Separate Representations Research Articles

Deep Learning-Based Speech Emotion Recognition Using Multi-Level Fusion of Concurrent Features

The detection and classification of emotional states in speech involves the analysis of audio signals and text transcriptions. There are complex relationships between the extracted features at different time intervals which ought to be analyzed to infer the emotions in speech. These relationships can be represented as spatial, temporal and semantic tendency features. In addition to emotional features that exist in each modality, the text modality consists of semantic and grammatical tendencies in the uttered sentences. Spatial and temporal features have been extracted sequentially in deep learning-based models using convolutional neural networks (CNN) followed by recurrent neural networks (RNN) which may not only be weak at the detection of the separate spatial-temporal feature representations but also the semantic tendencies in speech. In this paper, we propose a deep learning-based model named concurrent spatial-temporal and grammatical (CoSTGA) model that concurrently learns spatial, temporal and semantic representations in the local feature learning block (LFLB) which are fused as a latent vector to form an input to the global feature learning block (GFLB). We also investigate the performance of multi-level feature fusion compared to single-level fusion using the multi-level transformer encoder model (MLTED) that we also propose in this paper. The proposed CoSTGA model uses multi-level fusion first at the LFLB level where similar features (spatial or temporal) are separately extracted from a modality and secondly at the GFLB level where the spatial-temporal features are fused with the semantic tendency features. The proposed CoSTGA model uses a combination of dilated causal convolutions (DCC), bidirectional long short-term memory (BiLSTM), transformer encoders (TE), multi-head and self-attention mechanisms. Acoustic and lexical features were extracted from the interactive emotional dyadic motion capture (IEMOCAP) dataset. The proposed model achieves 75.50% and 75.82% of weighted and unweighted accuracy, 75.32% and 75.57% of recall and F1 score respectively. These results imply that concurrently learned spatial-temporal features with semantic tendencies learned in a multi-level approach improve the model’s effectiveness and robustness.

Selective Multibranch Attention Network With Material Constraint for Baggage Reidentification

Baggage reidentification (re-ID) expects to retrieve the unique baggage across multiple nonoverlapping cameras between the precheck and postcheck areas. This critical challenge task lies in two folds: intraclass dissimilarity by pose variations and interclass similarity due to the identical style. In this article, we solve the mentioned problems by a selective multibranch deep network (SMBNet) architecture with the attention mechanism. Specifically, SMBNet incorporates one branch for global feature representations and multiple-part representations corresponding to different local regions. Meanwhile, we plugged the attention block into the part branch to further help the network capture the dependence of the context on local features. Depending on the class response to each part, we propose an adaptive part selection (APS) to automatically select the appropriate part branch and joint with the global one to build a comprehensive baggage descriptor. It effectively blurs unreliable parts and significantly improves representational performance. Finally, we couple classification supervision and material signal in triplet loss to learn a discriminative embedding space that can compact class and material-invariant features and better separate specific representations. Extensive experiments demonstrate the superiority of SMBNet, which achieves 84.7% mean average precision (mAP) and 82.8% Rank-1 on the MVB dataset and significantly outperforms the state-of-the-art methods.

On the Bounded Partition Dimension of Some Generalised Graph Structures

Consider λ to be a connected graph with a vertex set V(λ) that may be partitioned into any partition set S. If each vertex in λ has a separate representation with regard to S and is an ordered k partition, then the set with S is a resolving partition of λ.. A partition dimension of λ, represented by pd, is the minimal cardinality of resolving k partitions of V(λ). The partition dimension of various generalised families of graphs, such as the Harary graph, Cayley graph, and Pendent graph, is given as a sharp upper bound in this article.

Analyzing Cell-Scaffold Interaction through Unsupervised 3D Nuclei Segmentation.

