Ruqian lu

Chinese Academy of Sciences | CAS · Academy of Mathematics and Systems Science

Deep metric learning (DML) has achieved great results on visual understanding tasks by seamlessly integrating conventional metric learning with deep neural networks. Existing deep metric learning methods focus on designing pair-based distance loss to decrease intra-class distance while increasing interclass distance. However, these methods fail to...

In order to describe the nonlinear distribution of the image dataset, researchers propose a manifold assumption, called manifold learning (MAL). The geometry information based on a manifold is measured by the Riemannian metric, such as the geodesic distance. Thus, owing to mining the intrinsic geometric structure of the dataset, we need to learn th...

Along with the development of information technologies such as mobile Internet, information acquisition technology, cloud computing and big data technology, the traditional knowledge engineering and knowledge-based software engineering have undergone fundamental changes where the network plays an increasingly important role. Within this context, it...

While there have been lots of work studying frequent subgraph mining, very rare publications have discussed frequent subnet mining from more complicated data structures such as Petri nets. This paper studies frequent subnets mining from a single large Petri net. We follow the idea of transforming a Petri net in net graph form and to mine frequent s...

This paper proposes for the first time an algorithm PSpan for mining frequent complete subnets from a set of Petri nets. We introduced the concept of complete subnets and the net graph representation. PSpan transforms Petri nets in net graphs and performs sub-net graph mining on them, then transforms the results back to frequent subnets. PSpan foll...

Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. However, there’s still no guarantee that the generated summaries are grammatical, concise, and convey all salient information as the original documents have. To make the summarizatio...

Since Shahshahani and Landgrebe published their seminal paper (Shahshahani and Landgrebe, 1994) [1] in 1994, the study on semi-supervised learning (SSL) developed fast and has already become one of the main streams of machine learning (ML) research. However, there are still some areas or problems where the capability of SSL remains seriously limite...

In this paper, we propose an evolving network model with information filtering and mixed attachment mechanisms. We theoretically analyze the in-degree distribution of networks generated by the proposed model in two special cases, and prove that the in-degree distribution is power-law if the new coming vertex does not filter information. Otherwise,...

We propose a novel paradigm of semi-supervised learning (SSL)--the semi-supervised multiple representation behavior learning (SSMRBL). SSMRBL aims to tackle the difficulty of learning a grammar for natural language parsing where the data are natural language texts and the 'labels' for marking data are parsing trees and/or grammar rule pieces. We ca...

Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model and domain knowledge concer...

The current remarkable development of communication technology is enabling the intelligent driving system by providing a V2X network to exchange and process transportation data. However, security, as a fundamental requirement, is still lacking in many aspects of current V2X networks. For V2X networks, low latency, as a critical requirement for V2X...

This paper presents a new approach of automatic text summarization which combines domain oriented text analysis (DoTA) and rhetorical structure theory (RST) in a grammar form: the attributed rhetorical structure grammar (ARSG), where the non-terminal symbols are domain keywords, called domain relations, while the rhetorical relations serve as attri...

We introduce some new perfect state transfer and teleportation schemes by quantum walks with two coins. Encoding the transferred information in coin 1 state and alternatively using two coin operators, we can perfectly recover the information on coin 1 state at target position only by at most two times of flipping operation. Based on quantum walks w...

After entering the big data era, a new term of ‘big knowledge’ has been coined to deal with challenges in mining a mass of knowledge from big data. While researchers used to explore the basic characteristics of big data, we have not seen any studies on the general and essential properties of big knowledge. To fill this gap, this paper studies the c...

Background In structural biology area, protein residue-residue contacts play a crucial role in protein structure prediction. Some researchers have found that the predicted residue-residue contacts could effectively constrain the conformational search space, which is significant for de novo protein structure prediction. In the last few decades, rela...

Lexical chain has been widely used in many NLP areas. However, when using it for Web text summarization, especially for domain-specific text summarization, we got low accuracy results. The main reason is that traditional lexical chains only take nouns into consideration while information of other grammatical parts is missing. We introduce lexical c...

Starting in July 2016, the Ministry of Science and Technology of China, along with several other national agencies, sponsors a 54-month 45-million RMB (Chinese Yuan) project on Knowledge Engineering with Big Data (www.bigke.org) for 15 top research and development institutions to study the fundamental theory and applications of BigKE, a big-data kn...

In this work, we propose a new quantum structure—weak quantum MV algebras (wQMV algebras)—and define coupled bimonoids and strong coupled bimonoids. We find that the coupled bimonoids and strong coupled bimonoids are ring-like structures corresponding to lattice-ordered wQMV algebras and lattice-ordered QMV algebras, respectively. Using an automate...

