Integrated generalized zero-shot learning for fine-grained classification
- Authors: Shermin, Tasfia , Teng, Shyh , Sohel, Ferdous , Murshed, Manzur , Lu, Guojun
- Date: 2022
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 122, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories of fine-grained GZSL methods. EL or FS using global features cannot discriminate fine details in the absence of local features. On the other hand, EL or FS methods exploiting local features either neglect direct attribute guidance or global information. Consequently, neither method performs well. In this paper, we propose to explore global and direct attribute-supervised local visual features for both EL and FS categories in an integrated manner for fine-grained GZSL. The proposed integrated network has an EL sub-network and a FS sub-network. Consequently, the proposed integrated network can be tested in two ways. We propose a novel two-step dense attention mechanism to discover attribute-guided local visual features. We introduce new mutual learning between the sub-networks to exploit mutually beneficial information for optimization. Moreover, we propose to compute source-target class similarity based on mutual information and transfer-learn the target classes to reduce bias towards the source domain during testing. We demonstrate that our proposed method outperforms contemporary methods on benchmark datasets. © 2021 Elsevier Ltd
Detecting outlier patterns with query-based artificially generated searching conditions
- Authors: Yu, Shuo , Xia, Feng , Sun, Yuchen , Tang, Tao , Yan, Xiaoran , Lee, Ivan
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 8, no. 1 (2021), p. 134-147
- Full Text:
- Reviewed:
- Description: In the age of social computing, finding interesting network patterns or motifs is significant and critical for various areas, such as decision intelligence, intrusion detection, medical diagnosis, social network analysis, fake news identification, and national security. However, subgraph matching remains a computationally challenging problem, let alone identifying special motifs among them. This is especially the case in large heterogeneous real-world networks. In this article, we propose an efficient solution for discovering and ranking human behavior patterns based on network motifs by exploring a user's query in an intelligent way. Our method takes advantage of the semantics provided by a user's query, which in turn provides the mathematical constraint that is crucial for faster detection. We propose an approach to generate query conditions based on the user's query. In particular, we use meta paths between the nodes to define target patterns as well as their similarities, leading to efficient motif discovery and ranking at the same time. The proposed method is examined in a real-world academic network using different similarity measures between the nodes. The experiment result demonstrates that our method can identify interesting motifs and is robust to the choice of similarity measures. © 2014 IEEE.
Efficient deterministic algorithm for huge-sized noisy sensor localization problems via canonical duality theory
- Authors: Latorre, Vittorio , Gao, David
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Cybernetics Vol. 51, no. 10 (2021), p. 5069-5081
- Full Text: false
- Reviewed:
- Description: This paper presents a new deterministic method and a polynomial-time algorithm for solving general huge-sized sensor network localization problems. The problem is first formulated as a nonconvex minimization, which was considered as an NP-hard based on conventional theories. However, by the canonical duality theory, this challenging problem can be equivalently converted into a convex dual problem. By introducing a new optimality measure, a powerful canonical primal-dual interior (CPDI) point algorithm is developed which can solve efficiently huge-sized problems with hundreds of thousands of sensors. The new method is compared with the popular methods in the literature. Results show that the CPDI algorithm is not only faster than the benchmarks but also much more accurate on networks affected by noise on the distances. © 2013 IEEE.
How to optimize an academic team when the outlier member is leaving?
- Authors: Yu, Shuo , Liu, Jiaying , Wei, Haoran , Xia, Feng , Tong, Hanghang
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Intelligent Systems Vol. 36, no. 3 (May-Jun 2021), p. 23-30
- Full Text:
- Reviewed:
- Description: An academic team is a highly cohesive collaboration group of scholars, which has been recognized as an effective way to improve scientific output in terms of both quality and quantity. However, the high staff turnover brings about a series of problems that may have negative influences on team performance. To address this challenge, we first detect the tendency of the member who may potentially leave. Here, the outlierness is defined with respect to familiarity, which is quantified by using collaboration intensity. It is assumed that if a team member has a higher familiarity with scholars outside the team, then this member might probably leave the team. To minimize the influence caused by the leaving of such an outlier member, we propose an optimization solution to find a proper candidate who can replace the outlier member. Based on random walk with graph kernel, our solution involves familiarity matching, skill matching, as well as structure matching. The proposed approach proves to be effective and outperforms existing methods when applied to computer science academic teams.
