Search

The semiconductor industry is the core industry of the information age. As a key link in the semiconductor industry, wafer fabrication plays a key role in its development. In the testing stage of the wafer, each die of the wafer is detected and marked, and a wafer map with a certain spatial pattern can be formed. The analysis and classification of these spatial patterns can identify the cause of wafer defects, thereby improving production yield. However, as wafer size increases, line widths become smaller, etc., the probability of a mixed defect mode wafer pattern increases. Moreover, the mixed defect mode wafer map is more difficult to identify and classify than the single defect mode wafer map. Therefore, this paper proposes an improved deep convolutional neural network (DCNN) structure model for the recognition and classification of mixed defect pattern wafer maps. From the perspective of increasing the width of the DCNN, the improved network structure can avoid problems such as over-fitting and limited extraction of features due to the continuous deepening of the DCNN. The network is called Multi-Path DCNN (MP-DCNN) structure. The experimental results show that the proposed Multi-Path DCNN structure has better performance and higher classification accuracy than existing methods. [ABSTRACT FROM AUTHOR]

The success of supervised models for emotion recognition on images heavily depends on the availability of images properly annotated. Although millions of images are presently available, only a few are annotated with reliable emotional information. Current emotion recognition solutions either use large amounts of weakly-labeled web images, which often contain noise that is unrelated to the emotions of the image, or transfer learning, which usually results in performance losses. Thus, it would be desirable to know which images would be useful to be annotated to avoid an extensive annotation effort. In this paper, we propose a novel approach based on active learning to choose which images are more relevant to be annotated. Our approach dynamically combines multiple active learning strategies and learns the best ones (without prior knowledge of the best ones). Experiments using nine benchmark datasets revealed that: (i) active learning allows to reduce the annotation effort, while reaching or surpassing the performance of a supervised baseline with as little as 3% to 18% of the baseline's training set, in classification tasks; (ii) our online combination of multiple strategies converges to the performance of the best individual strategies, while avoiding the experimentation overhead needed to identify them. [ABSTRACT FROM AUTHOR]

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

Wafer-level direct bonding technology is a key process for the production of backside illuminated (BSI) CMOS image sensor (CIS). Usually, constant-depth mode scanning acoustic microscope (C-SAM) 300mm wafer images are acquired and defect size distribution is provided to monitor defects that degrade bonding yield. This acquisition technique is used as it is nondestructive and is able to capture the full wafer. Current solutions are not providing information detailed enough to identify the root cause of this degradation. A consequence is that most measurements and classification is currently done manually which take time and have reproducibility issues. In this paper, we propose a rule-based method for the classification of the defects and automatic segmentation of the defects to extract precise measurements depending on the type of defect. The classes of defects are precisely defined based on their origin in the process. All these information will allow to reduce the time to analyze the images and improve the precision and consistency of the analysis. These results will allow to identify more precisely the defects thus the causes of yield degradation during bonding process. [ABSTRACT FROM AUTHOR]

Identifying the patterns of defective chips in wafer bin maps (WBMs) in semiconductor manufacturing processes is crucial because different defect patterns correspond to different root causes of process failures. Recently, mixed-type defect patterns (i.e., multiple defect patterns in a single wafer) have become increasingly common owing to the increased complexity of semiconductor manufacturing processes. Previous methods for classifying mixed-type defect patterns in WBMs focused on outputting only the class labels of the defect patterns and not their locations, although location information of the defect patterns is useful for tracking the root causes of failure and improving processes. Moreover, most previous methods used only labeled WBM data, although a larger quantity of unlabeled WBM data are more accessible because of the costly process of label annotation. Therefore, in this paper, we propose a semi-supervised learning method for classifying mixed-type defect patterns and detecting their locations simultaneously using both labeled and unlabeled WBM data. The proposed method extends a recent unsupervised object detection method called Attend-Infer-Repeat in a semi-supervised manner to perform object detection and classification simultaneously. The performance of the proposed method is verified using WBM datasets of different sizes. The results demonstrate the effectiveness of the proposed method for classification and location detection. [ABSTRACT FROM AUTHOR]

This paper presents an asset health index (HI) prediction methodology for high voltage transmission overhead lines (OHLs) using supervised machine learning and structured, unambiguous visual inspections. We propose a framework for asset HI predictions to determine the technical condition of individual OHL towers to improve grid reliability in a cost-effective manner. The paper focuses on asset HI prediction and the selection of the most parsimonious model. Based on the technical specifications and HI data, our methodology allows for the prediction of a HI for OHLs without HI data, and models asset aging behaviour. Technical specifications and the HI as defined in this paper are taken from the Estonian TSO periodical visual inspections implemented in 2018. The case study successfully demonstrates that the proposed methodology can predict tower HI values for a single OHL with nearly 80 percent accuracy without the need for additional measurements. [ABSTRACT FROM AUTHOR]

