Vector Concatenation Research Articles

Label-semantics enhanced multi-layer heterogeneous graph convolutional network for Aspect Sentiment Quadruplet Extraction

Aspect-based sentiment analysis (ABSA) is a pivotal area within natural language processing (NLP) that focuses on extracting fine-grained sentiment information from text. A particularly demanding task within ABSA is Aspect Sentiment Quadruplet Extraction (ASQE), which aims to identify quadruplets comprising aspect terms, their corresponding opinion terms, sentiment polarity, and categories. This level of analysis is crucial for downstream applications such as sentiment monitoring and user experience research, offering nuanced insights into textual data. However, current methodologies fall short of fully leveraging the rich linguistic features of sentences and the semantic information of labels embedded within sentences. To address this gap, this paper introduces a novel framework, the Label-Semantics Enhanced Multi-layer Heterogeneous Graph Convolutional Network (LSEMH-GCN), specifically designed for ASQE. Our model integrates sentence linguistic features and label semantics to construct a graph neural network tailored for this task. It employs a multi-layer graph convolutional network that synergizes various linguistic features, and utilizes Biaffine attention to enrich the label probability distribution for token pairs with semantic label information. Furthermore, our approach introduces a token pair vector concatenation strategy alongside an advanced asymmetric label tagging scheme to enhance quadruplet extraction. Comprehensive evaluations on benchmark datasets reveal that LSEMH-GCN significantly surpasses existing state-of-the-art models, establishing a new benchmark for ASQE. Our model achieves an average F1 score improvement of 15.52% and 12.30% on the Restaurant-ACOS and Laptop-ACOS datasets, respectively.

Slow feature subspace: A video representation based on slow feature analysis for action recognition

This paper proposes a new video representation for subspace-based action recognition. Traditional subspace-based methods represent a video as a subspace by applying principal component analysis (PCA) to its frames. However, this subspace might lead to an imprecise representation of actions, as PCA loses the temporal information of frames. Therefore, we introduce the slow feature subspace based on the slow feature analysis (SFA). SFA extracts a set of slow features of an input video by projecting the video frames onto the weight vectors that minimize the data variance over time. Motivated by these properties, several methods based on SFA were proposed for action recognition. However, they do not explicitly consider the distribution of the slow features, which represents essential action information. Therefore, our key idea is to capture this distribution through a low-dimensional subspace called slow feature subspace. Our subspace is generated by applying PCA to several weight vectors corresponding to the slowest components obtained by SFA. Our framework replaces the subspaces of several traditional mutual subspace methods with our slow feature subspace to improve their results in action recognition. This approach transforms the comparison between two videos into the comparison between two slow feature subspaces using the canonical angles between them, avoiding vector concatenation and data aggregation. The effectiveness of our framework is demonstrated through extensive experiments with various datasets. Our results show that our slow feature subspace can improve the traditional subspace-based methods and achieve competitive performance compared to different methods, including state-of-the-art neural networks.

FT-FVC: fast transformation-based feature vector concatenation for time series classification

FT-FVC: fast transformation-based feature vector concatenation for time series classification

Input-Output-Improved Reservoir Computing Based on Duffing Resonator Processing Dynamic Temperature Compensation for MEMS Resonant Accelerometer.

An MEMS resonant accelerometer is a temperature-sensitive device because temperature change affects the intrinsic resonant frequency of the inner silicon beam. Most classic temperature compensation methods, such as algorithm modeling and structure design, have large errors under rapid temperature changing due to the hysteresis of the temperature response of the accelerometer. To address this issue, we propose a novel reservoir computing (RC) structure based on a nonlinear silicon resonator, which is specifically improved for predicting dynamic information that is referred to as the input-output-improved reservoir computing (IOI-RC) algorithm. It combines the polynomial fitting with the RC on the input data mapping ensuring that the system always resides in the rich nonlinear state. Meanwhile, the output layer is also optimized by vector concatenation operation for higher memory capacity. Therefore, the new system has better performance in dynamic temperature compensation. In addition, the method is real-time, with easy hardware implementation that can be integrated with MEMS sensors. The experiment's result showed a 93% improvement in IOI-RC compared to raw data in a temperature range of -20-60 °C. The study confirmed the feasibility of RC in realizing dynamic temperature compensation precisely, which provides a potential real-time online temperature compensation method and a sensor system with edge computing.

