Search

Recent advances in wearable systems have made inertial sensors, such as accelerometers and gyroscopes, compact, lightweight, multimodal, low-cost, and highly accurate. Wearable inertial sensor-based multimodal human activity recognition (HAR) methods utilize the rich sensing data from embedded multimodal sensors to infer human activities. However, existing HAR approaches either rely on domain knowledge or fail to address the time-frequency dependencies of multimodal sensor signals. In this paper, we propose a novel method called deep wavelet convolutional neural networks (DWCNN) designed to learn features from the time-frequency domain and improve accuracy for multimodal HAR. DWCNN introduces a framework that combines continuous wavelet transforms (CWT) with enhanced deep convolutional neural networks (DCNN) to capture the dependencies of sensing signals in the time-frequency domain, thereby enhancing the feature representation ability for multiple wearable inertial sensor-based HAR tasks. Within the CWT, we further propose an algorithm to estimate the wavelet scale parameter. This helps enhance the performance of CWT when computing the time-frequency representation of the input signals. The output of the CWT then serves as input for the proposed DCNN, which consists of residual blocks for extracting features from different modalities and attention blocks for fusing these features of multimodal signals. We conducted extensive experiments on five benchmark HAR datasets: WISDM, UCI-HAR, Heterogeneous, PAMAP2, and UniMiB SHAR. The experimental results demonstrate the superior performance of the proposed model over existing competitors. [ABSTRACT FROM AUTHOR]

Lyrics-to-melody generation is an interesting and challenging topic in AI music research field. Due to the difficulty of learning the correlations between lyrics and melody, previous methods suffer from low generation quality and lack of controllability. Controllability of generative models enables human interaction with models to generate desired contents, which is especially important in music generation tasks towards human-centered AI that can facilitate musicians in creative activities. To address these issues, we propose a controllable lyrics-to-melody generation network, ConL2M, which is able to generate realistic melodies from lyrics in user-desired musical style. Our work contains three main novelties: (1) to model the dependencies of music attributes cross multiple sequences, inter-branch memory fusion (Memofu) is proposed to enable information flow between multi-branch stacked LSTM architecture; (2) reference style embedding (RSE) is proposed to improve the quality of generation as well as control the musical style of generated melodies; (3) sequence-level statistical loss (SeqLoss) is proposed to help the model learn sequence-level features of melodies given lyrics. Verified by evaluation metrics for music quality and controllability, initial study of controllable lyrics-to-melody generation shows better generation quality and the feasibility of interacting with users to generate the melodies in desired musical styles when given lyrics. [ABSTRACT FROM AUTHOR]

This paper considers the problem of identifying all locations of subtrees in a large tree or in a large collection of trees that are similar to a specified pattern tree, where all trees are assumed to be rooted and node-labeled. The tree edit distance is a widely-used measure of tree (dis-)similarity, but is NP-hard to compute for unordered trees. To cope with this issue, we propose a new similarity measure which extends the concept of unordered tree inclusion by taking the costs of insertion and substitution operations on the pattern tree into account, and present an algorithm for computing it. Our algorithm has the same time complexity as the original one for unordered tree inclusion, i.e., it runs in $O(T_1T_2)$ time, where $T_1$ and $T_2$ denote the pattern tree and the text tree, respectively, when the maximum outdegree of $T_1$ is bounded by a constant. Our experimental evaluation using synthetic and real datasets confirms that the proposed algorithm is fast and scalable and very useful for bibliographic matching, which is a typical entity resolution problem for tree-structured data. Furthermore, we extend our algorithm to also allow a constant number of deletion operations on $T_1$ while still running in $O(T_1T_2)$ time. [ABSTRACT FROM AUTHOR]

Traffic congestion occurs frequently in urban settings, and is not always caused by traffic incidents. In this paper, we propose a simple method for detecting traffic incidents from probe-car data by identifying unusual events that distinguish incidents from spontaneous congestion. First, we introduce a traffic state model based on a probabilistic topic model to describe the traffic states for a variety of roads. Formulas for estimating the model parameters are derived, so that the model of usual traffic can be learned using an expectation–maximization algorithm. Next, we propose several divergence functions to evaluate differences between the current and usual traffic states and streaming algorithms that detect high-divergence segments in real time. We conducted an experiment with data collected for the entire Shuto Expressway system in Tokyo during 2010 and 2011. The results showed that our method discriminates successfully between anomalous car trajectories and the more usual, slowly moving traffic patterns. [ABSTRACT FROM AUTHOR]

