UNB Scholar Research Repository :: Browsing by Author "Wachowicz, Monica"

Browsing by Author "Wachowicz, Monica"

Now showing 1 - 10 of 10

An evolutionary graph framework for analyzing fast-evolving networks
(University of New Brunswick, 2019) Ikechukwu, Maduako Derek; Wachowicz, Monica
Fast-evolving networks by definition are real-world networks that change their structure, becoming denser over time since the number of edges and nodes grows faster, and their properties are also updated frequently. Due to the dynamic nature of these networks, many are too large to deal with and complex to generate new insights into their evolution process. One example includes the Internet of Things, which is expected to generate massive networks of billions of sensor nodes embedded into a smart city infrastructure. This PhD dissertation proposes a Space-Time Varying Graph (STVG) as a conceptual framework for modelling and analyzing fast-evolving networks. The STVG framework aims to model the evolution of a real-world network across varying temporal and spatial resolutions by integrating time-trees, subgraphs and projected graphs. The proposed STVG is developed to explore evolutionary patterns of fast-evolving networks using graph metrics, ad-hoc graph queries and a clustering algorithm. This framework also employs a Whole-graph approach to reduce high storage overhead and computational complexities associated with processing massive real-world networks. Two real-world networks have been used to evaluate the implementation of the STVG framework using a graph database. The overall results demonstrate the application of the STVG framework for capturing operational-level transit performance indicators such as schedule adherence, bus stop activity, and bus route activity ranking. Finally, another application of STVG reveals evolving communities of densely connected traffic accidents over different time resolutions.
An IoT platform for occupancy prediction using support vector machine
(University of New Brunswick, 2019) Parise, Alec; Wachowicz, Monica
The Internet of Things (IoT) is a network of devices able to connect, interact and exchange data without human intervention. Most of today’s research focuses on collecting indoor sensor data with the purpose of reducing costs of operation facilities management. Innovative approaches ranging from context aware sensing platforms to dynamic robot sensing have been proposed in previous research work, but the challenge remains on understanding how sensor data can be used to predict occupancy usage patterns in smart buildings. This research aims at developing a non-intrusive sensing method for gathering sensor data for predicting occupancy usage patterns in indoor environments. There are several potential applications ranging from that can benefit from occupancy prediction. Smart building management systems; establishing communication with the HVAC system when an accurate occupancy classification and prediction for optimization of energy consumption. Towards this end, an IoT platform based on an open source architecture consisting of Arduino and Raspberry Pi 3 B+ is designed and deployed in three different environments at two University campuses. By utilizing temperature and humidity for observing indoor environmental characteristics while combining PIR motion sensors, CO2, and sound detectors a robust occupancy detection model is created, and by applying Support Vector Machine, occupancy usage patterns are predicted. This IoT platform is a low-cost and highly scalable both in terms of the variety of on-board sensors and portability of the sensor nodes, which makes it well suited for multiple applications related to occupancy usage and environmental monitoring.
Analysis of EV charging station clusters using a novel representation of temporally varying structures
(University of New Brunswick, 2021-11) Richard, René; Church, Ian; Wachowicz, Monica
Transport electrification introduces new opportunities in supporting sustainable mobility. Fostering Electric Vehicle (EV) adoption integrates vehicle range and infrastructure deployment concerns. An understanding of EV charging patterns is crucial for optimizing charging infrastructure placement and managing costs. Clustering EV charging events has been useful for ensuring service consistency and increasing EV adoption. However, clustering presents challenges for practitioners when first selecting the appropriate hyperparameter combination for an algorithm and later when assessing the quality of clustering results. Ground truth information is usually not available for practitioners to validate the discovered patterns. As a result, it is harder to judge the effectiveness of different modelling decisions since there is no objective way to compare them. This work proposes a clustering process that allows for the creation of relative rankings of similar clustering results. The overall goal is to support users by allowing them to compare a clustering result of interest against other similar groupings over multiple temporal granularities. The efficacy of this analytical process is demonstrated with a case study using real-world EV charging event data from charging station operators in New Brunswick.
Data stream affinity propagation for clustering indoor space localization data
(University of New Brunswick, 2021) Eshraghi Ivari, Nasrin; Wachowicz, Monica
