We consider a property about a result of non-negative matrix factorization under a parallel moving of data points. The shape of a cloud of original data points and that of data points moving parallel to a vector are identical. Thus it is sometimes required that the coefficients to basis vectors of both data points are also identical from the viewpoint of classification. We show a necessary and sufficient condition for such an invariance property under a translation of the data points.

As one type of machine-learning model, a “decision-tree ensemble model” (DTEM) is represented by a set of decision trees. A DTEM is mainly known to be valid for structured data; however, like other machine-learning models, it is difficult to train so that it returns the correct output value (called “prediction value”) for any input value (called “attribute value”). Accordingly, when a DTEM is used in regard to a system that requires reliability, it is important to comprehensively detect attribute values that lead to malfunctions of a system (failures) during development and take appropriate countermeasures. One conceivable solution is to install an input filter that controls the input to the DTEM and to use separate software to process attribute values that may lead to failures. To develop the input filter, it is necessary to specify the filtering condition for the attribute value that leads to the malfunction of the system. In consideration of that necessity, we propose a method for formally verifying a DTEM and, according to the result of the verification, if an attribute value leading to a failure is found, extracting the range in which such an attribute value exists. The proposed method can comprehensively extract the range in which the attribute value leading to the failure exists; therefore, by creating an input filter based on that range, it is possible to prevent the failure. To demonstrate the feasibility of the proposed method, we performed a case study using a dataset of house prices. Through the case study, we also evaluated its scalability and it is shown that the number and depth of decision trees are important factors that determines the applicability of the proposed method.

Multi-modal semantic trajectory prediction has become a new challenge due to the rapid growth of multi-modal semantic trajectories with text message. Traditional RNN trajectory prediction methods have the following problems to process multi-modal semantic trajectory. The distribution of multi-modal trajectory samples shifts gradually with training. It leads to difficult convergency and long training time. Moreover, each modal feature shifts in different directions, which produces multiple distributions of dataset. To solve the above problems, MNERM (Mode Normalization Enhanced Recurrent Model) for multi-modal semantic trajectory is proposed. MNERM embeds multiple modal features together and combines the LSTM network to capture long-term dependency of trajectory. In addition, it designs Mode Normalization mechanism to normalize samples with multiple means and variances, and each distribution normalized falls into the action area of the activation function, so as to improve the prediction efficiency while improving greatly the training speed. Experiments on real dataset show that, compared with SERM, MNERM reduces the sensitivity of learning rate, improves the training speed by 9.120 times, increases HR@1 by 0.03, and reduces the ADE by 120 meters.

Numerous applications such as autonomous driving, satellite imagery sensing, and biomedical imaging use computer vision as an important tool for perception tasks. For Intelligent Transportation Systems (ITS), it is required to precisely recognize and locate scenes in sensor data. Semantic segmentation is one of computer vision methods intended to perform such tasks. However, the existing semantic segmentation tasks label each pixel with a single object's class. Recognizing object attributes, e.g., pedestrian orientation, will be more informative and help for a better scene understanding. Thus, we propose a method to perform semantic segmentation with pedestrian attribute recognition simultaneously. We introduce an attribute-aware loss function that can be applied to an arbitrary base model. Furthermore, a re-annotation to the existing Cityscapes dataset enriches the ground-truth labels by annotating the attributes of pedestrian orientation. We implement the proposed method and compare the experimental results with others. The attribute-aware semantic segmentation shows the ability to outperform baseline methods both in the traditional object segmentation task and the expanded attribute detection task.

The similarity of words extracted from the rich text relation network is the main way to calculate the semantic similarity. Complex relational information and text content in Wikipedia website, Community Question Answering and social network, provide abundant corpus for semantic similarity calculation. However, most typical research only focused on single relationship. In this paper, we propose a semantic similarity calculation model which integrates multiple relational information, and map multiple relationship to the same semantic space through learning representing matrix and semantic matrix to improve the accuracy of semantic similarity calculation. In experiments, we confirm that the semantic calculation method which integrates many kinds of relationships can improve the accuracy of semantic calculation, compared with other semantic calculation methods.

According to the official TDOAS 2009~2017 survey, the penetration rate of social media in Taiwan has reached a record 96.8%, while the Internet access rate is as high as 99.7%. However, people using government online services access to relevant information has continued to decline over the years, from 50.8% in 2009 to 35.4% in 2017. At the same time, the proportion of e-transaction users has also dropped simultaneously from 30.3% to 27.7%. In particular, only 1.1% of them are interested in government online forums, while the remaining 97.2% are more willing to engage in social media as a source of personal reference. The study aims to explore why are users not interested in accessing e-government services? Are they affected by the popularity of social networking applications? What are the key factors for users to continue to use e-government service? The research framework was adapted from expectation confirmation theory and model (ECT/ECM), technology acceptance model (TAM) with trust theories, in validating attitude measures for a better understanding of continuance intention of using e-government service. In terms of measurement, the assessment used the structural equation modeling method (SEM) to explore the views and preferences of 400 college students on e-government service. The study results identified that perceived usefulness not only plays a full mediating role, it is expected to be the most important ex-post factor influencing user's intention to continue using e-government service. It also clarifies that the intent to continue to use e-government services is not related to use any alternative means such as social media application.

