Artificial Intelligence and Robotics Commons^™

Extracting Road Surface Marking Features From Aerial Images Using Deep Learning, Michael Kimollo

UNF Graduate Theses and Dissertations

The traffic and roadway safety agencies spend significant efforts each year collecting roadway data, including lane configurations and other road surface marking data, such as areas with school zone markings, sidewalks, left turns, right turns, bicycle lanes, etc., for safety analysis and planning purposes. The current manual data collection methods pose significant operational and quality control challenges as they are costly and prone to errors. In addition to that the manual data collection is labor intensive and takes too much time involving high equipment costs, questionable data accuracy guarantees, and concerns about the safety of the crew.

This study aims …

Assessing The Performance Of A Particle Swarm Optimization Mobility Algorithm In A Hybrid Wi-Fi/Lora Flying Ad Hoc Network, William David Paredes

UNF Graduate Theses and Dissertations

Research on Flying Ad-Hoc Networks (FANETs) has increased due to the availability of Unmanned Aerial Vehicles (UAVs) and the electronic components that control and connect them. Many applications, such as 3D mapping, construction inspection, or emergency response operations could benefit from an application and adaptation of swarm intelligence-based deployments of multiple UAVs. Such groups of cooperating UAVs, through the use of local rules, could be seen as network nodes establishing an ad-hoc network for communication purposes.

One FANET application is to provide communication coverage over an area where communication infrastructure is unavailable. A crucial part of a FANET implementation is …

Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan

Publications

In this article, we address two key challenges in deep reinforcement learning (DRL) setting, sample inefficiency, and slow learning, with a dual-neural network (NN)-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning (EDL) approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the EDL regime is an approximation …

Development Of Machine Learning Based Approach To Predict Fuel Consumption And Maintenance Cost Of Heavy-Duty Vehicles Using Diesel And Alternative Fuels, Sasanka Katreddi

Graduate Theses, Dissertations, and Problem Reports (ETD)

One of the major contributors of human-made greenhouse gases (GHG) namely carbon dioxide (CO2), methane (CH4), and nitrous oxide (NOX) in the transportation sector and heavy-duty vehicles (HDV) contributing to about 27% of the overall fraction. In addition to the rapid increase in global temperature, airborne pollutants from diesel vehicles also present a risk to human health. Even a small improvement that could potentially drive energy savings to the century-old mature diesel technology could yield a significant impact on minimizing greenhouse gas emissions. With the increasing focus on reducing emissions and operating costs, there is a need for efficient and …

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study, Haben Yhdego, Christopher Paolini, Michel Audette

Electrical & Computer Engineering Faculty Publications

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has …

Class Activation Mapping And Uncertainty Estimation In Multi-Organ Segmentation, Md. Shibly Sadique, Walia Farzana, Ahmed Temtam, Khan Iftekharuddin, Khan Iftekharuddin (Ed.), Weijie Chen (Ed.)

Electrical & Computer Engineering Faculty Publications

Deep learning (DL)-based medical imaging and image segmentation algorithms achieve impressive performance on many benchmarks. Yet the efficacy of deep learning methods for future clinical applications may become questionable due to the lack of ability to reason with uncertainty and interpret probable areas of failures in prediction decisions. Therefore, it is desired that such a deep learning model for segmentation classification is able to reliably predict its confidence measure and map back to the original imaging cases to interpret the prediction decisions. In this work, uncertainty estimation for multiorgan segmentation task is evaluated to interpret the predictive modeling in DL …

Exploiting The Advantages And Overcoming The Challenges Of The Cable In A Tethered Drone System, Rogerio Rodrigues Lima

Graduate Theses, Dissertations, and Problem Reports (ETD)

This dissertation proposes solutions for motion planning, localization, and landing of tethered drones using only tether variables. A tether-based multi-model localization framework for tethered drones is proposed. This framework comprises three independent localization strategies based on a different model. The first strategy uses simple trigonometric relations assuming that the tether is taut; the second method relies on a set of catenary equations for the slack tether case; the third estimator is a neural network-based predictor that can cover different tether shapes. Multi-layer perceptron networks previously trained with a dataset comprised of the tether variables (i.e., length, tether angles on the …

Mitigating Anomalous Electricity Consumption In Smart Cities Using An Ai-Based Stacked-Generalization Technique, Arshid Ali, Laiq Khan, Nadeem Javaid, Safdar Hussain Bouk, Abdulaziz Aldegheishem, Nabil Alrahjeh

Computer Science Faculty Publications

Energy management and efficient asset utilization play an important role in the economic development of a country. The electricity produced at the power station faces two types of losses from the generation point to the end user. These losses are technical losses (TL) and non-technical losses (NTL). TLs occurs due to the use of inefficient equipment. While NTLs occur due to the anomalous consumption of electricity by the customers, which happens in many ways; energy theft being one of them. Energy theft majorly happens to cut down on the electricity bills. These losses in the smart grid (SG) are the …

Deep Learning-Based Technique For The Perception Of The Cervical Cancer, Aya Haraz, Hossam El-Din Moustafa, Abeer Twakol Khaleel, Ahmed H. Eltanboly

Mansoura Engineering Journal

In third-world countries, cervical cancer is the most prevalent and leading cause of death. It is affected by a variety of factors, including smoking, poor nutritional status, immunological inadequacy, and prolonged use of contraception. The Pap smear test, which is intended to prevent cervical cancer, finds preneoplastic changes in cervical epithelial cells. This study framework classified cervical cancer cells from Pap smears into five specified cell types using machine learning-based classification algorithms. The SIPaKMeD database is used in this investigation. This public dataset, which was manually cropped from 966 cluster cell images taken from Pap smear slides, has 4045 isolated …