In the age of Internet of Things, the ability to find spatio-temporal patterns of people and devices moving in indoor spaces has become crucial for developing new applications. In particular, clustering indoor localization data streams has gained popularity in recent years due to their potential of generating relevant information for planning building automation, evaluating energy efficiency scenarios, and simulating emergency protocols. In this thesis, a data stream Affinity Propagation (DSAP) clustering algorithm is proposed for analyzing indoor localization data generated from e-counters and WiFi localization systems. The data sets are a sequence of potentially infinite and non-stationary data streams, arriving continuously where random access to the data is not feasible and storing all the arriving data is impractical. The DSAP algorithm is implemented based on a two-phase approach (i.e., online and offline clustering phases) using the landmark time window model. The proposed DSAP is non-parametric in the sense of not requiring any prior knowledge about the number of clusters and their respective labels. The validation and performance of the DSAP algorithm are evaluated using real-world data streams from two experiments aimed at finding stair usage patterns and occupancy behaviour in indoor spaces.
Design of a mobile application display meaningful real property information
(University of New Brunswick, 2018) Bulua, Amanda; McCully, Luke; Howe, Brandon; Monahan, John; Wachowicz, Monica
Developing a Resource-Constraint EdgeAI model for Surface Defect Detection
(2023) Mih, Atah Nuh; Cao, Hung; Kawnine, Asfia; Wachowicz, Monica
Resource constraints have restricted several EdgeAI applications to machine learning inference approaches, where models are trained on the cloud and deployed to the edge device. This poses challenges such as bandwidth, latency, and privacy associated with storing data off-site for model building. Training on the edge device can overcome these challenges by eliminating the need to transfer data to another device for storage and model development. On-device training also provides robustness to data variations as models can be retrained on newly acquired data to improve performance. We therefore propose a lightweight EdgeAI architecture modified from Xception, for on-device training in a resource-constraint edge environment. We evaluate our model on a PCB defect detection task and compare its performance against existing lightweight models - MobileNetV2, EfficientNetV2B0, and MobileViT-XXS. The results of our experiment show that our model has a remarkable performance with a test accuracy of 73.45% without pre-training. This is comparable to the test accuracy of non-pre-trained MobileViT-XXS (75.40%) and much better than other non-pre-trained models (MobileNetV2 - 50.05%, EfficientNetV2B0 - 54.30%). The test accuracy of our model without pre-training is comparable to pre-trained MobileNetV2 model - 75.45% and better than pre-trained EfficientNetV2B0 model - 58.10%. In terms of memory efficiency, our model performs better than EfficientNetV2B0 and MobileViT-XXS. We find that the resource efficiency of machine learning models does not solely depend on the number of parameters but also depends on architectural considerations. Our method can be applied to other resource-constraint applications while maintaining significant performance.
Developing an analytics everywhere framework for the Internet of Things in smart city applications
(University of New Brunswick, 2019) Cao, Hung; Wachowicz, Monica
Despite many efforts on developing protocols, architectures, and physical infrastructures for the Internet of Things (IoT), previous research has failed to fully provide automated analytical capabilities for exploring IoT data streams in a timely way. Mobility and co-location, coupled with unprecedented volumes of data streams generated by geo-distributed IoT devices, create many data challenges for extracting meaningful insights. This research work aims at exploring an edge-fog-cloud continuum to develop automated analytical tasks for not only providing higher-level intelligence from continuous IoT data streams but also generating long-term predictions from accumulated IoT data streams. Towards this end, a conceptual framework, called “Analytics Everywhere”, is proposed to integrate analytical capabilities according to their data life-cycles using different computational resources. Three main pillars of this framework are introduced: resource capability, analytical capability, and data life-cycle. First, resource capability consists of a network of distributed compute nodes that can handle automated analytical tasks either independently or in parallel, concurrently or in a distributed manner. Second, analytical capability orchestrates the execution of algorithms to perform streaming descriptive, diagnostic, and predictive analytics. Finally, data life-cycles are designed to manage both continuous and accumulated IoT data streams. The research outcomes from a smart parking and a smart transit scenario have confirmed that a single computational resource is not sufficient to support all analytical capabilities that are needed for IoT applications. Moreover, the implemented architecture relied on an edge-fog-cloud continuum and offered some empirical advantages: (1) on-demand and scalable storage; (2) seamlessly coordination of automated analytical tasks; (3) awareness of the geo-distribution and mobility of IoT devices; (4) latency-sensitive data life-cycles; and (5) resource contention mitigation.
Implementing scalable geoweb applications using cloud and internet computing
(University of New Brunswick, 2014) Mousavi, Seyed; Zhang, Yun; Wachowicz, Monica
