Search

Graph neural networks (GNNs) have demonstrated superior performance in various tasks on graphs. However, existing GNNs often suffer from weak-generalization due to sparsely labeled datasets. Here we propose a novel framework that learns to augment the input features using topological information and automatically controls the strength of augmentation. Our framework learns the augmentor to minimize GNNs’ loss on unseen labeled data while maximizing the consistency of GNNs’ predictions on unlabeled data. This can be formulated as a meta-learning problem and our framework alternately optimizes the augmentor and GNNs for a target task. Our extensive experiments demonstrate that the proposed framework is applicable to any GNNs and significantly improves the performance of graph neural networks on node classification. In particular, our method provides 5.78% improvement with Graph convolutional network (GCN) on average across five benchmark datasets.

Filter pruning is prevalent for pruning-based model compression. Most filter pruning methods have two main issues: 1) the pruned network capability depends on that of source pretrained models, and 2) they do not consider that filter weights follow a normal distribution. To address these issues, we propose a new pruning method employing both weight re-initialization and latent space clustering. For latent space clustering, we define filters and their feature maps as vertices and edges to be a graph, transformed into a latent space by graph convolution, alleviating to prune zero-near weight filters only. In addition, a part of filters is re-initialized with a constraint for enhancing filter diversity, and thus the pruned model is less dependent on the source network. This approach provides more robust accuracy even when pruned from the pretrained model with low accuracy. Extensive experimental results show our method decreases 56.6% and 84.6% of FLOPs and parameters of VGG16 with negligible loss of accuracy on CIFAR100, which is the state-of-the art performance. Furthermore, our method presents outperforming or comparable pruning results against state-of-the-art models on multiple datasets.

The problem of generating a set of diverse paraphrase sentences while (1) not compromising the original meaning of the original sentence, and (2) imposing diversity in various semantic aspects, such as a lexical or syntactic structure, is examined. Existing work on paraphrase generation has focused more on the former, and the latter was trained as a fixed style transfer, such as transferring from positive to negative sentiments, even at the cost of losing semantics. In this work, we consider style transfer as a means of imposing diversity, with a paraphrasing correctness constraint that the target sentence must remain a paraphrase of the original sentence. However, our goal is to maximize the diversity for a set of k generated paraphrases, denoted as the diversified paraphrase (DP) problem. Our key contribution is deciding the style guidance at generation towards the direction of increasing the diversity of output with respect to those generated previously. As pre-materializing training data for all style decisions is impractical, we train with biased data, but with debiasing guidance. Compared to state-of-the-art methods, our proposed model can generate more diverse and yet semantically consistent paraphrase sentences. That is, our model, trained with the MSCOCO dataset, achieves the highest embedding scores, .94/.95/.86, similar to state-of-the-art results, but with a lower mBLEU score (more diverse) by 8.73%.

Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; where tasks shares classes and is more realistic and practical. To address such task, we argue the importance of diversity of samples in an episodic memory. To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM). With extensive empirical validations on MNIST, CIFAR10, CIFAR100, and ImageNet datasets, we show that the proposed method significantly improves the accuracy in blurry continual learning setups, outperforming state of the arts by large margins despite its simplicity. Code and data splits will be available in https://github.com/clovaai/rainbow-memory., Accepted paper at CVPR 2021

Assessing advertisements, specifically on the basis of user preferences and ad quality, is crucial to the marketing industry. Although recent studies have attempted to use deep neural networks for this purpose, these studies have not utilized image-related auxiliary attributes, which include embedded text frequently found in ad images. We, therefore, investigated the influence of these attributes on ad image preferences. First, we analyzed large-scale real-world ad log data and, based on our findings, proposed a novel multi-step modality fusion network (M2FN) that determines advertising images likely to appeal to user preferences. Our method utilizes auxiliary attributes through multiple steps in the network, which include conditional batch normalization-based low-level fusion and attention-based high-level fusion. We verified M2FN on the AVA dataset, which is widely used for aesthetic image assessment, and then demonstrated that M2FN can achieve state-of-the-art performance in preference prediction using a real-world ad dataset with rich auxiliary attributes., Comment: published in Applied Soft Computing

