Artificial Intelligence and Robotics Commons^™

Design And Development Of Techniques To Ensure Integrity In Fog Computing Based Databases, Abdulwahab Fahad S. Alazeb

Graduate Theses and Dissertations

The advancement of information technology in coming years will bring significant changes to the way sensitive data is processed. But the volume of generated data is rapidly growing worldwide. Technologies such as cloud computing, fog computing, and the Internet of things (IoT) will offer business service providers and consumers opportunities to obtain effective and efficient services as well as enhance their experiences and services; increased availability and higher-quality services via real-time data processing augment the potential for technology to add value to everyday experiences. This improves human life quality and easiness. As promising as these technological innovations, they are prone …

Leveraging Big Data For Pattern Recognition Of Socio-Demographic And Climatic Factors In Correlation With Eye Disorders In Telangana State, India, Amna Alalawi, Les Sztandera, Parth Lalakia, Anthony Vipin Das, Sai Prashanthi Gumpili, Richard Derman

Kanbar College Faculty Papers

Purpose: Big data is the new gold, especially in health care. Advances in collecting and processing electronic medical records (EMR) coupled with increasing computer capabilities have resulted in an increased interest in the use of big data in health care. Ophthalmology has been an area of focus where results have shown to be promising. The objective of this study was to determine whether the EMR at a multi-tier ophthalmology network in India can contribute to the management of patient care, through studying how climatic and socio-demographic factors relate to eye disorders and visual impairment in the State of Telangana.

Methods: …

Signal Processing And Data Analysis For Real-Time Intermodal Freight Classification Through A Multimodal Sensor System., Enrique J. Sanchez Headley

Graduate Theses and Dissertations

Identifying freight patterns in transit is a common need among commercial and municipal entities. For example, the allocation of resources among Departments of Transportation is often predicated on an understanding of freight patterns along major highways. There exist multiple sensor systems to detect and count vehicles at areas of interest. Many of these sensors are limited in their ability to detect more specific features of vehicles in traffic or are unable to perform well in adverse weather conditions. Despite this limitation, to date there is little comparative analysis among Laser Imaging and Detection and Ranging (LIDAR) sensors for freight detection …

Scheduling Allocation And Inventory Replenishment Problems Under Uncertainty: Applications In Managing Electric Vehicle And Drone Battery Swap Stations, Amin Asadi

Graduate Theses and Dissertations

In this dissertation, motivated by electric vehicle (EV) and drone application growth, we propose novel optimization problems and solution techniques for managing the operations at EV and drone battery swap stations. In Chapter 2, we introduce a novel class of stochastic scheduling allocation and inventory replenishment problems (SAIRP), which determines the recharging, discharging, and replacement decisions at a swap station over time to maximize the expected total profit. We use Markov Decision Process (MDP) to model SAIRPs facing uncertain demands, varying costs, and battery degradation. Considering battery degradation is crucial as it relaxes the assumption that charging/discharging batteries do not …

Trust In And Ethical Design Of Carebots: The Case For Ethics Of Care, Gary Kok Yew Chan

Research Collection Yong Pung How School Of Law

The paper has two main objectives: to examine the challenges arising from the use of carebots as well as to discuss how the design of carebots can deal with these challenges. First, it notes that the use of carebots to take care of the physical and mental health of the elderly, children and the disabled as well as to serve as assistive tools and social companions encounter a few main challenges. They relate to the extent of the care robots’ ability to care for humans, potential deception by robot morphology and communications, (over)reliance on or attachment to robots, and the …

How Important Is The Train-Validation Split In Meta-Learning?, Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, D. Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong

Research Collection School Of Computing and Information Systems

Meta-learning aims to perform fast adaptation on a new task through learning a “prior” from multiple existing tasks. A common practice in meta-learning is to perform a train-validation split (train-val method) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split. Despite its prevalence, the importance of the train-validation split is not well understood either in theory or in practice, particularly in comparison to the more direct train-train method, which uses all the pertask data for both training and evaluation. We provide a detailed theoretical study on whether …

Oesense: Employing Occlusion Effect For In-Ear Human Sensing, Dong Ma, Andrea Ferlini, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Smart earbuds are recognized as a new wearable platform for personal-scale human motion sensing. However, due to the interference from head movement or background noise, commonly-used modalities (e.g. accelerometer and microphone) fail to reliably detect both intense and light motions. To obviate this, we propose OESense, an acoustic-based in-ear system for general human motion sensing. The core idea behind OESense is the joint use of the occlusion effect (i.e., the enhancement of low-frequency components of bone-conducted sounds in an occluded ear canal) and inward-facing microphone, which naturally boosts the sensing signal and suppresses external interference. We prototype OESense as an …