New advancements in technology such as the rise of social networks have led to more geospatial data being produced every day. The current issue with the large volume of geospatial data is to store and process it because of the scalability of the data.In this thesis, two computing implementations, cloud computing and Internet computing, are studied and evaluated for their capability in storing,processing and visualizing large volumes of geospatial data. For the cloud computing implementation,the different concepts of cloud computing have been analysed according to their applications, models and services. Moreover, a case study using cloud computing platforms has also been implemented for storing and processing geotagged tweets retrieved for a national recreational park in Vancouver, BC. For the Internet computing platform,the Open Geospatial Consortium’s Web Processing Service has been investigated as a framework for sharing geospatial data and processing it over Internet. A raster calculation algorithm in Web Processing Service platforms has also been implemented on 2 scenes of Lands at satellite imagery to evaluate WPS’ capabilities in handling large volume of data. Results of this research suggest that internet computing can be used to handle geospatial data processing but,when dealing with large volumes of data,this study proves that Internet computing and current Geospatial Information Systems are not suitable to be used and cloud computing platform can be utilized to handle large volumes of geospatial data.
Link prediction with local and global consistency preservation in spatio-temporal networks
(University of New Brunswick, 2022-11) Forouzandeh Jonaghani, Rouzbeh; Hanson, Trevor; Wachowicz, Monica; Church, Ian
With the increasing deployment of connected positioning devices, we are witnessing the proliferation of connected data sets in the form of spatio-temporal networks such as Location-Based Social Networks (LBSNs), the Internet of Things (IoT), and smart transportation networks. Link prediction is a key research field in studying spatiotemporal networks as it improves our understanding of the underlying dynamics of the connected data sets by predicting missing or future links that represent the relations in a system. However, current research on link predictions in spatio-temporal networks has been mostly limited to friendship prediction in Location-Based Social Networks (LBSN), and even though local and global consistency have been regarded as important factors in predictive analytics, they have not yet been studied in spatio-temporal networks. One of the main research challenges is mainly related to addressing local consistency due to the substantial difference between the sense of locality in spatio-temporal networks in comparison to non-spatial networks. Moreover, incorporating the role of communities in link prediction in spatio-temporal networks specifically under the concepts of global consistency is another challenge that has not been addressed yet. These challenges have been addressed by proposing methods for carrying out link prediction with local and global consistency which are tested using data from two different shared-mobility systems namely bike-sharing and taxi systems from Chicago and New York City. Different prediction scenarios including the presence of periodic variations in the data and multi-step prediction have been considered. The comparison of the results from the proposed and baseline methods indicates that the proposed methods accurately predict the flow and other related variables (e.g., check-ins) in shared-mobility systems in different scenarios. For example, The proposed MFLOG model improves the bike-flow and check-in/out prediction error by 4.5% and 7.5% respectively, w.r.t baseline models. This can be associated with the successful design of the methods and consideration of local and global consistency in the model.
Quantified self: building a multi-time window analytical workflow for clustering wearable data streams
(University of New Brunswick, 2021) McCully, Luke; Wachowicz, Monica
A new research domain known as the Quantified Self has recently emerged and is described as gaining self-knowledge through using technology to acquire spatio-temporal data on our behavior. Wearable technology is widely used in this domain since it generates a large amount of wearable stream data, which contains information on self-monitoring activities and physical health related problems. However, very little is known about which stream clustering algorithms should be used and which time windows can reveal individuals' spatio-temporal patterns that can yield new self-knowledge insights. This thesis proposes an analytical workflow developed to reveal self-quantified patterns that can be used to understand physical activity behavior. It consists of six phases that are devised to support tasks including retrieving, processing, and clustering wearable data streams. The streaming k-means clustering algorithm, based on an online/offline approach using both sliding and damped time window models, is proposed to uncover self-quantified patterns. An intervention experiment with 15 participants is used to gather Fitbit data logs and implement the proposed analytical workflow. The clustering results reveal the impact of a time window model has on exploring the evolution of micro-clusters and the labelling of macro-clusters to accurately explain regular and irregular individual physical behavior.

Browsing by Author "Wachowicz, Monica"

Results Per Page

Sort Options