Semi-bent functions have important applications in cryptography and coding theory. 2-rotation symmetric semi-bent functions are a class of semi-bent functions with the simplicity for efficient computation because of their invariance under 2-cyclic shift. However, no construction of 2-rotation symmetric semi-bent functions with algebraic degree bigger than 2 has been presented in the literature. In this paper, we introduce four classes of 2m-variable 2-rotation symmetric semi-bent functions including balanced ones. Two classes of 2-rotation symmetric semi-bent functions have algebraic degree from 3 to m for odd m≥3, and the other two classes have algebraic degree from 3 to m/2 for even m≥6 with m/2 being odd.

Secure two-party comparison plays a crucial role in many privacy-preserving applications, such as privacy-preserving data mining and machine learning. In particular, the available comparison protocols with the appropriate input/output configuration have a significant impact on the performance of these applications. In this paper, we firstly describe a taxonomy of secure two-party comparison protocols which allows us to describe the different configurations used for these protocols in a systematic manner. This taxonomy leads to a total of 216 types of comparison protocols. We then describe conversions among these types. While these conversions are based on known techniques and have explicitly or implicitly been considered previously, we show that a combination of these conversion techniques can be used to convert a perhaps less-known two-party comparison protocol by Nergiz et al. (IEEE SocialCom 2010) into a very efficient protocol in a configuration where the two parties hold shares of the values being compared, and obtain a share of the comparison result. This setting is often used in multi-party computation protocols, and hence in many privacy-preserving applications as well. We furthermore implement the protocol and measure its performance. Our measurement suggests that the protocol outperforms the previously proposed protocols for this input/output configuration, when off-line pre-computation is not permitted.

As the superstructure of knowledge graph, ontology has been widely applied in knowledge engineering. However, it becomes increasingly difficult to be practiced and comprehended due to the growing data size and complexity of schemas. Hence, ontology summarization surfaced to enhance the comprehension and application of ontology. Existing summarization methods mainly focus on ontology's topology without taking semantic information into consideration, while human understand information based on semantics. Thus, we proposed a novel algorithm to integrate semantic information and topological information, which enables ontology to be more understandable. In our work, semantic and topological information are represented by concept vectors, a set of high-dimensional vectors. Distances between concept vectors represent concepts' similarity and we selected important concepts following these two criteria: 1) the distances from important concepts to normal concepts should be as short as possible, which indicates that important concepts could summarize normal concepts well; 2) the distances from an important concept to the others should be as long as possible which ensures that important concepts are not similar to each other. K-means++ is adopted to select important concepts. Lastly, we performed extensive evaluations to compare our algorithm with existing ones. The evaluations prove that our approach performs better than the others in most of the cases.

This paper proposes a computationally efficient offline semi-supervised algorithm that yields a more accurate prediction than the label propagation algorithm, which is commonly used in online graph-based semi-supervised learning (SSL). Our proposed method is an offline method that is intended to assist online graph-based SSL algorithms. The efficacy of the tool in creating new learning algorithms of this type is demonstrated in numerical experiments.

This paper proposes a new rule-based approach to automatic question generation. The proposed approach focuses on analysis of both syntactic and semantic structure of a sentence. Although the primary objective of the designed system is question generation from sentences, automatic evaluation results shows that, it also achieves great performance on reading comprehension datasets, which focus on question generation from paragraphs. Especially, with respect to METEOR metric, the designed system significantly outperforms all other systems in automatic evaluation. As for human evaluation, the designed system exhibits similar performance by generating the most natural (human-like) questions.

This study proposes a novel machine learning architecture and various learning algorithms to build-in anti-phishing services for avoiding cyber-phishing attack. For the rapid develop of information technology, hackers engage in cyber-phishing attack to steal important personal information, which draws information security concerns. The prevention of phishing website involves in various aspect, for example, user training, public awareness, fraudulent phishing, etc. However, recent phishing research has mainly focused on preventing fraudulent phishing and relied on manual identification that is inefficient for real-time detection systems. In this study, we used methods such as ANOVA, X2, and information gain to evaluate features. Then, we filtered out the unrelated features and obtained the top 28 most related features as the features to use for the training and evaluation of traditional machine learning algorithms, such as Support Vector Machine (SVM) with linear or rbf kernels, Logistic Regression (LR), Decision tree, and K-Nearest Neighbor (KNN). This research also evaluated the above algorithms with the ensemble learning concept by combining multiple classifiers, such as Adaboost, bagging, and voting. Finally, the eXtreme Gradient Boosting (XGBoost) model exhibited the best performance of 99.2%, among the algorithms considered in this study.

