Qualitative analysis of goat and sheep production data using self-organizing maps

Abstract: The aim of this study was to analyse the relationship between different small ruminant livestock production systems with different levels of specialization. The analysis is carried out by using the self-organizing map. This tool allows high-dimensional input spaces to be mapped into much lower-dimensional spaces, thus making it much more straightforward to understand any set of data. These representations enable the visual extraction of qualitative relationships among variables (visual data mining), converting the data to maps. The data used in this study were obtained from surveys completed by farmers who are principally dedicated to goat and sheep production. With the self-organizing map we found a relationship between qualitative and quantitative variables showing that more specialized farms have greater milk incomes per goat, highlighting farms that have a greater number of animals, better facilities (including milking machines) or animals fed with elaborated diets. The use of self-organizing maps for the analysis of this kind of data has proven to be highly valuable in extracting qualitative conclusions and in guiding improvements in farm performance.     

A formal framework to represent spatial knowledge

Visual representations are an essential element in human–computer interaction and can be conceived as a collection of graphical objects arranged in a two-dimensional space. It is quite natural to model visual representations through the qualitative relationships holding between their objects, and therefore, qualitative spatial relations are a fundamental way of representing spatial knowledge. To this aim, in this paper we present a framework of qualitative spatial relations providing a general, domain-independent approach to specify visual representations.     

Personal authentication using multiple palmprint representation

Although several palmprint representations have been proposed for personal authentication, there is little agreement on which palmprint representation can provide best representation for reliable authentication. In this paper, we characterize user's identity through the simultaneous use of three major palmprint representations and achieve better performance than either one individually. This paper also investigates comparative performance between Gabor, line and appearance based palmprint representations and using their score and decision level fusion. The combination of various representations may not always lead to higher performance as the features from the same image may be correlated. Therefore we also propose product of sum rule which achieves better performance than any other fixed combination rules. Our experimental results on the database of 100 users achieve 34.56% improvement in performance (equal error rate) as compared to the case when features from single palmprint representation are employed. The proposed usage of multiple palmprint representations, especially on the peg-free and non-contact imaging setup, achieves promising results and demonstrates its usefulness.     

Bayesian network modelling through qualitative patterns

In designing a Bayesian network for an actual problem, developers need to bridge the gap between the mathematical abstractions offered by the Bayesian-network formalism and the features of the problem to be modelled. Qualitative probabilistic networks (QPNs) have been put forward as qualitative analogues to Bayesian networks, and allow modelling interactions in terms of qualitative signs. They thus have the advantage that developers can abstract from the numerical detail, and therefore the gap may not be as wide as for their quantitative counterparts. A notion that has been suggested in the literature to facilitate Bayesian-network development is causal independence. It allows exploiting compact representations of probabilistic interactions among variables in a network. In the paper, we deploy both causal independence and QPNs in developing and analysing a collection of qualitative, causal interaction patterns, called QC patterns. These are endowed with a fixed qualitative semantics, and are intended to offer developers a high-level starting point when developing Bayesian networks.     

基于注意力机制的混合神经网络关系分类方法

关系分类是自然语言处理领域的一项重要语义处理任务。传统的关系分类方法通过人工设计各类特征以及各类核函数来对句子内部2个实体之间的关系进行判断。近年来,关系分类方法的主要工作集中于通过各类神经网络获取句子的语义特征表示来进行分类,以减少手动构造各类特征。在句子中,不同关键词对关系分类任务的贡献程度是不同的,然而重要的词义有可能出现在句子中的任意位置。为此,提出了一种基于注意力的混合神经网络关系分类模型来捕获重要的语义信息,用来进行关系分类,该方法是一种端到端的方法。实验结果表明了该方法的有效性。     

Neural generators of sparse local linear models for achieving both accuracy and interpretability