Epilepsy is one of the most chronic brain disorder recorded from since 2000 BC. Almost one-third of epileptic patients experience seizures attack even with medicated treatment. The menace of SUDEP (Sudden unexpected death in epilepsy) in an adult epileptic patient is approximately 8–17% more and 34% in a children epileptic patient. The expert neurologist manually analyses the Electroencephalogram (EEG) signals for epilepsy diagnosis. The non-stationary and complex nature of EEG signals this task more error-prone, time-consuming and even expensive. Hence, it is essential to develop automatic epilepsy detection techniques to ensure an appropriate identification and treatment of this disease. Nowadays, graph-theory has been considered as a prominent approach in the neuroscience field. The network-based approach characterizes a hidden sight of brain activity and brain-behavior mapping. The graph-theory not even helps to understand the underlying dynamics of EEG signals at microscopic, mesoscopic, and macroscopic level but also provide the correlation among them. This paper provides a review report about graph-theory based automated epilepsy detection methods. Furthermore, it will assist the expert's neurologist and researchers with the information of complex network-based epilepsy detection and aid the technician for developing an intelligent system that improving the diagnosis of epilepsy disorder. [ABSTRACT FROM AUTHOR]

Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate the requirement of pixel-level dense annotations. Existing works mostly leverage the popular CNN classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we propose a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to improve the classification performance without a re-training burden. For each patch, we construct a multi-resolution image pyramid to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equip PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%). It greatly saves the computational resources and annotation efforts. The source code is available at: https://github.com/linjiatai/PDBL. [ABSTRACT FROM AUTHOR]

The power distribution system’s fault root cause classification is an important but challenging problem. Traditional classifiers fail to achieve high accuracy and good generalization performance due to data insufficiency. A large volume of unlabeled data is available, which can be utilized to improve classification performance. This paper proposes a novel classifier called Robust Semi-Supervised Prototypical Network (RSSPN) based on Prototypical Network architecture and semi-supervised learning to address this issue. The proposed method can mine information from unlabeled data to improve the generalization ability and classification accuracy. Furthermore, RSSPN adopts the idea of meta-learning to obtain the “few-shot learning” ability for identifying new fault classes using very few samples encountered during the operation and update online. Experiments have been conducted on a dataset consisting of 1152 labeled samples belonging to 12 different classes and 10000 unlabeled samples. The accuracy of the proposed method is significantly better than the traditional classifiers. [ABSTRACT FROM AUTHOR]

In the electroencephalography (EEG) based cross-subject motor imagery (MI) classification task, the device and subject problems can cause the time-related data distribution shift problem. In a single-source to single-target (STS) MI classification task, such a shift problem will certainly provoke an increase in the overall data distribution difference between the source and target domains, giving rise to poor classification accuracy. In this paper, a novel multi-subdomain adaptation method (MSDAN) is proposed to solve the shift problem and improve the classification accuracy of the traditional approaches. In the proposed MSDAN, the adaptation losses in both class-related and time-related subdomains (that are divided by different data labels and session labels) are obtained by measuring the distribution differences between the source and target subdomains. Then, the adaptation and classification losses in the loss function of MSDAN are minimized concurrently. To illustrate the application value of the proposed method, our method is applied to solve the STS MI classification task about data analysis with respect to the brain-computer interface (BCI) competition III-IVa dataset. The resultant experiment results demonstrate that compared with other well-known domain adaptation and deep learning methods, the proposed method is capable of solving the time-related data distribution problem at higher classification accuracy. [ABSTRACT FROM AUTHOR]

This paper describes a complete solution of a new dropped wireless sensor network (called “abandoned” since it is never picked up) dedicated to intelligence operation. The sensor network, named SEXTANT for Smart sEnsor X for Tactical situation AssessmeNT and presented in this paper is the achievement of several years of research and development in the fields of data fusion and smart sensors at the French Aerospace Lab. The main contribution of this paper is the presentation of experimental results obtained with our Joint Tracking and Classification (JTC) algorithm. The originality of this algorithm relies on the use contextual information in the target tracking processing and data fusion for target classification processing. [ABSTRACT FROM AUTHOR]

RFID-based pose perception can enable industrial automation applications such as industrial robot grasping. In this paper, a RFID pose estimation method based on classification algorithm and phase-position transformation model for moving objects is proposed, which converts the traditional pose estimation problem into a machine learning classification problem by dividing the direction angle value domain of the object into several classes. The phase information of multiple RFID tags attached to the object is transformed into position information using an unwrapped phase-position model, on which the input features of the classifier is constructed. A classifier based on the LightGBM framework is constructed and trained to realize the mapping between RFID phase information and the object’s pose. Extensive experiments demonstrate that the proposed method in this paper can accurately estimate the pose of moving objects in real time and successfully complete the robot grasping task for objects on the conveyor belt. [ABSTRACT FROM AUTHOR]

Waveform measurement units (WMUs) are a new class of smart grid sensors. They capture synchro-waveforms, i.e., time-synchronized high-resolution voltage waveform and current waveform measurements. In this paper, we propose new methods to detect and classify power quality events in power distribution systems by using synchro-waveform measurements. The methods are built upon a novel graphical concept, called synchronized Lissajous curve. The proposed event detection and event classification methods work by analyzing the shape of the synchronized Lissajous curves during disturbances and events. The impact of challenging factors, such as the angle, the location, and other parameters of the event are discussed. We show that these challenges can be addressed if we treat the synchronized Lissajous curves as images, instead of as time series as in the raw synchronized waveform measurements. Hence, we can take advantage of the recent advancements in the field of image processing so as to capture the overall characterizing patterns in the shapes of the synchronized Lissajous curves. We develop a Convolutional Neural Network (CNN) method to classify the events, where the input is the synchronized Lissajous images. The effectiveness of the proposed event detection and classification methods is demonstrated through computer simulations, including hardware-in-the-loop simulations, and real-world field data. Multiple case studies verify the performance of the proposed methods. The proposed event detection method can accurately detect events, and identify the start time and the end time of each event. The proposed event classification method can classify power quality events with high accuracy. The proposed detection and classification methods do not require any prior knowledge about the network. They use data from as few as only two WMUs. [ABSTRACT FROM AUTHOR]