To minimize the damage caused by landslides resulting from torrential rain, residents must quickly evacuate to a place of refuge. To make the decision to evacuate, residents must be able to collect and share disaster information. Firstly, this paper introduces the Grass-roots Information Distribution System and a fixed type monitoring system which our research group has been developing. The fixed type monitoring system is deployed at the location of apparent danger, whereas the Grass-roots Information Distribution System distributes disaster information acquired from the fixed type monitoring system through a mobile ad hoc network (MANET) to residents. The MANET is configured using mobile terminals of residents. Next, in this paper, an information dissemination scheme utilizing a MANET and cellular networks to communicate among mobile terminals is proposed and simulated in the area where our research group has been deploying the distribution system. The MANET topology and information distribution obtained from the simulation results for further field experiments are then discussed.

A number of all-optical signal processing schemes based on nonlinear optical effects have been proposed and demonstrated for use in future photonic networks. Since various modulation formats have been developed for optical communication systems, all-optical converters between different modulation formats will be a key technology to connect networks transparently and efficiently. This paper reviews our recent works on all-optical modulation format conversion technologies in order to highlight the fundamental principles and applications in variety of all-optical signal processing schemes.

Optical I/O core based on silicon photonics technology and optical/electrical assembly was developed as a fingertip-size optical module with high bandwidth density, low power consumption, and high temperature operation. The advantages of the optical I/O core, including hybrid integration of quantum dot laser diode and optical pin, allow us to achieve 300-m transmission at 25Gbps per channel when optical I/O core is mounted around field-programmable gate array without clock data recovery.

We propose a method to find assembly models contained in another assembly model given as a query from a set of 3D CAD assembly models. A 3D CAD assembly model consists of multiple components and is constructed using a 3D CAD software. The proposed method distinguishes assembly models which consist of a subset of components constituting the query model and also whose components have the same layout as the subset of the components. We compute difference between the shapes and the layouts of the components from the sinograms which are constructed by the Radon transform of their projections from various angles. We evaluate the proposed method experimentally using the assembly models which we prepare as a benchmark. The proposed method can also be used to find the database models which contains a query model.

Network embedding has attracted an increasing amount of attention in recent years due to its wide-ranging applications in graph mining tasks such as vertex classification, community detection, and network visualization. Network embedding is an important method to learn low-dimensional representations of vertices in networks, aiming to capture and preserve the network structure. Almost all the existing network embedding methods adopt the so-called Skip-gram model in Word2vec. However, as a bag-of-words model, the skip-gram model mainly utilized the local structure information. The lack of information metrics for vertices in global network leads to the mix of vertices with different labels in the new embedding space. To solve this problem, in this paper we propose a Network Representation Learning method with Deep Metric Learning, namely DML-NRL. By setting the initialized anchor vertices and adding the similarity measure in the training progress, the distance information between different labels of vertices in the network is integrated into the vertex representation, which improves the accuracy of network embedding algorithm effectively. We compare our method with baselines by applying them to the tasks of multi-label classification and data visualization of vertices. The experimental results show that our method outperforms the baselines in all three datasets, and the method has proved to be effective and robust.

Spectral graph theory gives an algebraic approach to the analysis of the dynamics of a network by using the matrix that represents the network structure. However, it is not easy for social networks to apply the spectral graph theory because the matrix elements cannot be given exactly to represent the structure of a social network. The matrix element should be set on the basis of the relationship between persons, but the relationship cannot be quantified accurately from obtainable data (e.g., call history and chat history). To get around this problem, we utilize the universality of random matrices with the feature of social networks. As such a random matrix, we use the normalized Laplacian matrix for a network where link weights are randomly given. In this paper, we first clarify that the universality (i.e., the Wigner semicircle law) of the normalized Laplacian matrix appears in the eigenvalue frequency distribution regardless of the link weight distribution. Then, we analyze the information propagation speed by using the spectral graph theory and the universality of the normalized Laplacian matrix. As a result, we show that the worst-case speed of the information propagation changes up to twice if the structure (i.e., relationship among people) of a social network changes.

Semitransparent organic solar cells were fabricated using lamination process. The devices were realized by using two independent substrates with transparent indium-tin-oxide electrode. One substrate was coated with poly(ethylenedioxy-thiophene)/poly(styrenesulfonate) layer and active layer of poly(3-hexylthiophene-2,5-diyl) (P3HT) and (6,6)-phenyl-C61 butyric acid methyl ester mixture. Another substrate was coated with ultra-thin polyethylenimine ethoxylated. The two substrates were laminated using hot press system. The device exhibited semitransparency and showed typical photovoltaic characteristics with open voltage of 0.59 V and short circuit current of 2.9 mA/cm2.

Copper (Cu) electroless plating was conducted on planar and microstructured polydimethylsiloxane (PDMS) substrates. In this study, organic thin films terminated with nitrogen (N)-containing groups, e.g. poly (dimethylaminoethyl methacrylate) brush (PDMAEMA), aminopropyl trimethoxysilane monolayer (APTES), and polydopamine (PDA) were used to anchor palladium (Pd) catalyst. While electroless plating was successfully promoted on all sample surfaces, PDMAEMA was found to achieve the best adhesion strength to the PDMS surfaces, compared to APTES- and PDA-covered PDMS substrates, due to covalent bonding, anchoring effects of polymer chains as well as high affinity of N atoms to Pd species. Our process was also successfully applied to the electroless plating of microstructured PDMS substrates.