For reliability, it is important for the predictions made by machine learning methods to be interpretable by humans. In general, deep neural networks (DNNs) can provide accurate predictions, although it is difficult to interpret why such predictions are obtained by the DNNs. On the other hand, interpretation of linear models is easy, although their predictive performance is low because real-world data are often intrinsically non-linear. To combine both the benefits of the high predictive performance of DNNs and the high interpretability of linear models into a single model, we propose neural generators of sparse local linear models (NGSLL). Sparse local linear models have high flexibility because they can approximate non-linear functions. NGSLL generates sparse linear weights for each sample using DNNs that take the original representations of each sample (e.g., word sequence) and their simplified representations (e.g., bag-of-words) as input. By extracting features from the original representations, the weights can contain rich information and achieve a high predictive performance. In addition, the prediction is interpretable because it is obtained through the inner product between the simplified representations and the sparse weights, where only a small number of weights are selected by our gate module in NGSLL. In experiments on image, text and tabular datasets, we demonstrate the effectiveness of NGSLL quantitatively and qualitatively by evaluating the prediction performance and visualizing generated weights.     

Multi-scale qualitative location: A direction-based model

Qualitative locations describe the locations of spatial objects by relating them to a reference frame with qualitative relations. Existing models concerned with regional partitions are mainly topology-based and do not consider the effects of scale changes on locations. This study develops a direction-based multi-scale qualitative location (DMQL) model to fill this gap. First, a cell partition is defined by extending the borders of the minimum bounding rectangles of the regions in a regional partition. Relating spatial objects to all regions by a set of directions is equal to representing the objects as a set of cells in a cell partition. Second, due to the multiple cell representations of spatial objects and the changes in direction relations across scales, some approaches are presented to derive the direction changes between regions in different frames, between spatial objects and regions, and between spatial objects at different scales. Third, the location and relation consistencies of qualitative locations are evaluated based on the cell representations of spatial objects at multiple scales through a case study. The results indicate that the DMQL model can locate objects more precisely than the topology-based models.     

Indexing and Integrating Multiple Features for WWW Images

In this paper, we present a novel indexing technique called Multi-scale Similarity Indexing (MSI) to index image's multi-features into a single one-dimensional structure. Both for text and visual feature spaces, the similarity between a point and a local partition's center in individual space is used as the indexing key, where similarity values in different features are distinguished by different scale. Then a single indexing tree can be built on these keys. Based on the property that relevant images have similar similarity values from the center of the same local partition in any feature space, certain number of irrelevant images can be fast pruned based on the triangle inequity on indexing keys. To remove the “dimensionality curse” existing in high dimensional structure, we propose a new technique called Local Bit Stream (LBS). LBS transforms image's text and visual feature representations into simple, uniform and effective bit stream (BS) representations based on local partition's center. Such BS representations are small in size and fast for comparison since only bit operation are involved. By comparing common bits existing in two BSs, most of irrelevant images can be immediately filtered. To effectively integrate multi-features, we also investigated the following evidence combination techniques—Certainty Factor, Dempster Shafer Theory, Compound Probability, and Linear Combination. Our extensive experiment showed that single one-dimensional index on multi-features improves multi-indices on multi-features greatly. Our LBS method outperforms sequential scan on high dimensional space by an order of magnitude. And Certainty Factor and Dempster Shafer Theory perform best in combining multiple similarities from corresponding multiple features.     

A neural network architecture for visual selection

This article describes a parallel neural net architecture for efficient and robust visual selection in generic gray-level images. Objects are represented through flexible star-type planar arrangements of binary local features which are in turn star-type planar arrangements of oriented edges. Candidate locations are detected over a range of scales and other deformations, using a generalized Hough transform. The flexibility of the arrangements provides the required invariance. Training involves selecting a small number of stable local features from a predefined pool, which are well localized on registered examples of the object. Training therefore requires only small data sets. The parallel architecture is constructed so that the Hough transform associated with any object can be implemented without creating or modifying any connections. The different object representations are learned and stored in a central module. When one of these representations is evoked, it "primes" the appropriate layers in the network so that the corresponding Hough transform is computed. Analogies between the different layers in the network and those in the visual system are discussed. Furthermore, the model can be used to explain certain experiments on visual selection reported in the literature.     