Disease Classification Model Based on Multi-Modal Feature Fusion

Aiming at the application of classification tasks in deep learning in disease classification, this paper proposes a disease classification model based on multi-modal feature fusion. In this model, chest X-ray images of patients are used as image modal data, and corresponding disease descriptions are used as text modal data. By innovatively pro-posing an adaptive multi-modal attention mechanism, the feature vectors extracted from the two modal data are fused for classification by classifier. In order to verify the effectiveness of the proposed model in disease classification, this paper uses Chest X-ray dataset in open I database. In order to solve the problem of small sample size and unbalanced sample categories in this dataset, SMOTE algorithm is used to expand the samples and ablation study is designed to compare the model effects. The results show that the model based on both image and text modes and sample expansion by SMOTE algorithm can solve the problems of overfitting, low recall and F1 value due to small samples and unbalanced samples. In addition, the classification accuracy of multi-modal model using image and text is improved by about 0.55% and 2.69% respectively compared with single-modal model using only image or text. Similarly, the addition of adaptive multi-modal attention mechanism also improves the classification effect of the model by about 0.41% compared with the feature fusion method using vector concatenation simply.

Transparency Order and Cross-Correlation Analysis of Boolean Functions

Transparency order is considered to be a cryptographically significant property that characterizes the resistance of S-boxes in opposition to differential power analysis attacks. The S-box having low transparency order is more resistant to these attacks. Until now, little attempts have been noticed to examine theoretically the transparency order and its relationship with other cryptographic properties. All constructions associated with transparency order are relying on search algorithms. In this paper, we discuss the new interpretation of bent functions in terms of their transparency order. Using the concept of vector concatenation and correlation characteristics, we find the transparency order of Boolean functions. The notion of complementary transparency order is given. For a pair of Boolean functions, we interpret complementary transparency order by their Walsh-Hadamard transform. We establish a relationship of transparency order with cross-correlation for a pair of Boolean functions. We find a relationship of transparency order with <img src=image/13428361_01.gif>−variable decomposition bent functions. We generalize the bounds on sum-of-squares of autocorrelation in terms of transparency order of Boolean functions using Walsh-Hadamard spectra. Further the transparency order of a function fulfilling the propagation criterion about a linear subspace is evaluated.

Improving Recognition of SIBI Gesture by Combining Skeleton and Hand Shape Features

SIBI (Sign System for Indonesian Language) is an official sign language system used in school for hearing impairment students in Indonesia. This work uses the skeleton and hand shape features to classify SIBI gestures. In order to improve the performance of the gesture classification system, we tried to fuse the features in several different ways. The accuracy results achieved by the feature fusion methods are, in descending order of accuracy: 88.016%, when using sequence-feature-vector concatenation, 85.448% when using Conneau feature vector concatenation, 83.723% when using feature-vector concatenation, and 49.618% when using simple feature concatenation. The sequence-feature-vector concatenation techniques yield noticeably better results than those achieved using single features (82.849% with skeleton feature only, 55.530% for the hand shape feature only). The experiment results show that the combined features of the whole gesture sequence can better distinguish one gesture from another in SIBI than the combined features of each gesture frame. In addition to finding the best feature combination technique, this study also found the most suitable Recurrent Neural Network (RNN) model for recognizing SIBI. The models tested are 1-layer, 2-layer LSTM, and GRU. The experimental results show that the 2-layer bidirectional LSTM has the best performance.

Set-Valued Shadow Matching Using Zonotopes for 3D-Map-Aided GNSS Localization

<h3>Abstract</h3> Unlike many urban localization methods that return point-valued estimates, a set-valued representation enables robustness by ensuring that a continuum of possible positions obeys safety constraints. One strategy with the potential for set-valued estimation is GNSS-based shadow matching (SM) in which one uses a three-dimensional (3D) map to compute GNSS shadows (where line-of-sight is blocked). However, SM requires a point-valued grid for computational tractability, with accuracy limited by grid resolution. We propose zonotope shadow matching (ZSM) for set-valued 3D-map-aided GNSS localization. ZSM represents buildings and GNSS shadows using constrained zonotopes, a convex polytope representation that enables propagating set-valued estimates using fast vector concatenation operations. Starting from a coarse set-valued position, ZSM refines the estimate depending on the receiver being inside or outside each shadow as judged by received carrier-to-noise density. We demonstrate our algorithm’s performance using simulated experiments on a simple 3D example map and on a dense 3D map of San Francisco.

