Li Weigang - Profile on Academia.edu (original) (raw)

Papers by Li Weigang

arXiv (Cornell University), Aug 17, 1998

A Parallel Self-Organizing Map (Parallel-SOM) is proposed to modify Kohonen's SOM in parallel com... more A Parallel Self-Organizing Map (Parallel-SOM) is proposed to modify Kohonen's SOM in parallel computing environment. In this model, two separate layers of neurons are connected together. The number of neurons in both layers and connections between them is the product of the number of all elements of input signals and the number of possible classification of the data. With this structure the conventional repeated learning procedure is modified to learn just once. The once learning manner is more similar to human learning and memorizing activities. During training, weight updating is managed through a sequence of operations among some transformation and operation matrices. Every connection between neurons of input/output layers is considered as a independent processor. In this way, all elements of the Euclidean distance matrix and weight matrix are calculated simultaneously. The minimum distance of every line of distance matrix can be found by Grover's search algorithm. This synchronization feature improves the weight updating sequence significantly. With a typical classification example, the convergence result demonstrates efficient performance of Parallel-SOM. Theoretic analysis and proofs also show some important properties of proposed model. Especially, the paper proves that Parallel-SOM has the same convergence property as Kohonen's SOM, but the complexity of former is reduced obviously.

Human skin detection in images is a widely studied topic of Computer Vision for which it is commo... more Human skin detection in images is a widely studied topic of Computer Vision for which it is commonly accepted that analysis of pixel color or local patches may suffice. This is because skin regions appear to be relatively uniform and many argue that there is a small chromatic variation among different samples. However, we found that there are strong biases in the datasets commonly used to train or tune skin detection methods. Furthermore, the lack of contextual information may hinder the performance of local approaches. In this paper we present a comprehensive evaluation of holistic and local Convolutional Neural Network (CNN) approaches on in-domain and crossdomain experiments and compare with state-of-the-art pixelbased approaches. We also propose a combination of inductive transfer learning and unsupervised domain adaptation methods, which are evaluated on different domains under several amounts of labelled data availability. We show a clear superiority of CNN over pixel-based approaches even without labelled training samples on the target domain. Furthermore, we provide experimental support for the counter-intuitive superiority of holistic over local approaches for human skin detection.

arXiv (Cornell University), Apr 27, 2021

This article reviews the "Once learning" mechanism that was proposed 23 years ago and the subsequ... more This article reviews the "Once learning" mechanism that was proposed 23 years ago and the subsequent successes of "One-shot learning" in image classification and "You Only Look Once -YOLO" in objective detection. Analyzing the current development of Artificial Intelligence (AI), the proposal is that AI should be clearly divided into the following categories: Artificial Human Intelligence (AHI), Artificial Machine Intelligence (AMI), and Artificial Biological Intelligence (ABI), which will also be the main directions of theory and application development for AI. As a watershed for the branches of AI, some classification standards and methods are discussed: 1) Human-oriented, machine-oriented, and biological-oriented AI R&D; 2) Information input processed by Dimensionality-up or Dimensionalityreduction; 3) The use of one/few or large samples for knowledge learning.

Neurocomputing, 2016

Virtual Worlds Generator is a grammatical model that is proposed to define virtual worlds. It int... more Virtual Worlds Generator is a grammatical model that is proposed to define virtual worlds. It integrates the diversity of sensors and interaction devices, multimodality and a virtual simulation system. Its grammar allows the definition and abstraction in symbols strings of the scenes of the virtual world, independently of the hardware that is used to represent the world or to interact with it. A case study is presented to explain how to use the proposed model to formalize a robot navigation system with multimodal perception and a hybrid control scheme of the robot. The result is an instance of the model grammar that implements the robotic system and is independent of the sensing devices used for perception and interaction. As a conclusion the Virtual Worlds Generator adds value in the simulation of virtual worlds since the definition can be done formally and independently of the peculiarities of the supporting devices.

HAL (Le Centre pour la Communication Scientifique Directe), Feb 23, 2017

4D Trajectory Conflict Detection and Resolution Using Decision Tree Pruning Method

IEEE Latin America Transactions

Conflict Detection and Resolution with Local Search Algorithms for 4D-Navigation in ATM

Advances in Intelligent Systems and Computing, 2019

Implementation of Trajectory Based Operations (TBO) has been updating the structure of the advanc... more Implementation of Trajectory Based Operations (TBO) has been updating the structure of the advanced Air Traffic Management (ATM). Although several methodologies for conflict detection and resolution (CDR) have been developed to the aviation community, the legacy problem is to find an efficient scheme to present the trajectories in this complex network with massive data and further to detect and resolve the conflicts. In this research we develop a CDR framework based on the management of predicted 4D-trajectories using a Not Only SQL (NoSQL) database and local search algorithms for conflict resolution. This paper describes the architecture and algorithms of the proposed solution in 4-Dimensional Trajectory (4DT). With the application of Trajectory Prediction (TP) simulator using the Brazilian flight plan database, the results from case study show the effectiveness of the proposed methods for this sophisticated problem in ATM.

