Renato Cordeiro de Amorim
Renato Cordeiro de Amorim
Institution: School of Computer Science and Electronic Engineering
Email: r.amorim@essex.ac.uk
DBSCAN is arguably the most popular density-based clustering algorithm, and it is capable of recovering non-spherical clusters. One of its main weaknesses is that it treats all features equally. In this paper, we propose a density-based clustering algorithm capable of calculating feature weights rep...
More
DBSCAN is arguably the most popular density-based clustering algorithm, and it is capable of recovering non-spherical clusters. One of its main weaknesses is that it treats all features equally. In this paper, we propose a density-based clustering algorithm capable of calculating feature weights representing the degree of relevance of each feature, which takes the density structure of the data into account. First, we improve DBSCAN and introduce a new algorithm called DBSCANR. DBSCANR reduces the number of parameters of DBSCAN to one. Then, a new step is introduced to the clustering process of DBSCANR to iteratively update feature weights based on the current partition of data. The feature weights produced by the weighted version of the new clustering algorithm, W-DBSCANR, measure the relevance of variables in a clustering and can be used in feature selection in data mining applications where large and complex real-world data are often involved. Experimental results on both artificial and real-world data have shown that the new algorithms outperformed various DBSCAN type algorithms in recovering clusters in data.
Less
Posted 1 year ago
Rui Zhu,
Rui Zhu
Institution: a Faculty of Actuarial Science and Insurance, Bayes Business School, City
Email: info@rnfinity.com
Fei Zhou,
Fei Zhou
Institution: College of Information Engineering
Email: info@rnfinity.com
Wenming Yang
Wenming Yang
Institution: Department of Electronic Engineering, Graduate School at Shenzhen
Email: info@rnfinity.com
Image quality assessment is usually achieved by pooling local quality scores. However, commonly used pooling strategies, based on simple sample statistics, are not always sensitive to distortions. In this short communication, we propose a novel perspective of pooling: reliable pooling through statis...
More
Image quality assessment is usually achieved by pooling local quality scores. However, commonly used pooling strategies, based on simple sample statistics, are not always sensitive to distortions. In this short communication, we propose a novel perspective of pooling: reliable pooling through statistical hypothesis testing, which enables effective detection of subtle changes of population parameters when the underlying distribution of local quality scores is affected by distortions. To illustrate the significance of this novel perspective, we design a new pooling strategy utilising simple one-sided one-sample t -test. The experiments on benchmark databases show the reliability of hypothesis testing-based pooling, compared with state-of-the-art pooling strategies.
Less
Posted 1 year ago
Jinming Duan,
Jinming Duan
Institution: School of Computer Science
Email: j.duan@bham.ac.uk
Joseph Bartlett,
Joseph Bartlett
Institution: School of Computer Science
Email: info@rnfinity.com
Wenqi Lu
Wenqi Lu
Institution: Tissue Image Analytics Centre, Department of Computer Science
Email: info@rnfinity.com
In this work, we investigate image registration in a variational framework and focus on regularization generality and solver efficiency. We first propose a variational model combining the state-of-the-art sum of absolute differences (SAD) and a new arbitrary order total variation regularization term...
More
In this work, we investigate image registration in a variational framework and focus on regularization generality and solver efficiency. We first propose a variational model combining the state-of-the-art sum of absolute differences (SAD) and a new arbitrary order total variation regularization term. The main advantage is that this variational model preserves discontinuities in the resultant deformation while being robust to outlier noise. It is however non-trivial to optimize the model due to its non-convexity, non-differentiabilities, and generality in the derivative order. To tackle these, we propose to first apply linearization to the model to formulate a convex objective function and then break down the resultant convex optimization into several point-wise, closed-form subproblems using a fast, over-relaxed alternating direction method of multipliers (ADMM). With this proposed algorithm, we show that solving higher-order variational formulations is similar to solving their lower-order counterparts. Extensive experiments show that our ADMM is significantly more efficient than both the subgradient and primal-dual algorithms particularly when higher-order derivatives are used, and that our new models outperform state-of-the-art methods based on deep learning and free-form deformation. Our code implemented in both Matlab and Pytorch is publicly available at https://github.com/j-duan/AOTV.
Less
Posted 1 year ago
Seyed Hossein Amirshahi,
Seyed Hossein Amirshahi
Institution: Amirkabir University of Technology (Tehran Polytechnic), School of Material Engineering and Advanced Processes
Email: hamirsha@aut.ac.ir
Ida Rezaei,
Ida Rezaei
Institution: Amirkabir University of Technology (Tehran Polytechnic), School of Material Engineering and Advanced Processes
Email: info@rnfinity.com
Ali Akbar Mahbadi
Ali Akbar Mahbadi
Institution: Amirkabir University of Technology (Tehran Polytechnic), School of Material Engineering and Advanced Processes
Email: info@rnfinity.com
Two regression methods, namely, Support Vector Regression (SVR) and Kernel Ridge Regression (KRR), are used to reconstruct the spectral reflectance curves of samples of Munsell dataset from the corresponding CIE XYZ tristimulus values. To this end, half of the samples (i.e., the odd ones) were used ...