Mmconv: An Environment For Multimodal Conversational Search Across Multiple Domains, Lizi Liao, Le Hong Long, Zheng Zhang, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Although conversational search has become a hot topic in both dialogue research and IR community, the real breakthrough has been limited by the scale and quality of datasets available. To address this fundamental obstacle, we introduce the Multimodal Multi-domain Conversational dataset (MMConv), a fully annotated collection of human-to-human role-playing dialogues spanning over multiple domains and tasks. The contribution is two-fold. First, beyond the task-oriented multimodal dialogues among user and agent pairs, dialogues are fully annotated with dialogue belief states and dialogue acts. More importantly, we create a relatively comprehensive environment for conducting multimodal conversational search with real user settings, structured …

Claim: Curriculum Learning Policy For Influence Maximization In Unknown Social Networks, Dexun Li, Meghna Lowalekar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information. Recently, it has also found application in HIV prevention, substance abuse prevention, micro-finance adoption, etc., where the goal is to identify the set of peer leaders in a real-world physical social network who can disseminate information to a large group of people. Unlike online social networks, real-world networks are not completely known, and collecting information about the network is costly as it involves surveying multiple people. In this paper, we focus on this problem of network discovery for …

Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Jing Jiang

Research Collection School Of Computing and Information Systems

We propose a new training objective named orderagnostic cross entropy (OAXE) for fully nonautoregressive translation (NAT) models. OAXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a common source of the critical multimodality problem in NAT. Concretely, OAXE removes the penalty for word order errors, and computes the cross entropy loss based on the best possible alignment between model predictions and target tokens. Since the log loss is very sensitive to invalid references, we leverage cross entropy initialization and loss truncation to ensure the model focuses on a good part of the search space. …

An Adaptive Large Neighborhood Search For The Green Mixed Fleet Vehicle Routing Problem With Realistic Energy Consumption And Partial Recharges, Vincent F. Yu, Panca Jodiawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

This study addresses a variant of the Electric Vehicle Routing Problem with Mixed Fleet, named as the Green Mixed Fleet Vehicle Routing Problem with Realistic Energy Consumption and Partial Recharges. This problem contains three important characteristics — realistic energy consumption, partial recharging policy, and carbon emissions. An adaptive Large Neighborhood Search heuristic is developed for the problem. Experimental results show that the proposed ALNS finds optimal solutions for most small-scale benchmark instances in a significantly faster computational time compared to the performance of CPLEX solver. Moreover, it obtains high quality solutions for all medium- and large-scale instances under a reasonable …

Task Similarity Aware Meta Learning: Theory-Inspired Improvement On Maml, Pan Zhou, Yingtian Zpu, Xiaotong Yuan, Jiashi Feng, Caiming Xiong, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Few-shot learning ability is heavily desired for machine intelligence. By meta-learning a model initialization from training tasks with fast adaptation ability to new tasks, model-agnostic meta-learning (MAML) has achieved remarkable success in a number of few-shot learning applications. However, theoretical understandings on the learning ability of MAML remain absent yet, hindering developing new and more advanced meta learning methods in a principled way. In this work, we solve this problem by theoretically justifying the fast adaptation capability of MAML when applied to new tasks. Specifically, we prove that the learnt meta-initialization can benefit the fast adaptation to new tasks with …

Methods For Detecting Floodwater On Roadways From Ground Level Images, Cem Sazara

Computational Modeling & Simulation Engineering Theses & Dissertations

Recent research and statistics show that the frequency of flooding in the world has been increasing and impacting flood-prone communities severely. This natural disaster causes significant damages to human life and properties, inundates roads, overwhelms drainage systems, and disrupts essential services and economic activities. The focus of this dissertation is to use machine learning methods to automatically detect floodwater in images from ground level in support of the frequently impacted communities. The ground level images can be retrieved from multiple sources, including the ones that are taken by mobile phone cameras as communities record the state of their flooded streets. …

Fire Suppression And Ignition With Unmanned Aerial Vehicles, Carrick Detweiler, Sebastian Elbaum, James Higgins, Christian Laney, Craig Allen, Dirac L. Twidwell Jr, Evan Michale Beachly

School of Computing: Faculty Publications

An unmanned aerial vehicle (UAV) can be configured for fire suppression and ignition. In some examples, the UAV includes an aerial propulsion system, an ignition system, and a control system. The ignition system includes a container of delayed-ignition balls and a dropper configured by virtue of one or more motors to actuate and drop the delayed-ignition balls. The control system is configured to cause the UAV to fly to a site of a prescribed burn and, while flying over the site of the prescribed burn, actuate one or more of the delayed-ignition balls. After actuating the one or more delayed-ignition …