Analyzing the associations between genotypic changes and phenotypic traits on a genome-wide scale can contribute to understanding the functional roles of distinct genetic variations during breed development. We performed a whole-genome analysis of Angus and Jersey cattle breeds using conditional mutual information, which is an information-theoretic method estimating the conditional independency among multiple factor variables. The proposed conditional mutual information-based approach allows breed-discriminative genetic variations to be explicitly identified from tens of millions of SNP (single nucleotide polymorphism) positions on a genome-wide scale while minimizing the usage of prior knowledge. Using this data-driven approach, we identified biologically relevant functional genes, including breed-specific variants for cattle traits such as beef and dairy production. The identified lipid-related genes were shown to be significantly associated with lipid and triglyceride metabolism, fat cell differentiation, and muscle development. In addition, we confirmed that milk-related genes are involved in mammary gland development, lactation, and mastitis-associated processes. Our results provide the distinct properties of Angus and Jersey cattle at a genome-wide level. Moreover, this study offers important insights into discovering unrevealed genetic variants for breed-specific traits and the identification of genetic signatures of diverse cattle breeds with respect to target breed-specific properties.

A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate our superiority in terms of visual quality, diversity, and scalability. To better assess image-to-image translation models, we release AFHQ, high-quality animal faces with large inter- and intra-domain differences. The code, pretrained models, and dataset can be found at https://github.com/clovaai/stargan-v2., Accepted to CVPR 2020

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through token-level self-attention. Such token-level encoding hinders the exploration of discourse-level coherence among utterances. This paper presents DialogBERT, a novel conversational response generation model that enhances previous PLM-based dialogue models. DialogBERT employs a hierarchical Transformer architecture. To efficiently capture the discourse-level coherence among utterances, we propose two training objectives, including masked utterance regression and distributed utterance order ranking in analogy to the original BERT training. Experiments on three multi-turn conversation datasets show that our approach remarkably outperforms the baselines, such as BART and DialoGPT, in terms of quantitative evaluation. The human evaluation suggests that DialogBERT generates more coherent, informative, and human-like responses than the baselines with significant margins., Comment: Published as a conference paper at AAAI 2021

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language understanding (E2E SLU) tasks. Taking phoneme posterior and subword-level text as an input, ST-BERT learns a contextualized cross-modal alignment via our two proposed pre-training tasks: Cross-modal Masked Language Modeling (CM-MLM) and Cross-modal Conditioned Language Modeling (CM-CLM). Experimental results on three benchmarks present that our approach is effective for various SLU datasets and shows a surprisingly marginal performance degradation even when 1% of the training data are available. Also, our method shows further SLU performance gain via domain-adaptive pre-training with domain-specific speech-text pair data., Comment: ICASSP 2021; 5 pages

Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services. Despite the advancement of ASR, however, most publicly available call-based speech corpora such as Switchboard are old-fashioned. Also, most existing call corpora are in English and mainly focus on open domain dialog or general scenarios such as audiobooks. Here we introduce a new large-scale Korean call-based speech corpus under a goal-oriented dialog scenario from more than 11,000 people, i.e., ClovaCall corpus. ClovaCall includes approximately 60,000 pairs of a short sentence and its corresponding spoken utterance in a restaurant reservation domain. We validate the effectiveness of our dataset with intensive experiments using two standard ASR models. Furthermore, we release our ClovaCall dataset and baseline source codes to be available via https://github.com/ClovaAI/ClovaCall., Comment: 5 pages, 2 figures, 4 tables, The first two authors equally contributed to this work