Symmetric Positive Definite (SPD) matrices have been widely used as feature descriptors in image recognition. However, the dimension of an SPD matrix built by image feature descriptors is usually high. So SPD matrices oriented dimensionality reduction techniques are needed. The existing manifold learning algorithms only apply to reduce the dimensio...

Much progress has been made in Protein structure prediction during the last few decades. As the predicted models can span a broad range of accuracy spectrum, the accuracy of quality estimation becomes one of the key elements of successful protein structure prediction. Over the past years, a number of methods have been developed to address this issu...

With computer technologies being widely used in animation field, the complex process of creating animations makes the animators more and more eager to a highly automatic animation technology. In consideration of the durable vitality and wide applications of the 2D animation in recent years, this paper proposes a technology for automatic generation...

We present recursion theoretical characterizations of the computational power of Turing machines in the framework of unsharp quantum logic. For unsharp quantum logic, let a lattice ordered quantum multiple valued (QMV) algebra be its truth value lattice. When lattice ordered QMV algebras satisfy a locally finite condition (that is, every non-zero e...

This paper proposed a knowware based supervised machine learning technique for domain specific regression and classification of Web documents. It is simple because it is only based on word counting techniques without natural language understanding and complicated statistic techniques. Starting from constructing a domain sub-division tree and assign...

In this paper, we consider Turing machines based on unsharp quantum logic. For a lattice-ordered quantum multiple-valued (MV) algebra E, we introduce E-valued non-deterministic Turing machines (ENTMs) and E-valued deterministic Turing machines (EDTMs). We discuss different E-valued recursively enumerable languages from width-first and depth-first r...

Ancient Chinese architecture represents a unique contribution to the world’s architectural heritage. However, there has been a serious lack of computer supported tools for representing, modeling and designing different forms of ancient Chinese buildings. We present ICA3D, an intelligent computer-aided system for designing ancient Chinese-style arch...

The present volume consists of the peer-reviewed papers presented at the CAA2011 conference held in Beijing, China between April 12 and 16, 2011. The theme of this conference was -Revive the Past, which means retrieving our history and using it to help create a new civilization. It was a great honour to organize the conference where over 130 resear...

For the purpose of analyzing the time cost of evolutionary algorithms (EAs) or other types of randomized search heuristics (RSHs) with certain requirements on the probability of obtaining a target solution, this paper proposes a new index, called the probable computational time (PCT), which complements expected running time analysis. Using simple t...

Educational Data Mining (EDM) is an emerging multidisciplinary research area, in which methods and techniques for exploring data originating from various educational information systems have been developed. EDM is both a learning science, as well as ...

When generalizing the projection-valued measurements to the positive operator-valued measurements, the notion of the quantum logic generalizes from the sharp quantum logic to the unsharp quantum logic. It is known that: (i) the distributive law is one of the main differences between the sharp quantum logic and the boolean logic, and the block or th...

We study the direct product decomposition of quantum many-valued algebras (QMV algebras) which generalizes the decomposition theorem of ortholattices (orthomodular lattices). In detail, for an idempotent element of a given QMV algebra, if it commutes with every element of the QMV algebra, it can induce a direct product decomposition of the QMV alge...

Identification and characterization of gene regulatory binding motifs is one of the fundamental tasks toward systematically understanding the molecular mechanisms of transcriptional regulation. Recently, the problem has been abstracted as the challenge planted (l,d)-motif problem. Previous studies have developed numerous methods to solve the proble...

Identification and characterization of gene regulatory binding motifs is one of the fundamental tasks toward systematically understanding the molecular mechanisms of transcriptional regulation. Recently, the problem has been abstracted as the challenge planted (l,d)-motif problem. Previous studies have developed numerous methods to solve the proble...

This paper proposes a scenario-driven agent-oriented requirement analysis methodology, where scenarios are textual descriptions of the interactions between various agents described by end-users. These scenarios are then transformed into an internal representation - Scenario-Trees. An inductive learning procedure is designed to decompose, cluster, a...

In this paper, definitions of ${\mathcal{K}}$ automata, ${\mathcal{K}}$ regular languages, ${\mathcal{K}}$ regular expressions and ${\mathcal{K}}$ regular grammars based on lattice-ordered semirings are given. It is shown that ${\mathcal{K}}$ NFA is equivalent to ${\mathcal{K}}$ DFA under some finite condition, the Pump Lemma holds if...

Identification and characterization of gene regulatory binding motifs is one of the fundamental tasks toward systematically understanding the molecular mechanisms of transcriptional regulation. Recently, the problem has been abstracted as the challenge planted (l, d)-motif problem. Previous studies have developed numerous methods to solve the probl...