DIRECTIONS FOR QUALITATIVE REASONING

Sacks & Doyle provide an excellent overview of the fundamental limitations of the SPQR representations for reasoning about the qualitative properties of dynamic systems. We take this opportunity to outline some new directions for qualitative reasoning. In this paper, we provide a rigorous mathematical characterization for the term "qualitative property" in the context of static and dynamic systems. Based on these characterizations, we show that interval representations are well suited for reasoning about the qualitative properties of static systems such as qualitative comparative statics and qualitative stability. Moreover, we also show that symbolic computations help in the derivation of useful global properties of dynamic systems which can be used to guide numerical sampling of differential equations. The integration of symbolic and numeric methods provides a powerful approach for automating the qualitative analysis of differential equations.     

Multiple representations, similarity matching, and results fusion for content-based image retrieval

In this paper, we show how the use of multiple content representations and their fusion can improve the performance of content-based image retrieval systems. We consider the case of texture and propose a new algorithm for texture retrieval based on multiple representations and their results fusion. Texture content is modeled using two different models: the well-known autoregressive model and a perceptual model based on perceptual features such as coarseness and directionality. In the case of the perceptual model, two viewpoints are considered: perceptual features are computed based on the original images viewpoint and on the autocovariance function viewpoint (corresponding to original images). So we consider a total of three content representations. The similarity measure used is based on Gower's index of similarity. Simple results of the fusion models are used to merge search results returned by different representations. Experimentations and benchmarking carried out on the well-known Brodatz database show a drastic improvement in search effectiveness with the fused model without necessarily altering their efficiency in an important way.     

Phonetic-enriched text representation for Chinese sentiment analysis with reinforcement learning

The Chinese pronunciation system offers two characteristics that distinguish it from other languages: deep phonemic orthography and intonation variations. In this paper, we hypothesize that these two important properties can play a major role in Chinese sentiment analysis. In particular, we propose two effective features to encode phonetic information and, hence, fuse it with textual information. With this hypothesis, we propose Disambiguate Intonation for Sentiment Analysis (DISA), a network that we develop based on the principles of reinforcement learning. DISA disambiguates intonations for each Chinese character (pinyin) and, hence, learns precise phonetic representations. We also fuse phonetic features with textual and visual features to further improve performance. Experimental results on five different Chinese sentiment analysis datasets show that the inclusion of phonetic features significantly and consistently improves the performance of textual and visual representations and surpasses the state-of-the-art Chinese character-level representations.     

Invariant object recognition in the visual system with novel views of 3D objects

To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.     

Robust Structure‐Based Shape Correspondence

We present a robust method to find region‐level correspondences between shapes, which are invariant to changes in geometry and applicable across multiple shape representations. We generate simplified shape graphs by jointly decomposing the shapes, and devise an adapted graph‐matching technique, from which we infer correspondences between shape regions. The simplified shape graphs are designed to primarily capture the overall structure of the shapes, without reflecting precise information about the geometry of each region, which enables us to find correspondences between shapes that might have significant geometric differences. Moreover, due to the special care we take to ensure the robustness of each part of our pipeline, our method can find correspondences between shapes with different representations, such as triangular meshes and point clouds. We demonstrate that the region‐wise matching that we obtain can be used to find correspondences between feature points, reveal the intrinsic self‐similarities of each shape and even construct point‐to‐point maps across shapes. Our method is both time and space efficient, leading to a pipeline that is significantly faster than comparable approaches. We demonstrate the performance of our approach through an extensive quantitative and qualitative evaluation on several benchmarks where we achieve comparable or superior performance to existing methods.     

