Jeremiah D. Deng

• PhD, MEng, BEng
• Professor (Associate) at University of Otago

Cognitive dysfunction often co-occurs with psychopathology. Advances in neuroimaging and machine learning have led to neural indicators that predict individual differences in cognition with reasonable performance. We examined whether these neural indicators explain the relationship between cognition and mental health in the UK Biobank cohort (n > 1...

Objective: Diagnosing pain in research and clinical practices still relies on self-report. This study aims to develop an automatic approach that works on resting-state raw EEG data for chronic knee pain prediction. Method: A new feature selection algorithm called "modified Sequential Floating Forward Selection" (mSFFS) is proposed. The improved...

ReduNet is a deep neural network model that leverages the principle of maximal coding rate \textbf{redu}ction to transform original data samples into a low-dimensional, linear discriminative feature representation. Unlike traditional deep learning frameworks, ReduNet constructs its parameters explicitly layer by layer, with each layer's parameters...

Amidst the rapid advancements in technology, there is a growing demand for processing an increasing volume and quality of images, which necessitates faster image processing capabilities. Enhancing the efficiency of image processing algorithms has thus become a critical priority. Existing quantum image edge detection algorithms tend to exhibit high...

Brain-wide association studies (BWASs) have attempted to relate cognitive abilities with brain phenotypes, but have been challenged by issues such as predictability, test-retest reliability, and cross-cohort generalisability. To tackle these challenges, we proposed a machine-learning “stacking” approach that draws information from whole-brain magne...

With the increase in the quantity and quality of images that need to be processed, there are higher requirements for the speed of image processing. Thus, it is necessary to speed-up the image processing algorithms. In this paper, we design a quantum image edge detection algorithm based on Laplacian of Gaussian (LoG) operator, which has significant...

We present an automatic approach that works on resting-state raw EEG data for chronic pain detection. A new feature selection algorithm - modified Sequential Floating Forward Selection (mSFFS) - is proposed. The improved feature selection scheme is rather compact but displays better class separability as indicated by the Bhattacharyya distance meas...

Obesity is a common issue in modern societies today that can lead to various diseases and significantly reduced quality of life. Currently, research has been conducted to investigate resting state EEG (electroencephalogram) signals with an aim to identify possible neurological characteristics associated with obesity. In this study, we propose a dee...

Federated Learning (FL) has emerged as a promising collaborative learning paradigm that enables to train machine learning models across decentralized devices, while keeping the training data localized to preserve user privacy. However, the heterogeneity in both decentralized training data and distributed computing resources has posed significant ch...

Background: Children under 18 years of age account for approximately 1 in 3 internet users worldwide. Largely unregulated, the internet-based world is evolving rapidly and becoming increasingly intrusive. There is a dearth of objective research globally on children’s real-time experiences of the internet-based world. Objective: This paper reports...

For energy-harvesting sensor nodes, rechargeable batteries play a critical role in sensing and transmissions. By coupling two simple Markovian queue models in a delay-tolerant networking setting, we consider the problem of battery sizing for these sensor nodes to operate effectively: given the intended energy depletion and overflow probabilities, h...

Capturing individual differences in cognition is central to human neuroscience. Yet our ability to estimate cognitive abilities via brain MRI is still poor in both prediction and reliability. Our study tested if this inability can be improved by integrating MRI signals across the whole brain and across modalities, including task-based functional MR...

To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential. We propose to introduce a novel cross-domain latent modulation mechanism to a variational autoencoder framework so as to achieve effective transfer learning. Our key idea is to procure deep representations from one data domain and...

As a common approach of deep domain adaptation in computer vision, current works have mainly focused on learning domain-invariant features from different domains, achieving limited success in transfer learning. In this paper, we present a novel “deep adversarial transition learning” (DATL) framework that bridges the domain gap by generating some in...

Collaborative learning such as federated learning enables to train a global prediction model in a distributed way without the need to share the training data. However, most existing schemes adopt deep learning models and require all local models to have the same architecture as the global model, making them unsuitable for applications using resourc...

BACKGROUND Children under 18 account for approximately one in three internet users worldwide. Largely unregulated, the online world is evolving rapidly and becoming increasingly intrusive. There is a dearth of objective research globally on children’s real-time experiences of the online world. OBJECTIVE This paper reports on an objective methodolo...

