Number Recognition

Number Recognition

From an image predict the number from it

Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

    Follow

Description

Number prediction

Default user avatar 57012e2942

Jay B. updated status

Default user avatar 57012e2942

Jay Barbeau

I am a long time developer in multiple languages. My focus is 3D graphics and graphics APIs, (OpenGL, Direct3D, Unity) along with music technology and audio. I have been experimenting with Inverse Kinematics (IK) 3D characters driven by MIDI data in realtime animating characters. My main goals are performance technologies and education technologies. I created an AI driven piano tutor. I want to determine if AI can be used as an expert programming tool to aid my efforts and make me more productive.

Medium 1

Prateek K. updated project WarHammer status

Medium 1

Prateek Kumar

For security providers, sophisticated machine learning provides fast and accurate threat detection, including zero-day and previously unknown threats. Advanced heuristics and rules allow machine learning models to help determine in near real time if a file, URL, IP, or application is a threat, and then communicate that information broadly.

Despite an ever changing threat landscape, machine learning enables very high detection rates over time. Machine learning technology is now emerging as a critical component across all of the various domains of cybersecurity.

Machine learning can power next-generation endpoint protection, mobile protection, threat intelligence, web security and network anomaly detection offerings. It enables threat activity across multiple security domains to be contextually associated in real time.

Medium 1

Prateek K. created project WarHammer

Medium 355b551b 3cf2 4f7d 979c d7303d310e2e

WarHammer

With modern technology becoming obsolete in cyber security, we need to come up with innovative ideas to increase the notch up in the fight against unauthorized access to our information and data. I will be taking help of Theano,Torch,Microsoft CNTKA framework to start with and then modify the implementation as i move in later stages of the project. I will be trying to modify various protection algorithms and try to come up with a ML algorithm that takes help of deep learning frameworks. I will also be taking help of Gensim to validate my data collection as efficiently as possible. The changes to encryption and decryption techniques will be studied thoroughly in later stages. In a manner where DNA cannot be replicated , similarly developing a neural network net around my algorithm against network intrusion will be the deciding factor in the efficiency of the modified algorithm. I will also taking help of Apache Hadoop in analyzing my stored data from cyber attacks and storing the result of my predicament in Apache Spark to make real-time decisions. The main problem in using machine learning algorithms in cyber security is the creation of an overhead which has an adverse effect on algorithm's performance. To eliminate it to a appreciable stage I will be taking help of BlueData without any changes to Hadoop or Spark framework. Finally the performance of the algorithm will be tested with the help of BigBench kit to get a full report on the project.

Default user avatar 57012e2942

mohamed e. created project Statistical Analysis in Structural Health Assessment

Medium b4c1ceac e5fd 4f76 98c9 c7848d06d8e8

Statistical Analysis in Structural Health Assessment

Structural Health Assessment (SHA) is a nondestructive technique to monitor the functionality of a certain structure or system. It utilizes the measured dynamic response of the system to detect, localize and quantify any damage or failure in that system. Current parametric approaches try to predict the damage in the structure by identifying its stiffness parameters. Such approaches require complicated analytical modeling for the structure, as well as complicated analytical analysis to extract the system parameters. Statistical modeling is currently trending, it uses a library of signatures for the structure responses, any further response from the structure can be classified as one or a combination of the damage scenarios recorded in that library. This current proposal aims to utilize a pre-generated library of damage scenarios to classify any new damage that occurs further. The investigated structure is a two-story single-bay frame structure as shown in the figure.

Questions to be answered using this analysis: Having the excitation and response of the structure, what is the damage scenario that best describes the current state of this structure? That is, is it a single or multiple element damages? What are those damaged elements? And to what extent is each damage?

Data analytics technique will be used: This problem does not require clustering, it is only a classification problem. The main challenge is the nonlinearity. Having the records of two structure responses for two single-element damage scenarios, they cannot be both combined to predict the response of a multiple-element damage. Thus, we need to consider the nonlinear effect in the classification. An initial approach is the Nearest Neighbour, it is simple but cannot account for nonlinearity. This requires a huge number of scenarios to be generated and then fed into the feature space for further analysis. A further approach to be applied is LASSO that could count for nonlinearity and cross relations between different elements of the structure. Other approaches can be used later based on the achieved progress in the previous two approaches.

See More

No users to show at the moment.

No users to show at the moment.