ITS discussion questions
Week 6 discussion
Part A
Initial Post
Data representation is the act displaying the visual form of your data. The process of identifying the most effective and appropriate solution for representing our data is unquestionably the most important feature of our visualization design. Working on this layer involves making decisions that cut across the artistic and scientific foundations of the field.
Here we find ourselves face-to-face with the demands of achieving that ideal harmony of form and function that was outlined in
Chapter 6
,Data Representation.We need to achieve the elegance of a design that aesthetically suits our intent and the functional behavior required to fulfill the effective imparting of information.
According to Kirk 2016, in order to dissect the importance ofdatarepresentation, we are going to “look at it from both theoretical and pragmatic perspectives.” Choose three of the storytelling techniques (Pages 161 – 209) in which data is presented and stories are being interpreted. Discuss the importance and the advantages of using these techniques. Provide an example of each technique.
Reference
Kirk, A. (2016).Data Visualisation: A Handbook for Data Driven Design.Thousand Oaks, CA:Sage Publications, Ltd.
Reply Post
When replying to a classmate, offer your opinion on what they posted as the important advantage of each technique. Also, are the examples, in your opinion, relevant and usable?
Discussion (Chapter 6): List and briefly describe the nine-step process in con-ducting a neural network project.
Note: The first post should be made by Wednesday 11:59 p.m., EST. I am looking for active engagement in the discussion. Please engage early and often.
Your response should be 250-300 words. Respond to two postings provided by your classmates.
There must be at least one APA formatted reference (and APA in-text citation) to support the thoughts in the post. Do not use direct quotes, rather rephrase the author’s words and continue to use in-text citations.
Part B
When submitting work, be sure to include an APA cover page and include at least two APA formatted references (and APA in-text citations) to support the work this week.
All work must be original (not copied from any source).
What is MLP, and how does it work? Explain the function
of summation and activation weights in MLP-type ANN.
Peer review
11 hours ago
Prathyusha Thalla
Discussion 6
Advantages of Storytelling Techniques
Storytelling techniques in which data is presented and stories are effectively interpreted include leveraging the archetype of the hero and his enemy, finding the hook and creating compelling visuals. The techniques are highly important in facilitating effective utilization of characters. In leveraging the archetype of a hero and his enemy, the importance is illustrated using a hero and an enemy as a challenge the hero has to solve or beat (Kirk, 2016). The technique is advantageous since characters used have to be relevant to the audience. For instance, in The Scarecrow, the scarecrow named Chipotle had to fight for other animals and help in feeding them. The example shows that Chipotle is well known through the role designated to him.
For Example, A line Chart construct a story about the change of values over a temporal plane directly without any comparison. A flow map can construct a story about the relationship between two points in a spatial plane without any external dependencies (Kirk, A. 2016). A Bar Chart alone cannot represent a story without any comparison with other similar bar charts. The only way to create a story of Categorial, Hierarchical and relational chart families is to incorporate a temporal dimension or to provide a descriptive narrative which involves a dimension of time.
The Line Chart is based in the temporal X-axis with equal intervals for an interval of time, which is very easy to analyze and understand by the user. The User can identify the minimum, maximum and range easily including the gaps and uncertainty in the representation. The best example of a line chart is stock market trends. The rise or fall of stock market over an interval of time narrates different perspectives with the pictorial representation.
A flow map is the representation of the flow of a phenomenon about a spatial region. The advantage of a flow map is, it does not have a template, but it displays the characteristics of origin and destination. They reduce the visual clutter by merging the edges (Kirk, A. 2016). The best example for the flow map is Google Maps representing the traffic in a city, which can construct a story of high traffic area, moderate traffic area and low traffic area during a time interval.
A Bar chart is a representation of the Quantitative values with different Categories. It is easy to analyze and understand. It can show each data category in a frequency distribution. It can summarize the large data set into a visual chart easily and clearly. But it needs comparison which a similar chart to construct a story (Kirk, A. 2016). A clustered Bar chart is used to narrate a story instead a bar chart. For example, A clustered bar chart with number of boys and girls who passed in the final exam in each standard of a school.
Reference
Kirk, A. (2016). Data visualization: a handbook for data driven design. Sage.
