Introduction to Creative Technologies

This document provides an introduction to creative technologies, including virtual reality, image manipulation, user interfaces, and artificial intelligence. It discusses the use of virtual reality and augmented reality in learning, image manipulation and video editing using Photoshop, user interfaces and mobile applications, and the concept of artificial intelligence and machine learning. The document also explores the benefits and challenges of these technologies and provides references for further reading.

Introduction to Creative
Technologies

Table of Contents
Portfolio................................................................................................................................................2
Portfolio Element 1 (Virtual and Augmented Reality).....................................................................2
Portfolio Element 2 (Image Manipulation and Video Editing)........................................................4
Portfolio Element 3 (User Interfaces and Mobile Applications)......................................................6
Portfolio Element 4 (Artificial Intelligence and Machine Learning)...............................................7
References............................................................................................................................................9

Portfolio
Portfolio is one of the essential tools that is used to getting business done and building
up of a professional brand. We have used wix.com for implementing the portfolio website
which is used for importing the images and videos. It contains container editor, logo, contact
information and manage media option (French, 2017). We have created a digital art website
and, the art image and video are imported to that webpage. The contact information is also
addressed in this webpage.
Portfolio Element 1 (Virtual and Augmented Reality)
Learning with VR/AR
The virtual reality and augmented realty are used to help in learning situation. The technical
skills such as manufacturing construction and related to health care industries. The virtual
reality is used to train the officers for how to handle situation and respond to a bioterrorism
threat (Wright, 2014). To tack this type of learning through a learning management system or
learning record store using API protocol.

Realistic Encounters
Consider the virtual human technology for research which used to an intelligent agent
framework that combines natural language processing and virtual reality. The gesture, notate,
gaze are depending on computer based RVHs that use body posture and verbal feedback just
like a real person. It generated the information to interact with learner.
Benefits of VR/AR Learning

The classroom based training for easier transfer of learning that allow to augment. To gain
practical experience and develop the skill related to virtual reality and augmented reality. The
learner to repeat practice and correct the targeted then gained new skills.
Portfolio Element 2 (Image Manipulation and Video Editing)
The next portfolio element is based on Photoshop that is used for editing photos and
videos. We have used adobe photo shop for editing or for merging the images. It is very easy
method for editing pictures or videos. We have to join one or more images (Xiaowu Chen et
al., 2013). We take three pictures for editing a single image. First we choose one main picture
then edit that image.

We have joined three images to make one picture by using photo shop application.
Portfolio Element 3 (User Interfaces and Mobile Applications)
Mobile user interface that allows the user interact with the application. We have used
unreal engine for developed the game. It has design requirements for develop application or
game in mobile view. The mobile design requirements is different from desktop computers.
The mobile requirement has symbols, mobile interface and it automatically hidden until
accessed. It is more flexible and it very easy to use. We have used unreal engine application
for game and it has only mobile design requirements.

Portfolio Element 4 (Artificial Intelligence and Machine Learning)
Artificial intelligence means which is made non natural and human thing and it
implemented by the system. The text and speech recognition using for machine understand
human language (YOU and MA, 2017).

Work Process
It can find patterns association in millions of data and that system understand the
word using speech and text recognition. If you type the word then the computer read that
word. The computer really don’t understand but it understand the word with help of machine
learning.
The computer understand the human language with help of set of algorithm. The algorithm
developed for that process and the computer can be understand natural language. The
machine learning and artificial intelligence concept are applied for that process. The game
developed by programming language. To apply the machine learning for application then the
computers that can play games. The computer can be used to play the games, read your
emotions, beat the Turing test, create a realistic virtual universe, and perform accurate
calculations. It mainly used for robotics and it do any complicated calculation.
The computer making more independent such as new space independently, recognising faces
and commands in robot technology. To move freely and interact with people in advanced
robotics. To create a simple creative output for future machines and robots.
How well it works in noisy environments (recognition)
The speech recognition recognizers degrade significantly when environment noise
occurs during use. It mainly caused by mismatches voice and it directed to reduce this
mismatch. It classified three categories such as similarity measurements, speech model
compensation for noise and speech enhancement. The area of digital techniques for
microphone speech recognition.

