Paper Group ANR 598
Positive-Unlabeled Classification under Class Prior Shift and Asymmetric Error. Anticipating epileptic seizures through the analysis of EEG synchronization as a data classification problem. Evolutionary optimisation of neural network models for fish collective behaviours in mixed groups of robots and zebrafish. Word2Vec and Doc2Vec in Unsupervised …
Positive-Unlabeled Classification under Class Prior Shift and Asymmetric Error
| Title | Positive-Unlabeled Classification under Class Prior Shift and Asymmetric Error |
| Authors | Nontawat Charoenphakdee, Masashi Sugiyama |
| Abstract | Bottlenecks of binary classification from positive and unlabeled data (PU classification) are the requirements that given unlabeled patterns are drawn from the test marginal distribution, and the penalty of the false positive error is identical to the false negative error. However, such requirements are often not fulfilled in practice. In this paper, we generalize PU classification to the class prior shift and asymmetric error scenarios. Based on the analysis of the Bayes optimal classifier, we show that given a test class prior, PU classification under class prior shift is equivalent to PU classification with asymmetric error. Then, we propose two different frameworks to handle these problems, namely, a risk minimization framework and density ratio estimation framework. Finally, we demonstrate the effectiveness of the proposed frameworks and compare both frameworks through experiments using benchmark datasets. |
| Tasks | |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.07011v3 |
| http://arxiv.org/pdf/1809.07011v3.pdf | |
| PWC | https://paperswithcode.com/paper/positive-unlabeled-classification-under-class |
| Repo | |
| Framework | |
Anticipating epileptic seizures through the analysis of EEG synchronization as a data classification problem
| Title | Anticipating epileptic seizures through the analysis of EEG synchronization as a data classification problem |
| Authors | Paolo Detti, Garazi Zabalo Manrique de Lara, Renato Bruni, Marco Pranzo, Francesco Sarnari |
| Abstract | Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting about 0.5–0.8% of the world population. Several studies investigated the relationship between seizures and brainwave synchronization patterns, pursuing the possibility of identifying interictal, preictal, ictal and postictal states. In this work, we introduce a graph-based model of the brain interactions developed to study synchronization patterns in the electroencephalogram (EEG) signals. The aim is to develop a patient-specific approach, also for a real-time use, for the prediction of epileptic seizures’ occurrences. Different synchronization measures of the EEG signals and easily computable functions able to capture in real-time the variations of EEG synchronization have been considered. Both standard and ad-hoc classification algorithms have been developed and used. Results on scalp EEG signals show that this simple and computationally viable processing is able to highlight the changes in the synchronization corresponding to the preictal state. |
| Tasks | EEG |
| Published | 2018-01-24 |
| URL | http://arxiv.org/abs/1801.07936v1 |
| http://arxiv.org/pdf/1801.07936v1.pdf | |
| PWC | https://paperswithcode.com/paper/anticipating-epileptic-seizures-through-the |
| Repo | |
| Framework | |
Evolutionary optimisation of neural network models for fish collective behaviours in mixed groups of robots and zebrafish
| Title | Evolutionary optimisation of neural network models for fish collective behaviours in mixed groups of robots and zebrafish |
| Authors | Leo Cazenille, Nicolas Bredeche, José Halloy |
| Abstract | Animal and robot social interactions are interesting both for ethological studies and robotics. On the one hand, the robots can be tools and models to analyse animal collective behaviours, on the other hand, the robots and their artificial intelligence are directly confronted and compared to the natural animal collective intelligence. The first step is to design robots and their behavioural controllers that are capable of socially interact with animals. Designing such behavioural bio-mimetic controllers remains an important challenge as they have to reproduce the animal behaviours and have to be calibrated on experimental data. Most animal collective behavioural models are designed by modellers based on experimental data. This process is long and costly because it is difficult to identify the relevant behavioural features that are then used as a priori knowledge in model building. Here, we want to model the fish individual and collective behaviours in order to develop robot controllers. We explore the use of optimised black-box models based on artificial neural networks (ANN) to model fish behaviours. While the ANN may not be biomimetic but rather bio-inspired, they can be used to link perception to motor responses. These models are designed to be implementable as robot controllers to form mixed-groups of fish and robots, using few a priori knowledge of the fish behaviours. We present a methodology with multilayer perceptron or echo state networks that are optimised through evolutionary algorithms to model accurately the fish individual and collective behaviours in a bounded rectangular arena. We assess the biomimetism of the generated models and compare them to the fish experimental behaviours. |