Capturing individual differences in cognitive abilities is central to human neuroscience. Yet our ability to estimate cognitive abilities via brain MRI is still poor in both prediction and reliability. Our study tested if this inability was partly due to the over-reliance on 1) non-task MRI modalities and 2) single modalities. We directly compared...

Semantic segmentation based on deep learning methods can attain appealing accuracy provided large amounts of annotated samples. However, it remains a challenging task when only limited labelled data are available, which is especially common in medical imaging. In this paper, we propose to use Leaking GAN, a GAN-based semi-supervised architecture fo...

The purpose of feature selection (FS) is to eliminate redundant and irrelevant features and leave useful features for classification, which can not only reduce the cost of classification, but also improve the classification accuracy. Existing algorithms mainly focus on finding one best feature subset for an optimization target or some Pareto soluti...

Electroencephalography (EEG) is a widely used non-invasive technique to measure multi-channel potentials that reflect the electrical activity of the brain. Over the last few decades, EEG analysis has been an intensively explored research topic due to its potentials in being applied to the diagnosis of neurological diseases, such as epilepsy, brain...

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to the reparameterization of the latent variable in another domain. Specifically, deep representations of the so...

Effective analysis of EEG signals for potential clinical applications remains a challenging task. So far, the analysis and conditioning of EEG have largely remained sex-neutral. This paper employs a machine learning approach to explore the evidence of sex effects on EEG signals, and confirms the generality of these effects by achieving successful s...

Effective analysis of EEG signals remains a challenging task. So far, the analysis and conditioning of EEG have largely remained gender-neutral. This paper explores the evidence of gender effects on EEG signals and confirms the generality of these effects by achieving successful gender prediction through EEG signals. Specifically, we propose a nove...

Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel "deep adversarial transition learning" (DATL) framework that bridges the domain gap by projecting the source and target domains into intermediate, tra...

Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilities to track individual motorcycles through multiple frames, or to distinguish drivers from passenge...

Surrogate-assisted evolutionary algorithms (SAEAs) have become one popular method to solve complex and computationally expensive optimization problems. However, most existing SAEAs suffer from performance degradation with the dimensionality increasing. To solve this issue, this article proposes a classifier-assisted level-based learning swarm optim...

Image segmentation benefits from using multi-feature ensembles. In this paper, we propose a novel multi-layer bipartite graph model for more effective feature fusion. This model employs multiple graph layers, each representing a feature space. They share common vertices but have individual edge sets that are obtained from different feature spaces....

Popular deep domain adaptation methods have mainly focused on learning discriminative and domain-invariant features of different domains. In this work, we present a novel approach inspired by human cognitive processes where receptive fields learned from other vision tasks are recruited to recognize new objects. First, representations of the source...

Previous phenological image analysis works use mostly close-up images or satellite remote sensing images. In this paper we employ ground-based tree images to investigate two related research tasks: colouring trends analysis and tree categorization. In the first task, we extracted a few colour features of image regions of three tree types: exotic de...

Coalition structure generation in multi-agent systems has long been a challenging problem because of its NP-hardness in computational complexity. In this paper, we propose a stochastic optimization approach that employs a modified population based incremental learning algorithm and a customized genotype encoding scheme to find the optimal coalition...

Coalition structure generation in multi-agent systems has long been a challenging problem because of its NP-hardness in computational complexity. In this paper, we propose a stochastic optimization approach that employs a modified population based incremental learning algorithm and a customized genotype encoding scheme to find the optimal coalition...

The idea of employing scavenged energy from human motion to run electronic devices is attracting increased attention of many researchers worldwide. However, there is still limited knowledge of energy characteristics generated by human motions. Moreover, level of human activities varies during a day from sitting for several hours to running on a tre...

The cooperation of agents in smart grids to form coalitions could bring benefit both for agent itself and the distribution power system. To tackle the problem as a game of partition form function poses significant computing challenges due to the huge search space for the optimization problem. In this paper, we propose a stochastic optimization appr...

In smart home applications, accurate sensor-based human activity recognition is based on learning patterns online from collections of sequential sensor events. A more challenging problem is to discover and learn unknown activities that have not been observed or predefined. This is because in a real-world environment, it is impractical to presume th...

In pedagogy, teachers usually separate mixed-level students into different levels, treat them differently and teach them in accordance with their cognitive and learning abilities. Inspired from this idea, we consider particles in the swarm as mixed-level students and propose a level-based learning swarm optimizer to settle large scale optimization,...