Mobile robotic sensors for environmental monitoring using gaussian markov random field
- Authors: Nguyen, Linh , Kodagoda, Sarath , Ranasinghe, Ravindra , Dissanayake, Gamini
- Date: 2021
- Type: Text , Journal article
- Relation: Robotica Vol. 39, no. 5 (2021), p. 862-884
- Full Text:
- Reviewed:
- Description: This paper addresses the issue of monitoring spatial environmental phenomena of interest utilizing information collected by a network of mobile, wireless, and noisy sensors that can take discrete measurements as they navigate through the environment. It is proposed to employ Gaussian Markov random field (GMRF) represented on an irregular discrete lattice by using the stochastic partial differential equations method to model the physical spatial field. It then derives a GMRF-based approach to effectively predict the field at unmeasured locations, given available observations, in both centralized and distributed manners. Furthermore, a novel but efficient optimality criterion is then proposed to design centralized and distributed adaptive sampling strategies for the mobile robotic sensors to find the most informative sampling paths in taking future measurements. By taking advantage of conditional independence property in the GMRF, the adaptive sampling optimization problem is proven to be resolved in a deterministic time. The effectiveness of the proposed approach is compared and demonstrated using pre-published data sets with appealing results. Copyright © The Author(s), 2020. Published by Cambridge University Press.
Siamese network for object tracking with multi-granularity appearance representations
- Authors: Zhang, Zhuoyi , Zhang, Yifeng , Cheng, Xu , Lu, Guojun
- Date: 2021
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 118, no. (2021), p.
- Full Text: false
- Reviewed:
- Description: A reliable tracker has the ability to adapt to change of objects over time, and is robust and accurate. We build such a tracker by extracting semantic features using robust Siamese networks and multi-granularity color features. It incorporates a semantic model that can capture high quality semantic features and an appearance model that can describe object at pixel, local and global levels effectively. Furthermore, we propose a novel selective traverse algorithm to allocate weights to semantic models and appearance models dynamically for better tracking performance. During tracking, our tracker updates appearance representations for objects based on the recent tracking results. The proposed tracker operates at speeds that exceed the real-time requirement, and outperforms nearly all other state-of-the-art trackers on OTB-2013/2015 and VOT-2016/2017 benchmarks. © 2021 Elsevier Ltd
Depth sequence coding with hierarchical partitioning and spatial-domain quantization
- Authors: Shahriyar, Shampa , Murshed, Manzur , Ali, Mortuza , Paul, Manoranjan
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Circuits and Systems for Video Technology Vol. 30, no. 3 (2020), p. 835-849
- Full Text:
- Reviewed:
- Description: Depth coding in 3D-HEVC deforms object shapes due to block-level edge-approximation and lacks efficient techniques to exploit the statistical redundancy, due to the frame-level clustering tendency in depth data, for higher coding gain at near-lossless quality. This paper presents a standalone mono-view depth sequence coder, which preserves edges implicitly by limiting quantization to the spatial-domain and exploits the frame-level clustering tendency efficiently with a novel binary tree-based decomposition (BTBD) technique. The BTBD can exploit the statistical redundancy in frame-level syntax, motion components, and residuals efficiently with fewer block-level prediction/coding modes and simpler context modeling for context-adaptive arithmetic coding. Compared with the depth coder in 3D-HEVC, the proposed one has achieved significantly lower bitrate at lossless to near-lossless quality range for mono-view coding and rendered superior quality synthetic views from the depth maps, compressed at the same bitrate, and the corresponding texture frames. © 1991-2012 IEEE.
MODEL : motif-based deep feature learning for link prediction
- Authors: Wang, Lei , Ren, Jing , Xu, Bo , Li, Jianxin , Luo, Wei , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 7, no. 2 (2020), p. 503-516
- Full Text:
- Reviewed:
- Description: Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%). © 2014 IEEE.