Passwordless authentication is a trending theme in cyber security, while biometrics gradually replace knowledge-based schemes. However, Personal Identification Numbers, passcodes, and graphical passwords are still considered as the primary means for authentication. Passwords must be memorable to be usable; therefore, users tend to choose easy to guess secrets, compromising security. The Android Pattern Unlock is a popular graphical password scheme that can be easily attacked by exploiting human behavioristic traits. Despite its vulnerabilities, the popularity of the scheme has led researchers to propose adjustments and variations that enhance security but maintain its familiar user interface. Nevertheless, prior work demonstrated that improving security while preserving usability remains frequently a hard task. In this paper we propose a novel graphical password scheme built on the foundations of the well-accepted Android Pattern Unlock method, which is usable, inclusive, universal, and robust against shoulder surfing and (basically) smudge attacks. Our scheme, named Bu-Dash, features a dynamic user interface that mutates every time a user swipes the screen. Our pilot studies illustrate that Bu-Dash attracts positive user acceptance rates, it is secure, and maintains high usability levels. We define complexity metrics that can be used to further diversify user input, and we conduct complexity and security assessments. [ABSTRACT FROM AUTHOR]

Presents a study which proposed fuzzy retrieval methods. Application of the methods to digital libraries; Algorithm of the proposed method; Conclusions.

One of the most popular recommender system techniques is collaborative filtering (CF). Nowadays, many researchers apply a neural network with CF, but few focus on the neighbors' concept of CF. This work needs to consider two major issues: the similarity levels between the neighbors and the target user and the user's rating pattern conversion. Because different neighbors have a different influence on the target user and different users usually have a different rating pattern, the ratings directly utilized by the neighbor's preference pattern may be incorrect for the target user. Under two main issues, we try to accomplish three main ideas of CF's prediction: the similarity between users' levels, the neighbor's rating, and the rating conversion. Thus, we propose three main modules, the rating conversion module, the similarity module, and the prediction module, to solve the two issues mentioned above. The rating conversion module projects the neighbor's rating into the target user's aspect. The similarity module uses the users' attentions to compute similarity levels between users. Finally, these similarity levels and the converted ratings are integrated to perform the prediction. The proposed method is compared with the current CF with friends and latent factor model using two types of datasets: real-world and synthetic datasets. We evaluate N neighbors and all neighbors on real-world datasets to prove the number of neighbor is important. Moreover, the performance of the rating conversion module is also evaluated. The proposed method simulates the full rating datasets and the partial rating dataset to compare the effectiveness of using different types of distribution and dataset size. The experimental results demonstrate that the proposed method effectively outperformed the baselines using ranking evaluation and prediction accuracy on real-world and synthetic datasets. Besides, The effectiveness of using different the number of neighbors depends on the quality of neighbors. [ABSTRACT FROM AUTHOR]

Bridge weigh-in-motion (BWIM) serves as a method to obtain the weight of passing vehicles from bridge responses. Most BWIM systems proposed so far rely on the measurement of bridge global vibration data, usually strain, to determine the vehicle load. However, because the bridge's global response is sensitive to all vehicles on the bridge, the global vibration-based BWIM techniques usually suffer from inaccuracy in the case where multiple vehicles are present on the bridge. In this paper, a data-driven approach is proposed to extract the passing vehicle's weight and driving speed from vertical acceleration at the bridge joint. As a type of local vibration, the impulse acceleration responses at a bridge joint can be recorded only during a short period when a vehicle is passing over the joint and are thus not sensitive to vehicles at other locations of the bridge. A field test is conducted at a bridge to prepare labeled training data for the use of a convolutional neural network. One accelerometer is installed on the bridge joint to record impulse acceleration, while the vehicle's weight and driving speed are obtained from a WIM station and a camera near the bridge, respectively. A network that detects the vehicle's passage as well as its passing lane is first proposed, followed by a 1-D convolutional neural network that uses the raw data of acceleration as the input to predict the vehicle's gross weight and driving speed. A comparison is made between the 1-D network and an updated 2-D network that uses the wavelet coefficients as the input matrix. The latter one shows better performance, indicating that it is important to choose the proper input data for the network to be trained. A transfer learning technique is used to test the feasibility of the proposed method. Results show that the proposed method can be extended with limited data to bridges other than the bridge where the network is trained. [ABSTRACT FROM AUTHOR]

