Engineering Science, School of

Receive updates for this collection

A Dataset of Labelled Objects on Raw Video Sequences

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-12-26
Abstract: 

We present an object labelled dataset called SFU-HW-Objects-v1, which contains object labels for a set of raw video sequences. The dataset can be useful for the cases where both object detection accuracy and video coding efficiency need to be evaluated on the same dataset. Object ground-truths for 18 of the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences have been labelled. The object categories used for the labeling are based on the Common Objects in Context (COCO) labels. A total of 21 object classes are found in test sequences, out of the 80 original COCO label classes. Brief descriptions of the labeling process and the structure of the dataset are presented.

Document type: 
Article
File(s): 

Scanning and Actuation Techniques for Cantilever-Based Fiber Optic Endoscopic Scanners—A Review

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2021-01-02
Abstract: 

Endoscopes are used routinely in modern medicine for in-vivo imaging of luminal organs. Technical advances in the micro-electro-mechanical system (MEMS) and optical fields have enabled the further miniaturization of endoscopes, resulting in the ability to image previously inaccessible small-caliber luminal organs, enabling the early detection of lesions and other abnormalities in these tissues. The development of scanning fiber endoscopes supports the fabrication of small cantilever-based imaging devices without compromising the image resolution. The size of an endoscope is highly dependent on the actuation and scanning method used to illuminate the target image area. Different actuation methods used in the design of small-sized cantilever-based endoscopes are reviewed in this paper along with their working principles, advantages and disadvantages, generated scanning patterns, and applications.

Document type: 
Article
File(s): 

Embedding the United Nations Sustainable Development Goals Into Energy Systems Analysis: Expanding the Food–Energy–Water Nexus

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2021-01-05
Abstract: 

Background

There have been numerous studies that consider the nexus interactions between energy systems, land use, water use and climate adaptation and impacts. These studies have filled a gap in the literature to allow for more effective policymaking by considering the trade-offs between land use, energy infrastructure as well as the use of water for agriculture and providing energy services. Though these studies fill a significant gap in the modelling literature, we argue that more work is needed to effectively consider policy trade-offs between the 17 United Nations sustainable development goals (SDGs) to avoid missing important interactions.

 

Results

We examine the 17 SDGs individually to determine if it should be included in a modelling framework and the challenges of doing so. We show that the nexus of climate, land, energy and water needs to be expanded to consider economic well-being of both individuals and the greater economy, health benefits and impacts, as well as land use in terms of both food production and in terms of sustaining ecological diversity and natural capital. Such an expansion will allow energy systems models to better address the trade-offs and synergies inherent in the SDGs. Luckily, although there are some challenges with expanding the nexus in this way, we feel the challenges are generally modest and that many model structures can already incorporate many of these factors without significant modification.

 

Finally, we argue that SDGs 16 and 17 cannot be met without open-source models and open data to allow for transparent analysis that can be used and reused with a low cost of entry for modellers from less well-off nations.

 

Conclusions

To effectively address the SDGs, there is a need to expand the common definition of the nexus of climate, land, energy, and water to include the synergies and trade-offs of health impacts, ecological diversity and the system requirements for human and environmental well-being. In most cases, expanding models to be able to incorporate these factors will be relatively straight forward, but open models and analysis are needed to fully support the SDGs.

Document type: 
Article
File(s): 

Fabrication of a Stepped Optical Fiber Tip for Miniaturized Scanner

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2021-01-01
Abstract: 

Advancements in fabrication of miniaturized optical scanners would benefit from micrometer sized optical fiber tips. The change in the cross section of an optical fiber tip is often accompanied with the presence of a longer tapered area. The reduction of the cross section of double clad optical fibers (DCFs) with a flat interface surface at the region where a change in the cross section takes place (with an abrupt change in the cross section) is considered in this paper. Various methods such as heating and pulling, wet etching using hydrofluoric acid (HF), and etching in a vaporous state were explored. The optical etching rate and its dependence on the temperature of the etchant solution were also determined. Optical fibers etch linearly with time, and the etching speed is dependent on the temperature of the etchant solution which shows a parabolic trend. The flatness of the surface at the cross section change is an interesting parameter in the fabrication of submillimeter sized scanners where the light is transmitted through the core of the DCF, and reflected light is collected through the inner cladding of the same fiber, or vice versa. The surface flatness at the interface was compared among different fiber samples developed using the aforementioned techniques. This research illustrates that the wet chemical etching performed by blocking the capillary rising of etchant solution along the fiber provided advantages over the heating and pulling technique in terms of light intensity transmitted to the target sample and the reflected light collected through the interface of etched cladding.