Fibrous scaffolds have been extensively used in three-dimensional (3D) cell culture systems to establish in vitro models in cell biology, tissue engineering, and drug screening. It is a common practice to characterize cell behaviors on such scaffolds using confocal laser scanning microscopy (CLSM). As a noninvasive technology, CLSM images can be utilized to describe cell-scaffold interaction under varied morphological features, biomaterial composition, and internal structure. Unfortunately, such information has not been fully translated and delivered to researchers due to the lack of effective cell segmentation methods. We developed herein an end-to-end model called Aligned Disentangled Generative Adversarial Network (AD-GAN) for 3D unsupervised nuclei segmentation of CLSM images. AD-GAN utilizes representation disentanglement to separate content representation (the underlying nuclei spatial structure) from style representation (the rendering of the structure) and align the disentangled content in the latent space. The CLSM images collected from fibrous scaffold-based culturing A549, 3T3, and HeLa cells were utilized for nuclei segmentation study. Compared with existing commercial methods such as Squassh and CellProfiler, our AD-GAN can effectively and efficiently distinguish nuclei with the preserved shape and location information. Building on such information, we can rapidly screen cell-scaffold interaction in terms of adhesion, migration and proliferation, so as to improve scaffold design.

Separable Algorithmic Representations of Classical Systems and Their Applications

The main results of the theory of separable algorithmic representations of classical algebraic systems are presented. The most important classes of such systems and their representations in the lower classes of the arithmetic hierarchy - positive and negative - are described. Special attention is paid to the algorithmic, structural and topological properties of separable representations of groups, rings and bodies, as well as to effective analogs of the Maltsev theorem on embedding rings in bodies. The possibilities of using the studied concepts in the framework of theoretical informatics are considered.

Using top-down modulation to optimally balance shared versus separated task representations

Human adaptive behavior requires continually learning and performing a wide variety of tasks, often with very little practice. To accomplish this, it is crucial to separate neural representations of different tasks in order to avoid interference. At the same time, sharing neural representations supports generalization and allows faster learning. Therefore, a crucial challenge is to find an optimal balance between shared versus separated representations. Typically, models of human cognition employ top-down modulatory signals to separate task representations, but there exist surprisingly little systematic computational investigations of how such modulation is best implemented. We identify and systematically evaluate two crucial features of modulatory signals. First, top-down input can be processed in an additive or multiplicative manner. Second, the modulatory signals can be adaptive (learned) or non-adaptive (random). We cross these two features, resulting in four modulation networks which are tested on a variety of input datasets and tasks with different degrees of stimulus-action mapping overlap. The multiplicative adaptive modulation network outperforms all other networks in terms of accuracy. Moreover, this network develops hidden units that optimally share representations between tasks. Specifically, different than the binary approach of currently popular latent state models, it exploits partial overlap between tasks.

A separated representation involving multiple time scales within the Proper Generalized Decomposition framework

Solutions of partial differential equations can exhibit multiple time scales. Standard discretization techniques are constrained to capture the finest scale to accurately predict the response of the system. In this paper, we provide an alternative route to circumvent prohibitive meshes arising from the necessity of capturing fine-scale behaviors. The proposed methodology is based on a time-separated representation within the standard Proper Generalized Decomposition, where the time coordinate is transformed into a multi-dimensional time through new separated coordinates, each representing one scale, while continuity is ensured in the scale coupling. For instance, when considering two different time scales, the governing Partial Differential Equation is commuted into a nonlinear system that iterates between the so-called microtime and macrotime, so that the time coordinate can be viewed as a 2D time. The macroscale effects are taken into account by means of a finite element-based macro-discretization, whereas the microscale effects are handled with unidimensional parent spaces that are replicated throughout the time domain. The resulting separated representation allows us a very fine time discretization without impacting the computational efficiency. The proposed formulation is explored and numerically verified on thermal and elastodynamic problems.

Retrospectiva știrilor false asupra evenimentelor din regiunea transnistreană din anul 1992: abordări comparative / Retrospective of false news on events in the Transnistrian region since 1992: comparative approaches

The analysis of the problem of false news and other media constructions is based on quantitative research, which shows the distribution of published materials in Chisinau and the Russian Federation. In these media, the materials addressed the topics regarding the events on the Dniester in 1992 in a negative, neutral or positive way. The qualitative research aims to describe the content of the articles divided into separate thematic blocks, sub-themes, and representation sections. The media construction of the events of the Dniester War in 1992 in the written and online press in the Republic of Moldova is contradictory. The Russian press and the left-wing press contribute to the false and erroneous perception that the phenomenon is known as „Transnistrian conflict” is a civil one, and that it is not Russia but Transnistria that is a „party” to the conflict, that Russia has the status of a neutral mediator and guarantor of the agreements between the parties and the provisions of the Memorandum on normalizing relations between the Republic of Moldova and Transnistria signed in 1997 in Moscow.