Investor Sentiment Combined with Multisource Information to Predict Stock Prices: An Analysis of China’s A-Share Market

Investor sentiment has been widely used in the research of the stock market, and how to accurately measure investor sentiment is still being explored. With the rise of social media, investor sentiment is no longer only influenced by macroeconomic data and news media, but also guided by We-Media and fragmented information. We take the data of China A-shares from January 2020 to December 2020 as the research object and propose a stock price prediction method that combines investor sentiment with multisource information. Firstly, the sentiment of macroeconomic data, brokerage research reports, news, and We-Media is calculated, respectively, and then the investor sentiment vector combining multisource information is obtained by the multilayer perceptron. Finally, the LSTM model is used to represent the stock time series characteristics. The results show that (1) the proposed algorithm is superior to the benchmark algorithm in terms of accuracy and F1-score, (2) investor sentiment vector can effectively measure the investment sentiment of stocks, and (3) compared with vector concatenation, multilayer perceptron can better represent investor sentiment.

A hybrid approach to building face shape classifier for hairstyle recommender system

Identifying human face shape is the first and the most vital process prior to choosing the right hairstyle to wear on according to guidelines from hairstyle experts, especially for women. This work presents a novel framework for a hairstyle recommender system that is based on face shape classifier. This framework enables an automatic hairstyle recommendation with a single face image. This has a direct impact on beauty industry service providers. It can simulate how the user looks like when she is wearing the chosen hairstyle recommended by the expert system. The model used in this framework is based on Support Vector Machine. The framework is evaluated on hand-crafted, deep-learned (VGG-face) features and VGG-face fine-tuned version for the face shape classification task. In addition to evaluating these individual features by a well-designed framework, we attempted to fuse these three descriptors together in order to improve the performance of the classification task. Two combination techniques were employed, namely: Vector Concatenation and Multiple Kernel Learning (MKL) techniques. All the hyper-parameters of the model were optimised by using Particle Swarm Optimisation. The results show that combining hand-crafted and VGG-face descriptors with MKL yielded the best results at 70.3% of accuracy which was statistically significantly better than using individual features. Thus, combining multiple representations of the data with MKL can improve the overall performance of the expert system. In addition, this proves that hand-crafted descriptor can be complementary to deep-learned descriptor.

Object recognition combining vision and touch

This paper explores ways of combining vision and touch for the purpose of object recognition. In particular, it focuses on scenarios when there are few tactile training samples (as these are usually costly to obtain) and when vision is artificially impaired. Whilst machine vision is a widely studied field, and machine touch has received some attention recently, the fusion of both modalities remains a relatively unexplored area. It has been suggested that, in the human brain, there exist shared multi-sensorial representations of objects. This provides robustness when one or more senses are absent or unreliable. Modern robotics systems can benefit from multi-sensorial input, in particular in contexts where one or more of the sensors perform poorly. In this paper, a recently proposed tactile recognition model was extended by integrating a simple vision system in three different ways: vector concatenation (vision feature vector and tactile feature vector), object label posterior averaging and object label posterior product. A comparison is drawn in terms of overall accuracy of recognition and in terms of how quickly (number of training samples) learning occurs. The conclusions reached are: (1) the most accurate system is “posterior product”, (2) multi-modal recognition has higher accuracy to either modality alone if all visual and tactile training data are pooled together, and (3) in the case of visual impairment, multi-modal recognition “learns faster”, i.e. requires fewer training samples to achieve the same accuracy as either other modality.

Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

Multimodal diagnosis of epilepsy using conditional dependence and multiple imputation.