| Tasks | |
| Published | 2018-08-09 |
| URL | http://arxiv.org/abs/1808.03166v1 |
| http://arxiv.org/pdf/1808.03166v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-optimisation-of-neural-network |
| Repo | |
| Framework | |
Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries
| Title | Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries |
| Authors | Qufei Chen, Marina Sokolova |
| Abstract | In this study, we explored application of Word2Vec and Doc2Vec for sentiment analysis of clinical discharge summaries. We applied unsupervised learning since the data sets did not have sentiment annotations. Note that unsupervised learning is a more realistic scenario than supervised learning which requires an access to a training set of sentiment-annotated data. We aim to detect if there exists any underlying bias towards or against a certain disease. We used SentiWordNet to establish a gold sentiment standard for the data sets and evaluate performance of Word2Vec and Doc2Vec methods. We have shown that the Word2vec and Doc2Vec methods complement each other results in sentiment analysis of the data sets. |
| Tasks | Sentiment Analysis |
| Published | 2018-05-01 |
| URL | http://arxiv.org/abs/1805.00352v1 |
| http://arxiv.org/pdf/1805.00352v1.pdf | |
| PWC | https://paperswithcode.com/paper/word2vec-and-doc2vec-in-unsupervised |
| Repo | |
| Framework | |
Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control
| Title | Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control |
| Authors | Wenqing Li, Chunhui Zhao, Biao Huang |
| Abstract | For large-scale industrial processes under closed-loop control, process dynamics directly resulting from control action are typical characteristics and may show different behaviors between real faults and normal changes of operating conditions. However, conventional distributed monitoring approaches do not consider the closed-loop control mechanism and only explore static characteristics, which thus are incapable of distinguishing between real process faults and nominal changes of operating conditions, leading to unnecessary alarms. In this regard, this paper proposes a distributed monitoring method for closed-loop industrial processes by concurrently exploring static and dynamic characteristics. First, the large-scale closed-loop process is decomposed into several subsystems by developing a sparse slow feature analysis (SSFA) algorithm which capture changes of both static and dynamic information. Second, distributed models are developed to separately capture static and dynamic characteristics from the local and global aspects. Based on the distributed monitoring system, a two-level monitoring strategy is proposed to check different influences on process characteristics resulting from changes of the operating conditions and control action, and thus the two changes can be well distinguished from each other. Case studies are conducted based on both benchmark data and real industrial process data to illustrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.03343v1 |
| http://arxiv.org/pdf/1809.03343v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-dynamic-modeling-and-monitoring |
| Repo | |
| Framework | |
Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery
| Title | Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery |
| Authors | Gaurav N. Shetty, Konstantinos Slavakis, Abhishek Bose, Ukash Nakarmi, Gesualdo Scutari, Leslie Ying |
| Abstract | This paper puts forth a novel bi-linear modeling framework for data recovery via manifold-learning and sparse-approximation arguments and considers its application to dynamic magnetic-resonance imaging (dMRI). Each temporal-domain MR image is viewed as a point that lies onto or close to a smooth manifold, and landmark points are identified to describe the point cloud concisely. To facilitate computations, a dimensionality reduction module generates low-dimensional/compressed renditions of the landmark points. Recovery of the high-fidelity MRI data is realized by solving a non-convex minimization task for the linear decompression operator and those affine combinations of landmark points which locally approximate the latent manifold geometry. An algorithm with guaranteed convergence to stationary solutions of the non-convex minimization task is also provided. The aforementioned framework exploits the underlying spatio-temporal patterns and geometry of the acquired data without any prior training on external data or information. Extensive numerical results on simulated as well as real cardiac-cine and perfusion MRI data illustrate noteworthy improvements of the advocated machine-learning framework over state-of-the-art reconstruction techniques. |