A computational model to investigate the influence of electrode lengths on the single probe bipolar radiofrequency ablation of the liver
- Authors: Cheong, Jason , Yap, Shelley , Ooi, Ean Tat , Ooi, Ean Hin
- Date: 2019
- Type: Text , Journal article
- Relation: Computer Methods and Programs in Biomedicine Vol. 176, no. (2019), p. 17-32
- Full Text: false
- Reviewed:
- Description: Background and objectives: Recently, there have been calls for RFA to be implemented in the bipolar mode for cancer treatment due to the benefits it offers over the monopolar mode. These include the ability to prevent skin burns at the grounding pad and to avoid tumour track seeding. The usage of bipolar RFA in clinical practice remains uncommon however, as not many research studies have been carried out on bipolar RFA. As such, there is still uncertainty in understanding the effects of the different RF probe configurations on the treatment outcome of RFA. This paper demonstrates that the electrode lengths have a strong influence on the mechanics of bipolar RFA. The information obtained here may lead to further optimization of the system for subsequent uses in the hospitals. Methods: A 2D model in the axisymmetric coordinates was developed to simulate the electro-thermophysiological responses of the tissue during a single probe bipolar RFA. Two different probe configurations were considered, namely the configuration where the active electrode is longer than the ground and the configuration where the ground electrode is longer than the active. The mathematical model was first verified with an existing experimental study found in the literature. Results: Results from the simulations showed that heating is confined only to the region around the shorter electrode, regardless of whether the shorter electrode is the active or the ground. Consequently, thermal coagulation also occurs in the region surrounding the shorter electrode. This opened up the possibility for a better customized treatment through the development of RF probes with adjustable electrode lengths. Conclusions: The electrode length was found to play a significant role on the outcome of single probe bipolar RFA. In particular, the length of the shorter electrode becomes the limiting factor that influences the mechanics of single probe bipolar RFA. Results from this study can be used to further develop and optimize bipolar RFA as an effective and reliable cancer treatment technique. (C) 2019 Elsevier B.V. All rights reserved.
The evolution of Turing Award Collaboration Network : bibliometric-level and network-level metrics
- Authors: Kong, Xiangjie , Shi, Yajie , Wang, Wei , Ma, Kai , Wan, Liangtian , Xia, Feng
- Date: 2019
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 6, no. 6 (2019), p. 1318-1328
- Full Text:
- Reviewed:
- Description: The year of 2017 for the 50th anniversary of the Turing Award, which represents the top-level award in the computer science field, is a milestone. We study the long-term evolution of the Turing Award Collaboration Network, and it can be considered as a microcosm of the computer science field from 1974 to 2016. First, scholars tend to publish articles by themselves at the early stages, and they began to focus on tight collaboration since the late 1980s. Second, compared with the same scale random network, although the Turing Award Collaboration Network has small-world properties, it is not a scale-free network. The reason may be that the number of collaborators per scholar is limited. It is impossible for scholars to connect to others freely (preferential attachment) as the scale-free network. Third, to measure how far a scholar is from the Turing Award, we propose a metric called the Turing Number (TN) and find that the TN decreases gradually over time. Meanwhile, we discover the phenomenon that scholars prefer to gather into groups to do research with the development of computer science. This article presents a new way to explore the evolution of academic collaboration network in the field of computer science by building and analyzing the Turing Award Collaboration Network for decades. © 2014 IEEE.
Clustering in large data sets with the limited memory bundle method
- Authors: Karmitsa, Napsu , Bagirov, Adil , Taheri, Sona
- Date: 2018
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 83, no. (2018), p. 245-259
- Relation: http://purl.org/au-research/grants/arc/DP140103213
- Full Text: false
- Reviewed:
- Description: The aim of this paper is to design an algorithm based on nonsmooth optimization techniques to solve the minimum sum-of-squares clustering problems in very large data sets. First, the clustering problem is formulated as a nonsmooth optimization problem. Then the limited memory bundle method [Haarala et al., 2007] is modified and combined with an incremental approach to design a new clustering algorithm. The algorithm is evaluated using real world data sets with both the large number of attributes and the large number of data points. It is also compared with some other optimization based clustering algorithms. The numerical results demonstrate the efficiency of the proposed algorithm for clustering in very large data sets.
Enhancing image registration performance by incorporating distribution and spatial distance of local descriptors
- Authors: Lv, Guohua , Teng, Shyh , Lu, Guojun
- Date: 2018
- Type: Text , Journal article
- Relation: Pattern Recognition Letters Vol. 103, no. (2018), p. 46-52
- Full Text: false
- Reviewed:
- Description: A data dependency similarity measure called mp-dissimilarity has been recently proposed. Unlike ℓp-norm distance which is widely used in calculating the similarity between vectors, mp-dissimilarity takes into account the relative positions of the two vectors with respect to the rest of the data. This paper investigates the potential of mp-dissimilarity in matching local image descriptors. Moreover, three new matching strategies are proposed by considering both ℓp-norm distance and mp-dissimilarity. Our proposed matching strategies are extensively evaluated against ℓp-norm distance and mp-dissimilarity on a few benchmark datasets. Experimental results show that mp-dissimilarity is a promising alternative to ℓp-norm distance in matching local descriptors. The proposed matching strategies outperform both ℓp-norm distance and mp-dissimilarity in matching accuracy. One of our proposed matching strategies is comparable to ℓp-norm distance in terms of recall vs 1-precision. © 2018 Elsevier B.V.