Weakly supervised object localization (WSOL) methods utilize the internal feature responses of a classifier trained only on image-level labels. Classifiers tend to focus on the most discriminative part of the target object, instead of considering its full extent. Adversarial erasing (AE) techniques have been proposed to ameliorate this problem. These techniques erase the most discriminative part during training, thereby encouraging the classifiers to learn the less discriminative parts of the object. Despite the success of AE-based methods, we have observed that the hyperparameters fail to generalize across model architectures and datasets. Therefore, new sets of hyperparameters must be determined for each architecture and dataset. The selection of hyperparameters frequently requires strong supervision (e.g., pixel-level annotations or human inspection). Because WSOL is premised on the assumption that such strong supervision is absent, the applicability of AE-based methods is limited. In this paper, we propose the region-based dropout with attention prior (RDAP) algorithm, which features hyperparameter transferability. We combined AE with regional dropout algorithms that provide greater stability against the selection of hyperparameters. We empirically confirmed that the RDAP method achieved state-of-the-art localization accuracy on four architectures, namely VGG-GAP, InceptionV3, ResNet-50 SE, and PreResNet-18, and two datasets, namely CUB-200-2011 and ImageNet-1k, with a single set of hyperparameters.

Converting hand-drawn sketches into clean line drawings is a crucial step for diverse artistic works such as comics and product designs. Recent data-driven methods using deep learning have shown their great abilities to automatically simplify sketches on raster images. Since it is difficult to collect or generate paired sketch and line images, lack of training data is a main obstacle to use these models. In this paper, we propose a training scheme that requires only unpaired sketch and line images for learning sketch-to-line translation. To do this, we first generate realistic paired sketch and line images from unpaired sketch and line images using rule-based line augmentation and unsupervised texture conversion. Next, with our synthetic paired data, we train a model for sketch-to-line translation using supervised learning. Compared to unsupervised methods that use cycle consistency losses, our model shows better performance at removing noisy strokes. We also show that our model simplifies complicated sketches better than models trained on a limited number of handcrafted paired data.

Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT$^2$) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a $1024\times1024$ resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, and pre-trained models are all available at https://github.com/ClovaAI/WCT2., Comment: Accepted to ICCV 2019, Code and data: https://github.com/ClovaAI/WCT2

Generating SQL codes from natural language questions (NL2SQL) is an emerging research area. Existing studies have mainly focused on clear scenarios where specified information is fully given to generate a SQL query. However, in developer forums such as Stack Overflow, questions cover more diverse tasks including table manipulation or performance issues, where a table is not specified. The SQL query posted in Stack Overflow, Pseudo-SQL (pSQL), does not usually contain table schemas and is not necessarily executable, is sufficient to guide developers. Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL. In addition, we define two new metrics suitable for the proposed NL2pSQL task, Canonical-BLEU and SQL-BLEU, instead of the conventional BLEU. With a baseline model using sequence-to-sequence architecture integrated by denoising autoencoder, we confirm the validity of our task. Experiments show that the proposed NL2pSQL approach yields well-formed queries (up to 43% more than a standard Seq2Seq model). Our code and datasets will be publicly released.

Precise prediction of severe diseases resulting in mortality is one of the main issues in medical fields. Even if pathological and radiological measurements provide competitive precision, they usually require large costs of time and expense to obtain and analyze the data for prediction. Recently, end-to-end approaches based on deep neural networks have been proposed, however, they still suffer from the low classification performance and difficulties of interpretation. In this study, we propose a novel disease prediction method, EHAN (EHR History-based prediction using Attention Network), based on the recurrent neural network (RNN) and attention mechanism. The proposed method incorporates (1) a bidirectional gated recurrent units (GRU) for automated sequential modeling, (2) attention mechanism for improving long-term dependence modeling, (3) RNN-based gradient-weighted class activation mapping (Grad-CAM) to visualize the class specific attention-weights. We conducted the experiments to predict the occurrence of risky disease containing cardiovascular and cerebrovascular diseases from more than 40,000 hypertension patients' electronic health records (EHR). The results showed that the proposed method outperformed the state-of-the-art model with respect to the various performance metrics. Furthermore, we confirmed that the proposed visualizing methods can be used to assist data-driven discovery.

Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks., Accepted to CVPR 2018 (Oral)

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

It is a critical issue to predict the prognosis of adult disease patients due to the possibility of spreading to high-risk symptoms in medical fields. Most studies for predicting prognosis have used complex data from patients such as biomedical images, biomarkers, and pathological measurements. We demonstrate a language model-like method for predicting high-risk prognosis from diagnosis histories of patients using deep recurrent neural networks (RNNs), i.e., prognosis prediction using RNN (PP-RNN). The proposed PP-RNN uses multiple RNNs for learning from diagnosis code sequences of patients in order to predict occurrences of high-risk diseases. The use of RNNs allows the model to learn the status changes of patients considering time, thus enhancing prediction accuracy. We evaluate our method on real-world diagnosis data of over 67,000 adult disease patients recorded for 14 years. Experimental results show the proposed PP-RNN outperforms other standard classification models. In particular, our method provides competitive performance with respect to recall and F1-score on high-risk diseases compared to other models. Furthermore, we investigate the effects of the parameters on the performances.

In general, a lot of computing time is needed to analyze the transient characteristics of a power transformer with complex geometry by field-circuit coupling method. This paper proposed a modified 2-D model and an efficient field-circuit coupling technique of a power transformer in order to reduce the computing time. To analyze the transient electromagnetic force acting on each disk of transformer windings, we made 2-D axisymmetric model. First, the transient current equation considering the residual flux was solved to get the inrush current. Next, the transient electromagnetic force due to the inrush current is obtained by applying finite element method (F.E.M.) to the modified 2-D model. The proposed method will be useful for the structure design of the power transformers.

Wearable devices, such as smart glasses and watches, allow for continuous recording of everyday life in a real world over an extended period of time or lifelong. This possibility helps better understand the cognitive behavior of humans in real life as well as build human-aware intelligent agents for practical purposes. However, modeling the human cognitive activity from wearable-sensor data stream is challenging because learning new information often results in loss of previously acquired information, causing a problem known as catastrophic forgetting. Here we propose a deep-learning neural network architecture that resolves the catastrophic forgetting problem. Based on the neurocognitive theory of the complementary learning systems of the neocortex and hippocampus, we introduce a dual memory architecture (DMA) that, on one hand, slowly acquires the structured knowledge representations and, on the other hand, rapidly learns the specifics of individual experiences. The DMA system learns continuously through incremental feature adaptation and weight transfer. We evaluate the performance on two real-life datasets, the CIFAR-10 image-stream dataset and the 46-day Lifelog dataset collected from Google Glass, showing that the proposed model outperforms other online learning methods.

Precise item categorization is a key issue in e-commerce domains. However, it still remains a challenging problem due to data size, category skewness, and noisy metadata. Here, we demonstrate a successful report on a deep learning-based item categorization method, i.e., deep categorization network (DeepCN), in an e-commerce website. DeepCN is an end-to-end model using multiple recurrent neural networks (RNNs) dedicated to metadata attributes for generating features from text metadata and fully connected layers for classifying item categories from the generated features. The categorization errors are propagated back through the fully connected layers to the RNNs for weight update in the learning process. This deep learning-based approach allows diverse attributes to be integrated into a common representation, thus overcoming sparsity and scalability problems. We evaluate DeepCN on large-scale real-world data including more than 94 million items with approximately 4,100 leaf categories from a Korean e-commerce website. Experiment results show our method improves the categorization accuracy compared to the model using single RNN as well as a standard classification model using unigram-based bag-of-words. Furthermore, we investigate how much the model parameters and the used attributes influence categorization performances.

We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language. DANs attend to specific regions in images and words in text through multiple steps and gather essential information from both modalities. Based on this framework, we introduce two types of DANs for multimodal reasoning and matching, respectively. The reasoning model allows visual and textual attentions to steer each other during collaborative inference, which is useful for tasks such as Visual Question Answering (VQA). In addition, the matching model exploits the two attention mechanisms to estimate the similarity between images and sentences by focusing on their shared semantics. Our extensive experiments validate the effectiveness of DANs in combining vision and language, achieving the state-of-the-art performance on public benchmarks for VQA and image-text matching.

