Dal Alert!

Receive alerts from Dalhousie by text message.

X

Research groups & institute

Big Data Analytics & Machine Learning

Institute for Big Data Analytics

The Institute for Big Data Analytics is a first of its kind in Canada. It has a mission create knowledge and expertise in the field of Big Data Analytics by facilitating fundamental, interdisciplinary and collaborative research, advanced applications, advanced training and partnerships with industry.

bigdata@cs.dal.ca
https://bigdata.cs.dal.ca

Director: Dr. Stan Matwin, Ph.D. CRC

Following his Ph.D., Stan was an Assistant Professor in the Department of Mathematics and Computer Science, Warsaw University. He joined University of Guelph in 1977, and Acadia University in 1980. Since 1981 at the University of Ottawa, as of 2011 a Distinguished University Professor (on leave). For many years in charge of graduate studies in Computer Science at the University of Ottawa, and a founding father of the Graduate Certificate in Electronic Commerce at University of Ottawa in 1999. Also affiliated with the Institute for Computer Science of the Polish Academy of Sciences as a Professor, Stan has worked at universities in the U.S, Europe, and Latin America. Recognized internationally for his work in text mining, applications of Machine Learning, and data privacy, author and co-author of more than 250 research paper. Former president of the Canadian Artificial Intelligence Association (CAIAC) and of the IFIP Working Group 12.2 (Machine Learning). Stan has significant experience and interest in innovation and technology transfer. One of the founders of Distil Interactive Inc. and Devera Logic Inc.

Q & A with Tier 1 Canada Research Chair, Dr. Stan Matwin
matwin-250

"Of particular interest for me is learning from text data: papers, blogs, tweets, notes, etc. I believe that such data calls for methods that take into account its linguistic character - we will have stronger methods if they understand the lexical, syntactic and semantic character of such data. That is the main topic of my Canada Research Chair here at Dal." Read the full Q & A.

Dalhousie Natural Language Processing (DNLP) Group

The Dalhousie Natural Language Processing Group (DNLP) provides information about NLP-related research conducted at the Dalhousie University, and it is a forum for discussion, collaboration, and interaction between researchers interested in the philosophies, theories, and applications related to NLP.

Group Website: http://dnlp.ca
Contact Information: Dr. Vlado Keselj
vlado@cs.dal.ca
Phone: 1-902-494-2893
Fax: 1-902-492-1517 (att. Vlado Keselj)
Research Areas and
Projects:
  • Language modeling, syntactic and semantic analysis, n-grams
  • Information extraction, information retrieval, question answering
  • Text data mining, text categorization, document clustering
  • Speech recognition, automatic translation
  • Computational linguistics, sylabification, multi-word expressions
  • Text messages normalization
  • Sentiment analysis in micro-blogs
  • Computational musicology, music structure analysis
Funding:
Faculty Members:
Other Members:
  • Dr. Axel Soto
Financial forecasting with Artificial Intelligence
Vlado

Artificial Intelligence for Financial Forecasting markets are considered to be one of the leading indicators of the economy. 

When markets begin to contract, the society braces for a slowdown in the economy or a possible recession; when markets expand, the economy builds a forward momentum. 

There are many factors and forces that influence market movement. They are complex, high correlated, and sometimes difficult to measure. A challenging problem is how to make accurate financial predictions using this complex set of inputs under tight time constraints. Read the full story.

Hierarchical Anticipatory Learning (HAL) Lab

We conduct research in the areas of mobile interaction, new media / mixed reality, usable privacy and security, animation / simulation, graphics, and visualization.

Recently, we have conducted research on the following topics: non-photorealistic rendering, image processing, 3D animation, data visualization, whole body interaction, mobile interfaces, and mixed reality collaborative environments.

By-products of our research have found applications in areas such as healthcare, digitally enhanced manufacturing, security and privacy, geo-spatial information systems, film production, text visualization, interactive media, and personal visual analytics.

Our lab has received funding from the Boeing Company, NSERC CRD program, NSERC Discovery grants, GRAND NCE, and MITACS, among other sources.

Group Website: http://projects.cs.dal.ca/hallab
Contact Information: Thomas Trappenberg at: tt@cs.dal.ca
Research Areas and
Projects:
  • Machine learning
  • Computational Neuroscience
  • Cognitive Robotics
Funding: NSERC, CIHR
Faculty Members:
Graduate Students and
Research Assistants:
  • Patrick Connor
  • Paul Hollenen
  • Warren Connors
Academic Collaborators:
  • Dr. Mae Seto (Engineering, DRDC)
  • Dr. Doug Munoz (Queens Univ.)
  • Dr. Brian Coe (Queens Univ.)
  • Dr. Pitoyo Hartono (Chukyo Univ.)
Industry Partners: DRDC
Seminar Series: Hallab chats Wednesdays 10am-11:30
Related Conferences and
Journals:
Cosyne, NIPS, IJCNN
How HAL Lab is using Machine Learning to learn more about our brains
88510

Dr. Thomas Trappenberg of the Faculty of Computer Science, runs the Hierarchical Anticipatory Learning (HAL) Lab. The HAL Lab works in three areas that are essentially connected: computational neuroscience, machine learning and robotics.

