Narrow Results

Multimodal hashing aims to efficiently integrate multi-source data into a unified discrete Hamming space, facilitating fast similarity searches with minimal query and storage overhead. Traditional multimodal hashing assumes that data from different sources are fully observed, an assumption that fails in real-world scenarios involving large-scale multimodal data, thereby compromising conventional methods. To address these limitations during both training and retrieval, our approach manages dual-stage data missing, occurring in both phases. In this paper, we introduce a novel framework called Flexible Dual Multimodal Hashing (FDMH), which recovers missing data at both stages by jointly leveraging low-dimensional data relations and semantic graph structural relationships in multi-source data, achieving promising performance in incomplete multimodal retrieval. We transform the original features into anchor graphs and use existing modalities to reconstruct the anchor graphs of missing modalities. Based on these anchor graphs, we perform weight-adaptive fusion in the semantic space, supervised by original semantic labels, and apply a tensor nuclear norm to enforce consistency constraints on the projection matrices across different modalities. Furthermore, our method flexibly fuses existing and recovered modalities during retrieval. We validate the effectiveness of our approach through extensive experiments on four large-scale multimodal datasets, demonstrating its robust performance in real-world dual-missing retrieval scenarios.

Similarity search for protein 3D structures become complex and computationally expensive due to the fact that the size of protein structure databases continues to grow tremendously. Recently, fast structural similarity search systems have been required to put them into practical use in protein structure classification whilst existing comparison systems do not provide comparison results on time.

Our approach uses multi-step processing that composes of a preprocessing step to represent geometry of protein structures with spatial objects, a filter step to generate a small candidate set using approximate topological string matching, and a refinement step to compute a structural alignment. This paper describes the preprocessing and filtering for fast similarity search using the discovery of topological patterns of secondary structure elements based on spatial relations. Our system is fully implemented by using Oracle 8i spatial. We have previously shown¹ that our approach has the advantage of speed of performance compared with other approach such as DALI. This work shows that the discovery of topological relations of secondary structure elements in protein structures by using spatial relations of spatial databases is practical for fast structural similarity search for proteins.

With the rapid development of information technology, we have already access to the era of big data. Time series is a sequence of data points associated with numerical values and successive timestamps. Time series not only has the traditional big data features, but also can be continuously generated in a high speed. Therefore, it is very time- and resource-consuming to directly apply the traditional time series similarity search methods on the raw time series data. In this paper, we propose a novel online segmenting algorithm for streaming time series, which has a relatively high performance on feature representation and similarity search. Extensive experimental results on different typical time series datasets have demonstrated the superiority of our method.

Icons and screenshots are important media displayed in game distribution platforms for providing a brief understanding of the game content to the customers. In this study, we develop ensemble convolutional neural networks for icon and screenshot analysis as three applications: an automatic genre classification, a similar game searching, and a recognition quality assessment. First, the genre classifier is developed using 154358 images from 18 030 games in 17 genres. The proposed genre classifiers achieve 40.5% and 47.6% accuracies for classifying a single icon and a single screenshot, which outperform the average performance of the human testers. The accuracy can be boosted to 54.2% by aggregating results from every image of the game. The Grad-CAM is applied to analyze what models learned. Then, the feature extraction part trained by this task is transferred to the other two applications. For the similar game searching, a dissimilarity of two images is directly computed by the Euclidean distance in the feature space. We define a dissimilarity between two games which are sets of multiple images based on their image-pairwise dissimilarity. The results show that the features are successfully transferred, and the model seems to be able to cluster the games with a similar gameplay and differentiate them from the other gameplays even if they come from the same genre. For the third application, we develop a system for quality assessment of game images based on the correctness of viewers’ understanding of game content by combining multiple models from three different problem definitions. Our system can identify good-genre-representing game images which most of the human testers can recognize their genre correctly with 75.0% accuracy for icons and 76.2% accuracy for screenshots.

With the development of modern agricultural facilities, crop diseases recognition, nutritional status and morphology achieved rapid growth. To avoid yield loss caused by the delay of disease detection, digital images that contain information with respect to crop growth, disease type and nutrition deficiency have been studied by some researchers. However, traditional image processing methods fail to extract typical disease features of crop images with ambiguous disease information. In this paper, a crop disease image recognition technique based on the salient region and hierarchical indexing was proposed. Improved Harris algorithm and maximum radius were used to calculate the widest salient region. In order to eliminate the effect of different salience distribution ranges between different features, a group of images in the cucumber disease image library were normalized. Experiment results indicate that the time complexity of each algorithm will go up as the size of the dataset increase. Especially when testing large datasets, nonhierarchical and nonclustering, hierarchical and nonclustering and hierarchical based on points all tend to raise the algorithm’s time complexity. Plant Village dataset and AI Challenger 2018 dataset were utilized to compare the recognition performances among the models based on machine learning, neural network, deep learning and our methods. The experiment results show that the method proposed in this paper is capable of recognizing local similar images effectively rather than global similar images, therefore, it has better recognition performance than the model learning methods in the early detection stage of crop disease.