In this study, direct reduction of using liquid calcium was investigated. The influence of molar ratio of Ca and , reaction time and temperature on the reduction behavior of was studied. Experiments were conducted in a closed stainless steel chamber under Ar atmosphere during 5 to 60 minutes. Most of the was reduced to Zr in 5 minutes at 1223 K and 3 Ca/ molar ratio. The minimum oxygen content in reduced metal Zr was obtained about 0.66 wt% at 1373 K after 30 minutes and 4 Ca/ molar ratio. The morphology of zirconium powder obtained was highly affected by the reaction temperature and reaction time.

This paper calculates the core and copper losses as heating sources of a 24MVA cast resin transformer, and analyzes the thermal distribution of the transformer to find out its hot-spot area by FEM program. Since the winding of the transformer is composed with many series and parallel circuits, the analyzing model of the winding is simplified and modelled by axi-symmetric domain. As the results, the maximum temperature is estimated by in the upper part of the low-voltage winding. The maximum temperature has discrepancy of approximately , which is able to be considered as an acceptable error range in the design stage of power transformers. For the overall pattern of the temperature distribution is almost same as test results, the analyzing method can be a useful tool to find out a hot-spot area of the winding.

In this paper, a simulation method of the internal winding fault is proposed to calculate winding current and electromagnetic force in a distribution power transformer by suing FEM program. The model of the transformer is a single phase, 60[Hz], 1[MVA], 22.9[kV]/220[V], cable-type winding. The short-circuit current and electromagnetic force are calculated by FEM(Finite Element Method) program(Flux2D) and the results we verified with theoretical formula and PSPICE program. The simulation results are fairly good agreement with the other verified methods within 5[%] error rate. The turn-to-turn short-circuit current is 500 times of the rated current and the electromagnetic force is about . The method presented in this study may serve as one of the useful tools in the electromagnetic force analysis of the transformer winding behavior under the short circuit condition for design of the structure.

Learning mutually-grounded vision-language knowledge is a foundational task for cognitive systems and human-level artificial intelligence. Most of knowledge-learning techniques are focused on single modal representations in a static environment with a fixed set of data. Here, we explore an ecologically more-plausible setting by using a stream of cartoon videos to build vision-language concept hierarchies continuously. This approach is motivated by the literature on cognitive development in early childhood. We present the model of deep concept hierarchy (DCH) that enables the progressive abstraction of concept knowledge in multiple levels. We develop a stochastic method for graph construction, i.e. a graph Monte Carlo algorithm, to search efficiently the huge compositional space of the vision-language concepts. The concept hierarchies are built incrementally and can handle concept drift, allowing for being deployed in lifelong learning environments. Using a series of approximately 200 episodes of educational cartoon videos we demonstrate the emergence and evolution of the concept hierarchies as the video stories unfold. We also present the application of the deep concept hierarchies for context-dependent translation between vision and language, i.e. the transcription of a visual scene into text and the generation of visual imagery from text.

This paper proposes a new use of the pseudospectral method to the eigenvalue analysis of the power transformer winding. The analysis method is based on the Chebyshev polynomials and collocated at the Gauss-Labatto collocation points. To verify the method, a helical-type winding of a power transformer is analyzed and numerical examples are provided for various boundary conditions. The computed results are in good agreement with finite-element method solutions. It shows that the method is straightforward and it has novel advantages in its conceptual simplicity

Predicting the clinical outcomes of cancer patients is a challenging task in biomedicine. A personalized and refined therapy based on predicting prognostic outcomes of cancer patients has been actively sought in the past decade. Accurate prognostic prediction requires higher-order representations of complex dependencies among genetic factors. However, identifying the co-regulatory roles and functional effects of genetic interactions on cancer prognosis is hindered by the complexity of the interactions. Here we propose a prognostic prediction model based on evolutionary learning that identifies higher-order prognostic biomarkers of cancer clinical outcomes. The proposed model represents the interactions of prognostic genes as a combinatorial space. It adopts a flexible hypergraph structure composed of a large population of hyperedges that encode higher-order relationships among many genetic factors. The hyperedge population is optimized by an evolutionary learning method based on sequential Bayesian sampling. The proposed learning approach effectively balances performance and parsimony of the model using information-theoretic dependency and complexity-theoretic regularization priors. Using MAQC-II project data, we demonstrate that our model can handle high-dimensional data more effectively than state-of-the-art classification models. We also identify potential gene interactions characterizing prognosis and recurrence risk in cancer.