On representations for continuous dynamic systems

Through the use of a simple example involving a buffer tank, we illustrate the problems faced when attempting to formalize the dynamic aspects of a continuous process system. The problems are especially severe if we attempt to employ a purely qualitative representation. We show that the theoretical results obtained within qualitative reasoning describing the limits of qualitative simulation can be extended to cover the rule based approach as well. We conclude that for those cases where it is necessary to make predictions from a model of a dynamic system, we need a model based on a quantitative mathematical representation. Since representations of this type will not support any kind of reasoning about the system, apart from the computation of related values for variables, we need to employ some kind of hybrid approach to be able to make predictions about the evolution of variables while retaining the ability to reason about the behavior of the system at the same time.     

Semantic consistent adversarial cross-modal retrieval exploiting semantic similarity

Cross-modal retrieval aims to search the semantically similar instances from the other modalities given a query from one modality. However, the differences of the distributions and representations between different modalities make that the similarity of different modalities can not be measured directly. To address this problem, in this paper, we propose a novel semantic consistent adversarial cross-modal retrieval (SC-ACMR), which learns semantic consistent representation for different modalities under adversarial learning framework by considering the semantic similarity from intra-modality and inter-modality. Specifically, for intra-modality, we minimize the intra-class distances. For the inter-modality, we require class center of different modalities with same semantic label to be as close as possible, and also minimize the distances between the samples and the class center with same semantic label from different modalities. Furthermore, we preserve the semantic similarity of transformed features of different modalities through a semantic similarity matrix. Comprehensive experiments on two benchmark datasets are conducted and the experimental results show that the proposed method have learned more compact semantic representations and achieved better performance than many existing methods in cross-modal retrieval.

     

Tracking people across disjoint camera views by an illumination-tolerant appearance representation

Tracking single individuals as they move across disjoint camera views is a challenging task since their appearance may vary significantly between views. Major changes in appearance are due to different and varying illumination conditions and the deformable geometry of people. These effects are hard to estimate and take into account in real-life applications. Thus, in this paper we propose an illumination-tolerant appearance representation, which is capable of coping with the typical illumination changes occurring in surveillance scenarios. The appearance representation is based on an online k-means colour clustering algorithm, a data-adaptive intensity transformation and the incremental use of frames. A similarity measurement is also introduced to compare the appearance representations of any two arbitrary individuals. Post-matching integration of the matching decision along the individuals‘ tracks is performed in order to improve reliability and robustness of matching. Once matching is provided for any two views of a single individual, its tracking across disjoint cameras derives straightforwardly. Experimental results presented in this paper from a real surveillance camera network show the effectiveness of the proposed method.     

Glyphmaker: creating customized visualizations of complex data

Glyphmaker allows nonexpert users to customize their own graphical representations using a simple glyph editor and a point-and-click binding mechanism. In particular, users can create and then alter bindings to visual representations, bring in new data or glyphs with associated bindings, change ranges for bound data, and do these operations interactively. They can also focus on data down to any level of detail, including individual elements, and then isolate or highlight the focused region. These features empower users, letting them employ their specialized domain knowledge to create customized visual representations for further exploration and analysis. For ease of design and use, we built Glyphmaker on top of Iris Explorer, the Silicon Graphics Inc. (SGI) dataflow visualization system. The current version of Glyphmaker has been successfully tested on a materials system simulation. We are planning a series of tests and evaluations by scientists and engineers using real data     

An Exploratory Study of Data Sketching for Visual Representation

Hand‐drawn sketching on napkins or whiteboards is a common, accessible method for generating visual representations. This practice is shared by experts and non‐experts and is probably one of the faster and more expressive ways to draft a visual representation of data. In order to better understand the types of and variations in what people produce when sketching data, we conducted a qualitative study. We asked people with varying degrees of visualization expertise, from novices to experts, to manually sketch representations of a small, easily understandable dataset using pencils and paper and to report on what they learned or found interesting about the data. From this study, we extract a data sketching representation continuum from numeracy to abstraction; a data report spectrum from individual data items to speculative data hypothesis; and show the correspondence between the representation types and the data reports from our results set. From these observations we discuss the participants’ representations in relation to their data reports, indicating implications for design and potentially fruitful directions for research.