churn through customer relationship management (CRM). Therefore, CRM analyzers are required to predict which customers will churn. This study proposes a customer-churn prediction system that uses an ensemble-learning technique consisting of stacking models and soft voting. Xgboost, Logistic regression, Decision tree, and Naïve Bayes machine-learning algorithms are selected to build a stacking model with two levels, and the three outputs of the second level are used for soft voting. Feature construction of the churn dataset includes equidistant grouping of customer behavior features to expand the space of features and discover latent information from the churn dataset. The original and new churn datasets are analyzed in the stacking ensemble model with four evaluation metrics. The experimental results show that the proposed customer churn predictions have accuracies of 96.12% and 98.09% for the original and new churn datasets, respectively. These results are better than state-of-the-art churn recognition systems.

Download Full-text