Representation of Different Types of Adjectival Polysemy in the Mental Lexicon.

We studied mental representations of literal, metonymically different, and metaphorical senses in Russian adjectives. Previous studies suggested that in polysemous words, metonymic senses, being more sense-related, were stored together with literal senses, whereas more distant metaphorical senses had separate representations. We hypothesized that metonymy may be heterogeneous with respect to its mental storage. “Whole-part” metonymy (“sad person” – “sad eyes”), which is cognitively closer to the literal sense and more regular, should be stored differently from temporal, causal or resultative metonymy (“sad person” – “sad time;” “sad person” – “sad news;” “lead.ADJ ball” – “lead.ADJ poisoning”), which is irregular and semantically distant from the literal sense. We conducted an online experiment with semantic clustering task in which the participants were asked to classify sentences with a literal, proximal metonymic, distal metonymic, or metaphorical sense of an adjective into virtual baskets so that sentences with the same perceived sense were put in the same basket. Our results showed that proximal metonymies were grouped together with the literal sense and with each other more often than with distal metonymies and metaphors. Distal metonymies, in turn, were grouped with literal senses more often than with metaphors. Overall, we concluded that literal senses and proximal metonymies were stored in single representations, distal metonymies formed hybrid representations with literal senses, and metaphors were stored separately from literal senses. Additionally, we discovered that perception of semantic differences is affected by the surrounding senses: distal metonymies were more discernible from literal senses when presented with proximal metonymies, and less so when presented with metaphors.

Fast computation of the multidimensional fractional Laplacian

The paper discusses new cubature formulas for the Riesz potential and the fractional Laplacian , , in the framework of the method approximate approximations. This approach, combined with separated representations, makes the method successful also in high dimensions. We prove error estimates and report on numerical results illustrating that our formulas are accurate and provide the predicted convergence rate 2, 4, 6, 8 up to dimension .

Enhanced parametric shape descriptions in PGD-based space separated representations

Space separation within the Proper Generalized Decomposition—PGD—rationale allows solving high dimensional problems as a sequence of lower dimensional ones. In our former works, different geometrical transformations were proposed for addressing complex shapes and spatially non-separable domains. Efficient implementation of separated representations needs expressing the domain as a product of characteristic functions involving the different space coordinates. In the case of complex shapes, more sophisticated geometrical transformations are needed to map the complex physical domain into a regular one where computations are performed. This paper aims at proposing a very efficient route for accomplishing such space separation. A NURBS-based geometry representation, usual in computer aided design—CAD—, is retained and combined with a fully separated representation for allying efficiency (ensured by the fully separated representations) and generality (by addressing complex geometries). Some numerical examples are considered to prove the potential of the proposed methodology.

Cross-Dialectal Novel Word Learning and Borrowing.

The objective of this paper was to study the cognitive processes underlying cross-dialectal novel word borrowing and loanword establishment in a Standard-Chinese-to-Shanghainese (SC-SH) auditory lexical learning and borrowing experiment. To investigate these underlying cognitive processes, SC-SH bi-dialectals were compared with SC monolectals as well as bi-dialectals of SC and other Chinese dialects (OD) to investigate the influence of short-term and long-term linguistic experience. Both comprehension and production borrowings were tested. This study found that early and proficient bi-dialectism, even if it is not directly related to the recipient dialect of lexical borrowing, has a protective effect on the ability of cross-dialectal lexical borrowing in early adulthood. Bi-dialectals tend to add separate lexical representations for incidentally encountered dialectal variants, while monolectals tend to assimilate dialectal variants to standard forms. Bi-dialectals, but not monolectals, use etymologically related morphemes between the source and recipient dialects to create nonce-borrowing compounds. Dialectal variability facilitates lexical borrowing via enriching instead of increasing the short-term lexical experience of learners. The long-term bi-dialectal experience of individuals, as well as their short-term exposure to each specific loanword, may collectively shape the route of lexical evolution of co-evolving linguistic varieties.

