Computer Sciences Commons^™

Weakly-Admissible Semantics And The Propagation Of Ambiguity In Abstract Argumentation Semantics, Pierpaolo Dondio

Other

The concept of ambiguous literals of defeasible logics is mapped to the set of undecided arguments identified by an argumentation semantics. It follows that Dung’s complete semantics are all ambiguity propagating, since the undecided status of an attacking argument is always propagated to the attacked argument, unless the latter is defeated by another accepted argument. In this paper we investigate a novel family of abstract argumentation semantics, called weakly-admissible semantics, where we do not require an acceptable argument to be necessarily defended from the attacks of undecided arguments. Weakly-admissible semantics are conflict-free, ambiguity blocking, non-admissible (in Dung’s sense), but employing …

Culture Clubs: Processing Speech By Deriving And Exploiting Linguistic Subcultures, David Guy Brizan

Dissertations, Theses, and Capstone Projects

Spoken language understanding systems are error-prone for several reasons, including individual speech variability. This is manifested in many ways, among which are differences in pronunciation, lexical inventory, grammar and disfluencies. There is, however, a lot of evidence pointing to stable language usage within subgroups of a language population. We call these subgroups linguistic subcultures.

The two broad problems are defined and a survey of the work in this space is performed. The two broad problems are: linguistic subculture detection, commonly performed via Language Identification, Accent Identification or Dialect Identification approaches; and speech and language processing tasks taken which may see …

Deep Learning Based Medical Image Analysis With Limited Data, Jiaxing Tan

Dissertations, Theses, and Capstone Projects

Deep Learning Methods have shown its great effort in the area of Computer Vision. However, when solving the problems of medical imaging, deep learning’s power is confined by limited data available. We present a series of novel methodologies for solving medical imaging analysis problems with limited Computed tomography (CT) scans available. Our method, based on deep learning, with different strategies, including using Generative Adversar- ial Networks, two-stage training, infusing the expert knowledge, voting based or converting to other space, solves the data set limitation issue for the cur- rent medical imaging problems, specifically cancer detection and diagnosis, and shows very …

Artificial Intelligence Hits The Barrier Of Meaning, Melanie Mitchell

Computer Science Faculty Publications and Presentations

Today’s AI systems sorely lack the essence of human intelligence: Understanding the situations we experience, being able to grasp their meaning. The lack of humanlike understanding in machines is underscored by recent studies demonstrating lack of robustness of state-of-the-art deep-learning systems. Deeper networks and larger datasets alone are not likely to unlock AI’s “barrier of meaning”; instead the field will need to embrace its original roots as an interdisciplinary science of intelligence.

Transnfcm: Translation-Based Neural Fashion Compatibility Modeling, Xun Yang, Yunshan Ma, Lizi Liao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Identifying mix-and-match relationships between fashion items is an urgent task in a fashion e-commerce recommender system. It will significantly enhance user experience and satisfaction. However, due to the challenges of inferring the rich yet complicated set of compatibility patterns in a large e-commerce corpus of fashion items, this task is still underexplored. Inspired by the recent advances in multi-relational knowledge representation learning and deep neural networks, this paper proposes a novel Translation-based Neural Fashion Compatibility Modeling (TransNFCM) framework, which jointly optimizes fashion item embeddings and category-specific complementary relations in a unified space via an end-to-end learning manner. TransNFCM places items …

Multiagent Decision Making For Maritime Traffic Management, Arambam James Singh, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We address the problem of maritime traffic management in busy waterways to increase the safety of navigation by reducing congestion. We model maritime traffic as a large multiagent systems with individual vessels as agents, and VTS authority as the regulatory agent. We develop a maritime traffic simulator based on historical traffic data that incorporates realistic domain constraints such as uncertain and asynchronous movement of vessels. We also develop a traffic coordination approach that provides speed recommendation to vessels in different zones. We exploit the nature of collective interactions among agents to develop a scalable policy gradient approach that can scale …