Deep Peak-Shaving Transformation Planning Of Thermal Power Units Based On Approximate Dynamic Programming, Weiqing Sun, Song He, Han Dong, Kunpeng Tian

Journal of System Simulation

Abstract: The generation of renewable energy has great randomness. The lack of flexibility of thermal power unit leads to the problem of peak adjustment. Three reformation schemes for thermal power units, including the thermal power unit internal transformation, configurating energy storage, and joint transformation of the two are proposed. Taking into account the additional cost of thermal powerunit in the deep peak regulation, the planning model of thermal power units depth peak-shaving transformation considering the unit combination is proposed, and the strategy iteration approximate dynamic programming algorithm to decouple the model is presented. The “curses of dimensionality” can be avoided …

Prediction Method For Health Degree Of Front Bearing Of Wind Turbine Generator And Implementation, Yin Shi, Guolian Hou, Chi Yan, Linjuan Gong, Xiaodong Hu

Journal of System Simulation

Abstract: Aiming at the deterioration trend of front bearing of doubly-fed wind turbine generator, a new combined modeling method is proposed to predict health degree of front bearing of generator. The GMM is used to identify operating conditions of wind turbines. The temperature model of front bearing based on ELM is established respectively in each sub-condition. Combining with temperature residual characteristics and time-frequency characteristics of vibration signal, the health degree of front bearing is calculated. Based on attention mechanism, the Bi-LSTM neural network is proposed to model and predict health degree of front bearing. The result shows that the …

Design Of Lvc Simulation Test Middleware For Saas, Du Nan, Yaxin Tan

Journal of System Simulation

Abstract: LVC (Live-Virtual-Constructive) technology provides a new technical means for equipment test. In view of the large number of heterogeneous simulation resource objects and complex interaction in the LVC system test, which can not meet the test task requirements of quick response of the weapon system, the middleware and application model framework is reformed according to the remote method invocation based on TENA. The functional modules of LVC simulation middleware including model running component, publishing and ordering component, message processing component and real-time running component are designed to provide efficient real-time communication mechanism for LVC simulation and support the application …

Simulation On The Development Of Residential Distributed Photovoltaic Power Generation Under The Declining Trend Of Feed-In-Tariff, Libo Zhang, Lulu Ge, Changqi Chen, Mingduan Tang

Journal of System Simulation

Abstract: Residential Distributed Photovoltaic Generation (R-DPVG) has become the important developing force of PV generation in China. As the declining of Feed-in-Tariff (FIT), system dynamics method is used to construct a causal loop model for R-DPVG’s development, and relevant factors and their feedback mechanism are qualitatively analyzed. Then a stock-flow model is build, and the ROI, installed capacity, and policy subsidy costs of R-DPVG are simulated under some combined scenarios based on declining FIT. The simulation proves R-DPVG’s FIT will be reduced to 0.05 ~ 0.1 yuan/(kW?h) in the next three years till cancelled. FIT cutting amplitude, capacity and targets …

Approximate Method Of Spares Demand Prediction For Weibull Distribution Items Based On Piecewise Function, Songshi Shao, Zhihua Zhang, Xiaojie Mo

Journal of System Simulation

Abstract: Demand prediction model for spare parts with Weibull distribution involves multiple infinite series, therefore, spares demand calculation is a difficult issue. The approximate calculation method generally used is often subject to large errors. According to the principle of renewal function, the approximated demand calculation method for spares of Weibull distribution using piecewise function to approximate the renewal function is proposed. It effectively avoids the issue of computational complexity for spares demand prediction. Theoretical analysis shows that the proposed approximated algorithm ensures the calculation result of spares demand is less than that of engineering approximation algorithm. According to the given …

Research On Description Specification Of Extensible Simulation Scenario, Xiangzhong Xu, Xiong Jun, Fengwei Shen

Journal of System Simulation

Abstract: Simulation scenario description specification is of great significance to speed the Simulation Scenario Data (SSD) preparation, to improve the quality and to promote the reuse of the SSD. An in-depth comparison between simulation scenario and military scenario is made. The composition and application process of military scenario based on the description specification are designed, above which, the design scheme of the description specification is discussed. The extensible military scenario description specification is proposed from the following two aspects, that is, the basic elements including time and coordinate system, and the data interchange format. Series of scenario instances are produced. …