This article studies the parameterized complexity of the unification problem with associative, commutative, or associative-commutative functions with respect to the parameter “number of variables”. It is shown that if every variable occurs only once then both of the associative and associative-commutative unification problems can be solved in polynomial time, but that in the general case, both problems are W [ 1 ] -hard even when one of the two input terms is variable-free. For commutative unification, an algorithm whose time complexity depends exponentially on the number of variables is presented; moreover, if a certain conjecture is true then the special case where one input term is variable-free belongs to FPT. Some related results are also derived for a natural generalization of the classic string and tree edit distance problems that allows variables. [ABSTRACT FROM AUTHOR]

Measuring the distance between data sequences is a challenging problem, especially in the presence of outliers and local distortions. Existing measures typically align the two sequences before calculating their distance based on the difference between the corresponding elements. However, those alignments are not flexible enough to accommodate local distortions and severe effects of outliers. In this article, we propose a novel distance, termed as Partial Ordered Wasserstein (POW), which is flexible to align two sequences and robust w.r.t outliers. We further analyze some properties of the proposed distance, and show that POW enables a simple way to automatically and adaptively select the amount of transported mass, so as to accommodate outliers. Two different applications of POW are then studied: time-series classification and multi-step localization. Finally, we conduct extensive experiments on widely available public datasets to evaluate the performance of the proposed distances. Experimental results, obtained via a thorough experimental protocol, show the performance superiority of POW over several existing distance measures. Our Python source code is available on https://github.com/TungDP/Partial-Ordered-Wasserstein-Distance • A novel distance that are flexible in alignment and robust to outliers is proposed. • Some properties of the proposed distance are theoretically analyzed. • The distance enables a simple way to automatically select a crucial hyper parameter. • Its application in time-series classification and multi-step localization are studied. • Extensive experimental results validate the advantages of the proposed distance. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a fixed-parameter algorithm for the tree edit distance problem for unordered trees under the unit cost model that works in time and space, where the parameter is the maximum bound of the edit distance and is the maximum size of input trees. This paper also presents polynomial-time algorithms for the case where the maximum degree of the largest common subtree is bounded by a constant. [ABSTRACT FROM AUTHOR]

Background: Measuring similarities between tree structured data is important for analysis of RNA secondary structures, phylogenetic trees, glycan structures, and vascular trees. The edit distance is one of the most widely used measures for comparison of tree structured data. However, it is known that computation of the edit distance for rooted unordered trees is NP-hard. Furthermore, there is almost no available software tool that can compute the exact edit distance for unordered trees. Results: In this paper, we present a practical method for computing the edit distance between rooted unordered trees. In this method, the edit distance problem for unordered trees is transformed into the maximum clique problem and then efficient solvers for the maximum clique problem are applied. We applied the proposed method to similar structure search for glycan structures. The result suggests that our proposed method can efficiently compute the edit distance for moderate size unordered trees. It also suggests that the proposed method has the accuracy comparative to those by the edit distance for ordered trees and by an existing method for glycan search. Conclusions: The proposed method is simple but useful for computation of the edit distance between unordered trees. The object code is available upon request. [ABSTRACT FROM AUTHOR]

Pattern is a reusable description of knowledge. Efficient software development can be achieved by sharing and reusing knowledge using patterns and their relations. Because the manual analysis of relations among patterns is costly, we proposed an automatic relation analysis technique for software patterns. Knowledge management in embedded software design has fallen behind. However, in these days, some patterns in embedded software design have become available on the World Wide Web (WWW) and other resources.The purpose of this paper is to obtain some useful relations among embedded software design patterns and GoF's design patterns. Our technique will be useful for the automated relation analysis among patterns. As a result of experiments, some relations among different pattern catalogs (e.g., GoF's design pattern catalog and real-time system design pattern catalog) are extracted. These relations are thought to be useful in software development. [ABSTRACT FROM AUTHOR]