The popular performance profiles and data profiles for benchmarking deterministic optimization algorithms are extended to benchmark stochastic algorithms for global optimization problems. A general confidence interval is employed to replace the significance test, which is popular in traditional benchmarking methods but suffering more and more criti...

The idea of employing scavenged power from human daily routines to run electronic devices are attracting increased attention of many researchers worldwide. However, there is still limited knowledge of energy characteristics generated by human motions. Moreover, level of human activities vary during a day from sitting for several hours to running on...

Virtual machine placement (VMP) and energy efficiency are significant topics in cloud computing research. In this paper, evolutionary computing is applied to VMP to minimize the number of active physical servers, so as to schedule underutilized servers to save energy. Inspired by the promising performance of the ant colony system (ACS) algorithm fo...

Large-scale optimization has become a significant yet challenging area in evolutionary computation. To solve this problem, this paper proposes a novel segment-based predominant learning swarm optimizer (SPLSO) swarm optimizer through letting several predominant particles guide the learning of a particle. First, a segment-based learning strategy is...

Large-scale optimization has become a significant yet challenging area in evolutionary computation. To solve this problem, this paper proposes a novel segment-based predominant learning swarm optimizer (SPLSO) swarm optimizer through letting several predominant particles guide the learning of a particle. First, a segment-based learning strategy is...

Detecting abnormal events in video surveillance is a challenging problem due to the large scale, stream fashion video data as well as the real-time constraint. In this paper, we present an online, adaptive, and real-time framework to address this problem. The spatial locations in a frame is partitioned into grids, in each grid the proposed Adaptive...

This paper investigates the problem of image segmentation using superpixels. We propose two approaches to enhance the discriminative ability of the superpixel's covariance descriptors. In the first one, we employ the Log-Euclidean distance as the metric on the covariance manifolds, and then use the RBF kernel to measure the similarities between cov...

This paper presents a novel framework to detect shot boundaries based on the One-Class Support Vector Machine (OCSVM). Instead of comparing the difference between pair-wise consecutive frames at a specific time, we measure the divergence between two OCSVM clas-sifiers, which are learnt from two contextual sets, i.e., immediate past set and immediat...

Sensor data stream mining methods have recently brought significant attention to smart homes research. Through the use of sliding windows on the streaming sensor data, activities can be recognized through the sensor events. However, it remains a challenge to attain real-time activity recognition from the online streaming sensor data. This paper pro...

High topographical heterogeneity in alpine environments can result in fine-scale thermal variations. The aim for this research is to quantify the impact of fine-scale topographical heterogeneity in alpine environments on microclimate, flowering phenology, and flowering patterns. The study was performed on two sites on the Rock and Pillar Range Sout...

We propose a novel, online adaptive one-class support vector machines algorithm for anomaly detection in crowd scenes. Integrating incremental and decremental one-class support vector machines with a sliding buffer offers an efficient and effective scheme, which not only updates the model in an online fashion with low computational cost, but also d...

Train localisation is important to railway safety. Using Wireless Sensor Networks (WSNs) in train localisation is a robust and cost effective way. A WSN-based train localisation system contains anchor nodes that are deployed along railway tracks and have known geographic coordinates. However, anchor nodes along the railway tracks are prone to hardw...

Limiting energy consumption is one of the primary aims for most real-world deployments of wireless sensor networks. Unfortunately, attempts to optimize energy efficiency are often in conflict with the demand for network reactiveness to transmit urgent messages. In this article, we propose SWIFTNET: a reactive data acquisition scheme. It is built on...

Service modelling has become an increasingly important area in today's telecommunications and information systems practice. We have adapted a Network Design course in order to teach service modelling to a mixed class of both the telecommunication engineering and information systems backgrounds. An integrated approach engaging mathematics teaching w...

Effective and efficient background subtraction is important to a number of computer vision tasks. In this paper, we introduce a new background model that integrates several new techniques to address key challenges for background modeling for moving objects detection in videos. The novel features of our proposed Self-Adaptive CodeBook (SACB) backgro...

Finding suitable routing paths for video streaming remains a challenging issue for multi-hop wireless networks, and previous studies rely on heuristics such as minimal hops or load-balancing. In this paper, we present an analytical approach that takes cross-layer factors into account and propose a new routing metric based on optimizing a queueing m...

Crowd scene analysis has caught significant attention both in academia and industry as it has a great number of potential applications. In this paper, we propose a novel spatial-temporal pyramid matching scheme for crowd scene analysis. Video segments are represented as concatenated histograms of all cells at all pyramid levels with corresponding w...