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramid×pyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios. [ABSTRACT FROM AUTHOR]

The goal of few-shot image classification is to learn a classifier that can be well generalized to the unseen classes with a few available labeled samples. One major challenge for few-shot learning is how to conduct effective image representation for support and query images. Recently, local region-based image representation and metric learning approaches have been demonstrated effectively for few-shot classification problem. However, existing approaches generally conduct representations of image regions individually which thus lack of considering the rich spatial/structural relationships among image regions. In this paper, we propose to bridge the individual regions and exploit the structural contexts among regions via a novel Region-Graph Transformer (RGTransformer). In RGTransformer, each region aggregates the information from its neighboring regions and thus can obtain context-aware feature representations for regions. Using the proposed RGTransformer, we propose an effective metric learning model for few-shot image classification. We evaluate the proposed method on four benchmark datasets and experimental results demonstrate the effectiveness and advantages of the proposed RGTransformer. [ABSTRACT FROM AUTHOR]

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images. [ABSTRACT FROM AUTHOR]

Pattern recognition based on a high-dimensional predictor is considered. A classifier is defined which is based on a Transformer encoder. The rate of convergence of the misclassification probability of the classifier towards the optimal misclassification probability is analyzed. It is shown that this classifier is able to circumvent the curse of dimensionality provided the a posteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between the Transformer classifiers theoretically analyzed in this paper and the ones used in practice today is illustrated by means of classification problems in natural language processing. [ABSTRACT FROM AUTHOR]

Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making. In this paper, we propose a novel Voting-based Adaptive Feature Fusion multi-task network (VAFF-Net) for joint segmentation, detection, and classification of RV, FAZ, and RVJ in optical coherence tomography angiography (OCTA). A task-specific voting gate module is proposed to adaptively extract and fuse different features for specific tasks at two levels: features at different spatial positions from a single encoder, and features from multiple encoders. In particular, since the complexity of the microvasculature in OCTA images makes simultaneous precise localization and classification of retinal vascular junctions into bifurcation/crossing a challenging task, we specifically design a task head by combining the heatmap regression and grid classification. We take advantage of three different en face angiograms from various retinal layers, rather than following existing methods that use only a single en face. We carry out extensive experiments on three OCTA datasets acquired using different imaging devices, and the results demonstrate that the proposed method performs on the whole better than either the state-of-the-art single-purpose methods or existing multi-task learning solutions. We also demonstrate that our multi-task learning method generalizes across other imaging modalities, such as color fundus photography, and may potentially be used as a general multi-task learning tool. We also construct three datasets for multiple structure detection, and part of these datasets with the source code and evaluation benchmark have been released for public access. [ABSTRACT FROM AUTHOR]

The clustering of incomplete patterns is a very challenging task because the estimations may negatively affect the distribution of real centers and thus cause uncertainty and imprecision in the results. To address this problem, a new belief-based incomplete pattern unsupervised classification method (BPC) is proposed in this paper. First, the complete patterns are grouped into a few clusters by a classical soft method like fuzzy $c$ c -means to obtain the corresponding reliable centers and thereby are partitioned into reliable patterns and unreliable ones by an optimization method. Second, a basic classifier trained by reliable patterns is employed to classifies unreliable patterns and the incomplete patterns edited by the neighbors. In this way, most of the edited incomplete patterns can be submitted to specific clusters. Finally, some ambiguous patterns will be carefully repartitioned again by a new distance-based rule depending on the obtained reliable centers and belief functions theory. By doing this, a few patterns that are very difficult to classify between different specific clusters will be reasonably submitted to meta-cluster which can characterize the uncertainty and imprecision of the clusters due to missing values. The simulation results show that the BPC has the potential to deal with real datasets. [ABSTRACT FROM AUTHOR]

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

Android malware is an ongoing threat to billions of smart devices’ security, ranging from mobile phones to car infotainment systems. Despite numerous approaches and previous studies to develop solutions for detecting and preventing Android malware, the rapid continuous development of new malware variants requires a careful reconsideration and the development of effective methods to identify malware families given a meager number of malware instances. In this paper, we present DroidMalVet, a novel Android malware family classification and detection approach that does not require to perform complex program analyses or utilize large feature sets. DroidMalVet is the first to use a promising, diverse, and small set of software metrics as features in a supervised learning platform to classify and detect various Android malware families. Our extensive empirical evaluations on two large public malware datasets show that DroidMalVet accurately detects both small and large malware families with F-Score accuracy of 94.4% and 96%, and AUC equal to 99.5% and 99.7% on the malware families in Drebin and AMD datasets, respectively. Moreover, our results demonstrate the superior performance of DroidMalVet in detecting small families (i.e., families with few samples). DroidMalVet complements existing approaches and presents an early warning tool for detecting known and emerging malware families. [ABSTRACT FROM AUTHOR]