In this paper, we present a new method for the design of an n-bit synchronous binary up counter in quantum-dot cellular automata (QCA). This method is based on the JK flip-flop which almost always produces the simplest combinational logic in traditional sequential circuits. We implement a new QCA architecture for the JK flip-flop. Compared to the e...

Quantum-dot cellular automata (QCA) has been widely considered as a replacement candidate for complementary metal-oxide semiconductor (CMOS). The fundamental logic device in QCA is the majority gate. In this paper, we propose an efficient methodology for majority logic synthesis of arbitrary Boolean functions. We prove that our method provides a mi...

In this paper we introduced an algebraic semantics for process algebra in form of abstract data types. For that purpose, we developed a particular type of algebra, the seed algebra, which describes exactly the behavior of a process within a labeled transition system. We have shown the possibility of characterizing the bisimulation of two processes...

Ruqian Lu first presented the notion of knowware in 2005 through his IEEE Intelligent Systems paper entitled “From hardware to software to knowware: IT’s third liberation?”. He further elaborated the notion in the book “Kowware, the third star after hardware and software”, published in 2007 by Polimetrica. Lu defines knowware as an independent and...

By studying two unsharp quantum structures, namely extended lattice ordered effect algebras and lattice ordered QMV algebras, we obtain some characteristic theorems of MV algebras. We go on to discuss automata theory based on these two unsharp quantum structures. In particular, we prove that an extended lattice ordered effect algebra (or a lattice...

Developing a desirable framework for handling inconsistencies in software requirements specifications is a challenging problem. It has been widely recognized that the relative priority of requirements can help developers to make some necessary trade-off decisions for resolving con- flicts. However, for most distributed development such as viewpoint...

This article consists of nine short essays discussing research pursued by AI researchers in China and their perspectives on research in several AI subareas. The article first introduces the mechanization of mathematics, an area in which Chinese scientists have made significant contributions. It then discusses research in automated reasoning, tempor...

The guest editors introduce the IEEE Intelligent Systems special issue on AI in China. This special issue intends to share recent research contributions and developments from the AI researchers in China.

The first part of this paper reviews our efforts on knowledge-based software engineering, namely PROMIS, started from 1990s. The key point of PROMIS is to generate applications automatically based on domain knowledge as well as software knowledge. That is featured by separating the development of domain knowledge from the development of software. B...

Knowledge and Intelligence have a much closed relationship. Knowledge is both the crystallization and source of intelligence. Knowledge embodies intelligence, and intelligence emerges from knowledge. Every ICAX system (Intelligent Computer Aided X, where X may mean any domain, such as education, design or manufacturing, etc.), such as ICAI (I = Ins...

This book proposes to separate knowledge from software and to make it a commodity that is called knowware. The architecture, representation and function of Knowware are discussed. The principles of knowware engineering and its three life cycle models: furnace model, crystallization model and spiral model are proposed and analyzed. Techniques of sof...

It has been widely recognized that the relative priority of requirements can help developers to resolve inconsistencies and make some necessary trade-off decisions. However, for most distributed development such as Viewpoints-based approaches, different stakeholders may assign different levels of priority to the same shared requirements statement f...

In this position paper, we set out to explore the possibilities of formulating problems in requirements engineering with concepts and frameworks from cybernetics. The objective is to seek practical synergies and to understand notable differences between the two areas. We try to understand to what extent known research results from cybernetics can b...

Common substring problems allowing errors are known to be NP-hard. The main challenge of the problems lies in the combinatorial explosion of potential candidates. In this paper, we propose and study a generalized center string (GCS) problem, where not only all models (center strings) of any length, but also the positions of all their (degenerative)...

In this paper, we describe the relationships between pseudo MV algebras and semirings. We also give definitions of automata on lattice ordered semi- rings, prove that the family of K-Languages is closed under union, and discuss the conditions for the closed- ness of families of K-languages under intersection, gen- eralized intersection and reversal...

Eliciting requirements for a proposed system inevitably involves the problem of handling undesirable information about customer's needs, including inconsistency, vagueness, redundancy, or incompleteness. We term the requirements statements involved in the undesirable information non-canonical software requirements. In this paper, we propose an appr...

Knowledge engineering stems from E. A. Figenbaum’s proposal in 1977, but it will enter a new decade with the new challenges. This paper first summarizes three knowledge engineering experiments we have undertaken to show possibility of separating knowledge development from intelligent software development. We call it the ICAX mode of intelligent app...

Most techniques for probabilistic reasoning focus on reasoning about conditional probability constraints. However, human experts are accustomed to representing uncertain knowledge in the form of expectation rather than probability distribution directly in many cases. It is necessary to provide a logic for encoding hybrid probabilistic knowledge bas...