More
Two regression methods, namely, Support Vector Regression (SVR) and Kernel Ridge Regression (KRR), are used to reconstruct the spectral reflectance curves of samples of Munsell dataset from the corresponding CIE XYZ tristimulus values. To this end, half of the samples (i.e., the odd ones) were used as training set while the even samples left out for the evaluation of reconstruction performances. Results were reviewed and compared with those obtained from Principal Component Analysis (PCA) method, as the most common context-based approach. The root mean squared error (RMSE), goodness fit coefficient (GFC), and CIE LAB color difference values between the actual and reconstruct spectra were reported as evaluation metrics. However, while both SVR and KRR methodologies provided better spectral and colorimetric performances than the classical PCA method, the computation costs were considerably longer than PCA method.
Less
Posted 1 year ago
Current developments in object tracking and detection techniques have directed remarkable improvements in distinguishing attacks and adversaries. Nevertheless, adversarial attacks, intrusions, and manipulation of images/ videos threaten video surveillance systems and other object-tracking applicatio...
More
Current developments in object tracking and detection techniques have directed remarkable improvements in distinguishing attacks and adversaries. Nevertheless, adversarial attacks, intrusions, and manipulation of images/ videos threaten video surveillance systems and other object-tracking applications. Generative adversarial neural networks (GANNs) are widely used image processing and object detection techniques because of their flexibility in processing large datasets in real-time. GANN training ensures a tamper-proof system, but the plausibility of attacks persists. Therefore, reviewing object tracking and detection techniques under GANN threats is necessary to reveal the challenges and benefits of efficient defence methods against these attacks. This paper aims to systematically review object tracking and detection techniques under threats to GANN-based applications. The selected studies were based on different factors, such as the year of publication, the method implemented in the article, the reliability of the chosen algorithms, and dataset size. Each study is summarised by assigning it to one of the two predefined tasks: applying a GANN or using traditional machine learning (ML) techniques. First, the paper discusses traditional applied techniques in this field. Second, it addresses the challenges and benefits of object detection and tracking. Finally, different existing GANN architectures are covered to justify the need for tamper-proof object tracking systems that can process efficiently in a real-time environment.
Less
Posted 1 year ago
Jeongeun Park,
Jeongeun Park
Institution: Department of Artificial Intelligence
Email: baro0906@korea.ac.kr
Seungyoun Shin,
Seungyoun Shin
Institution: Department Computer Engineering
Email: info@rnfinity.com
Sangheum Hwang
Sangheum Hwang
Institution: Department of Data Science, Seoul National University of Science and Technology
Email: info@rnfinity.com
Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed method can not only successfully learn the clean target distribution from a dirty dataset but also can estimate the unde...
More
Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed method can not only successfully learn the clean target distribution from a dirty dataset but also can estimate the underlying noise pattern. To this end, we leverage a mixture-of-experts model that can distinguish two different types of predictive uncertainty, aleatoric and epistemic uncertainty. We show that the ability to estimate the uncertainty plays a significant role in elucidating the corruption patterns as these two objectives are tightly intertwined. We also present a novel validation scheme for evaluating the performance of the corruption pattern estimation. Our proposed method is extensively assessed in terms of both robustness and corruption pattern estimation in the computer vision domain. Code has been made publicly available at https://github.com/jeongeun980906/Uncertainty-Aware-Robust-Learning.
Less
Posted 1 year ago
Joni Virta
Joni Virta
Institution: Department of Mathematics and Statistics
Email: joni.virta@utu.fi
We develop a dimension reduction framework for data consisting of matrices of counts. Our model is based on the assumption of existence of a small amount of independent normal latent variables that drive the dependency structure of the observed data, and can be seen as the exact discrete analogue of...
More
We develop a dimension reduction framework for data consisting of matrices of counts. Our model is based on the assumption of existence of a small amount of independent normal latent variables that drive the dependency structure of the observed data, and can be seen as the exact discrete analogue of a contaminated low-rank matrix normal model. We derive estimators for the model parameters and establish their limiting normality. An extension of a recent proposal from the literature is used to estimate the latent dimension of the model. The method is shown to outperform both its vectorization-based competitors and matrix methods assuming the continuity of the data distribution in analysing simulated data and real world abundance data.