It is our great pleasure to introduce the proceedings of the Second Workshop on Machine Learning for Sensory Data Analysis (MLSDA'14), held on 2 December, 2014 in the sunny Gold Coast, QLD, Australia. Following the inaugural event successfully held in conjunction with AI'2013 in Dunedin, New Zealand, MLSDA'14 joins the 13-th Pacific Rim Internation...

Delay tolerant networks under wireless intermittent settings have gathered growing research interests in recent years. There remains, however, a lacking of performance modelling results for DTN protocols. In this paper, we propose to model the system-level performance of DTN protocols using the Erlang B queueing model, and profile the performance m...

Markov chain models have been a popular tool used for wind speed data modelling. This paper presents a novel approach of assessing similarity between Markov chain models, hence enabling cluster analysis of wind speed profiles based on Markov chains. We experiment with real-world wind speed data and construct weekly and monthly Markov chain models f...

A superpixel can be characterized as a vector in a color space or a covariance matrix on a manifold, by which two graph layers can be modeled on the common vertex sets. In this paper, we propose a novel approach for clustering such kind of multi-layer bipartite graphs. By Laplacian eigenmaps, each layer of the bipartite graph can be represented as...

We propose to use color covariance matrices of superpixels as a feature in addition to colors. A non-Euclidean distance metric is employed for the covariance matrix manifolds. We then introduce three ways of fusing the similarity matrices obtained from both feature spaces for affinity graph generation. Experiments carried out using a benchmark data...

Real-time train localization using wireless sensor networks (WSNs) offers huge benefits in terms of cost reduction and safety enhancement in railway environments. A challenging problem in WSN-based train localization is how to guarantee timely communication between the anchor sensors deployed along the track and the gateway deployed on the train wi...

While wireless sensor networks WSN are increasingly equipped to handle more complex functions, in-network processing still requires the battery-powered sensors to judiciously use their constrained energy so as to prolong the elective network life time. There are a few protocols using sensor clusters to coordinate the energy consumption in a WSN, bu...

Wireless Sensor Networks (WSNs) have found many practical applications in recent years. Apart from both the vast new opportunities and challenges raised by the availability of large amounts of sensory data, energy conservation remains a challenging research topic that demands intelligent solutions. Various data aggregation techniques have been prop...

It is our great pleasure to introduce the proceedings of the first workshop on Machine Learning for Sensory Data Analysis, held on 3 December, 2013 in Dunedin, New Zealand. This inaugural event is a response to the imminent research issues in machine learning and wireless sensor networking areas. There has been a growing trend in applying sensor te...

We propose a new video manifold learning method for event recognition and anomaly detection in crowd scenes. A novel feature descriptor is proposed to encode regional optical flow features of video frames, where quantization and binarization of the feature code are employed to improve the differentiation of crowd motion patterns. Based on the new f...

This paper presents a novel growing neural gas based background model (GNG-BM) for foreground detection in videos. We proposed a pixel-level background model, where the GNG algorithm is modified for clustering the input pixel data and a new algorithm for initial training is introduced. Also, a new method is introduced for foreground-background clas...

Software development effort estimation is important for quality management in the software development industry, yet its automation still remains a challenging issue. Applying machine learning algorithms alone often cannot achieve satisfactory results. This paper presents an integrated data mining framework that incorporates domain knowledge into a...

The Mixture of Gaussians (MoG) is a frequently used method for moving objects detection in a video, but its parameter setting is often tricky for dynamic scenes. Therefore, in this paper we propose an adaptive algorithm for the parameters learning by using working set of recent random samples. Furthermore, a novel Spatio-Temporal voting scheme is i...

Effective and efficient background subtraction is important to a number of computer vision tasks. We introduce several new techniques to address key challenges for background modeling using a Gaussian mixture model (GMM) for moving objects detection in a video acquired by a static camera. The novel features of our proposed model are that it automat...

In this paper, we propose SWIFTNET: a fast-reactive data acquisition scheme. SWIFTNET is built on the synergies between compressive sensing and prediction algorithms and limits the energy consumption in environmental monitoring and surveillance networks. We show how this approach dramati-cally reduces the amount of communication required to monitor...

Data reduction strategy is one of the schemes employed to extend network lifetime. In this paper we present an implementation of a light-weight forecasting algorithm for sensed data which saves packet transmission in the network. The proposed Naive algorithm achieves high energy savings with a limited computational overhead on a node. Simulation re...