Multiagent Decision Making For Maritime Traffic Management, Arambam James Singh, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We address the problem of maritime traffic management in busy waterways to increase the safety of navigation by reducing congestion. We model maritime traffic as a large multiagent systems with individual vessels as agents, and VTS authority as the regulatory agent. We develop a maritime traffic simulator based on historical traffic data that incorporates realistic domain constraints such as uncertain and asynchronous movement of vessels. We also develop a traffic coordination approach that provides speed recommendation to vessels in different zones. We exploit the nature of collective interactions among agents to develop a scalable policy gradient approach that can scale …

Manifold-Valued Image Generation With Wasserstein Generative Adversarial Nets, Zhiwu Huang, Wu J., G. L. Van

Research Collection School Of Computing and Information Systems

Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued images and exploits three typical instances: hue-saturation-value (HSV) color image generation, chromaticity-brightness (CB) color image generation, and diffusion-tensor (DT) image generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to …

Dish: Democracy In State Houses, Nicholas A. Russo

Master's Theses

In our current political climate, state level legislators have become increasingly impor- tant. Due to cuts in funding and growing focus at the national level, public oversight for these legislators has drastically decreased. This makes it difficult for citizens and activists to understand the relationships and commonalities between legislators. This thesis provides three contributions to address this issue. First, we created a data set containing over 1200 features focused on a legislator’s activity on bills. Second, we created embeddings that represented a legislator’s level of activity and engagement for a given bill using a custom model called Democracy2Vec. Third, we …

Comparative Study Of Sentiment Analysis With Product Reviews Using Machine Learning And Lexicon-Based Approaches, Heidi Nguyen, Aravind Veluchamy, Mamadou Diop, Rashed Iqbal

SMU Data Science Review

In this paper, we present a comparative study of text sentiment classification models using term frequency inverse document frequency vectorization in both supervised machine learning and lexicon-based techniques. There have been multiple promising machine learning and lexicon-based techniques, but the relative goodness of each approach on specific types of problems is not well understood. In order to offer researchers comprehensive insights, we compare a total of six algorithms to each other. The three machine learning algorithms are: Logistic Regression (LR), Support Vector Machine (SVM), and Gradient Boosting. The three lexicon-based algorithms are: Valence Aware Dictionary and Sentiment Reasoner (VADER), Pattern, …

Improving Vix Futures Forecasts Using Machine Learning Methods, James Hosker, Slobodan Djurdjevic, Hieu Nguyen, Robert Slater

SMU Data Science Review

The problem of forecasting market volatility is a difficult task for most fund managers. Volatility forecasts are used for risk management, alpha (risk) trading, and the reduction of trading friction. Improving the forecasts of future market volatility assists fund managers in adding or reducing risk in their portfolios as well as in increasing hedges to protect their portfolios in anticipation of a market sell-off event. Our analysis compares three existing financial models that forecast future market volatility using the Chicago Board Options Exchange Volatility Index (VIX) to six machine/deep learning supervised regression methods. This analysis determines which models provide best …

Improving Gas Well Economics With Intelligent Plunger Lift Optimization Techniques, Atsu Atakpa, Emmanuel Farrugia, Ryan Tyree, Daniel W. Engels, Charles Sparks

SMU Data Science Review

In this paper, we present an approach to reducing bottom hole plunger dwell time for artificial lift systems. Lift systems are used in a process to remove contaminants from a natural gas well. A plunger is a mechanical device used to deliquefy natural gas wells by removing contaminants in the form of water, oil, wax, and sand from the wellbore. These contaminants decrease bottom-hole pressure which in turn hampers gas production by forming a physical barrier within the well tubing. As the plunger descends through the well it emits sounds which are recorded at the surface by an echo-meter that …

Analyzing Neuronal Dendritic Trees With Convolutional Neural Networks, Olivier Trottier, Jonathon Howard