Background Dysregulation of genetic factors such as microRNAs (miRNAs) and mRNAs has been widely shown to be associated with cancer progression and development. In particular, miRNAs and mRNAs cooperate to affect biological processes, including tumorigenesis. The complexity of miRNA-mRNA interactions presents a major barrier to identifying their co-regulatory roles and functional effects. Thus, by computationally modeling these complex relationships, it may be possible to infer the gene interaction networks underlying complicated biological processes. Results We propose a data-driven, hypergraph structural method for constructing higher-order miRNA-mRNA interaction networks from cancer genomic profiles. The proposed model explicitly characterizes higher-order relationships among genetic factors, from which cooperative gene activities in biological processes may be identified. The proposed model is learned by iteration of structure and parameter learning. The structure learning efficiently constructs a hypergraph structure by generating putative hyperedges representing complex miRNA-mRNA modules. It adopts an evolutionary method based on information-theoretic criteria. In the parameter learning phase, the constructed hypergraph is refined by updating the hyperedge weights using the gradient descent method. From the model, we produce biologically relevant higher-order interaction networks showing the properties of primary and metastatic prostate cancer, as candidates of potential miRNA-mRNA regulatory circuits. Conclusions Our approach focuses on potential cancer-specific interactions reflecting higher-order relationships between miRNAs and mRNAs from expression profiles. The constructed miRNA-mRNA interaction networks show oncogenic or tumor suppression characteristics, which are known to be directly associated with prostate cancer progression. Therefore, the hypergraph-based model can assist hypothesis formulation for the molecular pathogenesis of cancer.

Text-to-image retrieval is to retrieve the images associated with the textual queries. A text-to-image retrieval model requires an incremental learning method for its practical use since the multimodal data grow up dramatically. Here we propose an incremental text-to-image retrieval method using a multimodal association model. The association model is based on a hypernetwork (HN) where a vertex corresponds to a textual word or a visual patch and a hyperedge represents a higher-order multimodal association. Using the HN incrementally learned by a sequential Bayesian sampling, in the multimodal hypernetwork-based text-to-image retrieval, a given text query is crossmodally expanded to the visual query and then similar images are retrieved to the expanded visual query. We evaluated the proposed method using 3,000 images with textual description from Flickr.com. The experimental results present that the proposed method achieves very competitive retrieval performances compared to a baseline method. Moreover, we demonstrate that our method provides robust text-to-image retrieval results for the increasing data.

Cortical analysis becomes increasingly important for brain research and clinical diagnosis. This problem involves a combinatorial search to find the essential modules among a large number of brain regions. Despite several statistical approaches, cortical analysis remains a formidable challenge due to high-dimensionality and sparsity of data. Here we describe an evolutionary method for finding significant modules from cortical data. The method uses a hypernetwork which is encoded as a population of hyperedges, where hyperedges represent building blocks or potential modules. We develop an efficient method for evolving the hypernetwork using mutual information to generate essential hyperedges. We evaluate the method on predicting intelligence quotient (IQ) levels and finding potential significant modules on IQ from brain MRI data consisting of 62 healthy adults with over 80,000 measured points (variables). The experimental results show that our information-theoretic evolutionary hypernetworks improve the classification accuracy by 5∼15%. Moreover, it extracts significant cortical modules that distinguish high IQ from low IQ groups.