Grouping points by shared subspaces for effective subspace clustering
- Authors: Zhu, Ye , Ting, Kaiming , Carman, Mark
- Date: 2018
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 83, no. (2018), p. 230-244
- Full Text: false
- Reviewed:
- Description: Clusters may exist in different subspaces of a multidimensional dataset. Traditional full-space clustering algorithms have difficulty in identifying these clusters. Various subspace clustering algorithms have used different subspace search strategies. They require clustering to assess whether cluster(s) exist in a subspace. In addition, all of them perform clustering by measuring similarity between points in the given feature space. As a result, the subspace selection and clustering processes are tightly coupled. In this paper, we propose a new subspace clustering framework named CSSub (Clustering by Shared Subspaces). It enables neighbouring core points to be clustered based on the number of subspaces they share. It explicitly splits candidate subspace selection and clustering into two separate processes, enabling different types of cluster definitions to be employed easily. Through extensive experiments on synthetic and real-world datasets, we demonstrate that CSSub discovers non-redundant subspace clusters with arbitrary shapes in noisy data; and it significantly outperforms existing state-of-the-art subspace clustering algorithms.
A comparison of bidding strategies for online auctions using fuzzy reasoning and negotiation decision functions
- Authors: Kaur, Preetinder , Goyal, Madhu , Lu, Jie
- Date: 2017
- Type: Text , Journal article
- Relation: IEEE Transactions on Fuzzy Systems Vol. 25, no. 2 (2017), p. 425-438
- Full Text:
- Reviewed:
- Description: Bidders often feel challenged when looking for the best bidding strategies to excel in the competitive environment of multiple and simultaneous online auctions for same or similar items. Bidders face complicated issues for deciding which auction to participate in, whether to bid early or late, and how much to bid. In this paper, we present the design of bidding strategies, which aim to forecast the bid amounts for buyers at a particular moment in time based on their bidding behavior and their valuation of an auctioned item. The agent develops a comprehensive methodology for final price estimation, which designs bidding strategies to address buyers' different bidding behaviors using two approaches: Mamdani method with regression analysis and negotiation decision functions. The experimental results show that the agents who follow fuzzy reasoning with a regression approach outperform other existing agents in most settings in terms of their success rate and expected utility.
A count data model for heart rate variability forecasting and premature ventricular contraction detection
- Authors: Allami, Ragheed , Stranieri, Andrew , Balasubramanian, Venki , Jelinek, Herbert
- Date: 2017
- Type: Text , Journal article
- Relation: Signal Image and Video Processing Vol. 11, no. 8 (2017), p. 1427-1435
- Full Text:
- Reviewed:
- Description: Heart rate variability (HRV) measures including the standard deviation of inter-beat variations (SDNN) require at least 5 min of ECG recordings to accurately measure HRV. In this paper, we predict, using counts data derived from a 3-min ECG recording, the 5-min SDNN and also detect premature ventricular contraction (PVC) beats with a high degree of accuracy. The approach uses counts data combined with a Poisson-generated function that requires minimal computational resources and is well suited to remote patient monitoring with wearable sensors that have limited power, storage and processing capacity. The ease of use and accuracy of the algorithm provide opportunity for accurate assessment of HRV and reduce the time taken to review patients in real time. The PVC beat detection is implemented using the same count data model together with knowledge-based rules derived from clinical knowledge.