Less
Posted 1 year ago
Iman Azimi,
Iman Azimi
Institution: Department of Computer Science
Email: info@rnfinity.com
Arman Anzanpour,
Arman Anzanpour
Institution: Department of Computing
Email: info@rnfinity.com
Amir M. Rahmani
Amir M. Rahmani
Institution: Department of Computer Science
Email: info@rnfinity.com
Photoplethysmography (PPG) is a non-invasive technique used in wearable devices to measure vital signs (e.g., heart rate). The method is, however, highly susceptible to motion artifacts, which are inevitable in remote health monitoring. Noise reduces signal quality, leading to inaccurate decision-ma...
More
Photoplethysmography (PPG) is a non-invasive technique used in wearable devices to measure vital signs (e.g., heart rate). The method is, however, highly susceptible to motion artifacts, which are inevitable in remote health monitoring. Noise reduces signal quality, leading to inaccurate decision-making. In addition, unreliable data collection and transmission waste a massive amount of energy on battery-powered devices. Studies in the literature have proposed PPG signal quality assessment (SQA) enabled by rule-based and machine learning (ML)-based methods. However, rule-based techniques were designed according to certain specifications, resulting in lower accuracy with unseen noise and artifacts. ML methods have mainly been developed to ensure high accuracy without considering execution time and device’s energy consumption. In this paper, we propose a lightweight and energy-efficient PPG SQA method enabled by a semi-supervised learning strategy for edge devices. We first extract a wide range of features from PPG and then select the best features in terms of accuracy and latency. Second, we train a one-class support vector machine model to classify PPG signals into “Reliable” and “Unreliable” classes. We evaluate the proposed method in terms of accuracy, execution time, and energy consumption on two embedded devices, in comparison to five state-of-the-art PPG SQA methods. The methods are assessed using a PPG dataset collected via smartwatches from 46 individuals in free-living conditions. The proposed method outperforms the other methods by achieving an accuracy of 0.97 and a false positive rate of 0.01. It also provides the lowest latency and energy consumption compared to other ML-based methods.
Less
Posted 1 year ago
Sudarsana Reddy Kadiri,
Sudarsana Reddy Kadiri
Institution: Department of Information and Communications Engineering
Email: sudarsana.kadiri@aalto.fi
Paavo Alku
Paavo Alku
Institution: Department of Information and Communications Engineering
Email: info@rnfinity.com
In this study, formant tracking is investigated by refining the formants tracked by an existing data-driven tracker, DeepFormants, using the formants estimated in a model-driven manner by linear prediction (LP)-based methods. As LP-based formant estimation methods, conventional covariance analysis (...
More
In this study, formant tracking is investigated by refining the formants tracked by an existing data-driven tracker, DeepFormants, using the formants estimated in a model-driven manner by linear prediction (LP)-based methods. As LP-based formant estimation methods, conventional covariance analysis (LP-COV) and the recently proposed quasi-closed phase forward–backward (QCP-FB) analysis are used. In the proposed refinement approach, the contours of the three lowest formants are first predicted by the data-driven DeepFormants tracker, and the predicted formants are replaced frame-wise with local spectral peaks shown by the model-driven LP-based methods. The refinement procedure can be plugged into the DeepFormants tracker with no need for any new data learning. Two refined DeepFormants trackers were compared with the original DeepFormants and with five known traditional trackers using the popular vocal tract resonance (VTR) corpus. The results indicated that the data-driven DeepFormants trackers outperformed the conventional trackers and that the best performance was obtained by refining the formants predicted by DeepFormants using QCP-FB analysis. In addition, by tracking formants using VTR speech that was corrupted by additive noise, the study showed that the refined DeepFormants trackers were more resilient to noise than the reference trackers. In general, these results suggest that LP-based model-driven approaches, which have traditionally been used in formant estimation, can be combined with a modern data-driven tracker easily with no further training to improve the tracker’s performance.
Less
Posted 1 year ago
There has been an increasing interest in the development of deep-learning models for the large data processing such as images, audio, or video. Image processing has made breakthroughs in addressing important problems such as genome-wide biological networks, map interactions of genes and proteins, ne...
More
There has been an increasing interest in the development of deep-learning models for the large data processing such as images, audio, or video. Image processing has made breakthroughs in addressing important problems such as genome-wide biological networks, map interactions of genes and proteins, network, etc. With the increase in sophistication of the system, and other areas such as internet of things, social media, web development, etc., the need for classification of image data has been felt more than ever before. It is more important to develop intelligent approaches that can take care of the sophistication of systems. Several researchers are working on the real-time images to solve the problems related to the classification of images. The algorithms to be developed will have to meet the large image datasets. In this paper, the generalized hierarchical fuzzy deep learning approach is discussed and developed to meet such demands. The objective is to design the algorithm for image classification so that it results in high accuracy. The approach is for real-life intelligent systems and the classification results have been shared for large image datasets such as the YaleB database. The accuracy of the algorithm has been obtained for various classes of images using image thresholding. The development of learning algorithms has been validated on corrupted and noisy data and results of various classes of images are presented.
Less
Posted 1 year ago