Bevacizumab-Induced Tumor Vasculature Normalization and Sequential Chemotherapy in Colorectal Cancer: An Interesting and Still Open Question.

Bevacizumab is a recombinant fully humanized IgG1 targeting the Vascular Endothelial Growth Factor A (VEGF-A). The rationale of its use in oncology relies on the critical role of VEGF-A-induced neo-angiogenesis in the growth of many solid tumors (1–3). Since its discovery, many evidences suggested that it did not display direct antitumor action but rather contributes to improve the effects of associated chemotherapy. In fact, following bevacizumab administration, intratumoral vessels become morphologically more organized, and hypoxia and interstitial fluid pressure reduce (“vasculature normalization”); as a consequence, chemotherapy drug delivery into tumor masses ameliorates (4). Avallone et al. published the first randomized phase III study (OBELICS study) comparing the sequential administration of bevacizumab before standard oxaliplatin-based chemotherapy versus a traditional concomitant regimen in metastatic colorectal cancer (CRC) (5). The intent was to optimize bevacizumab and chemotherapy association by administering the chemotherapy in the “normalization window” and ameliorate the antitumor effects. The “normalization window” is the time window during which the anarchist texture of tumor vasculature becomes macroscopically more linear and less dense (1–4) ( Figure 1 ). The authors fail to meet the primary end-point based on a difference in objective response rate (ORR) between the two arms. The odds ratio of response for experimental (ORR: 56.5%) versus standard arm (ORR: 57.4%) was 0.96 (95% CI: 0.55–1,68, P=0.89). We would add insights and prompt discussion making hypotheses on the causes of failure. This is important for scientific discussion and for planning future trials. Open in a separate window Figure 1 Schematic representation of the “normalization window” of anti-angiogenic treatment of tumor masses during time and space.

PROTECTING THE CHILD VICTIM IN SEXUAL OFFENCES: IS THERE A NEED FOR SEPARATE LEGAL REPRESENTATION?

The number of children being sexually violated on a daily basis continues to escalate against a backdrop of a dearth in the conviction rate of their attackers. This is notwithstanding global efforts being made to protect children from the harrowing experience of being sexually violated. Creative measures such as the introduction of innovative child legislation have been largely neutralized by the inability of the criminal justice system to complement the child’s healing process. The gulf between policy and practice has given rise to a lack of protection in respect of the rights of children. In this paper, we seek to highlight the gaps in the South African criminaljustice system when it comes to safeguarding the interests of the minor complainant during the criminal process. We analyse key legislative instruments which purport to protect the minor victim. The analysis is aimed at determining whether or not the specified key provisions are in conflict with the Constitution. The introduction of separate legal representatives for child complainants is evaluated as an option in improving the plight of young child victims. The paper then concludes on an optimistic note by boldly opining that in line with legal developments in other international jurisdictions, the South African criminal justice system can accommodate the legal novelty of introducing separate legal representation for child victims.

A proper generalized decomposition based Padé approximant for stochastic frequency response analysis

AbstractThis article presents a proper generalized decomposition (PGD) based Padé approximant for efficient analysis of the stochastic frequency response. Due to the high nonlinearity of the stochastic response with respect to the input uncertainties, the classical stochastic Galerkin (SG) method utilizing polynomial chaos exhibits slow convergence near the resonance. Furthermore, the dimension of the SG method is the product of deterministic and stochastic approximation spaces, and hence resolution over a banded frequency range is computationally expensive or even prohibitive. In this study, to tackle these problems, the PGD first generates the solution of stochastic frequency equations as a separated representation of deterministic and stochastic components. For the banded frequency range computations, the deterministic vectors are exploited as a reduced basis in conjunction with singular value decomposition. Subsequently, the Padé approximant is applied based on the PGD solution, and the stochastic frequency response is represented by a rational function. Through various numerical studies, it is demonstrated that the proposed framework improves not only the accuracy in the vicinity of resonance but also the computational efficiency, compared with the SG method.