Density-ratio based clustering for discovering clusters with varying densities
- Authors: Zhu, Ye , Ting, Kaiming , Carman, Mark
- Date: 2016
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 60, no. (2016), p. 983-997
- Full Text: false
- Reviewed:
- Description: Density-based clustering algorithms are able to identify clusters of arbitrary shapes and sizes in a dataset which contains noise. It is well-known that most of these algorithms, which use a global density threshold, have difficulty identifying all clusters in a dataset having clusters of greatly varying densities. This paper identifies and analyses the condition under which density-based clustering algorithms fail in this scenario. It proposes a density-ratio based method to overcome this weakness, and reveals that it can be implemented in two approaches. One approach is to modify a density-based clustering algorithm to do density-ratio based clustering by using its density estimator to compute density-ratio. The other approach involves rescaling the given dataset only. An existing density-based clustering algorithm, which is applied to the rescaled dataset, can find all clusters with varying densities that would otherwise impossible had the same algorithm been applied to the unscaled dataset. We provide an empirical evaluation using DBSCAN, OPTICS and SNN to show the effectiveness of these two approaches. © 2016 Elsevier Ltd
Enhancing SIFT-based image registration performance by building and selecting highly discriminating descriptors
- Authors: Lv, Guohua , Teng, Shyh , Lu, Guojun
- Date: 2016
- Type: Text , Journal article
- Relation: Pattern Recognition Letters Vol. 84, no. (2016), p. 156-162
- Full Text: false
- Reviewed:
- Description: In this paper we will investigate the gradient utilization in building SIFT (Scale Invariant Feature Transform)-like descriptors for image registration. There are generally two types of gradient information, i.e. gradient magnitude and gradient occurrence, which can be used for building SIFT-like descriptors. We will provide a theoretical analysis on the effectiveness of each of the two types of gradient information when used individually. Based on our analysis, we will propose a novel technique which systematically uses both types of gradient information together for image registration. Moreover, we will propose a strategy to select keypoint matches with a higher discrimination. The proposed technique can be used for both mono-modal and multi-modal image registration. Our experimental results show that the proposed technique improves registration accuracy over existing SIFT-like descriptors. © 2016 Elsevier B.V.
Nonsmooth DC programming approach to the minimum sum-of-squares clustering problems
- Authors: Bagirov, Adil , Taheri, Sona , Ugon, Julien
- Date: 2016
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 53, no. (2016), p. 12-24
- Relation: http://purl.org/au-research/grants/arc/DP140103213
- Full Text: false
- Reviewed:
- Description: This paper introduces an algorithm for solving the minimum sum-of-squares clustering problems using their difference of convex representations. A non-smooth non-convex optimization formulation of the clustering problem is used to design the algorithm. Characterizations of critical points, stationary points in the sense of generalized gradients and inf-stationary points of the clustering problem are given. The proposed algorithm is tested and compared with other clustering algorithms using large real world data sets. © 2015 Elsevier Ltd. All rights reserved.
Effective and efficient contour-based corner detectors
- Authors: Teng, Shyh , Najmus Sadat, Rafi , Lu, Guojun
- Date: 2015
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 48, no. 7 (2015), p. 2185-2197
- Full Text: false
- Reviewed:
- Description: Corner detection is an essential operation in many computer vision applications. Among the contour-based corner detectors in the literature, the Chord-to-Point Distance Accumulation (CPDA) detector is reported to have one of the highest repeatability in detecting robust corners and the lowest localization error. However, based on our analysis, we found that the CPDA detector often fails to accurately detect the true corners when a curve has multiple corners but the sharpness of one or a few of them is much more prominent than the rest. This detector also might not perform well when the corners are closely located. Furthermore, the CPDA detector is also computationally very expensive. To overcome these weaknesses, we propose two effective and efficient corner detectors using simple triangular theory and distance calculation. Our experimental results show that our proposed detectors outperform CPDA and nine other existing corner detectors in terms of repeatability. Our proposed detectors also have a relatively low or comparable localization error and are computationally more efficient. © 2015 Elsevier Ltd.
LiNearN : A new approach to nearest neighbour density estimator
- Authors: Wells, Jonathan , Ting, Kaiming , Washio, Takashi
- Date: 2014
- Type: Text , Journal article
- Relation: Pattern Recognition Vol. 47, no. 8 (2014), p. 2702-2720
- Full Text: false
- Reviewed:
- Description: Despite their wide spread use, nearest neighbour density estimators have two fundamental limitations: O(n2) time complexity and O(n) space complexity. Both limitations constrain nearest neighbour density estimators to small data sets only. Recent progress using indexing schemes has improved to near linear time complexity only.We propose a new approach, called LiNearN for Linear time Nearest Neighbour algorithm, that yields the first nearest neighbour density estimator having O(n) time complexity and constant space complexity, as far as we know. This is achieved without using any indexing scheme because LiNearN uses a subsampling approach for which the subsample values are significantly less than the data size. Like existing density estimators, our asymptotic analysis reveals that the new density estimator has a parameter to trade off between bias and variance. We show that algorithms based on the new nearest neighbour density estimator can easily scale up to data sets with millions of instances in anomaly detection and clustering tasks. Highlights•Reject the premise that a NN algorithm must find the NN for every instance.•The first NN density estimator that has O(n) time complexity and O(1) space complexity.•These complexities are achieved without using any indexing scheme.•Our asymptotic analysis reveals that it trades off between bias and variance.•Easily scales up to large data sets in anomaly detection and clustering tasks.