Yale Day of Data

In the biological sciences, image analysis software are used to detect, segment or classify a variety of features encountered in living matter. However, the algorithms that accomplish these tasks are often designed for a specific dataset, making them hardly portable to accomplish the same tasks on images of different biological structures. Recently, convolutional neural networks have been used to perform complex image analysis on a multitude of datasets. While applications of these networks abound in the technology industry and computer science, use cases are not as common in the academic sciences. Motivated by the generalizability of neural networks, we aim …

A Comparative Evaluation Of Recommender Systems For Hotel Reviews, Ryan Khaleghi, Kevin Cannon, Raghuram Srinivas

SMU Data Science Review

There has been increasing growth in deployment of recommender systems across Internet sites, with various models being used. These systems have been particularly valuable for review sites, as they seek to add value to the user experience to gain market share and to create new revenue streams through deals. Hotels are a prime target for this effort, as there is a large number for most destinations and a lot of differentiation between them. In this paper, we present an evaluation of two of the most popular methods for hotel review recommender systems: collaborative filtering and matrix factorization. The accuracy of …

Application Of Virtual Reality In Rehabilitation Of Special Populations, Tingting Liu, Liu Zhen, Ping'an Qian, Rongrong Xuan, Wang Jin, Yanjie Chai

Journal of System Simulation

Abstract: With the continuous development of urbanization and the trend of population aging, the number of people who need physical and mental rehabilitation continues to increase. Using information technology to assist the rehabilitation process has the important practical significance. The existing studies about the application of virtual reality (VR) technology in the rehabilitation, psychological problems and children with autism for stroke are reviewed. A framework for the intelligent rehabilitation system is proposed. Virtual agent, the technology of somatosensory and voice recognition are advised to be used. Based on the proposed framework, a prototype rehabilitation game for autism and an upper …

A Review Of Rare Event Simulation, Liping Wang, Wenhui Fan

Journal of System Simulation

Abstract: Rare-event has a great significance for its lower probability of occurrence and greater harmfulness, the traditional Monte Carlo method is difficult to analyze it effectively. Rare-event simulation technique which is developed quickly and applied in many areas can sample the rare-event effectively with variance reduction methods and can estimate the occurrence probability of rare-event. The research status of rare-event simulation technique is summarized firstly; the principles, problems and progress of the main methods are analyzed and concluded secondly; after that the application fields of the technique are elaborated and summarized; the future development tendency of rare event simulation technique …

Integrated Modeling For Time Delay Stability Analysis In Gcps, Jianbo Jiang, Li Peng, Aimin Miao, Cao Min, Songhai Zhang, Tan Lei, Kerun Li

Journal of System Simulation

Abstract: According to the separation problems of physical and cyber modeling in time delay stability analysis for grid cyber-physical system (GCPS), an integrated modeling method is presented and proved by single machine infinite bus system (SMIBS). The time delay and stability of GCPS are analyzed and discussed, and the physical and cyber models of SMIBS are established respectively. The dynamic linking library by EA and VS based on information model (CIM) are generated, and the united simulation platform is achieved by MATLAB. The results of the simulation show that the unified structure of information flow …

Parameter Estimation Of Lfmcw Signals Based On Improved Sm Method, Jiang Li, Junni Zhou, Runling Yang, Liu Li

Journal of System Simulation

Abstract: The parameter estimation of linear frequency modulation continuous wave (LFMCW) signal is a research hotspot in electronic reconnaissance systems. In this paper, the time frequency distribution feature of LFMCW signals is studied first. Based on the improved S-method (SM), an algorithm for parameter estimation of LFMCW signals is proposed. It uses short-time Fourier transform (STFT) to calculate the SM with adaptive window width, which can suppress the crossterm interferences and improve the time-frequency resolution. Theoretical analysis and simulation experiment results demonstrate the validity of the proposed algorithm under low SNR.