Most of the existing classification systems assume that the data used is high-quality labeled. However, the labeling process in real-world may inevitably introduce corruptions into labels which can confuse the performances of classifiers. In this paper, based on Broad Learning System (BLS), we propose a novel label noise tolerant method to classify the pattern with corrupted labels. The standard BLS has shown promising efficiency and accuracy in general classification, but its learning process is prone to be affected by the noisy labels. Here, by detailed probabilistic analysis, we first give the reason for lacks of robustness in standard BLS. Then a maximum likelihood estimation-based objective function is derived for robust classification. In addition, a manifold regularization term is integrated to preserve the local geometry of data, which makes the model to be more robust and flexible to learn the output weights. Given some basic assumptions on the approximation errors, the obtained model can be transformed to a graph regularized reweighted BLS problem. The negative effects of noisy labels in data can be inhibited adaptively by assigning reasonable weights. Theoretical analysis and extensive experiments are provided to demonstrate the robustness and effectiveness of the proposed robust BLS model, especially for the case of large amounts of noisy labels. [ABSTRACT FROM AUTHOR]

The KNN algorithm is one of the most popular data mining algorithms. It has been widely and successfully applied to data analysis applications across a variety of research topics in computer science. This paper illustrates that, despite its success, there remain many challenges in KNN classification, including K computation, nearest neighbor selection, nearest neighbor search and classification rules. Having established these issues, recent approaches to their resolution are examined in more detail, thereby providing a potential roadmap for ongoing KNN-related research, as well as some new classification rules regarding how to tackle the issue of training sample imbalance. To evaluate the proposed approaches, some experiments were conducted with 15 UCI benchmark datasets. [ABSTRACT FROM AUTHOR]

A dilemma faced by classification is that the data is not collected at the same frequency in some applications. We investigate the mixed frequency data in a new way and recognize them as a special style of multi-view data, in which each view data is collected at a different sampling frequency. This article proposes a discriminative dictionary pair learning method constrained by ordinal locality for mixed frequency data classification (shorted by DPLOL-MF). This method integrates synthesis dictionary and analysis dictionary into a dictionary pair, which not only improves computational cost caused by the ${\ell _0}$ ℓ 0 or ${\ell _1}$ ℓ 1 -norm constraint, but also can deal with the sampling frequency inconsistency. The DPLOL-MF utilizes a synthesis dictionary to learn class-specified reconstruction information and employs an analysis dictionary to generate coding coefficients by analyzing samples. Particularly, the ordinal locality preserving term is leveraged to constrain the atoms of dictionaries pair to further facilitate the learned dictionary pair to be more discriminative. Besides, we design a specific classification scheme for the inconsistent sample size of mixed frequency data. This paper illustrates a novel idea to solve the classification task of mixed frequency data and the experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper introduces an approach for classifying adolescents suffering from MDD using resting-state fMRI. Accurate diagnosis of MDD involves interviews with adolescent patients and their parents, symptom rating scales based on Diagnostic and Statistical Manual of Mental Disorders (DSM), behavioral observation as well as the experience of a clinician. Discovering predictive biomarkers for diagnosing MDD patients using functional magnetic resonance imaging (fMRI) scans can assist the clinicians in their diagnostic assessments. This paper investigates various static and dynamic connectivity measures extracted from resting-state fMRI for assisting with MDD diagnosis. First, absolute Pearson correlation matrices from 85 brain regions are computed and they are used to calculate static features for predicting MDD. A predictive sub-network extracted using sub-graph entropy classifies adolescent MDD vs. typical healthy controls with high accuracy, sensitivity and specificity. Next, approaches utilizing dynamic connectivity are employed to extract tensor based, independent component based and principal component based subject specific attributes. Finally, features from static and dynamic approaches are combined to create a feature vector for classification. A leave-one-out cross-validation method is used for the final predictor performance. Out of 49 adolescents with MDD and 33 matched healthy controls, a support vector machine (SVM) classifier using a radial basis function (RBF) kernel using differential sub-graph entropy combined with dynamic connectivity features classifies MDD vs. healthy controls with an accuracy of 0.82 for leave-one-out cross-validation. This classifier has specificity and sensitivity of 0.79 and 0.84, respectively. [ABSTRACT FROM AUTHOR]

Occupancy estimation has a broad range of applications in security, surveillance, traffic and resource management in smart building environments. Low-resolution thermal imaging sensors can be used for real-time non-intrusive occupancy estimation. Such sensors have a resolution that is too low to identify occupants, but it may provide sufficient data for real-time occupancy estimation. In this paper, we present a systematic study of three thermal imaging sensors with different resolutions, with a focus on sensor characterization, estimation algorithms, and comparative analysis of occupancy estimation performance. A unified processing algorithms pipeline for occupancy estimation is presented and the performance of three sensors are compared side-by-side. A number of specific algorithms are proposed for pre-processing of sensor data, feature extraction, and fine-tuning of the occupancy estimation algorithms. Our results show that it is possible to achieve about 99% accuracy for occupancy estimation with our proposed approach, which might be sufficient for many practical smart building applications. [ABSTRACT FROM AUTHOR]