After a short introduction to the concepts of knowware, knowware engineering and knowledge middleware, this paper proposes to study the software/knowware co-engineering. Different from the traditional software engineering process, it is a mixed process involving both software engineering and knowware engineering issues. The technical subtleties of...

Chinese researchers have been conducting AI research for more than four decades. Here, we sample some of the most promising areas Chinese AI researchers are studying and predict related future activities. The AI areas research area follows: automatic geometrical theorem proving: beyond mathematical mechanization, intelligence science: toward a mole...

It seems to be inevitable to confront vague information about customer’s needs during the software requirements stage. It may be desirable to record and clarify the vague information to avoid missing real requirements. In this paper, we provide an inconsistency-based strategy to handle vague information in the framework of Annotated Predicate Calcu...

A typed category theory is proposed for the abstract description of knowledge and knowledge processing. It differs from the traditional category theory in two directions: all morphisms have types and the composition of morphisms is not necessary a morphism. Two aspects of application of typed category theory are discussed: cones and limits of knowl...

Dialog System is an important research area in natural language processing. This paper presents a research work on the multi-talk dialog system, which is supported by a large scaled knowledge base called Pangu. Our experience in the design, improvement, xible and natural dialog, modularized knowledge evaluation of the multi-talk system are introduc...

We propose the concept of finite stop quantum automata (ftqa) based on Hilbert space and compare it with the finite state quantum automata (fsqa) proposed by Moore and Crutchfield (Theoretical Computer Science 237(1–2), 2000, 275–306). The languages accepted by fsqa form a proper subset of the languages accepted by ftqa. In addition, the fsqa form...

A popular solution to improving the speed and scalability of association rule mining is to do the algorithm on a random sample instead of the entire database. But it is at the expense of the accuracy of answers. In this paper, we present a sampling ensemble approach to improve the accuracy for a given sample size. Then, using Monte Carlo theory, we...

In the field of requirements engineering, measuring inconsistency is crucial to effective inconsistency management. A practical measure must consider both the degree and significance of inconsistency in specification. The main contribution of this paper is providing an approach for measuring inconsistent specification in terms of the priority-based...

Knowware is a natural development in IT after hardware and software. It is a knowledge module that is independent, commercialized, suitable for computer manipulation, and directly usable by a class of software. It is directly related to intelligence: if software is the condensation and crystallization of knowledge, then knowware is the condensation...

Knowledge, cognition and intelligence are three tightly connected concepts. The Turing test is widely accepted as a test stone for machine intelligence. This paper analyzes experiences obtained in a research project on a Turing test for children and discusses its meaning with respect to some knowledge and cognition issues.

Modeling of tissue deformation is of great importance to virtual reality (VR)-based medical simulations. Considerable effort has been dedicated to the development of interactively deformable virtual tissues. In this paper, an efficient and scalable deformable ...

Not all lattice-valued quantum automata possess the pumping property in its strict form. However the pumping lemma can be generalized, and all lattice-valued quantum automata possess the generalized pumping property.

Not Available

There are several purposes for modeling and analyzing the problem domain before starting the software requirements analysis. First, it focuses on the problem domain, so that the domain users could be involved easily. Secondly, a comprehensive description on the problem domain will advantage getting a comprehensive software requirements model. This...

Many approaches have been proposed to enhance software productivity and reliability. These approaches typically fall into three categories: the engineering approach, the formal approach and the knowledge-based approach. But the optimal gain in software productivity cannot be obtained if one relies on only one of these approaches. This paper describ...

Neural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural networks. ...

We defined and studied three different types of lattice-valued finite state quantum automata (LQA) and four different kinds of LQA operations, discussed their advantages, disadvantages, and various properties. There are four major results obtained in this paper. First, no one of the above mentioned LQA follows the law of lattice value conservation....

Due to the limitation of lacking of intelligence of current database and knowledge base structures, we present Agent-Oriented Knowledge Base (AOKB) to be a more intelligent and autonomous schema for knowledge representation, communication, reasoning and application. An agentontology-relation hierarchy is designed aiming at the modularization and hi...

Part of this work was done while this Guest Editor was with Tsinghua University, Beijing

No Yes

Domain analysis is the activity of identifying and representing the relevant information in a domain, so that the information can be shared and reused in similar systems. But until now, no efficient approaches are available for capturing and representing the results of domain analysis and then for sharing and reusing the domain knowledge. This pape...

When querying on a large-scale knowledge base, a major technique of improving performance is to preload knowledge to minimize the number of roundtrips to the knowledge base. In this paper, an ontology-based semantic cache is proposed for an agent and ontology-oriented knowledge base (AOKB). In AOKB, an ontology is the collection of relationships be...

The light planning in SWAN is accomplished in four procedures.