In this paper, we propose a new class of techniques to identify periodicities in data. We target the period estimation directly rather than inferring the period from the signal's spectrum. By doing ...so, we obtain several advantages over the traditional spectrum estimation techniques such as DFT and MUSIC. Apart from estimating the unknown period of a signal, we search for finer periodic structure within the given signal. For instance, it might be possible that the given periodic signal was actually a sum of signals with much smaller periods. For example, adding signals with periods 3, 7, and 11 can give rise to a period 231 signal. We propose methods to identify these "hidden periods" 3, 7, and 11. We first propose a new family of square matrices called Nested Periodic Matrices (NPMs), having several useful properties in the context of periodicity. These include the DFT, Walsh-Hadamard, and Ramanujan periodicity transform matrices as examples. Based on these matrices, we develop high dimensional dictionary representations for periodic signals. Various optimization problems can be formulated to identify the periods of signals from such representations. We propose an approach based on finding the least l 2 norm solution to an under-determined linear system. Alternatively, the period identification problem can also be formulated as a sparse vector recovery problem and we show that by a slight modification to the usual l 1 norm minimization techniques, we can incorporate a number of new and computationally simple dictionaries.
This paper reports on a qualitative study of dictionary use at the School of Economics and Business, University of Ljubljana, Slovenia, during which nine students were given look-up tasks with the ...online Merriam-Webster Learner's Dictionary. The study employed a combination of research methods: semi-structured oral interviews and the researchers' direct observation of the participants as they looked up words. As the students completed these tasks, they were observed and questioned about their habits of dictionary use, their lookup experience, and their perceptions of the utility and quality of the dictionary definitions and examples. The results provide insight into the efficacy of the specific dictionary used. In addition, the study reveals much about how these students regard dictionaries and how they approach their use. Many of the participants had no relationship with dictionaries and no real understanding of their purpose. Their comments demonstrate that they are "demanding" users with very firm ideas and high expectations about the type of information they wish to receive in an online dictionary - and how they prefer to have it delivered. Some recommendations are made for those involved in learner lexicography concerning the improvement of part-of-speech information to make lookup easier, improvement of dictionary examples and improvement of the way dictionary information is presented. This paper also discusses what the takeaways are for concerned dictionary makers; in particular, it will reflect on how students should be taught about dictionaries today - if we still want them to use dictionaries tomorrow.
Transitioning to a low-/zero-carbon energy ecosystem requires a thorough and accurate understanding of how energy is consumed on the demand side. To achieve this goal, user profiling has become a ...crucial data analytical tool to understand consumers' energy activities and characterize the patterns/trends of different consumers. Though useful, user profiling remains a challenge due to the high irregularity and volatility inherited in consumer energy activities. Moreover, traditional user profiling requires time-series load consumption data to be collected and processed in a centralized server, which increases processing budgets and privacy leakage risks. To address these challenges, we propose a federated shift-invariant dictionary learning clustering approach to enable distributed and computationally efficient user profiling. The proposed approach elucidates the characteristics of each user by decomposing its time-series load consumption data into a linear combination of electricity consumption patterns. Furthermore, with the aid of a federated learning framework, the proposed approach allows most user profiling steps to be completed locally. Simulation studies based on real-world dataset show that compared with conventional federated clustering methods, the proposed approach is capable of better revealing the patterns behind the load series data, which improves the accuracy and effectiveness of user profiling.
We propose a method for imaging in scattering media when large and diverse datasets are available. It has two steps. Using a dictionary learning algorithm the first step estimates the true Green's ...function vectors as columns in an unordered sensing matrix. The array data comes from many sparse sets of sources whose location and strength are not known to us. In the second step, the columns of the estimated sensing matrix are ordered for imaging using the multidimensional scaling algorithm with connectivity information derived from cross-correlations of its columns, as in time reversal. For these two steps to work together, we need data from large arrays of receivers so the columns of the sensing matrix are incoherent for the first step, as well as from sub-arrays so that they are coherent enough to obtain connectivity needed in the second step. Through simulation experiments, we show that the proposed method is able to provide images in complex media whose resolution is that of a homogeneous medium.
Data encoded as symmetric positive definite (SPD) matrices frequently arise in many areas of computer vision and machine learning. While these matrices form an open subset of the Euclidean space of ...symmetric matrices, viewing them through the lens of non-Euclidean Riemannian (Riem) geometry often turns out to be better suited in capturing several desirable data properties. Inspired by the great success of dictionary learning and sparse coding (DLSC) for vector-valued data, our goal in this paper is to represent data in the form of SPD matrices as sparse conic combinations of SPD atoms from a learned dictionary via a Riem geometric approach. To that end, we formulate a novel Riem optimization objective for DLSC, in which the representation loss is characterized via the affine-invariant Riem metric. We also present a computationally simple algorithm for optimizing our model. Experiments on several computer vision data sets demonstrate superior classification and retrieval performance using our approach when compared with SC via alternative non-Riem formulations.
Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, ...implying existence of a structure among visual tasks. Knowing this structure has notable values; it is the concept underlying transfer learning and provides a principled way for identifying redundancies across tasks, e.g., to seamlessly reuse supervision among related tasks or solve many tasks in one system without piling up the complexity. We proposes a fully computational approach for modeling the structure of space of visual tasks. This is done via finding (first and higher-order) transfer learning dependencies across a dictionary of twenty six 2D, 2.5D, 3D, and semantic tasks in a latent space. The product is a computational taxonomic map for task transfer learning. We study the consequences of this structure, e.g. nontrivial emerged relationships, and exploit them to reduce the demand for labeled data. We provide a set of tools for computing and probing this taxonomical structure including a solver users can employ to find supervision policies for their use cases.