How well it works with different accents (recognition)
In machine learning, the speech recognition system that despite the technological
leaps and bounds (Chen and Liu, 2018). To understand non-American accents than those of
native born users. It observed in automated systems the predict and even in the content
recommendation algorithms.
How well it copes with multiple speakers simultaneously (recognition)
The cloud speech to text recognition including different voice and individual speakers
assigned by each word number. The same speakers has same word number. So the transcript
result based on number of word and that word speakers. It identify uniquely that produced a
running aggregate of all results.
How well it deals with ambiguous spellings (recognition)
To indicate a desired character in alphabetic string and press that word where each
key press resents two or more letters (SAYEM, 2014). The user select recognition candidate
from a choice. The multiple press indicate the unambiguous alphabetic filtering and
ambiguous key to disambiguate which letter is intended.
How well you can understand it without reading along (synthesis)
To write syntheses depends on ability and it refers relationship among sources. To write own
material is often reflected in the wording which is used to evaluate text (Sesa-Nogueras and
Faundez-Zanuy, 2012).The synthesis is the combining of information and ideas and it must
have some basis.
How quickly it can communicate and still be intelligible (synthesis)
To consider normal conservation requires the recognition and it truly amazing human
capacity. The speech recognition make machine recognition system have proven difficult. It
used to speech synthesizer can be implemented in software and hardware products.
Which voice is considered most realistic (synthesis). Try a Turing test strategy
The Turing test of a machines ability to intelligent behaviour that proposed human evaluator.
The natural conservation between machine and human. Two partners in conservation is a

machine and that has limits text only channel such as screen and computer keyboard
(Vorobeychik and Kantarcioglu, 2018).
Does adding an accent to synthesized speech affect comprehension?
The accented speech on sentence comprehension with different degrees. To enhance
comprehension of accented speech that earlier acquisition of speech. It showed reduced
comprehension accuracy of accented speech but it only for nonsensical sentences.
References
French, N. (2017). Designing a Portfolio Website with Muse. [Carpinteria, Calif.]:
Lynda.com.
Kim, J. (2014). Web Accessibility-based Website Design and Realization - With focus on T-
Cast-Integrated Website. KOREA SCIENCE & ART FORUM, 15, p.167.
Kim, M. and Kim, N. (2015). User Perspective Website Clustering for Site Portfolio
Construction. Journal of Internet Computing and Services, 16(3), pp.59-69.
Sona, J. (2012). Enhancing the Website Structure by Reconciling Website. IOSR Journal of
Engineering, 02(09), pp.122-125.
Xiaowu Chen, Hongyu Wu, Xin Jin and Qinping Zhao (2013). Face Illumination
Manipulation Using a Single Reference Image by Adaptive Layer Decomposition. IEEE
Transactions on Image Processing, 22(11), pp.4249-4259.
Zhu, J., Yin, X., Bai, J. and Wang, Y. (2016). Mobility-assisted big data collecting in wireless
sensor networks. International Journal of Distributed Sensor Networks, 12(8),
p.155014771666423.
Chen, Z. and Liu, B. (2018). Lifelong Machine Learning, Second Edition. Synthesis Lectures
on Artificial Intelligence and Machine Learning, 12(3), pp.1-207.
SAYEM, A. (2014). Speech Analysis for Alphabets in Bangla Language: Automatic Speech
Recognition. International Journal of Engineering Research, 3(2), pp.88-93.
Sesa-Nogueras, E. and Faundez-Zanuy, M. (2012). Biometric recognition using online
uppercase handwritten text. Pattern Recognition, 45(1), pp.128-144.
Vorobeychik, Y. and Kantarcioglu, M. (2018). Adversarial Machine Learning. Synthesis
Lectures on Artificial Intelligence and Machine Learning, 12(3), pp.1-169.

Wright, W. (2014). Using virtual reality to augment perception, enhance sensorimotor
adaptation, and change our minds. Frontiers in Systems Neuroscience, 8.
YOU, C. and MA, B. (2017). Spectral-domain speech enhancement for speech
recognition. Speech Communication, 94, pp.30-41.