Research On Method Of Battlefield Situation Representation Based On Multiplex Information Cell, Xiying Huang, Dinghai Zhao, Shao Wei

Journal of System Simulation

Abstract: We adopt the grid-space method to represent the battlefield as discrete cell model. And we construct the multiplex information cell (MIC) using the situation-meta’s information such as position, states collection, indexed by position. The positions of MICs correspond to the battlefield’s positions. Both of them can be represented as stack or data array. This method gives a way to build the whole mapping relationship between data structure which the computer can understand and the battle factors such as position and state of situation-meta. When the position or state of the situation-meta changes, the computer can redraw the view according …

Towards The Automatic Evolution Of Workload Models In Large-Scale Astronomical Data Management, Huajin Wang, Wan Meng, Han Rui, Ren Wei, Haiming Zhang, Jianhui Li

Journal of System Simulation

Abstract: The benchmark's guiding role in system selection/optimization requires its workload model has the ability to: Run on various systems of the target application scenario (be portable); Reflect the typical tasks' characteristics and data access patterns (be representative). The emerging systems and tasks in large-scale astronomical data management field have led workload models constructed by existing methods to be prone to lose portability and representativeness. An automatic evolutionary workload modeling method has been proposed: Abstract operations are used to keep the workload model’s portability; Automatic workload log analytics are used to keep the workload model’s representativeness. The feasibility of this …

Analysis Of Lane Changing Conflict Based On Tta In Expressway Weaving Area, Wang Bao, Linjie Gao, Zhicai Juan

Journal of System Simulation

Abstract: The study of lane changing behavior in expressway weaving area is of great significance to the analysis of the traffic flow conflict and driving behavior characteristics. In this paper, a lane changing conflict model was established and trajectory extraction software was used to extract and calculate TTA (time to avoidance) and TTC (time to collision). We got 336 TTAs and 233 TTCs and 4 grades of the lane changing conflict level were built by using statistical method. We came up with the proposed lane changing speed and some traffic management strategies. The study will help to …

Direct Parameter Identification Method For Steam Turbine And Its Governing System, Jingliang Zhong, Xiaolong Gou, Tongtian Deng

Journal of System Simulation

Abstract: Since most of the traditional parameter identification methods used in the steam turbine and its governing system have the shortages of poor fitness, complicated identification process and long period, a novel identification method based on least square theory, called direct identification method, is proposed in this paper. Parameter to be identified can be obtained quickly and accurately through direct identification method if the identification process is transferred to solve nonlinear equation which represents the minimal error between simulated data and measured data. The identification results show that during identification process the proposed method has high identification efficiency, accurate identification …

Research On Conceptual Model For Trainer Embedded Training System, Jierong Tian, Zhang Li, Han Liang, Cunhu Shi

Journal of System Simulation

Abstract: Embedded training is an effective way to solve the problem of pilot tactical training, and represents a new technique trend in military training. Aiming at the requirements of trainer embedded training, the visual conceptual model that includes case model, static model and dynamic model for trainer embedded training system is constructed by unified modeling language (UML). Based on the conceptual model and the trainer characteristics, with the consideration of the reality and the future development, the structure model of embedded training system is designed referring to foreign architecture of embedded training system. The bus communication of embedded training …

Damage Simulation Of A Certain Type Of Armored Equipment Based On Finite Element Analysis, Junqing Huang, Tuan Wang, Guanghui Li, Fan Rui

Journal of System Simulation

Abstract: Based on the finite element numerical simulation method, the damage simulation of a certain type of armored equipment was studied. The numerical simulation model of ammo power was established. Based on 3D modeling technology, the vulnerability model of the armored equipment in the component level with high-resolution was established. The spatial relation model of projectile and target was established based on the interaction analysis of projectile and target. According to the characteristic of ammo damage element, combined with the damage criterion of armored equipment component, the damage condition of the component and the damage grade of the armored equipment …