WIT Transactions on Information and Communication Technologies, 1970

A Know ledge-Based System (KBS) has been designed for the Air Traffic Flow Management (ATFM) prob... more A Know ledge-Based System (KBS) has been designed for the Air Traffic Flow Management (ATFM) problem. For timetable rescheduling, the system tends to modify airlines timetable to smooth traffic peaks at airports during rush-hours. For centralized flow control, the system works on-line to forecast the place, time and magnitude of the congestions and to take some actions to prevent these congestions. As an Artificial Intelligence language, Prolog was chosen to develop the prototype of the Knowledge-Based ATFM System. By using this system, Brazilian ATFM, which includes the principal airports of this country, has been studied.

Towards Intelligent System Wide Information Management for Air Traffic Management

Security, Privacy, and Anonymity in Computation, Communication, and Storage, 2017

This paper briefly reviews the state-of-the-art in Artificial Intelligence (AI) applied to Air Tr... more This paper briefly reviews the state-of-the-art in Artificial Intelligence (AI) applied to Air Traffic Management (ATM). The research topics include the application of semantic ontology, multi-agent systems, reinforcement learning (RL), and game theory in ATM. Likewise, this paper also highlights our research advances in this area. In this case, we describe a new Probabilistic Web Ontology Language (PR-OWL) algorithm to enable the reasoning on big datasets in polynomial time. Then, we present the use of both Particle Swarm Optimization (PSO) and Simulated Annealing (SA) algorithms in 4D trajectory management. Next, we describe the usage of Multi-agent Planning (MAP) theory on airport ground handling management. Finally, this paper envisions some research and development directions of AI applied to ATM. It includes: (a) mapping and reducing the gaps between advanced AI technologies and ATM; (b) considering uncertainty in Semantic Ontology for SWIM data exchanging models in ATM; (c) using big data analytics in SWIM; and (d) integrating collaborative ATM technologies towards intelligent SWIM (I-SWIM).

Inaccurate carbon emissions predictions may be one of the root factors leading to the overall ine... more Inaccurate carbon emissions predictions may be one of the root factors leading to the overall ineffectiveness of the European Union environmental regulatory framework. Therefore, the present article aims at introducing a novel computational learning framework for carbon emissions prediction incorporating a RReliefF driven features selection and an iterative neural network architecture improvement. Our learning framework algorithmic architecture iteratively chains the features selection process and the backpropagation artificial neural network architecture design based on the data assessment accomplished by the RReliefF algorithm. Thus a better features set / neural network architecture combination is obtained for each specific prediction target. The implemented framework was trained and tested with real world data obtained from the European Union, International Energy Agency, Organisation for Economic Co-operation and Development, and World Bank, for the period 1990–2017. The framew...

Classification of text documents is of significant importance in the field of data mining and mac... more Classification of text documents is of significant importance in the field of data mining and machine learning. However, the vector representation of documents, in classification problems, results in a highly sparse data with immense number of variables. This necessitates applying an efficient variables selection and dimensionality reduction technique that ensures model’s selectivity, accuracy and robustness with fewer variables. This paper introduces a new coefficient, the Variables Strength Coefficient (VSC), which permits retaining variables with strong Modeling and Discriminatory powers. A variable with VSC greater than a predefined threshold is considered to have strong power in both modeling data and discriminating classes and thus retained, while weaker variables are discarded. This straightforward technique results in maximizing the differences between classes while preserving the modeling power of variables. This paper also proposes applying a classification technique that ...

ISPRS International Journal of Geo-Information, 2021

Misappropriation of public lands is an ongoing government concern. In Brazil, the beach zone is p... more Misappropriation of public lands is an ongoing government concern. In Brazil, the beach zone is public property, but many private establishments use it for economic purposes, requiring constant inspection. Among the undue targets, the individual mapping of straw beach umbrellas (SBUs) attached to the sand is a great challenge due to their small size, high presence, and agglutinated appearance. This study aims to automatically detect and count SBUs on public beaches using high-resolution images and instance segmentation, obtaining pixel-wise semantic information and individual object detection. This study is the first instance segmentation application on coastal areas and the first using WorldView-3 (WV-3) images. We used the Mask-RCNN with some modifications: (a) multispectral input for the WorldView3 imagery (eight channels), (b) improved the sliding window algorithm for large image classification, and (c) comparison of different image resizing ratios to improve small object detect...