Fusing a low spatial resolution hyperspectral image (LR-HSI) with a high spatial resolution multispectral image (HR-MSI) to obtain a high spatial resolution hyperspectral image (HR-HSI) has attracted ...increasing interest in recent years. In this paper, we propose a coupled sparse tensor factorization (CSTF)-based approach for fusing such images. In the proposed CSTF method, we consider an HR-HSI as a 3D tensor and redefine the fusion problem as the estimation of a core tensor and dictionaries of the three modes. The high spatial-spectral correlations in the HR-HSI are modeled by incorporating a regularizer, which promotes sparse core tensors. The estimation of the dictionaries and the core tensor are formulated as a coupled tensor factorization of the LR-HSI and of the HR-MSI. Experiments on two remotely sensed HSIs demonstrate the superiority of the proposed CSTF algorithm over the current state-of-the-art HSI-MSI fusion approaches.
Danmaku video provides a platform for users to communicate online while watching videos. Danmaku is a live commenting function where the comments related to the video being screened are created by ...users and prominently shown in real-time on the video screen. These live comments contain complex and rich sentiments, reflecting users' instant opinions and feelings on video programs. In some sense, danmaku provides emotional timing information about video data, and it also offers an innovative mean to analyze video data. However, existing sentiment classification methods are not suitable for danmaku data analysis. To solve this problem, this paper constructs a danmaku sentiment dictionary and presents a new method using sentiment dictionary and Naïve Bayes for the sentiment analysis of danmaku reviews. The method is greatly helpful in supervising the overall emotional orientation of a danmaku video and predicting its popularity. Through the processes of extracting emotional information from a danmaku video, classifying sentiment and visualizing data, the time distribution of the seven sentiment dimensions can be obtained. In addition, a weight calculation can be conducted for classifying the sentiment polarity of danmaku reviews. Experimental results show that the proposed method has a significant effect on sentiment score and polarity detection.
This article is a first publication of the dictionary materials on the Karelian and Komi-Zyrian languages from the hand-written volume made in 1668 by monastic deacon Prochor Kolomnjatin in the ...Rostov-Jaroslavl land. The volume was discovered by N. V. Saveljeva in the Manuscripts Department of the State Historical Museum (Moscow). Apart from the materials stated above, it contains a unique Turkic-Russian thesaurus, as well as copies of several known lexicographical monuments. The Karelian collection includes some 600, and the Komi collection about 100 words, representing colloquial vocabulary and terminology associated with work and natural environment. The Komi-Zyrian phrasebook also contains a detailed invoice and a translation of the Holy God prayer. The publishers believe that the content of the dictionaries was recorded directly from native speakers, by ear, and thus reflects the language actually spoken in the 17th century. The publication of the dictionaries is supplied with linguistic comments permitting some preliminary conclusions to be made concerning the language of these sources and their origins. The main parameters of the lexeme collection in the Karelian dictionary suggest it belongs to the Karelian proper variant, bearing some Tver or related dialectal features. At the same time, it contains some lexemes and phonetic traits comparable to Eastern Finnish dialectal data. The Komi-Zyrian dictionary, although much smaller, contains quite definite information about the dialectal characteristics of the language in the source. The phonetic correspondences phrase omitted, the palatal phrase omitted and the clusters phrase omitted, and deaffrication of phrase omitted into occlusive-palatal partial derivative', which are the main discriminants for Komi dialects, as well as dialect-oriented vocabulary suggest that the language of the source is affiliated (or close) to the Vym dialect, one of the earliest dialects of the Komi language. The Karelian or Komi original can be found or reconstructed for a vast majority of words in the volume. This source generally demonstrates that the languages represented there have not undergone major changes over the past 350 years. Keywords: Karelian language, Komi-Zyrian language, dictionary, lexicography, 17th-century written sources, linguistic commentary.
Change detection is one of the most important applications of remote sensing technology. It is a challenging task due to the obvious variations in the radiometric value of spectral signature and the ...limited capability of utilizing spectral information. In this paper, an improved sparse coding method for change detection is proposed. The intuition of the proposed method is that unchanged pixels in different images can be well reconstructed by the joint dictionary, which corresponds to knowledge of unchanged pixels, while changed pixels cannot. First, a query image pair is projected onto the joint dictionary to constitute the knowledge of unchanged pixels. Then reconstruction error is obtained to discriminate between the changed and unchanged pixels in the different images. To select the proper thresholds for determining changed regions, an automatic threshold selection strategy is presented by minimizing the reconstruction errors of the changed pixels. Adequate experiments on multispectral data have been tested, and the experimental results compared with the state-of-the-art methods prove the superiority of the proposed method. Contributions of the proposed method can be summarized as follows: 1) joint dictionary learning is proposed to explore the intrinsic information of different images for change detection. In this case, change detection can be transformed as a sparse representation problem. To the authors' knowledge, few publications utilize joint learning dictionary in change detection; 2) an automatic threshold selection strategy is presented, which minimizes the reconstruction errors of the changed pixels without the prior assumption of the spectral signature. As a result, the threshold value provided by the proposed method can adapt to different data due to the characteristic of joint dictionary learning; and 3) the proposed method makes no prior assumption of the modeling and the handling of the spectral signature, which can be adapted to different data.