Comparing protein structures in three dimensions is a computationally expensive process that makes a full scan of a protein against a library of known protein structures impractical. To reduce the cost, we can use an approximation of the three dimensional structure that allows protein comparison to be performed quickly to filter away dissimilar proteins. In this paper, we present a new algorithm, called SCALE, for protein structure comparison. In SCALE, a protein is represented as a sequence of secondary structure elements (SSEs) augmented with 3D structural properties such as the distances and angles between the SSEs. As such, the comparison between two proteins is reduced to a sequence alignment problem between their corresponding sequences of SSEs. The 3-D structural properties of the proteins contribute to the similarity score between the two sequences. We have implemented SCALE, and compared its performance against existing schemes. Our performance study shows that SCALE outperforms existing methods in terms of both efficiency and effectiveness (measured in terms of precision and recall). To avoid exhaustive search, an index based on the structural properties is also proposed. The index prunes away a considerable amount of dissimilar proteins given a query protein.

The performance of nearest neighbor (NN) queries degrades noticeably with increasing dimensionality of the data due to reduced selectivity of high-dimensional data and an increased number of seek operations during NN-query execution. If the NN-radii would be known in advance, the disk accesses could be reordered such that seek operations are minimized. We therefore propose a new way of estimating the NN-radius based on the fractal dimensionality and sampling. It is applicable to any page-based index structure. We show that the estimation error is considerably lower than for previous approaches. In the second part of the paper, we present two applications of this technique. We show how the radius estimations can be used to transform k-NN queries into at most two range queries, and how it can be used to reduce the number of page reads during all-NN queries. In both cases, we observe significant speedups over traditional techniques for synthetic and real-world data.

This paper proposes an indexing technique for fast retrieval of similar image subsequences using the multi-dimensional time warping distance. The time warping distance is a more suitable similarity measure as compared to the L_p distance in many applications where sequences may be of different lengths and/or different sampling rates. Our indexing scheme employs a disk-based suffix tree as an index structure and uses a lower-bound distance function to filter out dissimilar subsequence without false dismissals. It applies the normalization for an easier control of relative weighting of feature dimensions and the discretization to compress the index tree. Experiments on medical and synthetic image sequences verified that the proposed method significantly outperforms the naïve method and scales well in a large volume of image sequence databases.

We address the problem of similarity search in large multi-dimensional time sequence databases. There has been a lot of attention in similarity search in time sequence databases. However, most of the previous work on time sequences focused on one-dimensional sequences. Many applications such as multimedia databases or weather databases, however, need to handle multi-dimensional time sequences. In this paper, we extend our previous work on the similarity search by considering query types in multi-dimensional time sequence databases and more intensive experimental results that were not reported in the previous paper are illustrated. The proposed method can efficiently reduce the search space and guarantees no false dismissals.

We propose a general approach to compute the seed sensitivity, that can be applied to different definitions of seeds. It treats separately three components of the seed sensitivity problem — a set of target alignments, an associated probability distribution, and a seed model — that are specified by distinct finite automata. The approach is then applied to a new concept of subset seeds for which we propose an efficient automaton construction. Experimental results confirm that sensitive subset seeds can be efficiently designed using our approach, and can then be used in similarity search producing better results than ordinary spaced seeds.

Learning to hash is receiving increasing research attention due to its effectiveness in addressing the large-scale similarity search problem. Most of the existing hashing algorithms are focused on learning hash functions in the form of numeric quantization of some projected feature space. In this work, we propose a novel hash learning method that encodes features’ relative ordering instead of quantizing their numeric values in a set of low-dimensional ranking subspaces. We formulate the ranking-based hash learning problem as the optimization of a continuous probabilistic error function using softmax approximation and present an efficient learning algorithm to solve the problem. As a generalization of Winner-Take-All (WTA) hashing, the proposed algorithm naturally enjoys the numeric stability benefits of rank correlation measures while being optimized to achieve high precision with very compact code. Additionally, the proposed method can also be easily extended to nonlinear kernel spaces to discover ranking structures that can not be revealed in linear subspaces. We demonstrate through extensive experiments that the proposed method can achive competitive performances as compared to a number of state-of-the-art hashing methods.

Time sequences occur in many applications, ranging from science and technology to business and entertainment. In many of these applications, searching through large, unstructured databases based on sample sequences is often desirable. Such similarity-based retrieval has attracted a great deal of attention in recent years. Although several different approaches have appeared, most are based on the common premise of dimensionality reduction and spatial access methods. This chapter gives an overview of recent research and shows how the methods fit into a general context of signature extraction.

Amphotericin B (AmB) is a choice antibiotic against fungal infections. Since AmB has many side effects, it is desired to come up with new molecules with similar activity and less toxicity. In this work, attempt has been made to design a series of molecules by chem/bioinformatics. The structure of AmB was divided into two fragments and the best modified molecules were chosen, according to binding energy obtained through in silico dock experiments. A similarity search was performed on the molecules, and the available similar compounds resulted to a set of structurally matched compounds with 70% and above for similarity value. Several molecules from the library were selected and evaluated for in vitro antifungal assay. The result of the evaluations was finding compounds, which their antifungal effect had not been reported before or proposed new mechanism of action possibly involve in binding to membrane components such as ergosterol.

Fungal infections of humans are serious, especially in immunocompromised patients. One difficultly in treating fungal infections is the lack of adeqate number of effective antifungal drugs. Amphotericin B (AmB) is a well known polyene macrolide antibiotic used to treat systemic fungal infections. AmB despite its toxicity, exhibits several positive features, including potency, and relative lack of resistance. Therefore, AmB would serve as a suitable model in the drug discovery and development process. The purpose of this work was to identify novel antifungal compounds based on the structure and function of AmB, using in silico methods. We have found compounds by these methods that appear to inhibit fungal growth and contain molecular features close to AmB.