2015 18th International Conference on Information Fusion (Fusion), 2015

Twitter is an online social networking (OSN) service that enables users to send and read short me... more Twitter is an online social networking (OSN) service that enables users to send and read short messages called “tweets”. As of December 2014, Twitter has more than 500 million users, out of which more than 284 million are active users and about 500 million tweets are posted every day. Tweet sentiment analysis (TSA) identifies a valuable platform for the OSN study which provides insights into the opinion of the public about culture, products and political agendas and thereby is able to predict the trends in specific domains. In order to execute efficient TSA on a particular topic or domain, a TSA approach with unified tool, UnB TSA, is proposed consisting of four steps: tweets collection, refinement (excluding noisy tweets), sentiment lexicon creation and sentiment analysis. As a key part, the lexicon is domain-specific that incorporates expressions whose sentiment varies from one domain to another. Four algorithms including expanding limited hashtags into a larger and more complete ...

Lecture Notes in Business Information Processing, 2015

The problem of capacity shortage in some airports needs to be dealt with sustainable solutions in... more The problem of capacity shortage in some airports needs to be dealt with sustainable solutions including a more efficient use of the existing runway slots at the airports. The Collaborative Decision Making (CDM) is an important approach applied to Air Traffic Management (ATM) to achieve this efficient use of the slots allocation. Using the Matching approach for two-sided markets of Game theory, the Top Trading Cycle CDM (TTC-CDM) algorithm developed in this research is an extension of the CDM approach aggregating the Ground Delay Program (GDP) of the air sector. The paper compared the developed TTC-CDM model to the existing models such as the conventional Compression algorithm in CDM, the Trade Cycle algorithm and the Deferred Acceptance CDM (DA-CDM) model to evaluate the performance of the proposed model. Through a case study, the results show the effective application of TTC-CDM model to slot allocation in ATM and also presents the advantage of considering the preferences of airport managers beside ATC controllers and airlines in the decision processing.

Probabilistic OWL (PR-OWL) improves the Web Ontology Language (OWL) with the ability to treat unc... more Probabilistic OWL (PR-OWL) improves the Web Ontology Language (OWL) with the ability to treat uncertainty using Multi-Entity Bayesian Networks (MEBN). PROWL 2 presents a better integration with OWL and its underlying logic, allowing the creation of ontologies with probabilistic and deterministic parts. However, there are scalability problems since PROWL 2 is built upon OWL 2 DL which is a version of OWL based on description logic SROIQ(D) and with high complexity. To address this issue, this paper proposes PROWL 2 RL, a scalable version of PROWL based on OWL 2 RL profile and triplestores (databases based on RDF triples). OWL 2 RL allows reasoning in polynomial time for the main reasoning tasks. This paper also presents First-Order expressions accepted by this new language and analyzes its expressive power. A comparison with the previous language presents which kinds of problems are more suitable for each version of PROWL .

A Genetic Algorithm Model for Slot Allocation Optimization to Brazilian CTOP Approach

Advances in intelligent systems and computing, Jul 5, 2018

The Collaborative Trajectory Options Program (CTOP) makes each airline possible to share its rout... more The Collaborative Trajectory Options Program (CTOP) makes each airline possible to share its route options to air traffic control center, and so achieve better business goals by reducing strategic operational costs. In Brazil, there are initial efforts to verify the benefits of CTOP implementation to improve the air traffic fluency and financial results. This paper presents a novel approach for Brazilian airspace using Genetic Algorithms to decrease the delay between available slots during CTOP. The slot optimization keeps improving in a safety-separating window of each aircraft en route. The case study presented an reducement about 70% of delay of a certain airline, when used this decision support system by air traffic control authority.

Categoria Melhor Monografia 2º Lugar: Otimização de negociação dinâmica para múltiplas áreas restritas de fluxo no programa de opções de trajetórias colaborativo

Evaluation of Typing Efficiency Using Language Model for the Chinese Typewriter

2022 4th International Conference on Natural Language Processing (ICNLP), Mar 1, 2022

Game Theory Approach to Brazilian Air Traffic Management Using Collaborative Trajectory Options Program

Communications in computer and information science, 2018

Air traffic management (ATM) has increased the complexity of computational solutions over the las... more Air traffic management (ATM) has increased the complexity of computational solutions over the last decades to support the discovery process and knowledge management in decision-making process. It involves dealing with more information about flights, weather, delays, forecasting scenarios, and others. An evolution of ATM programs was the Collaborative Trajectory Options Program (CTOP), which is applied in the USA since 2014. In Brazil, some initial studies are analyzing this evolution and how the current air traffic management could be improved. One option is to implement the concept addressed by CTOP and its specificities based on Brazil context. This paper presents a computational solution that uses the main concept of CTOP with a collaborative approach to implement the program in Brazil. The main objective is to reduce delays of flights captured by the CTOP, so that the airlines collaboratively reduce delays in their flights and each airline can their business goals, using techniques of Artificial Intelligence with Game Theory and Folk Theorem. The CTOP approach to Brazilian air traffic management is a first initiative to improve the air traffic programs by using the collaborative decision-making process to achieve better results. The achieved results were important for this initial case study, decreasing about 18% of delays in CTOP captured flights, when it was considered only the priority flights of an airline.