Artificial Intelligence and Robotics Commons^™

Applying Deep Learning For Cell Detection In Time-Lapse Microscopic Images, Jay Patel

Honors Theses

The budding yeast Saccharomyces cerevisiae is an effective model for studying cellular aging. We can measure the lifespan of yeast cells in two ways: replicative and chronological lifespans. Chronological focuses on the time that a cell can survive. The replicative lifespan (RLS) is the number of cell divisions that a single mother cell can go through before ceases to be dividing. RLS is a measurement of individual cells and is more informative on the aging process than in chronological lifespan. Many genes that influence yeast RLS have been shown to be highly conserved and have a similar effect on aging …

Data Mining For Structural Damage Identification Using Hybrid Artificial Neural Network Based Algorithm For Beam And Slab Girder, Gordan Meisam

Student Works (2020-2029)

One of the approaches for structural health monitoring (SHM) consists of two major components, i.e. a network of sensors to collect the response data and an extraction method to obtain information on the structural health condition. Data mining (DM) is a novel data extraction technology which can employ for development of inverse analysis. Implementation of DM techniques in different areas of civil engineering has recently given very good results. However, application of DM in SHM is not used as much as expected, thus, many challenges are still ahead. Therefore, it is necessary to develop the applicability of DM in SHM. …

Feature Pyramid Transformer, Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang, Xian-Sheng Hua, Qianru Sun

Research Collection School Of Computing and Information Systems

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN’s increasing receptive fields or actively encoded by non-local convolution. Yet, the non-local spatial interactions are not across scales, and thus they fail to capture the non-local contexts of objects (or parts) residing in different scales. To this end, we propose a fully active feature interaction across both space and scales, called Feature Pyramid Transformer (FPT). It transforms any feature pyramid into another feature pyramid of the same size but with richer contexts, by using …

An Ensemble Of Epoch-Wise Empirical Bayes For Few-Shot Learning, Yaoyao Liu, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predictions. In this paper, we propose to meta-learn the ensemble of epoch-wise empirical Bayes models (E3BM) to achieve robust predictions. “Epoch-wise'' means that each training epoch has a Bayes model whose parameters are specifically learned and deployed. ”Empirical'' means that the hyperparameters, e.g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data. We introduce four kinds of hyperprior learners by considering inductive vs. transductive, and epoch-dependent …

An Attention-Based Rumor Detection Model With Tree-Structured Recursive Neural Networks, Jing Ma, Wei Gao, Shafiq Joty, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Rumor spread in social media severely jeopardizes the credibility of online content. Thus, automatic debunking of rumors is of great importance to keep social media a healthy environment. While facing a dubious claim, people often dispute its truthfulness sporadically in their posts containing various cues, which can form useful evidence with long-distance dependencies. In this work, we propose to learn discriminative features from microblog posts by following their non-sequential propagation structure and generate more powerful representations for identifying rumors. For modeling non-sequential structure, we first represent the diffusion of microblog posts with propagation trees, which provide valuable clues on how …

Intersentiment: Combining Deep Neural Models On Interaction And Sentiment For Review Rating Prediction, Shi Feng, Kaisong Song, Daling Wang, Wei Gao, Yifei Zhang

Research Collection School Of Computing and Information Systems

Review rating prediction is commonly approached from the perspective of either Collaborative Filtering (CF) or Sentiment Classification (SC). CF-based approach usually resorts to matrix factorization based on user–item interaction, and does not fully utilize the valuable review text features. In contrast, SC-based approach is focused on mining review content, but can just incorporate some user- and product-level features, and fails to capture sufficient interactions between them represented typically in a sparse matrix as CF can do. In this paper, we propose a novel, extensible review rating prediction model called InterSentiment by bridging the user-product interaction model and the sentiment model …

Commanding And Re-Dictation: Developing Eyes-Free Voice-Based Interaction For Editing Dictated Text, Debjyoti Ghosh, Can Liu, Shengdong Zhao, Kotaro Hara