| Tasks | Dimensionality Reduction |
| Published | 2018-12-27 |
| URL | https://arxiv.org/abs/1812.10617v2 |
| https://arxiv.org/pdf/1812.10617v2.pdf | |
| PWC | https://paperswithcode.com/paper/bi-linear-modeling-of-data-manifolds-for |
| Repo | |
| Framework | |
Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking
| Title | Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking |
| Authors | Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes |
| Abstract | Current multi-person localisation and tracking systems have an over reliance on the use of appearance models for target re-identification and almost no approaches employ a complete deep learning solution for both objectives. We present a novel, complete deep learning framework for multi-person localisation and tracking. In this context we first introduce a light weight sequential Generative Adversarial Network architecture for person localisation, which overcomes issues related to occlusions and noisy detections, typically found in a multi person environment. In the proposed tracking framework we build upon recent advances in pedestrian trajectory prediction approaches and propose a novel data association scheme based on predicted trajectories. This removes the need for computationally expensive person re-identification systems based on appearance features and generates human like trajectories with minimal fragmentation. The proposed method is evaluated on multiple public benchmarks including both static and dynamic cameras and is capable of generating outstanding performance, especially among other recently proposed deep neural network based approaches. |
| Tasks | Person Re-Identification, Trajectory Prediction |
| Published | 2018-03-09 |
| URL | http://arxiv.org/abs/1803.03347v1 |
| http://arxiv.org/pdf/1803.03347v1.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-by-prediction-a-deep-generative |
| Repo | |
| Framework | |
Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification
| Title | Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification |
| Authors | Minho Ha, Younghoon Byeon, Youngjoo Lee, Sunggu Lee |
| Abstract | Deep convolutional neural networks have proven to be well suited for image classification applications. However, if there is distortion in the image, the classification accuracy can be significantly degraded, even with state-of-the-art neural networks. The accuracy cannot be significantly improved by simply training with distorted images. Instead, this paper proposes a multiple neural network topology referred to as a selective deep convolutional neural network. By modifying existing state-of-the-art neural networks in the proposed manner, it is shown that a similar level of classification accuracy can be achieved, but at a significantly lower cost. The cost reduction is obtained primarily through the use of fewer weight parameters. Using fewer weights reduces the number of multiply-accumulate operations and also reduces the energy required for data accesses. Finally, it is shown that the effectiveness of the proposed selective deep convolutional neural network can be further improved by combining it with previously proposed network cost reduction methods. |
| Tasks | Image Classification |
| Published | 2018-07-04 |
| URL | http://arxiv.org/abs/1807.01418v2 |
| http://arxiv.org/pdf/1807.01418v2.pdf | |
| PWC | https://paperswithcode.com/paper/selective-deep-convolutional-neural-network |
| Repo | |
| Framework | |
Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
| Title | Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras |
| Authors | Pedro Miraldo, Francisco Eiras, Srikumar Ramalingam |
| Abstract | Vanishing points and vanishing lines are classical geometrical concepts in perspective cameras that have a lineage dating back to 3 centuries. A vanishing point is a point on the image plane where parallel lines in 3D space appear to converge, whereas a vanishing line passes through 2 or more vanishing points. While such concepts are simple and intuitive in perspective cameras, their counterparts in catadioptric cameras (obtained using mirrors and lenses) are more involved. For example, lines in the 3D space map to higher degree curves in catadioptric cameras. The projection of a set of 3D parallel lines converges on a single point in perspective images, whereas they converge to more than one point in catadioptric cameras. To the best of our knowledge, we are not aware of any systematic development of analytical models for vanishing points and vanishing curves in different types of catadioptric cameras. In this paper, we derive parametric equations for vanishing points and vanishing curves using the calibration parameters, mirror shape coefficients, and direction vectors of parallel lines in 3D space. We show compelling experimental results on vanishing point estimation and absolute pose estimation for a wide range of catadioptric cameras in both simulations and real experiments. |