Exploring micro RNA (miRNA) and mRNA regulatory interactions may give new insights into diverse biological phenomena. While elucidating complex miRNA-mRNA interactions has been studied with experimental and computational approaches, it is still difficult to infer miRNA-mRNA regulatory modules. Here we present a novel method for identifying functional miRNA-mRNA modules from heterogeneous expression data. The proposed approach is layered hypernetworks consisting of two layers which are the layer of modality-dependent hypernetworks and of an integrating hypernetwork. The layered hypernetwork model is suitable for detecting relationships between heterogeneous modalities. Applied to the analysis of miRNA and mRNA expression profiles on multiple human cancers, the proposed model identifies oncogenic miRNA-mRNA regulatory modules. The experimental results show that our method provides a competitive performance to support vector machines, and outperforms other standard machine learning algorithms. The biological significance of the discovered miRNA-mRNA modules were validated by literature reviews.

Conventional methods for multimodal data retrieval use text-tag based or cross-modal approaches such as tag-image co-occurrence and canonical correlation analysis. Since there are differences of granularity in text and image features, however, approaches based on lower-order relationship between modalities may have limitations. Here, we propose a novel text and image keyword generation method by cross-modal associative learning and inference with multimodal queries. We use a modified hypernetwork model, i.e. layered hypernetworks (LHNs) which consists of the first (lower) layer and the second (upper) layer which has more than two modality-dependent hypernetworks and one modality-integrating hypernetwork, respectively. LHNs learn higher-order associative relationships between text and image modalities by training on an example set. After training, LHNs are used to extend multimodal queries by generating text and image keywords via cross-modal inference, i.e. text-to-image and image-to-text. The LHNs are evaluated on Korean magazine articles with images on women fashions and life-style. Experimental results show that the proposed method generates vision-language cross-modal keywords with high accuracy. The results also show that multimodal queries improve the accuracy of keyword generation compared with uni-modal ones.

This paper proposes a simulation method of the internal winding fault to calculate the short-circuit current, electromagnetic force and vibration mode in a distribution power transformer by suing FEM and analytic algorithm. A usage of the pseudospectral method is also presented for the vibration analysis of the winding during the short-circuit. The equations of the winding are approximated by the series expansions of Chebyshev polynomials and the Gauss-Lobatto collocation process is performed. The simulation examples are provided for the cable type winding of the transformer(22.9 kV/220 V, 1000 kVA) to verify the method. The simulation results are in good agreement with FEM solutions and analytical methods.

We present a biology-inspired probabilistic graphical model, called the hypernetwork model, and its application to medical diagnosis of disease. The hypernetwork models are a way of simulated DNA computing. They have a set of hyperedges representing a subset of features in the training data. These characteristics allow the hypernetwork models to work similarly to associative memories and make their learning results more understandable. This comprehensibility is one of main advantages of the models over other machine learning algorithms such as support vector machines and artificial neural networks which are used in a wide range of applications but are not easy to understand their learning results. Since medical applications require both competitive performance and understandability of results, the hypernetwork models are suitable for this kind of applications. However, ordinary hypernetwork models have limitations that hyperedges cannot be changed after they are sampled once. To improve this diversity problem, we adopted simple evolutionary computation method, the hyperedges replacement strategy as the method of keeping the diversity into conventional hypernetworks in addition to error correction for model learning. To show the improvement, we used aptamer-based cardiovascular disease data. Experiment results show that the hypernetworks can achieve fairly competitive performance and the results are also comprehensible.

In this paper, the design procedure and electrical performance of a new triple-band antenna are reported and investigated. The operating frequency of the proposed antenna includes the PCS/IMT-2000/Bluetooth bands for the mobile communication system. It adopt the CPW-fed structure that is easily integrated with MMIC and fabricated in a simplified configuration. For the radiating elements, the proposed antenna employs a meander-line structure for size reduction. By adjusting the gap of the CPW ground and the feed line, the antenna achieves a good matching between the input impedance of the antenna and microstrip feed line. The resonant frequency was obtained by adjusting the length of the meander-line, the relative position of the CPW feed line and radiating elements (R). in addition, the width of the radiating elements and the size of the CPW ground play important roles in achieving increased input impedance bandwidth. 10dB return loss with the required bandwidth can be obtained by adjusting the gap of the meander-line. It is expected that the proposed antenna is small enough to be applicable for practical mobile communication systems.