17 hours ago
Riyaz Shaik
Week 6 Discussion
COLLAPSE
Data representation has become an integral part of business, education entities and other related aspects in presenting data. Data storytelling is one of the methods used to narrate and provide visuals of data. It is a structured approach used to communicate insights into data. There are several techniques used in data storytelling in data visualization (Knaflic, 2015). They include understanding the story, determining the type of data, identifying the right chart to use, defining the audience and many others. The essay will talk about the first three techniques.
Concerning the determining the data, the presented needs to understand the data to know how to justify a catch the attention. Data storytelling aims to make the data understood by the audience (Kirk, 2016).. For instance, when presenting a project, the data should have different segments such as introduction, literature review, methodology and other required sections. The individual can explore and connect with other data visualization to turn the data to power visual story capable of influencing the audience. It has advantages, such as capturing the attention of the audience and knowing how to present effectively.
Second, the right chart that matches with the story makes it easier to present data. A person needs to choose the most suitable chart that goes along with the data presented (Evergreen, 2019).A good example, when showing trends, line graphs would the most appropriate. Through this, an individual can make the story more exciting and make the audience understand all the concept used in data storytelling. Knowing makes it easier to understand how to address and language to use.
Finally, defining the audience enables the individual presenting the data to see the type of audience is addressing. Also, the person can understand the size of the people, ethnicity, and how to play with words and ideas which are more appealing to them. For example, address a large number of people, the person needs an address system. Through the data, the present is enabling to brainstorm before storytelling.
References
Evergreen, S. D. (2019).Effective data visualization: The right chart for the right data. Sage Publications.
Kirk, A. (2016).Data visualisation: a handbook for data driven design. Sage.
Knaflic, C. N. (2015).Storytelling with data: A data visualization guide for business professionals. John Wiley & Sons.
48 minutes ago
Bhargav Modepalli
Discussion6
COLLAPSE
Nine step process in conducting neural network project are Collect, organize and format the data, separate data into training, validation and testing sets, Decide on a network architecture and structure, select a learning algorithm, Set network parameters and initialize their values, Initialize weights and start training, Stop training, free the network weights, Test the trained network, deploy the network for use on unknown new cases.
First we need to collect and organize the data and then separate data into training, validation, and testing sets, then we need to decide on a network architecture and structure with a selective algorithm. We need to set the network parameters and initialize their values. Then we start training and stop training and freeze the network weights. We need to test the trained network and deploy the network for use on unknown new cases.
12 hours ago
Sampath Reddy Lachireddygari
Discussion
COLLAPSE
The process of development in artificial neural network model comprises of nine steps.
The Step 1 comprises of gathering of data that is meant for testing and training purposes. This data is collected, although important underlying fact is that a problem that has been highlighted is prone to neural solutions and collection of adequate data. The step 2, aims to identify that data, and setting up a plan that can be used for testing the assessment of the network. Talking of steps 3 and 4, an adequate networking architecture and a learning methodology can be used. The presence and usage of adequate performance tools determine the development of the model and the type of neural network that needs to be considered. There have been problems that have resulted a very high success rate along with various configurations. An important point to note that the neurons must be exact in number and the numerous layers hidden inside. There are packages that make extensive use of algorithm so that the appropriate networking design can be selected (Babikir & Mwambi, 2016).
The Step 5, follows the initiation of the network weights and the place where the parameters are modified, the moment the training feedback is received. In addition to this, it is also important to note that it helps in maintain the efficiency and duration of the training. In step 6, the data undergoes transformation into the format that is required by the neural network. This may also want the software to update their processes in such a manner that it fits into the ANN model. The techniques for manipulation and storage of data has been designed in a convenient manner. The application data often ensures that the data is highly accurate. Reaching out to steps 7 and 8, the testing and training need to be conducted so that the given input and the desired output on the network are obtained. The network helps in computing the outputs and the upcoming weights are attained. In step 9, a stabilised set of weights is achieved. The network is now capable to generate the required output on the basis of given inputs (Fahd, 2014).
References
Babikir, A., & Mwambi, H. (2016). Factor Augmented Artificial Neural Network Model. Neural Processing Letters, 45(2), 507-521.
Fahd, S. (2014). Artificial Neural Network Model for Friction Stir Processing. International Journal of Engineering Research, 3(6), 396-397.