Research Collection School Of Computing and Information Systems

Existing voice-based interfaces have limited support for text editing, especially when seeing the text is difficult, e.g., while walking or cooking. This research develops voice interaction techniques for eyes-free text editing. First, with a Wizard-of-Oz study, we identified two primary user strategies: using commands, e.g., “replace go with goes” and re-dictating over an erroneous portion, e.g., correcting “he go there” by saying “he goes there.” To support these user strategies with an actual system implementation, we developed two eyes-free voice interaction techniques, Commanding and Re-dictation, and evaluated them with a controlled experiment. Results showed that while Re-dictation performs significantly better …

An Analysis Of Sketched Irls For Accelerated Sparse Residual Regression, Daichi Iwata, Michael Waechter, Wen-Yan Lin, Yasuyuki Matsushita

Research Collection School Of Computing and Information Systems

This paper studies the problem of sparse residual regression, i.e., learning a linear model using a norm that favors solutions in which the residuals are sparsely distributed. This is a common problem in a wide range of computer vision applications where a linear system has a lot more equations than unknowns and we wish to find the maximum feasible set of equations by discarding unreliable ones. We show that one of the most popular solution methods, iteratively reweighted least squares (IRLS), can be significantly accelerated by the use of matrix sketching. We analyze the convergence behavior of the proposed method …

Waste Cooking Oil Classification Using Artificial Intelligence Technology, Kar Sin Lau

Student Works (2020-2029)

Palm oil – one of the most common edible oil consumed in Malaysia. It is because Malaysia is one of the countries which supply palm oil to the global market and it is cheap to obtain for the consumer in Malaysia. Most of the Malaysian consume it via food preparation such as deep-frying and cooking. However, due to widely available for Malaysians, consumers also lacking awareness in dealing after using the edible oil. Most of the household consumers discard excess waste cooking oil (WCO) into sewage and with courtesy, some of them stored them in containers and sell to NGOs. …

Application Of Artificial Intelligence And Geographic Information System For Developing Automated Walkability Score, Md Mehedi Hasan

Dissertations

Walking is considered as one of the major modes of active transportation, which contributes to the livability of cities. It is highly important to ensure walk friendly sidewalks to promote human physical activities along roads. Over the last two decades, different walk scores were estimated in respect to walkability measures by applying different methods and approaches. However, in the era of big data and machine learning revolution, there is still a gap to measure the composite walkability score in an automated way by applying and quantifying the activityfriendliness of walkable streets. In this study, a street-level automated walkability score was …

Machine Learning Enhanced Free-Space And Underwater Oam Optical Communications, Patrick L. Neary

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Communications, bandwidth, security, and hardware simplicity are principles of interest to society at large. Recent advances in optics and in understanding properties of light, such as orbital angular momentum (OAM), have provided new potential mediums for communication.

Machine learning has wound its way into a broad range of fascinating areas. An emerging field of research is the use of a unique property of lasers called orbital angular momentum (OAM). With the proper hardware, a laser can go from a Gaussian shaped distribution to a doughnut shaped pattern, where the radius can be changed. Multiple OAM patterns, or modes, can be …

An Investigation Into Multi-View Error Correcting Output Code Classifiers Applied To Organ Tissue Classification, Daniel Alvarez

UNLV Theses, Dissertations, Professional Papers, and Capstones

Large amounts of data is being generated constantly each day, so much data that it is difficult to find patterns in order to predict outcomes and make decisions for both humans and machines alike. It would be useful if this data could be simplified using machine learning techniques. For example, biological cell identity is dependent on many factors tied to genetic processes. Such factors include proteins, gene transcription, and gene methylation. Each of these factors are highly complex mechanism with immense amounts of data. Simplifying these can then be helpful in finding patterns in them. Error-Correcting Output Codes (ECOC) does …

Action Real-Time Strategy Gaming Experience Related To Enhanced Capacity Of Visual Working Memory, Yutong Yao, Ruifang Cui, Yi Li, Lu Zeng, Jinliang Jiang, Nan Qiu, Li Dong, Diakun Gong, Guojian Yan, Weiyi Ma, Tiejun Liu