The tree inclusion problem is, given two node-labeled trees P and T (the "pattern tree" and the "target tree"), to locate every minimal subtree in T (if any) that can be obtained by applying a sequence of node insertion operations to P. Although the ordered tree inclusion problem is solvable in polynomial time, the unordered tree inclusion problem is NP-hard. The currently fastest algorithm for the latter is a classic algorithm by Kilpeläinen and Mannila from 1995 that runs in O (d 2 2 d m n) time, where m and n are the sizes of the pattern and target trees, respectively, and d is the degree of the pattern tree. Here, we develop a new algorithm that runs in O (d 2 d m n 2) time, improving the exponential factor from 2 2 d to 2 d by considering a particular type of ancestor-descendant relationships that is suitable for dynamic programming. We also study restricted variants of the unordered tree inclusion problem. • We present an O ⁎ (2 d) -time algorithm for the unordered tree inclusion problem. • This is the first improvement since the O ⁎ (4 d) -time algorithm from 1995 by Kilpeläinen and Mannila. • Even faster algorithms are given for some versions of the problem with restrictions on the node labels and tree heights. • A special case of the problem where only the leaves have distinct labels is proved to be NP-hard. [ABSTRACT FROM AUTHOR]

The largest common subtree problem is to find a bijective mapping between subsets of nodes of two input rooted trees of maximum cardinality or weight that preserves labels and ancestry relationship. The problem is known to be NP-hard for unordered trees. In this paper, we consider a restricted unordered case in which the maximum outdegree of a common subtree is bounded by a constant D . We present an O ( n D ) time algorithm where n is the maximum size of two input trees, which improves a previous O ( n 2 D ) time algorithm. We also present an O ( ( H 2 ⋅ 2 2 H − 1 ⋅ D 2 H ) D − 1 poly ( n ) ) time algorithm, where H is the maximum height of two input trees. [ABSTRACT FROM AUTHOR]

Abstract: Given two rooted, labeled, unordered trees, the common subtree problem is to find a bijective matching between subsets of nodes of the trees of maximum cardinality which preserves labels and ancestry relationship. The tree edit distance problem is to determine the least cost sequence of insertions, deletions and substitutions that converts a tree into another given tree. Both problems are known to be hard to approximate within some constant factor in general. We tackle these problems from two perspectives: giving exact algorithms, either for special cases or in terms of some parameters; and approximation algorithms and hardness of approximation. We present a parameterized algorithm in terms of the number of branching nodes that solves both problems and yields polynomial algorithms for several special classes of trees. This is complemented with a tighter APX-hardness proof that holds when the trees are of height one and two, respectively. Furthermore, we present the first approximation algorithms for both problems. In particular, for the common subtree problem for trees, we present an algorithm achieving a ratio, where is the number of branching nodes in the optimal solution. We also present constant factor approximation algorithms for both problems in the case of bounded height trees. [Copyright &y& Elsevier]

Many kinds of tree-structured data, such as RNA secondary structures, have become available due to the progress of techniques in the field of molecular biology. To analyze the tree-structured data, various measures for computing the similarity between them have been developed and applied. Among them, tree edit distance is one of the most widely used measures. However, the tree edit distance problem for unordered trees is NP-hard. Therefore, it is required to develop efficient algorithms for the problem. Recently, a practical method called clique-based algorithm has been proposed, but it is not fast for large trees. This article presents an improved clique-based method for the tree edit distance problem for unordered trees. The improved method is obtained by introducing a dynamic programming scheme and heuristic techniques to the previous clique-based method. To evaluate the efficiency of the improved method, we applied the method to comparison of real tree structured data such as glycan structures. For large tree-structures, the improved method is much faster than the previous method. In particular, for hard instances, the improved method achieved more than 100 times speed-up. [ABSTRACT FROM AUTHOR]

Abstract. Digital libraries on the Internet are constructed separately and managed autonomously, and their semantics are different from each other. On the other hand, users of digital libraries have their own information needs. In order for users to fully utilize digital libraries, therefore, a new method for promoting mediation between the semantics of digital libraries and users' information needs is vital. COSPEX (COnceptual SPace EXplorer), proposed in this paper, is a system that can enhance such mediation. Through the exploration of information spaces encompassing multiple digital libraries, users of COSPEX can construct their own private digital libraries. [ABSTRACT FROM AUTHOR]