“We are most interested in understanding how the brain works—in particular how activities in neurons and the architecture of the brain enables high-level thinking,” says Dr. Trappenberg. “A central ingredient for all of this is how humans and animals learn. This brings us to the scientific area of machine learning.”  Read more about Deep Learning and Neural Networks with Dr. Thomas Trappenberg.

Image Pattern Analysis and Machine Intelligence (IPAMI)

The research interests of the group include human vision perception and perceptual organization, computation models of perception and perceptify technology, statistical and structural image pattern analysis, perceptual pattern learning, generic image segmentation, perceptual feature classification and grouping, vision applications on surveillance (motion), content based image retrieval, medical imaging, and robot vision, etc.

Group Website: http://projects.cs.dal.ca/ipami/
Contact Information: Dr. Qigang Gao
Phone: 1-902-494-3356
Email: q.gao@dal.ca
Research Areas and
Projects:
  • Vision Perceptify
    • Vision perceptify language: perceptual partition and grouping
    • Vision based computer-user interface
  • Image Segmentation
    • Perceptify token-based generic region segmentation
    • Medical imaging: retina vessel map extraction
  • Content-based Image Retrieval
    • Content-based image retrieval using perceptual shape features
    • Content-based image retrieval using extended autocorrelogram
  • Surveillance and Motion Analysis
    • Motion object analysis: motion tracking and license recognition
    • Gesture analysis for video game control
  • Robot Vision
    • Web-based robot control, Multi-sensor data fusion
    • Autonomous underwater hexapod robot
  • Case-based reasoning and expert systems
  • Visual attention and computational neuroscience
Funding: NSERC, MITACS & Industrial partners
Faculty Members:
Other Members:
  • Dr. Jason Gu, jason.gu@dal.ca, Department of Electrical and Computer Engineering
Engaging with industry
Call to action qigang

Industry partners gain access to the unique knowledge and expertise of researchers in order to solve problems relevant to their organization. Researchers apply their knowledge to real-world problems while staying abreast with current technologies used within the private sector. Students and postdocs gain exposure to problems with a practical significance, which often becomes part of their thesis work – and connections are made within industry that can lead to future employment.

IPAMI talks about their partnership with iWave Information Systems Inc. Read the full story.

 

kNowledge Intensive Computing for Healthcare Enterprises (NICHE)

The NICHE (kNowledge Intensive Computing for Healthcare Enterprises) Research Group conducts research in advancing knowledge technologies and developing innovative knowledge-intensive solutions, in particular for healthcare enterprises.

The NICHE group both promotes and pursues inter-disciplinary research whereby the group's investigations span from the abstract epistemological orientations of knowledge to the capture and representation of knowledge to practical operationalization of knowledge via intelligent systems.

Group Website: http://niche.cs.dal.ca/
Contact Information: niche@cs.dal.ca
Tel: 1-902-494-2129
Fax: 1-902-492-1517
Research Areas and
Projects:

The wide spectrum of activities conducted in NICHE group falls in the realm of four inter-related research areas:
1. Knowledge Management and Semantic Web
2. Health Informatics
3. Intelligent Information and Services Personalization
4. Health Data Mining

NICHE researchers work across a cross-section of the above-mentioned themes, developing both novel knowledge-centric methods and applying these methods in knowledge-intensive tools. Currently, the researchers are working towards the development of a knowledge creation, morphing and sharing framework for capturing and operationalizing heterogeneous knowledge modalities present within an enterprise; the development and application of intelligent techniques to customize web-based services and information content as per a user-model; the formal computerization of healthcare knowledge artifacts to offer point-of-care decision support services; and the application of knowledge and data-driven intelligent systems to provide innovative healthcare services for both practitioners and patients. Details of individual projects can be found at the individual researcher's websites. Our research projects are largely funded by government agencies, private organizations and industry.

Funding: The NICHE projects have been funded by CANARIE, National Sciences and Engineering Research Council of Canada (NSERC), Canadian Foundation of Innovation (CFI), Nova Scotia Health Research Foundation (NSHRF), Green Shield Foundation Canada and Agfa Healthcare Canada.
Faculty Members: Dr. Raza Abidi

 

Health Informatics finds its NICHE
MI Round Table discussion

They’ve established their niche on the fourth floor of the Goldberg Computer Science Building; a group of 20 researchers who are changing the face of health care. Led by Dr. Raza Abidi, the team is known as the NICHE group (kNowledge Intensive Computing for Healthcare Enterprises). 