General Human Environmental Sciences Faculty Publications and Presentations

Action real-time strategy gaming (ARSG)—a major genre of action video gaming (AVG)—has both action and strategy elements. ARSG requires attention, visual working memory (VWM), sensorimotor skills, team cooperation, and strategy-making abilities, thus offering promising insights into the learning-induced plasticity. However, it is yet unknown whether the ARSG experience is related to the development of VWM capacity. Using both behavioral and event-related potential (ERP) measurements, this study tested whether ARSG experts had larger VWM capacity than non-experts in a change detection task. The behavioral results showed that ARSG experts had higher accuracy and larger VWM capacity than non-experts. In addition, the …

Predictive Insights For Improving The Resilience Of Global Food Security Using Artificial Intelligence, Meng Leong How, Yong Jiet Chan, Sin Mei Cheah

Research Collection Lee Kong Chian School Of Business

Unabated pressures on food systems affect food security on a global scale. A human-centric artificial intelligence-based probabilistic approach is used in this paper to perform a unified analysis of data from the Global Food Security Index (GFSI). The significance of this intuitive probabilistic reasoning approach for predictive forecasting lies in its simplicity and user-friendliness to people who may not be trained in classical computer science or in software programming. In this approach, predictive modeling using a counterfactual probabilistic reasoning analysis of the GFSI dataset can be utilized to reveal the interplay and tensions between the variables that underlie food affordability, …

A Multicut Outer-Approximation Approach For Competitive Facility Location Under Random Utilities, Tien Mai, Andrea Lodi

Research Collection School Of Computing and Information Systems

This work concerns the maximum capture facility location problem with random utilities, i.e., the problem of seeking to locate new facilities in a competitive market such that the captured demand of users is maximized, assuming that each individual chooses among all available facilities according to a random utility maximization model. The main challenge lies in the nonlinearity of the objective function. Motivated by the convexity and separable structure of such an objective function, we propose an enhanced implementation of the outer approximation scheme. Our algorithm works in a cutting plane fashion and allows to separate the objective function into a …

Off-Policy Reinforcement Learning For Efficient And Effective Gan Architecture Search, Tian Yuan, Wang Qin, Zhiwu Huang, Wen Li, Dengxin Dai, Minghao Yang, Jun Wang, Olga Fink

Research Collection School Of Computing and Information Systems

In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is …

Situation Assessment Method For Cooperative Air Combat Based On Dynamic Combat Power Field, Zhanwu Li, Yizhe Chang, Haiyan Yang, Yingxin Kou, Xu An

Journal of System Simulation

Abstract: Considering on the remaining problem in current situation assessment of Beyond-Visual-Range cooperative air combat, such as isolation of static/dynamic state superiority, the concept of combat power field was applied in situation assessment of Beyond-Visual-Range cooperative air combat. Coupled with characteristics of cooperative air combat, the model of combat power field was constructed by aspects of attack, communication, detection, maneuverability, electronic countermeasure and cooperation and alert. The method was verified by the simulation. The result shows the method has advantages of integrity, visualization and continuity compared with former situation assessment methods, and is also able to improve the quality and …

Research On Optimizing Lot Sizing Of Job Shop Based On Em_Plant, Xiaobing Pei, Linlin Tan

Journal of System Simulation

Abstract: Considering maximizing the rate of account and choosing production process time as the optimization objectives to solve the lot sizing optimization problems of job shop, the model about production time under ideal conditions was established, and accordingly the formula of solving theoretical optimal lot sizing was derived. To compensate for the limitations of mathematical modeling and improve the feasibility of the optimal solution, the actual manufacturing operations in job shop was simulated and optimized according to production batch simulation optimization strategy by eM_plant software. By running the simulation model the theoretical optimal solution was amended, to make optimal …

Design And Implementation Of Quantum-Inspired Bee Colony Algorithm, Shuyun Yang, Panchi Li

Journal of System Simulation

Abstract: To enhance the performance of artificial bee colony algorithm, a quantum-inspired bee colony algorithm was proposed. In the proposed approach, the bees were encoded with the qubits described on the Bloch sphere. The evolutionary search was achieved by rotating the qubit about the rotation axis on the Bloch sphere. The Bloch coordinates of qubit can be obtained by measuring with the Pauli matrices, and the optimization solutions can be presented through the solution space transformation. The highlight advantages of this method are the ability to simultaneously adjust two parameters of a qubit and automatically achieve the best match between …