| Tasks | Calibration, Pose Estimation |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09460v1 |
| http://arxiv.org/pdf/1804.09460v1.pdf | |
| PWC | https://paperswithcode.com/paper/analytical-modeling-of-vanishing-points-and |
| Repo | |
| Framework | |
Left ventricle segmentation By modelling uncertainty in prediction of deep convolutional neural networks and adaptive thresholding inference
| Title | Left ventricle segmentation By modelling uncertainty in prediction of deep convolutional neural networks and adaptive thresholding inference |
| Authors | Alireza Norouzi, Ali Emami, S. M. Reza Soroushmehr, Nader Karimi, Shadrokh Samavi, Kayvan Najarian |
| Abstract | Deep neural networks have shown great achievements in solving complex problems. However, there are fundamental problems that limit their real world applications. Lack of measurable criteria for estimating uncertainty in the network outputs is one of these problems. In this paper, we address this limitation by introducing deformation to the network input and measuring the level of stability in the network’s output. We calculate simple random transformations to estimate the prediction uncertainty of deep convolutional neural networks. For a real use-case, we apply this method to left ventricle segmentation in MRI cardiac images. We also propose an adaptive thresholding method to consider the deep neural network uncertainty. Experimental results demonstrate state-of-the-art performance and highlight the capabilities of simple methods in conjunction with deep neural networks. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1803.00406v1 |
| http://arxiv.org/pdf/1803.00406v1.pdf | |
| PWC | https://paperswithcode.com/paper/left-ventricle-segmentation-by-modelling |
| Repo | |
| Framework | |
A Divide-and-Conquer Approach to Geometric Sampling for Active Learning
| Title | A Divide-and-Conquer Approach to Geometric Sampling for Active Learning |
| Authors | Xiaofeng Cao |
| Abstract | Active learning (AL) repeatedly trains the classifier with the minimum labeling budget to improve the current classification model. The training process is usually supervised by an uncertainty evaluation strategy. However, the uncertainty evaluation always suffers from performance degeneration when the initial labeled set has insufficient labels. To completely eliminate the dependence on the uncertainty evaluation sampling in AL, this paper proposes a divide-and-conquer idea that directly transfers the AL sampling as the geometric sampling over the clusters. By dividing the points of the clusters into cluster boundary and core points, we theoretically discuss their margin distance and {hypothesis relationship}. With the advantages of cluster boundary points in the above two properties, we propose a Geometric Active Learning (GAL) algorithm by knight’s tour. Experimental studies of the two reported experimental tasks including cluster boundary detection and AL classification show that the proposed GAL method significantly outperforms the state-of-the-art baselines. |
| Tasks | Active Learning, Boundary Detection |
| Published | 2018-05-31 |
| URL | https://arxiv.org/abs/1805.12321v2 |
| https://arxiv.org/pdf/1805.12321v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-active-learning-via-enclosing-ball |
| Repo | |
| Framework | |
Deep Motion Boundary Detection
| Title | Deep Motion Boundary Detection |
| Authors | Xiaoqing Yin, Xiyang Dai, Xinchao Wang, Maojun Zhang, Dacheng Tao, Larry Davis |
| Abstract | Motion boundary detection is a crucial yet challenging problem. Prior methods focus on analyzing the gradients and distributions of optical flow fields, or use hand-crafted features for motion boundary learning. In this paper, we propose the first dedicated end-to-end deep learning approach for motion boundary detection, which we term as MoBoNet. We introduce a refinement network structure which takes source input images, initial forward and backward optical flows as well as corresponding warping errors as inputs and produces high-resolution motion boundaries. Furthermore, we show that the obtained motion boundaries, through a fusion sub-network we design, can in turn guide the optical flows for removing the artifacts. The proposed MoBoNet is generic and works with any optical flows. Our motion boundary detection and the refined optical flow estimation achieve results superior to the state of the art. |