The group spends their day actively investigating and developing innovative health informatics technologies to support both healthcare providers and patients. They conduct research in four main areas: Healthcare Knowledge Management and Semantic Web; Health Data Analytics; Personalized Patient Support; and Mobile Health. Seven postdoctoral fellows, Seven PhD students, five masters students and two research associates form the core team. Read the full story.

MALNIS

Combining content and link information for describing, classifying, clustering and visualizing networked information spaces.

The focus of the group is the application of machine learning, graph theory and natural language processing to problems in networked information spaces, i.e. large document collections which have the form of a graph, where nodes are occupied by documents and links represent relations between documents (hyperlinks or citations). Specific research problems addressed include similarity and clustering based on both content and link information, low-dimensional representations of special text corpora based on lexical ontologies and automatically extracted terms, summarization of web document
collections, and information extraction. Networked information spaces of particular interest include the scientific and medical research literature, the Web and corporate Web spaces. To address the computational requirements associated with processing large data sets, attention is focusing on the use
of coarse-grained parallelism (on clusters of Linux workstations).

Specific projects include web site summarization, information extraction from web sources, automatic term extraction from special text corpora, modelling of user browsing patterns, detection of abnormal patters in large dynamic communication graphs.

The MALNIS lab cooperates with the Web Information Filtering Lab and the Dalhousie Natural Language Processing Group.

Group Website: https://projects.cs.dal.ca/malnis/
Contact Information: Dr. Evangelos Milios
Email: eem@cs.dal.ca
Phone: 902-494-7111
Fax: 902-492-1517
Research Areas and
Projects:
  • Modelling and Mining of Networked Information Spaces,
  • Text Mining,
  • Graph Mining,
  • Social Network Analysis.
Funding:
Faculty Members:

Beiko's Lab in Bioinformatics

Specializing in Bioinformatics, Dr. Robert Beiko leads a team of graduate students and postdoctoral fellows in a range of projects with direct applications to real-world problems.

For full details on the lab, visit: kiwi.cs.dal.ca/beikolabWordPress/

Contact: Dr. Beiko at beiko@cs.da.ca

Finding your way through the genes
100916

When you think of all the possibilities for new discoveries that have opened up with the ability to decode the gene sequences of living organisms, you might envision some scientist in a white lab coat, surrounded by an array of test tubes.

The process of decoding DNA sequences produces an avalanche of data – and finding the meaning and knowledge hidden in that data is a challenge being tackled today by computer scientists. They’re the researchers who work with algorithms and focus on interpreting genetic data instead of the messy business of samples and test tubes. Read the full story.

 

Systems & Networks 

EMerging WIreless Technologies Research (MYTech) Lab

Welcome to the digital home of the Emerging Wireless Technologies Research Group.

The contemporary world is witness to the introduction of new technologies and applications with each passing day. The traditional modes of computing are fast being replaced by mobile computing. Mobile computing begins with the high-configuration laptop (or, notebook) computers and includes tablet computers, cellular phones, and smaller elements such as sensor nodes, RFID (Radio Frequency Identification) and NFC (Near Field Communication) tags. In a perfect infrastructure, these elements will be connected by a backend enterprise infrastructure for managing all data associated with them. This is given by the concept of cloud computing. These are the key elements of the Internet of Things (IoT).

Our work focuses mainly on addressing the security, reliability (quality of service (QoS) and resource management) and application requirements of these emerging wireless technologies. Specifically, we work on:

  • Vulnerability analysis of WiFi, WiMAX, Ad Hoc wireless, RFID/NFC, Sensor (WSN – Wireless Sensor Networks and WBAN – Wireless Body Area Networks) and Smartphone networks;
  • Design of Cryptographic algorithms for group key management in resource-constrained networks;
  • Design of security best practices, risk mitigation and analysis, and design of intrusion detection / prevention mechanisms;
  • Enhancement of QoS in 3G+ wireless networks, optical burst switching techniques for QoS, and performance analysis of wireless networks;
  • Design and analysis of security mechanisms for the cloud;
  • Design, implementation and evaluation of smartphone applications;
Group Website: https://projects.cs.dal.ca/mytech/w/
Contact Information: Dr. Srinivas (Srini) Sampalli at (902)494-1657
   
Faculty Members: Dr. Srinivas (Srini) Sampalli
Digital access at your fingertips
SWAP02

The idea for SWAP has its roots in Tiwari’s own experience and research. A few years ago, Tiwari had lost money to hackers and knew friends who had as well. Later, during his master’s research at Dal he decided to focus on coming up with a new security protocol to help reduce reliance on passwords — something he did with the help of his thesis supervisor, Srinivas Sampalli.