Intelligent Detecting For Infrared Aerial Small Target Based On Non-Subsampled Contourlet Transform, Liu Gang, Xingyuan Xu, Zhou Heng, Xitao Zhang

Journal of System Simulation

Abstract: Aiming at the problem of infrared aerospace small target's detecting under complex background, an intelligent algorithm was proposed based on the non-subsampled contourlet transform and BP neutral network. By using the morphologic top-hat transform which had adaptive structural element, some infrared background was suppressed. By defining the center vector of subband coefficients, the proposed method constructed the synthetical image at high frequency and suppressed the complex background further. Subsequently, taking pixel's gray level, horizontal gradient, vertical gradient, diagonal gradient, neighbour mean and neighbour variance as input character vector, a BP neutral network which had three layers was constructed by …

Dynamic Simulation And Test Of Mountain Orchard Double-Track Transport Traction System, Yuping Ouyang, Tiansheng Hong, Yudong Ma

Journal of System Simulation

Abstract: After the traction system virtual prototype model of mountain orchard transport was established, virtual simulation test was done to get the force of wire rope and the dynamic characteristics. Compared with trapezoidal velocity, under S type velocity curve, vehicle vibration amplitude was decreased obviously in each stage, average maximum force and average force of four key points was respectively decreased by 9.2% and 12.7%. Average relative error between kinetic parameters calculation and simulation values was 4.8%. Average relative error between test and simulation values was 4.02 %. This research results have provided a simulation platform and reference to whole …

Performance Analysis Of Netted Radar Data Fusion Systems, Zhijie Chen, Bin Rao, Yongzhen Li, Zhiwei Zong

Journal of System Simulation

Abstract: The performance analysis of netted radar data fusion systems was proposed. The principles of two representative radar netting modes (i.e., centralized fusion and distributed fusion) were introduced and the associated capabilities of anti-jamming, anti-stealth, fusion accuracy, fusion discrimination, and communication requirements were quantitatively analyzed. Simulation results indicate that the netting essence is, centralized fusion by using ‘or' rule to complement information and realize trajectory composition whereas distributed fusion by using ‘and' rule to reduce information redundancy and realize discrimination ability. The research can provide some enlightenment for the newly-developed intellective netted radar data fusion systems.

Parameter Optimization On Coordinated Control System Of Thermal Power Units In High Rate Variable Load Operation Mode, Tian Liang, Liu Fang, Xinping Liu, Jizhen Liu

Journal of System Simulation

Abstract: The frequent fluctuations and rapid change of power grid generating load instruction cause the deterioration of control quality of generating load and throttle pressure in thermal power units. To solve this problem, a trial and error method, the parameters adjustment range of which could be quantified, was proposed. Based on the model of controlled object, the initial value of controller parameters were set conservatively. By calculating the difference between current value and the target value of load change rate, the optimization times were determined, the PID controller parameters optimization method of coordinated control system was studied, and the effectiveness …

Research On Section Optimization Of Water Quality Monitoring Based On Comprehensive Hierarchical Clustering, Xiaofeng Lian, Peng Sen, Xiaoyi Wang, Zaiwen Liu

Journal of System Simulation

Abstract: In order to optimize the layout of water quality monitoring section of river, lake and reservoir effectively, a new method for water quality monitoring section optimization was proposed based on comprehensive hierarchical clustering (CHC). A normalized matrix was constructed according to the original monitoring data of water quality. The method calculated the similarity to obtain the affinity-disaffinity relationship among the monitoring variables by 5 different distance algorithms, and then clustered the data set automatically by 4 different connection algorithms. Moreover, taking the correlation coefficient as the evaluation criteria, optimal hierarchical clustering algorithm was selected. With the generation …

Sliding Parameters Calculation Of Agricultural Tracked Robot Based On Ukf And Smo, Jiao Jun, Kong Wen, Lichuan Gu, Wang Qiang, Ya Gao, Chenchen Yuan