| Tasks | Boundary Detection, Optical Flow Estimation |
| Published | 2018-04-13 |
| URL | http://arxiv.org/abs/1804.04785v1 |
| http://arxiv.org/pdf/1804.04785v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-motion-boundary-detection |
| Repo | |
| Framework | |
Multi-Antenna Channel Interpolation via Tucker Decomposed Extreme Learning Machine
| Title | Multi-Antenna Channel Interpolation via Tucker Decomposed Extreme Learning Machine |
| Authors | Han Zhang, Bo Ai, Wenjun Xu, Li Xu, Shuguang Cui |
| Abstract | Channel interpolation is an essential technique for providing high-accuracy estimation of the channel state information (CSI) for wireless systems design where the frequency-space structural correlations of multi-antenna channel are typically hidden in matrix or tensor forms. In this letter, a modified extreme learning machine (ELM) that can process tensorial data, or ELM model with tensorial inputs (TELM), is proposed to handle the channel interpolation task. The TELM inherits many good properties from ELMs. Based on the TELM, the Tucker decomposed extreme learning machine (TDELM) is proposed for further improving the performance. Furthermore, we establish a theoretical argument to measure the interpolation capability of the proposed learning machines. Experimental results verify that our proposed learning machines can achieve comparable mean squared error (MSE) performance against the traditional ELMs but with 15% shorter running time, and outperform the other methods for a 20% margin measured in MSE for channel interpolation. |
| Tasks | |
| Published | 2018-12-26 |
| URL | https://arxiv.org/abs/1812.10506v2 |
| https://arxiv.org/pdf/1812.10506v2.pdf | |
| PWC | https://paperswithcode.com/paper/mimo-channel-interpolation-via-tucker |
| Repo | |
| Framework | |
Neural Comic Style Transfer: Case Study
| Title | Neural Comic Style Transfer: Case Study |
| Authors | Maciej Pęśko, Tomasz Trzciński |
| Abstract | The work by Gatys et al. [1] recently showed a neural style algorithm that can produce an image in the style of another image. Some further works introduced various improvements regarding generalization, quality and efficiency, but each of them was mostly focused on styles such as paintings, abstract images or photo-realistic style. In this paper, we present a comparison of how state-of-the-art style transfer methods cope with transferring various comic styles on different images. We select different combinations of Adaptive Instance Normalization [11] and Universal Style Transfer [16] models and confront them to find their advantages and disadvantages in terms of qualitative and quantitative analysis. Finally, we present the results of a survey conducted on over 100 people that aims at validating the evaluation results in a real-life application of comic style transfer. |
| Tasks | Style Transfer |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01726v2 |
| http://arxiv.org/pdf/1809.01726v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-comic-style-transfer-case-study |
| Repo | |
| Framework | |
A novel topology design approach using an integrated deep learning network architecture
| Title | A novel topology design approach using an integrated deep learning network architecture |
| Authors | Sharad Rawat, M. H. Herman Shen |
| Abstract | Topology design optimization offers tremendous opportunity in design and manufacturing freedoms by designing and producing a part from the ground-up without a meaningful initial design as required by conventional shape design optimization approaches. Ideally, with adequate problem statements, to formulate and solve the topology design problem using a standard topology optimization process, such as SIMP (Simplified Isotropic Material with Penalization) is possible. In reality, an estimated over thousands of design iterations is often required for just a few design variables, the conventional optimization approach is in general impractical or computationally unachievable for real world applications significantly diluting the development of the topology optimization technology. There is, therefore, a need for a different approach that will be able to optimize the initial design topology effectively and rapidly. Therefore, this work presents a new topology design procedure to generate optimal structures using an integrated Generative Adversarial Networks (GANs) and convolutional neural network architecture. |
| Tasks | |
| Published | 2018-08-03 |
| URL | http://arxiv.org/abs/1808.02334v2 |
| http://arxiv.org/pdf/1808.02334v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-topology-design-approach-using-an |
| Repo | |
| Framework | |