When a friend suggested Tiwari build a business around his technology, he decided to give it a try. Within weeks, he and his five teammates — Jared Perry, Armando Tenias, Rahul Tiwari, Nigel Lutchman and Raghav V. Sampangi — entered SWAP in a business competition at Saint Mary’s University and walked away with the $20,000 cash prize. Then after a bit of Internet searching, he stumbled upon the LaunchPad program. Read the full student research story of work from MYTech Lab.

Network Information Management and Security (NIMS) Lab

Organizations are increasingly relying on networks for the seamless integration of distributed information systems. This has provided many advantages but it has also increased the capacity for the disruption of mission critical services. Some of these problems can be addressed by augmenting existing network management tools, but new approaches, ones that can be integrated with the existing infrastructure, must be developed in order to deal with novel threats. The Network Information Management and Security (NIMS) group proposes a holistic yet distributed approach to network information management and security. The NIMS group has a strong background in networking as well as machine learning and artificial intelligence. The group meets biweekly at the Faculty of Computer Science, Dalhousie University.

Group Website: http://projects.cs.dal.ca/projectx/
Contact Information: Dr. Nur Zincir-Heywood at zincir@cs.dal.ca
Faculty Members:
In the news: Welcome to NIMS Lab
Nur Malcolm Group

We call them the Network Information Management and Security Group; also known as NIMS lab. Tucked away in their headquarters on the 2nd floor of the Goldberg Computer Science Building, Nur Zincir-Heywood and Malcolm Heywood have become a fundamental staple within the Faculty of Computer Science.

Their lab is equipped with twenty brilliant graduate and undergraduate students who dare to imagine systems that work autonomously! Read the full story.

 

Human-Computer Interaction & Visualization

Graphics and Experiential Media (GEM) Lab

We conduct research in the areas of mobile interaction, new media / mixed reality, usable privacy and security, animation / simulation, graphics, and visualization.

Recently, we have conducted research on the following topics: non-photorealistic rendering, image processing, 3D animation, data visualization, whole body interaction, mobile interfaces, and mixed reality collaborative environments.

By-products of our research have found applications in areas such as healthcare, digitally enhanced manufacturing, security and privacy, geo-spatial information systems, film production, text visualization, interactive media, and personal visual analytics.

Our lab has received funding from the Boeing Company, NSERC CRD program, NSERC Discovery grants, GRAND NCE, and MITACS, among other sources.

Group Website: gem.cs.dal.ca
Faculty Members:
Ubiquitous Computing @ Dal
20131007_reilly_derek_operation_citadel-1

Stretching the Boundaries: Ubiquitous Computing @ Dal

Digital technology pervades our everyday lives. We can find nearby Thai restaurants, compare reviews, menus and prices, and view relative distances and locations on interactive maps or superimposed onto our field of view. We can follow a route to a chosen spot and be reminded that we need to buy a birthday card as we pass the local stationary store. At the restaurant, we can capture and immediately share images and videos, annotated with time, place and the people present. Before leaving, we can even add our own review.  Read Dr. Derek Reilly's full story.

Hypertext Augmenting Intelligent Knowledge Use (HAIKU)

H.A.I.K.U. is all about harnessing the potential of hypertext to help individuals find and use information.  Some of the projects are about fundamental issues but others are about doing something soon since technology and people co-develop so rapidly if you don't do something early you cannot have any influence, and there are many bad influences already.

One project about fundamental principles which has reached an important point is about the basis of people's use of hypertext.  Many researchers have noted that people who score highly on certain tests of spatial reasoning tend to use hypertext successfully (that is quickly and accurately) and vice versa.  However when hypertext interfaces are redesigned to the benefit of people with lower scores on spatial ability tests, there is an inversion in success. It is not clear if the two groups completely swap positions however.

H.A.I.K.U.'s research in this area has been to explore the role of domain expertise in comprehending hypertext versions of scholarly publications.  The particular importance of this work is that it could lead to new interfaces for presenting the WWW and to new ways of teaching people to use the WWW.

One of the other project within H.A.I.K.U. which is being conducted as time and research assistants are available, is an automated tool to check colours on webpages to ensure they meet some profile (e.g. suitable for red-green colour blind readers or not a problem for people with ADD) and suggest changes to the author of the webpage.  The work has progressed a lot in the past two years.  Some of thetool's features are unmatched.  Combining it with another teams' work could have a big impact on the WWW.

A major project within H.A.I.K.U. is the development of tools for scholars (including students) to use electronic texts. Work continues on note-taking, sense-making and annotation.  Stay tuned for future developments.

Research Areas and
Projects:

Hypertext Augmenting Intelligent Knowledge Use

  • Hypertext
  • Tools for scholarly reading (annotation, marginalia, glossaries, etc.)
  • The WWW
  • Digital Libraries
  • Human-computer interaction, Human factors
  • Accessibility Tools for the WWW
  • Information-seeking behaviour
Funding: NSERC, CFI, SSHRC
Faculty Members: