Influential user detection is critical in supporting the human facilitator-based facilitation in the online forum. Traditional approaches to detect influential users in the online forum focus on the statistical activity information such as the number of posts. However, statistical activity information cannot fully reflect the influence that users bring to the online forum. In this paper, we propose to detect the influencers from the influence propagation perspective and focus on the influential maximization (IM) problem which aims at choosing a set of users that maximize the influence propagation from the entire social network. An online forum influence propagation network (OFIPN) is proposed to model the influence from an individual user perspective and influence propagation between users, and a heuristic algorithm that is proposed to find influential users in OFIPN. Experiments are conducted by simulations with a real-world social network. Our empirical results show the effectiveness of the proposed algorithm.

As the Internet has become prevalent, the popularity of net media has been growing, to a point that it has taken over conventional mass media. However, TWtrends, the Twitter trends visualization system operated by our research team since 2019, indicates that many topics on TV programs frequently appear on Twitter trendlines. This study investigates the relationship between Twitter and TV programs by collecting information on Twitter trends and TV programs simultaneously. Although this study provides a rough estimation of the volume of tweets that mention TV programs, the results show that several tweets mention TV programs at a constant rate, which tends to increase on the weekend. This tendency of TV-related tweets stems from the audience rating survey results. Considering the study outcome, and the fact that many TV programs introduce topics popular in social media, implies codependency between Internet media (social media) and mass media.

In recent years, with the aging of society, many kinds of research have been actively conducted to recognize human activity in a home to watch over the elderly. Multiple sensors for activity recognition are used. However, we need to consider privacy when using these sensors. One of the candidates of the sensors that keep privacy is a sound sensor. MFCC (Mel-Frequency Cepstral Coefficient) is widely used as a feature extraction algorithm for voice recognition. However, it is not suitable to apply conventional MFCC to activity recognition by sounds of daily life. We denote “sounds of daily life” as “life sounds” simply in this paper. The reason is that conventional MFCC does not extract well several features of life sounds that appear at high frequencies. This paper proposes the improved MFCC and reports the evaluation results of activity recognition by machine learning SVM (Support Vector Machine) using features extracted by improved MFCC.

Animating 3D characters using motion capture data requires basic expertise and manual labor. To support the creativity of animation design and make it easier for common users, we present a sketch-based interface DualMotion, with rough sketches as input for designing daily-life animations of characters, such as walking and jumping. Our approach enables to combine global motions of lower limbs and the local motion of the upper limbs in a database by utilizing a two-stage design strategy. Users are allowed to design a motion by starting with drawing a rough trajectory of a body/lower limb movement in the global design stage. The upper limb motions are then designed by drawing several more relative motion trajectories in the local design stage. We conduct a user study and verify the effectiveness and convenience of the proposed system in creative activities.

At manufacturing sites, mass customization is expanding along with the increasing variety of customer needs. This situation leads to complications in production planning for the factory manager, and production plans are likely to change suddenly at the manufacturing site. Because such sudden fluctuations in production often occur, it is particularly difficult to optimize the parts supply operations in these production processes. As a solution to such problems, Industry 4.0 has expanded to promote the use of digital technologies at manufacturing sites; however, these solutions can be expensive and time-consuming to introduce. Therefore, not all factory managers are favorable toward introducing digital technology. In this study, we propose a method to support parts supply operations that decreases work stagnation and fluctuation without relying on the experience of workers who supply parts in the various production processes. Furthermore, we constructed a system that is inexpensive and easy to introduce using both LPWA and BLE communications. The purpose of the system is to level out work in in-process logistics. In an experiment, the proposed method was introduced to a manufacturing site, and we compared how the workload of the site's workers changed. The experimental results show that the proposed method is effective for workload leveling in parts supply operations.

Companies listed on the stock exchange are required to share their annual reports with the U.S. Securities and Exchange Commission (SEC) within the first three months following the fiscal year. These reports, namely 10-K Filings, are presented to public interest by the SEC through an Electronic Data Gathering, Analysis, and Retrieval database. 10-K Filings use standard file formats (xbrl, html, pdf) to publish the financial reports of the companies. Although the file formats propose a standard structure, the content and the meta-data of the financial reports (e.g. tag names) is not strictly bound to a pre-defined schema. This study proposes a data collection and data preprocessing method to semantify the financial reports and use the collected data for further analysis (i.e. machine learning). The analysis of eight different datasets, which were created during the study, are presented using the proposed data transformation methods. As a use case, based on the datasets, five different machine learning algorithms were utilized to predict the existence of the corresponding company in the S&P 500 index. According to the strong machine learning results, the dataset generation methodology is successful and the datasets are ready for further use.

Aiming at the different abilities of the defogging algorithms in different fog concentrations, this paper proposes a fog image classification algorithm for a small and imbalanced sample dataset based on a convolution neural network, which can classify the fog images in advance, so as to improve the effect and adaptive ability of image defogging algorithm in fog and haze weather. In order to solve the problems of environmental interference, camera depth of field interference and uneven feature distribution in fog images, the CutBlur-Gauss data augmentation method and focal loss and label smoothing strategies are used to improve the accuracy of classification. It is compared with the machine learning algorithm SVM and classical convolution neural network classification algorithms alexnet, resnet34, resnet50 and resnet101. This algorithm achieves 94.5% classification accuracy on the dataset in this paper, which exceeds other excellent comparison algorithms at present, and achieves the best accuracy. It is proved that the improved algorithm has better classification accuracy.

Annealing machines such as quantum annealing machines and semiconductor-based annealing machines have been attracting attention as an efficient computing alternative for solving combinatorial optimization problems. They solve original combinatorial optimization problems by transforming them into a data structure called an Ising model. At that time, the bit-widths of the coefficients of the Ising model have to be kept within the range that an annealing machine can deal with. However, by reducing the Ising-model bit-widths, its minimum energy state, or ground state, may become different from that of the original one, and hence the targeted combinatorial optimization problem cannot be well solved. This paper proposes an effective method for reducing Ising model's bit-widths. The proposed method is composed of two processes: First, given an Ising model with large coefficient bit-widths, the shift method is applied to reduce its bit-widths roughly. Second, the spin-adding method is applied to further reduce its bit-widths to those that annealing machines can deal with. Without adding too many extra spins, we efficiently reduce the coefficient bit-widths of the original Ising model. Furthermore, the ground state before and after reducing the coefficient bit-widths is not much changed in most of the practical cases. Experimental evaluations demonstrate the effectiveness of the proposed method, compared to existing methods.

Memory-efficient Internet Protocol (IP) lookup with high speed is essential to achieve link-speed packet forwarding in IP routers. The rapid growth of Internet traffic and the development of optical link technologies have made IP lookup a major performance bottleneck in core routers. In this paper, we propose a new IP route lookup architecture based on hardware called Prefix-Route Trie (PR-Trie), which supports both IPv4 and IPv6 addresses. In PR-Trie, we develop a novel structure called Overlapping Hybrid Trie (OHT) to perform fast longest-prefix-matching (LPM) based on Multibit-Trie (MT), and a hash-based level matching query used to achieve only one off-chip memory access per lookup. In addition, the proposed PR-Trie also supports fast incremental updates. Since the memory complexity in MT-based IP lookup schemes depends on the level-partitioning solution and the data structure used, we develop an optimization algorithm called Bitmap-based Prefix Partitioning Optimization (BP²O). The proposed BP²O is based on a heuristic search using Ant Colony Optimization (ACO) algorithms to optimize memory efficiency. Experimental results using real-life routing tables prove that our proposal has superior memory efficiency. Theoretical performance analyses show that PR-Trie outperforms the classical Trie-based IP lookup algorithms.

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%.

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9% character error rate.

Multimodal named entity recognition (MNER) is the task of recognizing named entities in multimodal context. Existing methods focus on utilizing co-attention mechanism to discover the relationships between multiple modalities. However, they still have two deficiencies: First, current methods fail to fuse the multimodal representations in a fine-grained way, which may bring noise of visual modalities. Second, current methods ignore bridging the semantic gap between heterogeneous modalities. To solve the above issues, we propose a novel MNER method with bottleneck fusion and contrastive learning (BFCL). Specifically, we first incorporate the transformer-based bottleneck fusion mechanism, subsequently, information between different modalities can only be exchanged through several bottleneck tokens, thus reducing the noise propagation. Then we propose two decoupled image-text contrastive losses to align the unimodal representations, making the representations of semantically similar modalities closer, while the representations of semantically different modalities farther away. Experimental results demonstrate that our method is competitive to the state-of-the-art models, and achieves 74.54% and 85.70% F1-scores on Twitter-2015 and Twitter-2017 datasets, respectively.

Why and how do people view lyrics? Although various lyrics-based music systems have been proposed, this fundamental question remains unexplored. Better understanding of lyrics viewing behavior would be beneficial for both researchers and music streaming platforms to improve their lyrics-based systems. Therefore, in this paper, we investigate why and how people view lyrics, especially when they listen to music on a smartphone. To answer “why,” we conduct a questionnaire-based online user survey involving 206 participants. To answer “how,” we analyze over 23 million lyrics request logs sent from the smartphone application of a music streaming service. Our analysis results suggest several reusable insights, including the following: (1) People have high demand for viewing lyrics to confirm what the artist sings, more deeply understand the lyrics, sing the song, and figure out the structure such as verse and chorus. (2) People like to view lyrics after returning home at night and before going to sleep rather than during the daytime. (3) People usually view the same lyrics repeatedly over time. Applying these insights, we also discuss application examples that could enable people to more actively view lyrics and listen to new songs, which would not only diversify and enrich people's music listening experiences but also be beneficial especially for music streaming platforms.

Common schedulers for long-term running services that perform task-level optimization fail to accommodate short-living batch processing (BP) jobs. Thus, many efficient job-level scheduling strategies are proposed for BP jobs. However, the existing scheduling strategies perform time-consuming objective optimization which yields non-negligible scheduling delay. Moreover, they tend to assign BP jobs in a centralized manner to reduce monetary cost and synchronization overhead, which can easily cause resource contention due to the task co-location. To address these problems, this paper proposes TEBAS, a time-efficient balance-aware scheduling strategy, which spreads all tasks of a BP job into the cluster according to the resource specifications of a single task based on the observation that computing tasks of a BP job commonly possess similar features. The experimental results show the effectiveness of TEBAS in terms of scheduling efficiency and load balancing performance.

We propose GConvLoc, a WiFi fingerprinting-based indoor localization method utilizing graph convolutional networks. Using the graph structure, we can consider the fingerprint data of the reference points and their location labels in addition to the fingerprint data of the test point at inference time. Experimental results show that GConvLoc outperforms baseline methods that do not utilize graphs.

To overcome the challenge in micro-expression recognition that it only emerge in several small facial regions with low intensity, some researchers proposed facial region partition mechanisms and introduced group sparse learning methods for feature selection. However, such methods have some shortcomings, including the complexity of region division and insufficient utilization of critical facial regions. To address these problems, we propose a novel Group Sparse Reduced Rank Tensor Regression (GSRRTR) to transform the fearure matrix into a tensor by laying blocks and features in different dimensions. So we can process grids and texture features separately and avoid interference between grids and features. Furthermore, with the use of Tucker decomposition, the feature tensor can be decomposed into a product of core tensor and a set of matrix so that the number of parameters and the computational complexity of the scheme will decreased. To evaluate the performance of the proposed micro-expression recognition method, extensive experiments are conducted on two micro expression databases: CASME2 and SMIC. The experimental results show that the proposed method achieves comparable recognition rate with less parameters than state-of-the-art methods.