Multi-label classification has gained in importance in the last decade and it is today confronted to the current needs to process massive raw data from heterogeneous sources. Therefore, dimensionality reduction, which aims at reducing the number of features, labels, or both, knows a renewed interest to enhance the scaling properties of the classifiers and their predictive performances. In this paper we review more than fifty papers presenting dimensionality reduction approaches for multi-label classification and we propose an analysis in three steps : (i) a typology of the methods describing the main components of their strategies, the problem they tackle and the way they solve it (ii) a unified formalization of the problems to help to distinguish the similarities and differences between the approaches, and (iii) a meta-analysis of the published experimental results inspired by the consensus theory to identify the most efficient algorithms. [ABSTRACT FROM AUTHOR]

Uncertain data objects are objects that can be characterized by either a probability density function (PDF) or with multiple points. Because of existing levels of uncertainty for uncertain data objects, the scatter of this type of objects might be very different than the scatter of certain data objects. Measures of scatter for uncertain objects have not been defined before. In this paper, we define covariance matrix, within scatter matrix, and between scatter matrix as the measures of scatter for uncertain data objects. Also, in this paper, we extend the idea of Fisher linear discriminant analysis for uncertain objects (UFLDA). We also develop kernel Fisher discriminant analysis for uncertain objects (UKFDA). The developed uncertain kernel Fisher discriminants are for two cases: 1) when the uncertain objects are given with PDF and 2) when the uncertain objects are given with multiple points. We compare the performance of our developed uncertain Fisher discriminants (UFLDA and UKFDA) with a few other methods in classification of uncertain data objects through several examples on both simulated and real-world data. We will show in the experiments that our developed uncertain Fisher discriminants outperform other methods in classifying uncertain data objects. [ABSTRACT FROM AUTHOR]

Accurate breast cancer detection using automated algorithms remains a problem within the literature. Although a plethora of work has tried to address this issue, an exact solution is yet to be found. This problem is further exacerbated by the fact that most of the existing datasets are imbalanced, i.e., the number of instances of a particular class far exceeds that of the others. In this paper, we propose a framework based on the notion of transfer learning to address this issue and focus our efforts on histopathological and imbalanced image classification. We use the popular VGG-19 as the base model and complement it with several state-of-the-art techniques to improve the overall performance of the system. With the ImageNet dataset taken as the source domain, we apply the learned knowledge in the target domain consisting of histopathological images. With experimentation performed on a large-scale dataset consisting of 277,524 images, we show that the framework proposed in this paper gives superior performance than those available in the existing literature. Through numerical simulations conducted on a supercomputer, we also present guidelines for work in transfer learning and imbalanced image classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a modified strategy using sparse representation to identify the authorship of online handwritten documents. The note-worthy aspect of this paper lies in the introduction of a-priori information for each dictionary atom, that in a way indicates its degree of importance with respect to the dynamic characteristics of the writer. The methodology behind obtaining this information for the dictionary atoms is based on the computation of entropy values over histograms that are generated from the sparse coefficients during the training phase. The prelearned values are incorporated on the traditional schemes of “max” and “mean” pooling of sparse codes, thereby resulting in a modified writer descriptor. Experiments performed with the proposed sparse classification strategy on the handwritten samples of the IAM and IBM-UB1 online handwriting databases demonstrate promising results. [ABSTRACT FROM AUTHOR]

As the extension of high efficiency video coding (HEVC) standard, three dimensional-HEVC (3D-HEVC) is the latest 3D video coding standard. 3D-HEVC adopts many complicated coding algorithms to generate additional intermediate views for 3D video representation, which result in extremely high coding complexity. Therefore, this paper proposed a fast depth intra coding approach to reduce the 3D-HEVC complexity, which is based on convolutional neural network (CNN). First, we established a database based on the independent view of the depth map, which includes coding unit (CU) partition data of the depth map. Second, we constructed a depth edge classification CNN (DEC-CNN) framework to classify the edges for the depth map and embedded the network into a 3D-HEVC test platform. Finally, we utilized the pixel value of the binarized depth image to correct the above classification results. The experimental results demonstrated that our approach can reduce the intra coding time by 72.5% on average under negligible degradation of coding performance. This result outperforms the other state-of-the-art methods to reduce the coding complexity of 3D-HEVC. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing is on the cusp of a revolution – the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network (SP&A-Net). This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks. [ABSTRACT FROM AUTHOR]

Although deep networks have been shown to perform very well on a variety of medical imaging tasks, inference in the presence of pathology presents several challenges to common models. These challenges impede the integration of deep learning models into real clinical workflows, where the customary process of cascading deterministic outputs from a sequence of image-based inference steps (e.g. registration, segmentation) generally leads to an accumulation of errors that impacts the accuracy of downstream inference tasks. In this paper, we propose that by embedding uncertainty estimates across cascaded inference tasks, performance on the downstream inference tasks should be improved. We demonstrate the effectiveness of the proposed approach in three different clinical contexts: (i) We demonstrate that by propagating T2 weighted lesion segmentation results and their associated uncertainties, subsequent T2 lesion detection performance is improved when evaluated on a proprietary large-scale, multi-site, clinical trial dataset acquired from patients with Multiple Sclerosis. (ii) We show an improvement in brain tumour segmentation performance when the uncertainty map associated with a synthesised missing MR volume is provided as an additional input to a follow-up brain tumour segmentation network, when evaluated on the publicly available BraTS-2018 dataset. (iii) We show that by propagating uncertainties from a voxel-level hippocampus segmentation task, the subsequent regression of the Alzheimer’s disease clinical score is improved. [ABSTRACT FROM AUTHOR]

Industrial Augmented Reality (iAR) has demonstrated its advantages to communicate technical information in the fields of maintenance, assembly, and training. However, literature is scattered among different visual assets (i.e., AR visual user interface elements associated with a real scene). In this work, we present a systematic literature review of visual assets used in these industrial fields. We searched five databases, initially finding 1757 papers. Then, we selected 122 iAR papers from 1997 to 2019 and extracted 348 visual assets. We propose a classification for visual assets according to (i) what is displayed, (ii) how it conveys information (frame of reference, color coding, animation), and, (iii) why it is used. Our review shows that product models, text and auxiliary models are, in order, the most common, with each most often used to support operating, checking and locating tasks respectively. Other visual assets are scarcely used. Product and auxiliary models are commonly rendered world-fixed, color coding is not used as often as expected, while animations are limited to product and auxiliary model. This survey provides a snapshot of over 20 years of literature in iAR, useful to understand established practices to orientate in iAR interface design and to present future research directions. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based graph convolutional network (GCN) models, but also bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) signals are usually affected by presence of missing data because of various reasons. Depending on the percentage of missing data, it affects significantly the classification accuracy which in turn affects the performance of prosthesis. Moreover, it has also been observed that there exists no universal classifier which performs best in all types of data. Therefore, in this paper, we propose a framework to employ tensor-based Canonical/Polyadiac Weighted-optmization (CP-WOPT) and Artificial Neural Network (ANN) to recover missing data and perform classification, respectively. The results of classification have been compared with established methods such as Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), Logistic regression, Boosted trees, Bagged trees and k-nearest neighbor (kNN). The results indicate significant improvement in classification accuracy on complete, missing and recovered data when ANN is employed. Classifiers are applied on complete, missing and recovered data explicitly to test the performance of our framework. Results show that mean classification accuracy on complete data, missing data and recovered data was 88%, 62% and 81% respectively which shows applicability of our framework. [ABSTRACT FROM AUTHOR]

In this paper, we propose to leverage freely available unlabeled video data to facilitate few-shot video classification. In this semi-supervised few-shot video classification task, millions of unlabeled data are available for each episode during training. These videos can be extremely imbalanced, while they have profound visual and motion dynamics. To tackle the semi-supervised few-shot video classification problem, we make the following contributions. First, we propose a label independent memory (LIM) to cache label related features, which enables a similarity search over a large set of videos. LIM produces a class prototype for few-shot training. This prototype is an aggregated embedding for each class, which is more robust to noisy video features. Second, we integrate a multi-modality compound memory network to capture both RGB and flow information. We propose to store the RGB and flow representation in two separate memory networks, but they are jointly optimized via a unified loss. In this way, mutual communications between the two modalities are leveraged to achieve better classification performance. Third, we conduct extensive experiments on the few-shot Kinetics-100, Something-Something-100 datasets, which validates the effectiveness of leveraging the accessible unlabeled data for few-shot classification. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs), including convolutional neural networks (CNNs) and residual networks (ResNets) models, are able to learn abstract representations from the input data by considering a deep hierarchy of layers that perform advanced feature extraction. The combination of these models with visual attention techniques can assist with the identification of the most representative parts of the data from a visual standpoint, obtained through more detailed filtering of the features extracted by the operational layers of the network. This is of significant interest for analyzing remotely sensed hyperspectral images (HSIs), characterized by their very high spectral dimensionality. However, few efforts have been conducted in the literature in order to adapt visual attention methods to remotely sensed HSI data analysis. In this paper, we introduce a new visual attention-driven technique for the HSI classification. Specifically, we incorporate attention mechanisms to a ResNet in order to better characterize the spectral–spatial information contained in the data. Our newly proposed method calculates a mask that is applied to the features obtained by the network in order to identify the most desirable ones for classification purposes. Our experiments, conducted using four widely used HSI data sets, reveal that the proposed deep attention model provides competitive advantages in terms of classification accuracy when compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, e.g. 30 or 90 days, after the discharge. The motivation is to help health providers deliver better treatment and post-discharge strategies, lower the hospital readmission rate, and eventually reduce the medical costs. Due to inherent complexity of diseases and healthcare ecosystems, modeling hospital readmission is facing many challenges. By now, a variety of methods have been developed, but existing literature fails to deliver a complete picture to answer some fundamental questions, such as what are the main challenges and solutions in modeling hospital readmission; what are typical features/models used for readmission prediction; how to achieve meaningful and transparent predictions for decision making; and what are possible conflicts when deploying predictive approaches for real-world usages. In this paper, we systematically review computational models for hospital readmission prediction, and propose a taxonomy of challenges featuring four main categories: (1) data variety and complexity; (2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation. The review summarizes methods in each category, and highlights technical solutions proposed to address the challenges. In addition, a review of datasets and resources available for hospital readmission modeling also provides firsthand materials to support researchers and practitioners to design new approaches for effective and efficient hospital readmission prediction. [ABSTRACT FROM AUTHOR]

