UMBC ebiquity
2016 February

Archive for February, 2016

Image description using deep neural networks

February 27th, 2016, by Tim Finin, posted in AI, Machine Learning, NLP

Image description using deep neural networks

Sunil Gandhi
10:30 am, Monday, February 29, 2016 ITE 346

With the explosion of image data on the internet, there has been a need for automatic generation of image descriptions. In this project we use deep neural networks for extracting vectors from images and we use them to generate text that describes the image. The model that we built makes use of the pre-trained VGGNET- a model for image classification and a recurrent neural network (RNN) for language modelling. The combination of the two neural networks provides a multimodal embedding between image vectors and word vectors. We trained the model on 8000 images from the Flickr8k dataset and we present our results on test images downloaded from the Internet. We provide a web-service for image description generation that takes the image URL as input and provides image description and image categories as output. Through our service, a user can correct the description automatically generated by the system so that we can improve our model using corrected description.

Sunil Gandhi is a Computer Science Ph.D. student at UMBC who is part of the  Cognition Robotics and Learning Lab (CORAL) research lab.

Detecting Botnets Using a Collaborative Situational-Aware IDPS

February 17th, 2016, by Tim Finin, posted in Ontologies, Security, Semantic Web

M. Lisa Mathews, Anupam Joshi and Tim Finin, Detecting Botnets Using a Collaborative Situational-Aware IDPS, 2nd Int. Conf. on Information Systems Security and Privacy, Rome, IT, February 2016

Botnet attacks turn susceptible victim computers into bots that perform various malicious activities while under the control of a botmaster. Some examples of the damage they cause include denial of service, click fraud, spamware, and phishing. These attacks can vary in the type of architecture and communication protocol used, which might be modified during the botnet lifespan. Intrusion detection and prevention systems are one way to safeguard the cyber-physical systems we use, but they have difficulty detecting new or modified attacks, including botnets. Only known attacks whose signatures have been identified and stored in some form can be discovered by most of these systems. Also, traditional IDPSs are point-based solutions incapable of utilizing information from multiple data sources and have difficulty discovering new or more complex attacks. To address these issues, we are developing a semantic approach to intrusion detection that uses a variety of sensors collaboratively. Leveraging information from these heterogeneous sources leads to a more robust, situational-aware IDPS that is better equipped to detect complicated attacks such as botnets.

Developmental Memetic Algorithms: A Fast and Efficient Approach for Optimization Applications

February 15th, 2016, by Tim Finin, posted in Machine Learning

Developmental Memetic Algorithms: A Fast and
Efficient Approach for Optimization Applications

Ramin Ayanzadeh
10:30am, Monday, 22 February 2016, ITE 346

A Memetic algorithm, as a hybrid strategy, is an intelligent optimization method in problem solving. These algorithms are similar in nature to genetic algorithms as they follow evolutionary strategies, but they also incorporate a refinement phase during which they learn about the problem and search space. The efficiency of these algorithms depends on the nature and architecture of the imitation operator used. In this presentation, after a brief introduction, pros and cons of employing memetic algorithms would be discussed. Afterwards, developmental memetic algorithms will be proposed as an approach for subsiding the costs of using standard memetic algorithms. Developmental memetic algorithm is an adaptive memetic algorithm that has been developed in which the influence factor of environment on the learning abilities of each individual is set adaptively. This translates into a level of autonomous behavior, after a while that individuals gain some experience. Simulation results on benchmark function proved that this adaptive approach can increase the quality of the results and decrease the computation time simultaneously. The adaptive memetic algorithm also shows better stability when compared with the classic memetic algorithm.

You are currently browsing the UMBC ebiquity weblog archives for February, 2016.

  Home | Archive | Login | Feed