PGR meeting and Research Presentations – January 2017

Our monthly PGR meeting was held at Room MC3108 at 14:00 on Wednesday, 11th January.

We had have 1 speaker for this month seminar:

Speaker: Hussein Alahmer

Title: Computer-Aided Classification of Liver Lesions from CT Images Based on Multiple ROI

Abstract: This presentation introduces an automated Computer-Aided Classification (CAD) system to classify liver lesion into Benign or Malignant. The system consists of three stages; firstly, automatic liver segmentation and lesion’s detection. Secondly, extracting features from Multiple ROI, which is the novelty. Finally, classifying liver lesions into benign and malignant. The proposed system divides a segmented lesion into three areas, i.e. inside, outside and border areas. This is because the inside lesion, boundary, and surrounding lesion area contribute different information about the lesion. The features are extracted from the three areas and used to build a new feature vector to feed a classifier. The novelty lies in using the features from the multiple ROIs, and particularly surrounding area (outside), because the Malignant lesion affects the surrounding area differently compared to, the Benign lesion. Utilising the features from inside, border, and outside lesion area supports in better differentiation between benign and malignant lesion. The experimental results showed an enhancement in the classification accuracy (using multiple ROI technique) compared to the accuracy using a single ROI

The next seminar will be held in February. The date and venue for the next meeting will be announced.

PGR meeting and Research Presentations – November 2016

The monthly PGR meeting was held at Room MC3108 at 14:00 on Wednesday, 9th November.

We had 1 speaker for this month seminar:

Speaker: Francesco Caliva

Title: Extraction of the retinal vascular trees

Abstract: The retina is a non-invasive access point to the vascular network, and several studies have shown that systemic (and local) disorders can affect blood vessels geometry and alter haemodynamic conditions within. Fundus photography is the gold standard screening technique of the retina. Therefore fundus images are employed in our research. This talk will present the subject of our research, which aims at identifying the retinal vascular trees and differentiate them as arterial and venous.

 

This was followed by discussions regarding the PGR studies in the School, organised by Dr Marc Hanheide.

 

The next seminar will be held in December. The date and venue for the next meeting will be announced.

PGR meeting and Research Presentations – October 2016

The monthly PGR meeting was held at Room MC3108 at 14:00 on Wednesday, 12th October.

We had 2 speakers for this month seminar:

Speaker: Qinbing Fu

Title: Bio-inspired Collision Detector with Enhanced Selectivity for Ground Robotic Vision System

Abstract: There are many ways of building collision-detecting systems. We propose a novel collision selective visual neural network inspired by LGMD2 neurons in the juvenile locusts. Such collision-sensitive neuron matures early in the first-aged or even hatching locusts, and is only selective to detect looming dark objects against bright background in depth, represents swooping predators, a situation which is similar to ground robots or vehicles. However, little has been done on modeling LGMD2, let alone its potential applications in robotics and other vision-based areas. Compared to other state-of-the-arts,our major contributions are first, enhancing the collision selectivity in a bio-inspired way, via constructing a computing efficient visual sensor, and realizing the revealed specific characteristics of LGMD2. Second,we applied the neural network to help near range path navigation of an autonomous ground miniature robot in an arena. We also examined its neural properties through systematic experiments challenged against image streams from a visual sensor of the micro-robot.

 

Speaker: Xuqiang Zheng

Title: “A 5-50 Gb/s Quarter Rate Transmitter with a 4-Tap Multiple-MUX based FFE in 65 nm CMOS”

Abstract: We present a 5-50 Gb/s quarter-rate transmitter with a 4-tap feed-forward equalization (FFE) based on multiple-multiplexer (MUX). A bandwidth enhanced 4:1 MUX with the capability of eliminating charge-sharing effect is proposed to increase the maximum operating speed. To produce the quarter-rate parallel data streams with appropriate delays,a compact latch array associated with an interleaved-retiming technique is designed. Implemented in 65 nm CMOS technology, the transmitter occupying an area of 0.6 mm2 achieves a maximum data rate of 50 Gb/s with an energy efficiency of 3.1 pJ/bit.

 

 

The next seminar will be held in November. The date and venue for the next meeting will be announced.

PGR meeting and Research Presentations – September 2016

The monthly PGR meeting was held on Wednesday 21st September, 10:00-12:00, Room MC3108.

We had 1 speakers for this month seminar:

Miss Grace Ataguba

Exploring Story Telling Technologies for Memorialization in Cemetery and Living Spaces

Abstract: Memories are interesting part of everyday lives and storytelling is one form we adopt to share memories. Memorialization of the dead which involves remembering the dead through story telling has been in existence since time immemorial. The rise in digital death has relatively brought about a rise in digital memorialization as compared to an existing practice where the bereaved is constrained by cultural and religious beliefs as well as a certain space to commemorate their dead; especially the cemetery. Therefore the shift in the use of current technologies for memorialization is one of the indicators of how well people are willing to continuously establish bonds with the dead. In our study, we wish to consider stories people are willing to share in memory of their loved ones to identify relationship that exist among the likely variables that influences their response. These variables include: the length of time since the loss: closeness of the relationship measured in various forms and the story teller. The research will be adopting participatory research design approach in getting the focused group involved in the study. However we designed our instrument- an online survey to collect these stories which has been given ethical consideration and approval. Participants for the study are being recruited through emails, university news blogs, advertisements, social media and discussion groups. The data collected will be analysed using basic concepts of data sciences – emotion mining and statistics. Results of the analysis will serve as a pilot study to our main study.

 

The next seminar will be held in October. The date and venue for the next meeting will be announced.

PGR meeting and Research Presentations – July 2016

The monthly PGR meeting was held on Wednesday 13th July, 14:00-16:00, Room MC3108.

We had 2 speakers for this month seminar:

 
* Claudio Coppola

We investigate how incremental learning of long-term human activity patterns improves the accuracy of activity classification over time.Rather than trying to improve the classification methods themselves, we assume that they can take into account prior probabilities of activities occurring at a particular time and location.We use the classification results to build spatial and temporal models that can provide these priors to the classifiers.As our system gradually learns about typical patterns of human activities, the accuracy of activity classification improves, which results in even more accurate priors. Two datasets collected over several months containing hand-annotated activity in residential and office environments were chosen to evaluate the approach.Several types of spatial and temporal models were evaluated for each of these datasets.The results indicate that incremental learning of daily routines leads to a significant improvement in activity classification.

 

 
* Evangelia Kotsiliti

Diabetic retinopathy is a complication of diabetes affecting the eye and a leading cause of blindness worldwide. In many countries around the world, systematic screening for diabetic retinopathy is provided to the patients diagnosed with diabetes in order to reduce the burden of blindness. However, considering the rising numbers of people who are diagnosed with diabetes every year, it is plausible to think that the provision of screening services to an increased demand may no longer be affordable. This projects aims at the utilisation of simple, commonly available patient characteristics and biochemical measures to identify patients at high risk of having retinopathy at the time of screening. A subsequent step aims at the development of a cost-effectiveness model to compare the cost and consequences of the risk model against the current manual grading. The ultimate outcome would be the development of reliable clinical model that can reduce the overall screening cost and retain effectiveness.

 

There will be no seminar in August. The date and venue for the next meeting in September 2016 will be announced.