Journal of System Simulation

Abstract: In order to make ensure an Agricultural Tracked Robot (ATR) stable driving in farmland and reduce the slip phenomenon parameters, a novel sliding parameters estimation scheme of ATR based on UKF (Unscented Kalman Filter) and SMO (Sliding Mode Observer) was proposed. The motion equation and measurement equation of ATR were fused by UKF to compensate the measurement error from sensors and to reconstruct the precision pose parameters of ATR. Three slip parameter observers were designed for the sideslip angle, left and right track slip rate, which used the tangent function was used as the switching function to cover chattering …

Experiment Platform For Pure Electric Vehicles And Bi-Directional Power Conversion, Shaojian Song, Qingfang Lin, Xiaofeng Lin

Journal of System Simulation

Abstract: As the energy consumption and environmental pollution brought by traditional internal combustion engine vehicles, the experimental platform for pure electric vehicle research is scarce, and most of the research uses virtual vehicle simulation software, which is difficult to accurately reflect the real vehicle system. An experiment platform for LiFePO₄ Battery pack (the main energy source) and ultra-capacitor (the auxiliary energy source) hybrid pure electric vehicles and bi-directional power conversion was introduced. The test results show that the introduced experimental platform can be performance test for the key components of pure electric vehicle and energy management, running under …

Implementation And Application Of Coordinate Stretched Pml Under Two-Dimensional Cylindrical Coordinate, Anshi Zhu, Zili Chen, Yang Yong, Yunhui Zhen

Journal of System Simulation

Abstract: According to the numerical calculation of electromagnetic field under cylindrical coordinate, the conventional split field absorbing boundary is no longer applicable. The coordinate stretched perfectly matched layers (CS-PML) were applied in the two-dimensional stretched cylindrical coordinate system. The updating equations of Maxwell curl equations in CS-PML were derived by using auxiliary equation method. The simulation results show that theoretical derivation is correct. The reflection coefficient of CS-PML is less than -30 dB, and it is able to meet the precision demand of numerical calculation. Besides, the CS-PML was adopted to investigate the radiation characteristic of the …

Simulation Of Converter Torsional Vibration Based On Multi-Body Dynamics, Hongbin Liu, Yongsheng Shi, Zhang Lei, Hongbiao Han

Journal of System Simulation

Abstract: Torsional vibration of large converter is very easy to cause the transmission gear failure. In order to solve large converters' torsional vibration during working, a converter multi-body dynamic analysis model on rigid-flexible coupling method was built by using of multi-body dynamics simulation software RecurDyn and the finite element analysis software ANSYS. And the dynamic simulation study of this model was carried out. The effects of torsional vibration by different parking methods, parking times, the converters' vibration frequency and the amplitude were obtained through the dynamics simulation calculation. The results show that the torsional vibration amplitude of converter can …

Study On Theory Of Scale Model Simulation Of Light Wave-Microwave System On Inequality Electrical Length Conditions, He Jing, Miao Qiang, Qifan Zhao

Journal of System Simulation

Abstract: Light wave model measurement microwave system at big scale factor on inequality electrical length conditions was proposed. The analysis idea of such model measurement was put forward. The feasibility of simulating electromagnetic scattering at microwave band using optic wave was discussed from the angle of physical similitude and technological feasibility. Then according to this idea, the similitude relationship and conditions in the application such as RCS measurement and multipath effect measurement were analyzed in detail on inequality electrical length conditions model measurement. The research result offers a new research approach in the field of large scale electromagnetic system simulation.

Finite Element Simulation Of Machining 7075 Aluminum Alloy Based On Advantedge And Corresponding Experimental Study, Yusong Liao, Han Jiang

Journal of System Simulation

Abstract: Abstract: The finite element simulation of cutting 7050 aluminum alloy was carried out based on the software of AdvantEdge, and Johnson-Cook constitutive model was chosen for the workpiece material in the model. The parameters for the constitutive model were obtained through the Hopkinson experiment. The cutting forces and surface qualities were observed through different cutting velocities and cutting depths. The cutting velocity and cutting depth were optimized, and the experiment was carried out with the guidance of the simulation results. The machined workpiece obtained from the experiment shows that the optimized cutting parameters can improve the machined surface property …