Document type: 
Article

FMG- and RNN-Based Estimation of Motor Intention of Upper-Limb Motion in Human-Robot Collaboration

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-12-03
Abstract: 

Research on human-robot interactions has been driven by the increasing employment of robotic manipulators in manufacturing and production. Toward developing more effective human-robot collaboration during shared tasks, this paper proposes an interaction scheme by employing machine learning algorithms to interpret biosignals acquired from the human user and accordingly planning the robot reaction. More specifically, a force myography (FMG) band was wrapped around the user's forearm and was used to collect information about muscle contractions during a set of collaborative tasks between the user and an industrial robot. A recurrent neural network model was trained to estimate the user's hand movement pattern based on the collected FMG data to determine whether the performed motion was random or intended as part of the predefined collaborative tasks. Experimental evaluation during two practical collaboration scenarios demonstrated that the trained model could successfully estimate the category of hand motion, i.e., intended or random, such that the robot either assisted with performing the task or changed its course of action to avoid collision. Furthermore, proximity sensors were mounted on the robotic arm to investigate if monitoring the distance between the user and the robot had an effect on the outcome of the collaborative effort. While further investigation is required to rigorously establish the safety of the human worker, this study demonstrates the potential of FMG-based wearable technologies to enhance human-robot collaboration in industrial settings.

Document type: 
Article
File(s): 

Differential Diagnosis of Frontotemporal Dementia, Alzheimer's Disease, and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-10-22
Abstract: 

Methods: Alzheimer's disease and Frontotemporal dementia are the first and third most common forms of dementia. Due to their similar clinical symptoms, they are easily misdiagnosed as each other even with sophisticated clinical guidelines. For disease-specific intervention and treatment, it is essential to develop a computer-aided system to improve the accuracy of their differential diagnosis. Recent advances in deep learning have delivered some of the best performance for medical image recognition tasks. However, its application to the differential diagnosis of AD and FTD pathology has not been explored.

Approach: In this study, we proposed a novel deep learning based framework to distinguish between brain images of normal aging individuals and subjects with AD and FTD. Specifically, we combined the multi-scale and multi-type MRI-base image features with Generative Adversarial Network data augmentation technique to improve the differential diagnosis accuracy.

Results: Each of the multi-scale, multitype, and data augmentation methods improved the ability for differential diagnosis for both AD and FTD. A 10-fold cross validation experiment performed on a large sample of 1,954 images using the proposed framework achieved a high overall accuracy of 88.28%.

Conclusions: The salient contributions of this study are three-fold: (1) our experiments demonstrate that the combination of multiple structural features extracted at different scales with our proposed deep neural network yields superior performance than individual features; (2) we show that the use of Generative Adversarial Network for data augmentation could further improve the discriminant ability of the network regarding challenging tasks such as differentiating dementia sub-types; (3) and finally, we show that ensemble classifier strategy could make the network more robust and stable.

Document type: 
Article
File(s): 

Practical Diversity Design for PCB IoT Terminals

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-11-02
Abstract: 

Mobile or nomadic diversity antennas feature a variety of element types and layouts, mostly PCB-based, reflecting complex design trade-offs between their performance and the required compactness. The design stage is electromagnetic-based but must include several signal-based diversity metrics, and there is a shortfall of information about their assumptions and the impact of their violation. The evaluation stage normally includes simulation, with physical measurements being the bottom line. Pattern measurement is particularly challenging, but accurately measured patterns are critical parameters, enabling the calculation of mean gains and correlations, and the impact of different propagation scenarios. For developers, the complex set of processes for design and evaluation make it difficult to have confidence with their in-house procedures without access to independent results for a variety of antenna types. For the design stage, we review and clarify the diversity metrics, and for evaluation, a set of typical and new diversity designs implemented on printed circuit board (PCB) are also presented. The methods cover lossy antennas and the expected performance in a directional propagation scenario. This information helps designers and developers to better understand the design process and to check their evaluation procedures.