If I do A, B will happen: Dissecting circuits detecting causal relations between actions and outcomes in marmoset prefrontal cortex

In this issue of Neuron, Duan etal. (2021) use pharmacological manipulation to reveal opposing influences of anterior cingulate and orbitofrontal cortex of marmosets on decisions that are based on action-outcome associations.

Old Rebellions, New Minorities: Ma Family Leaders and Debates Over Communal Representation Following the Xinhai Rebellion, 1911

ABSTRACT Following the 1911 Xinhai Rebellion, the new leadership began to stress the fundamental unity of the peoples of the new Republic of China, even as newspaper commentaries foretold the need for separate Muslim representation as the only way to buy the participation of that constituency in the new state. Influential Chinese Muslim military leaders controlled much of the northwest; their participation in the new state was crucial to its survival. However, whilst the legacies of a nineteenth century process of minoritization meant it was often assumed Muslims would want either separate representation or independence, separate representation was never a cause the northwestern leadership truly espoused. Instead, although figures such as Ma Anliang, Ma Bufang and Ma Fuxiang were recognized unofficially as ‘Muslim leaders’, they promoted themselves as experts on other minorities, and as guardians of the integrity of the old, multi-ethnic space that had been the Qing empire. This article argues that in rejecting their own minoritization, the Chinese Muslim leaders sought to ensure the place of other minorities – Tibetan, Mongolian, Turkic – in the emerging framework of the Chinese Nationalist state, often with great violence. Only then could they be afforded space within that new state as one minority among others.

Smooth aggregation of Bayesian experts

I study the ex-ante aggregation of preferences of Bayesian agents in a purely subjective framework. I relax the assumption of a Bayesian social preference while keeping the Pareto condition. Under a simple axiom that relates society's preference to those of the agents, I obtain an additively separable representation of society's preference. Adding an ambiguity aversion axiom I obtain a representation that resembles the Smooth Ambiguity Criterion of Klibanoff et al. (2005). I then briefly consider applications of this framework to inequality and treatment choice under ambiguity.

Impact of Water Extraction on Malonamide Aggregation: A Molecular Dynamics and Graph Theoretic Approach.

Solution structure in liquid-liquid extraction affects the efficacy of separation; however, even for simplified organic phases, structural characterization and attribution of aggregation to intermolecular interactions are fundamental challenges. We investigate water uptake into organic phases for two malonamides commonly applied to actinide and lanthanide separations. Extracted water induces reorganization of the amphiphilic extractant molecules, although we find this rearrangement is not strongly manifested in small-angle X-ray scattering making it challenging to probe without methods such as atomistic simulation. Using a graph theoretic approach to define hydrogen bonded water/malonamide aggregates from molecular dynamics simulations, we find evidence of a characteristic aggregate size by water number that results from geometric accommodation of the surrounding malonamide molecules. This implies a degree of size selectivity inherent to these water-in-oil aggregates. Conversely, we find no evidence of a characteristic size of the aggregates with respect to their malonamide number. By defining a separate graphical representation of self-association of the amphiphilic malonamides, we quantify how water affects the local and nonlocal topology of the malonamide network, providing a basis for characterization of the structure and impact of polar solutes in increasingly complex organic phases.

Variational formulation of stationary two-phase flow distribution

This paper discusses the extremisation of the entropy production in fluidic networks to gain insight into using non-equilibrium thermodynamics for mathematically formulating thermal engineering transfer phenomena. In the study, a variational formulation of the two-phase flow distribution in a fluidic junction is developed. Moreover, based on the flow representation, it is shown that the flow is distributed such that the entropy production rate is either maximised or minimised. Specifically, considering a homogeneous representation of the flow in an adiabatic fluidic network, the flow rates are distributed to maximize the entropy generation rate. Contrarily, when a separate flow representation is adopted, the stationary flow rates are distributed to yield the minimum entropy generation rate. Additionally, various characteristics which affect the flow distribution ratio and phase separation, such as the geometric imbalance, the gravitational static head, the total inlet mass flux, different thermo-physical properties of the fluid, and a generalised number of parallel branches are explored. This supports the possibility of relying on non-equilibrium thermodynamics, instead of introducing case-specific empirical correlations, for obtaining general mathematical formulations of thermal engineering transfer phenomena.