Sparsity-constrained optimization problems are common in machine learning, such as sparse coding, low-rank minimization and compressive sensing. However, most of previous studies focused on constructing various hand-crafted sparse regularizers, while little work was devoted to learning adaptive sparse regularizers from given input data for specific tasks. In this paper, we propose a deep sparse regularizer learning model that learns data-driven sparse regularizers adaptively. Via the proximal gradient algorithm, we find that the sparse regularizer learning is equivalent to learning a parameterized activation function. This encourages us to learn sparse regularizers in the deep learning framework. Therefore, we build a neural network composed of multiple blocks, each being differentiable and reusable. All blocks contain learnable piecewise linear activation functions which correspond to the sparse regularizer to be learned. Furthermore, the proposed model is trained with back propagation, and all parameters in this model are learned end-to-end. We apply our framework to multi-view clustering and semi-supervised classification tasks to learn a latent compact representation. Experimental results demonstrate the superiority of the proposed framework over state-of-the-art multi-view learning models. [ABSTRACT FROM AUTHOR]

Label-specific features serve as an effective strategy to learn from multi-label data, where a set of features encoding specific characteristics of each label are generated to help induce multi-label classification model. Existing approaches work by taking the two-stage strategy, where the procedure of label-specific feature generation is independent of the follow-up procedure of classification model induction. Intuitively, the performance of resulting classification model may be suboptimal due to the decoupling nature of the two-stage strategy. In this paper, a wrapped learning approach is proposed which aims to jointly perform label-specific feature generation and classification model induction. Specifically, one (kernelized) linear model is learned for each label where label-specific features are simultaneously generated within an embedded feature space via empirical loss minimization and pairwise label correlation regularization. Comparative studies over a total of sixteen benchmark data sets clearly validate the effectiveness of the wrapped strategy in exploiting label-specific features for multi-label classification. [ABSTRACT FROM AUTHOR]

Even if Application-Specific Integrated Circuits (ASIC) have proven to be a relevant choice for integrating inference at the edge, they are often limited in terms of applicability. In this paper, we demonstrate that an ASIC neural network accelerator dedicated to image processing can be applied to multiple tasks of different levels: image classification and compression, while requiring a very limited hardware. The key component is a reconfigurable, mixed-precision (3b/2b/1b) encoder that takes advantage of proper weight and activation quantizations combined with convolutional layer structural pruning to lower hardware-related constraints (memory and computing). We introduce an automatic adaptation of linear symmetric quantizer scaling factors to perform quantized levels equalization, aiming at stabilizing quinary and ternary weights training. In addition, a proposed layer-shared Bit-Shift Normalization significantly simplifies the implementation of the hardware-expensive Batch Normalization. For a specific configuration in which the encoder design only requires 1Mb, the classification accuracy reaches 87.5% on CIFAR-10. Besides, we also show that this quantized encoder can be used to compress image patch-by-patch while the reconstruction can performed remotely, by a dedicated full-frame decoder. This solution typically enables an end-to-end compression almost without any block artifacts, outperforming patch-based state-of-the-art techniques employing a patch-constant bitrate. [ABSTRACT FROM AUTHOR]

Objective: The performance of an EEG-based brain-computer interface (BCI) system is highly dependent on signal preprocessing. This manuscript presents a filtering method to improve the feature classification algorithms typically used in BCI. Methods: A graph Laplacian quadratic form using the Phase Locking Value (PLV) is applied to generate a new filtered signal in the preprocessing stage. Results: The accuracy of the classification algorithms improved significantly (up to 27.18% in the BCI Competition IV dataset, and up to 42.56% with records made with an Emotiv EPOC+). In addition, the proposed filtering algorithm has similar or better results when compared with the Filter Bank Common Spatial Pattern (FBCSP), which has disadvantages in a multiclass classification. Conclusion: This paper shows how our PLV-based filtering between EEG channels could improve the performance of a BCI. [ABSTRACT FROM AUTHOR]

Sleep is a vital process of our daily life as we roughly spend one-third of our lives asleep. In order to evaluate sleep quality and potential sleep disorders, sleep stage classification is a gold standard method. In this paper, we introduce a novel fully convolutional neural network architecture (SleepFCN) to classify sleep stages into five classes using single-channel electroencephalograms (EEGs). The framework of SleepFCN includes two major parts for feature extraction and temporal sequence encoding namely multi-scale feature extraction (MSFE) and residual dilated causal convolutions (ResDC), respectively. These are then followed by convolutional layers of 1-sized kernels instead of dense layers to build the fully convolutional neural network. Due to the imbalance in the distribution of sleep stages, we incorporate a weight corresponding to the number of samples of each class in our loss function. We evaluated the performance of SleepFCN using the Sleep-EDF and SHHS datasets. Our experimental results show that the proposed method outperforms state-of-the-art works in both classification correctness and learning speed. [ABSTRACT FROM AUTHOR]