Document type: 
Article
File(s): 

Planning Capacity for 5G and Beyond Wireless Networks by Discrete Fireworks Algorithm With Ensemble of Local Search Methods

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-09-23
Abstract: 

In densely populated urban centers, planning optimized capacity for the fifth-generation (5G) and beyond wireless networks is a challenging task. In this paper, we propose a mathematical framework for the planning capacity of a 5G and beyond wireless networks. We considered a single-hop wireless network consists of base stations (BSs), relay stations (RSs), and user equipment (UEs). Wireless network planning (WNP) should decide the placement of BSs and RSs to the candidate sites and decide the possible connections among them and their further connections to UEs. The objective of the planning is to minimize the hardware and operational cost while planning capacity of a 5G and beyond wireless networks. The formulated WNP is an integer programming problem. Finding an optimal solution by using exhaustive search is not practical due to the demand for high computing resources. As a practical approach, a new population-based meta-heuristic algorithm is proposed to find a high-quality solution. The proposed discrete fireworks algorithm (DFWA) uses an ensemble of local search methods: insert, swap, and interchange. The performance of the proposed DFWA is compared against the low-complexity biogeography-based optimization (LC-BBO), the discrete artificial bee colony (DABC), and the genetic algorithm (GA). Simulation results and statistical tests demonstrate that the proposed algorithm can comparatively find good-quality solutions with moderate computing resources.

Document type: 
Article
File(s): 

Passive Observer of Activities for Aging in Place Using a Network of RGB-D Sensors

Peer reviewed: 
Yes, item is peer reviewed.
Date created: 
2020-10-23
Abstract: 

Aging in place is a notion which supports the independent living of older adults at their own place of residence for as long as possible. To support this alternative living which can be in contrast to various other types of assisted living options, modes of monitoring technology need to be explored and studied in order to determine a balance between the preservation of privacy and adequacy of sensed information for better estimation and visualization of movements and activities. In this paper, we explore such monitoring paradigm on how a network of RGB-D sensors can be utilized for this purpose. This type of sensor offers both visual and depth sensing modalities from the scene where the information can be fused and coded for better protection of privacy. For this purpose, we introduce the novel notion of passive observer. This observer is only triggered by detecting the absence of movements of older adults in the scene. This is accomplished by classifying and localizing objects in the monitoring scene from both before and after the detection of movements. A deep learning tool is utilized for visual classification of known objects in the physical scene followed by virtual reality reconstructing of the scene where the shape and location of objects are recreated. Such reconstruction can be used as a visual summary in order to identify objects which were handled by an older adult in-between observation. The simplified virtual scene can be used, for example, by caregivers or monitoring personnel in order to assist in detecting any anomalies. This virtual visualization can offer a high level of privacy protection without having any direct visual access to the monitoring scene. In addition, using the scene graph representation, an automatic decision-making tool is proposed where spatial relationships between the objects can be used to estimate the expected activities. The results of this paper are demonstrated through two case studies.

Document type: 
Article
File(s): 

Introduction to Energy Modelling (SEE 310 Course Pack)

Peer reviewed: 
No, item is not peer reviewed.
Date created: 
2020-04-09
Abstract: 

This course pack provides an overview of energy systems modelling for an introductory 3rd year, 4th year, or graduate level course.  There are four main sections: Introduction, Optimization Models, Building Energy Models, and Energy-Economy Models. The introduction provides context on the importance and environmental impacts of the energy system through an engineering and socio-political lens.  Two types of optimization models are covered in section 2: capacity expansion and power system models.  An overview of solutions to optimization models through linear and mixed integer programming is provided.  Section 3 provides an overview of building energy modelling with practice problems on calculating wall r-values and using eQuest for basic building energy modelling.  Energy-economy models are then introduced including Input-Output, Computable General Equilibrium and Partial Equilibrium models.

Document type: 
Other
File(s):