Analysis And Optimization For Combat Capability Based On Sequential Simulation Experiment, Chenyan Kong, Zhu Jing, Jiao Song, Shaojie Mao

Journal of System Simulation

Abstract: To deal with the optimization of combat capability, the sequential simulation experiment method was proposed. The simulation evaluation method with precision constraint was used to control the simulation running times. The sensitivity analysis experiment was carried out to identify the important factors affecting the combat capability. The relation model between the important factors and combat capability was constructed via regression analysis experiment. To get the combat capability improvement as large as possible with the price as small as possible, the optimization was used. In the application example, the air-defense combat capability was improved by the method.

Modeling And Simulation For Automobile Connecting Rod Production Line Based On System Dynamics, Li Han, Wenhui Fan, Feng Yuan, Mengni Zhu, Shengxiao Zhang

Journal of System Simulation

Abstract: In the production line system, it is of much significance to assign operation to workstations in order to balance the manufacturing workload and increase productivity under the given constraint conditions. Based on System Dynamics theory, this paper builds a simulation model of a connecting rod production line in an automobile component company. With this model, the paper analyses the balancing rate and influential factors. Then some preliminary optimization is made to improve the production line performance.

Modeling And Simulation Of Connecting Rod Production Line, Yuanyuan Yan, Wenhui Fan, Feng Yuan

Journal of System Simulation

Abstract: Discrete event system simulation method is widely applied to solve various problems, and line balancing problem is also one of them. In this paper, we use discrete event system simulation method to solve line balancing problem. Connecting rod production line is modeled by using DES. A production line model is built and simulated in AnyLogic, the bottleneck process and the problems to be optimized are analyzed. A small program in MATLAB is used to optimize the production line, and find the optimal solution. Simulate again.

Design Of Simulation Platform For Space Operation Mission, Yuan Jing, Jianpin Yuan, Mingming Wang, Wang Fei, Zhang Chi

Journal of System Simulation

Abstract: The design of simulation platform for space mission operations is investigated. The platform has the advantages of high generality and extensibility, being easy to build up new task. FMI (Functional Mockup Interface) standard is adopted to achieve integration of multisource models, and Python scripts are used to realize the task schedule. Unity3D is adopted to implement the visual display system which could display space manipulation process with high fidelity 3D virtual scenes. Configuration tool is developed to map the 3D objects in visual scene with simulation physical variables for complex space control mechanism, which greatly improves the …

Restrain Boundary Effect Of Emd Based On Least Square Fitting, Zhenpeng He, Zhiqi Zhu, Haichao Xie, Yawen Wang, Zongqiang Li, He Rui, Chaoping Du, Jinlan Li

Journal of System Simulation

Abstract: To improve the accuracy of mechanical fault diagnosis, it’s meaningful to do research on the boundary effect of EMD. In this article, least squares linear method is applied to extend local extremum points at the end of a data series, which judges that whether the maximum value is within the wave fluctuation range of the original signal maximum points, whether the minimum value is within the wave fluctuation range of the original signal minimum points. It compares the extended extreme points and endpoint values, so the best signal endpoint is obtained. By calculating the value of similarity coefficient and …

Simulation Research On Post-Earthquake Road Network Repair Schedule Under Dynamic Traffic Flows, Shuanglin Li, Bin Zheng

Journal of System Simulation

Abstract: It is critical to repair the road network immediately to improve the emergency efficiency after earthquake. A mathematics model for post-earthquake road network repair scheduling under dynamic traffic flows (PRNRSDTF) is created and a hybrid genetic algorithm is provided to maximum the cumulative utilities. Finally, in the context of Wenchuan earthquake, a numerical example is abstract from Jingyang district of Deyang City to verify the reliability and validity of the proposed model and algorithm. The normal road network repair scheduling model without considering dynamical traffic flows is taken as a comparison. The results show that the PRNRSDTF model …