The definitive diagnosis of the type of epilepsy, if it exists, in medication-resistant seizure disorder is based on the efficient combination of clinical information, long-term video-electroencephalography (EEG) and neuroimaging. Diagnoses are reached by a consensus panel that combines these diverse modalities using clinical wisdom and experience. Here we compare two methods of multimodal computer-aided diagnosis, vector concatenation (VC) and conditional dependence (CD), using clinical archive data from 645 patients with medication-resistant seizure disorder, confirmed by video-EEG. CD models the clinical decision process, whereas VC allows for statistical modeling of cross-modality interactions. Due to the nature of clinical data, not all information was available in all patients. To overcome this, we multiply-imputed the missing data. Using a C4.5 decision tree, single modality classifiers achieved 53.1%, 51.5% and 51.1% average accuracy for MRI, clinical information and FDG-PET, respectively, for the discrimination between non-epileptic seizures, temporal lobe epilepsy, other focal epilepsies and generalized-onset epilepsy (vs. chance, p<0.01). Using VC, the average accuracy was significantly lower (39.2%). In contrast, the CD classifier that classified with MRI then clinical information achieved an average accuracy of 58.7% (vs. VC, p<0.01). The decrease in accuracy of VC compared to the MRI classifier illustrates how the addition of more informative features does not improve performance monotonically. The superiority of conditional dependence over vector concatenation suggests that the structure imposed by conditional dependence improved our ability to model the underlying diagnostic trends in the multimodality data.

Rate-Distortion Optimized Pixel-Based Motion Vector Concatenation for Reference Picture Selection

Reference picture selection (RPS) is a powerful error-control technique for video streaming. Previously, two fast block-based motion vector concatenation (MVC) algorithms were proposed for video transcoding based on forward dominant vector selection (FDVS) and activity dominant vector selection (ADVS). In this paper, we cast these algorithms in the rate-distortion (RD) optimization framework. We also present two novel RD optimized pixel-based MVC schemes for RPS. Experimental results indicate that the proposed methods provide higher video quality compared to both FDVS and ADVS. In addition, we study the complexity of various RPS algorithms as a function of the loss rate and round trip time.

Utterance partitioning with acoustic vector resampling for GMM–SVM speaker verification

Recent research has demonstrated the merit of combining Gaussian mixture models and support vector machine (SVM) for text-independent speaker verification. However, one unaddressed issue in this GMM–SVM approach is the imbalance between the numbers of speaker-class utterances and impostor-class utterances available for training a speaker-dependent SVM. This paper proposes a resampling technique – namely utterance partitioning with acoustic vector resampling (UP-AVR) – to mitigate the data imbalance problem. Briefly, the sequence order of acoustic vectors in an enrollment utterance is first randomized, which is followed by partitioning the randomized sequence into a number of segments. Each of these segments is then used to produce a GMM supervector via MAP adaptation and mean vector concatenation. The randomization and partitioning processes are repeated several times to produce a sufficient number of speaker-class supervectors for training an SVM. Experimental evaluations based on the NIST 2002 and 2004 SRE suggest that UP-AVR can reduce the error rate of GMM–SVM systems.

Computer-assisted pit-pattern classification in different wavelet domains for supporting dignity assessment of colonic polyps

In this paper, we show that zoom-endoscopy images can be well classified according to the pit-pattern classification scheme by using texture-analysis methods in different wavelet domains. We base our approach on three different variants of the wavelet transform and propose that the color channels of the RGB and LAB color model are an important source for computing image features with high discriminative power. Color-channel information is incorporated by either using simple feature vector concatenation and cross-cooccurrence matrices in the wavelet domain. Our experimental results based on k-nearest neighbor classification and forward feature selection exemplify the advantages of the different wavelet transforms and show that color-image analysis is superior to grayscale-image analysis regarding our medical image classification problem.

PMD fundamentals: polarization mode dispersion in optical fibers.

This paper reviews the fundamental concepts and basic theory of polarization mode dispersion (PMD) in optical fibers. It introduces a unified notation and methodology to link the various views and concepts in Jones space and Stokes space. The discussion includes the relation between Jones vectors and Stokes vectors, rotation matrices, the definition and representation of PMD vectors, the laws of infinitesimal rotation, and the rules for PMD vector concatenation.

Associative memory neural networks with concatenated vectors and nonzero diagonal terms

The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14 N, N being the length of the stored vectors.