Identification of autism spectrum disorder (ASD) in children is challenging due to the complexity and heterogeneity of ASD. Currently, most existing methods mainly rely on a single modality with limited information and often cannot achieve satisfactory performance. To address this issue, this paper investigates from internal neurophysiological and external behavior perspectives simultaneously and proposes a new multimodal diagnosis framework for identifying ASD in children with fusion of electroencephalogram (EEG) and eye-tracking (ET) data. Specifically, we designed a two-step multimodal feature learning and fusion model based on a typical deep learning algorithm, stacked denoising autoencoder (SDAE). In the first step, two SDAE models are designed for feature learning for EEG and ET modality, respectively. Then, a third SDAE model in the second step is designed to perform multimodal fusion with learned EEG and ET features in a concatenated way. Our designed multimodal identification model can automatically capture correlations and complementarity from behavior modality and neurophysiological modality in a latent feature space, and generate informative feature representations with better discriminability and generalization for enhanced identification performance. We collected a multimodal dataset containing 40 ASD children and 50 typically developing (TD) children to evaluate our proposed method. Experimental results showed that our proposed method achieved superior performance compared with two unimodal methods and a simple feature-level fusion method, which has promising potential to provide an objective and accurate diagnosis to assist clinicians. [ABSTRACT FROM AUTHOR]

Mild cognitive impairment (MCI) belongs to the prodromal stage of Alzheimer’s disease (AD). Accurate diagnosis of MCI is very important for possibly deferring AD progression. Graph kernels, which measure the similarity between paired brain connectivity networks, have been widely used to diagnose brain diseases (e.g., MCI) and yielded promising classification performance. However, most of the existing graph kernels are based on unweighted graphs, and neglect the valuable weighted information of the edges in brain connectivity networks where edge weights convey the strengths of fiber connection or temporal correlation between paired brain regions. Accordingly, in this paper, we propose a new graph kernel called ordinal pattern kernel for measuring brain connectivity network similarity and apply it to brain disease classification tasks. Different from the existing graph kernels which measure the topological similarity of the unweighted graphs, our proposed ordinal pattern kernel can not only calculate the similarity of paired brain connectivity networks, but also capture the ordinal pattern relationship of edge weights in brain connectivity networks. To appraise the effectiveness of our proposed method, we perform extensive experiments in functional magnetic resonance imaging data of brain disease from Alzheimer’s Disease Neuroimaging Initiative database. The experimental results show that our proposed ordinal pattern kernel outperforms the state-of-the-art graph kernels in the classification tasks of MCI. [ABSTRACT FROM AUTHOR]

Point-level weakly-supervised temporal action localization (P-WSTAL) aims to localize temporal extents of action instances and identify the corresponding categories with only a single point label for each action instance for training. Due to the sparse frame-level annotations, most existing models are in the localization-by-classification pipeline. However, there exist two major issues in this pipeline: large intra-action variation due to task gap between classification and localization and noisy classification learning caused by unreliable pseudo training samples. In this paper, we propose a novel framework CRRC-Net, which introduces a co-supervised feature learning module and a probabilistic pseudo label mining module, to simultaneously address the above two issues. Specifically, the co-supervised feature learning module is applied to exploit the complementary information in different modalities for learning more compact feature representations. Furthermore, the probabilistic pseudo label mining module utilizes the feature distances from action prototypes to estimate the likelihood of pseudo samples and rectify their corresponding labels for more reliable classification learning. Comprehensive experiments are conducted on different benchmarks and the experimental results show that our method achieves favorable performance with the state-of-the-art. [ABSTRACT FROM AUTHOR]

Metric-based methods achieve promising performance on few-shot classification by learning clusters on support samples and generating shared decision boundaries for query samples. However, existing methods ignore the inaccurate class center approximation introduced by the limited number of support samples, which consequently leads to biased inference. Therefore, in this paper, we propose to reduce the approximation error by class center calibration. Specifically, we introduce the so-called Pair-wise Similarity Module (PSM) to generate calibrated class centers adapted to the query sample by capturing the semantic correlations between the support and the query samples, as well as enhancing the discriminative regions on support representation. It is worth noting that the proposed PSM is a simple plug-and-play module and can be inserted into most metric-based few-shot learning models. Through extensive experiments in metric-based models, we demonstrate that the module significantly improves the performance of conventional few-shot classification methods on four few-shot image classification benchmark datasets. Codes are available at: https://github.com/PRIS-CV/Pair-wise-Similarity-module. [ABSTRACT FROM AUTHOR]

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios. [ABSTRACT FROM AUTHOR]

Latent subspace learning aims to produce a latent representation for better reconstruction and classification from high-dimensional data through exploiting the optimal subspace. Current latent subspace learning methods commonly have three problems: 1) The discriminative property is ignored when learning the latent subspace, 2) The redundancy exists between the latent subspace and the prediction space, 3) There is no unified latent subspace that exploits knowledge jointly from the raw space, latent subspace, and label space. In this paper, we formulate the Joint Discriminative Latent Subspace Learning (JDLSL) problem to address these issues, and provide its optimization solution. JDLSL learns image representation from two aspects: a) the joint learning of latent subspaces for data reconstruction and prediction, b) the joint learning of label space and latent subspace for data reconstruction. To integrate knowledge from the joint learning, we organize the sparsity-induced latent subspace, where row-sparsity and column sparsity are simultaneously imposed. We provide the theoretical proof for the discriminativity learning ability of the sparsity-induced latent subspace. Extensive experiments and comparisons with the state-of-the-art showed that the proposed method has better performance. JDLSL shows a competitive performance with deep features compared to deep learning architectures, reflecting it potential integrating with deep learning. [ABSTRACT FROM AUTHOR]