Design And Implementation Of Cardiopulmonary Resuscitation Simulation Model, Mbazingwa Mkiramweni

Tanzania Journal of Engineering and Technology (TJET)

Cardiopulmonary resuscitation (CPR) is a life-saving procedure that can multiply a person's chances of survival after a cardiac arrest. The effectiveness of CPR procedures is heavily influenced by the individual skills of the rescuer providing assistance. Chest compressions delivered at an appropriate depth and rate, allowing full chest recoil and with minimal interruptions, are critical for improving cardiac arrest survival. The lack of quality CPR training models in developing countries has a significant impact on the quality of CPR training and skills acquired. Therefore, in this paper, we aim at improving CPR training by designing a high-fidelity CPR training manikin. …

Examining Early Elementary Computer Science Identity Repertoires Within A Curriculum: Implications For Epistemologically Pluralistic Identities, Eleanor Richard, Shakhnoza Kayumova

Journal of Computer Science Integration

As computer science (CS) enters an increasing number of elementary classrooms, researchers must investigate the representations of what kinds of people are presented as doing computer science within CS curricula. In this paper, we explore a widely used, freely accessible, web-based, early elementary CS curriculum to examine the kinds of identity repertoires (behaviors, actions, skills, and socioemotional norms) that are promoted as representative of being/becoming a CS person. More specifically, we draw on identity studies and employ critical discourse analysis to examine how the kinds of norms and repertoires of CS practice made available in the curricular materials might construct …

Emulating Future Neurotechnology Using Magic, Jay A. Olson, Mariève Cyr, Despina Z. Artenie, Thomas Strandberg, Lars Hall, Matthew L. Tompkins, Amir Raz, Petter Johansson

Psychology Faculty Articles and Research

Recent developments in neuroscience and artificial intelligence have allowed machines to decode mental processes with growing accuracy. Neuroethicists have speculated that perfecting these technologies may result in reactions ranging from an invasion of privacy to an increase in self-understanding. Yet, evaluating these predictions is difficult given that people are poor at forecasting their reactions. To address this, we developed a paradigm using elements of performance magic to emulate future neurotechnologies. We led 59 participants to believe that a (sham) neurotechnological machine could infer their preferences, detect their errors, and reveal their deep-seated attitudes. The machine gave participants randomly assigned positive …

Overview Of Research And Application On Autonomous Vehicle Oriented Perception System Simulation, Ruoxuan Wang, Jianping Wu, Hui Xu

Journal of System Simulation

Abstract: Following the rapid progress of science and technology, vehicles with autonomous driving or auxiliary driving function enter into vehicle market. However, in the past decade, traffic accidents still occurred frequently, and the safety of these functions become the focus. Simulation technology provides a good platform to test the perception system of autonomous vehicle. Focus on the sensor simulation modeling of autonomous vehicle perception system, from the perspective of single sensor simulation, multi-sensor simulation and classic simulation platform including millimeter wave radar, lidar and camera, the existing research are reviewed, and the shortcomings and development trends of simulation modeling of …

Anomaly Detection Method Of Electrical Power Consumption Based On Deep Autoencoder, Ningke Sun, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: Aiming at the nonlinear and non-stationary characteristics of electrical power consumption data, an abnormal electrical power consumption detection model based on deep autoencoder is proposed. Gated recurrent unit (GRU) network of the deep learning is combined with autoencoder structure, and the encoder and decoder parts of traditional autoencoder are realized by gated recurrent unit network, which gives full play to the data feature extraction capability of gated recurrent unit and the data reconstruction function of autoencoder structure. Based on the reconstruction error between original data and reconstructed data, abnormal data points of the electrical power consumption are detected. By …

Short-Term Prediction Method Of Wind Power Based On Blp-Alo-Svm, Yefeng Jiao, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: To effectively predict the short-term wind power and its fluctuation range, a prediction method based on hybrid algorithm-optimized support vector machine is proposed. Exploratory data analysis is used to preprocess the original wind speed data to improve the data quality. Chaotic map, Levy flight strategy and particle swarm optimization are used to improve the ant lion algorithm. The support vector machine model optimized by hybrid algorithm is used to predict the wind power. The experimental results show that, compared with the new wind power prediction model, the prediction error of the output results of the method is lower, and …

Long-Term Resilience Simulation On Low-Carbon Urban Grid Based On Evolutionary Game, Zhengda Cui, Weiqiang Yao, Qin Xu, Chen Fang, Ying Chen

Journal of System Simulation

Abstract: Because of the more frequent extreme disasters, the resilience of urban grid becomes more important. In the background of carbon neutralization policy, the decarbonization transition of urban grid also affects the development of grid resilience. An evolutionary game is used to simulate the resilience evolution of low-carbon urban grid and the evolution model is constructed. The decision to install photovoltaic and energy storage system for residents and to upgrade the grid for resilience is considered in the model and the stability conditions of equilibriums of the evolutionary game are analyzed. The resilience evolution simulation model considering disaster stochasticity is …

Simulation-Driven Based Utility Evaluation And Recommendation Of Expressway Proactive Speed Limit, Geqi Qi, Sijin Liu, Yikang He, Meng Wang, Ailing Huang

Journal of System Simulation

Abstract: Outside the specific punishment area, the traditional roadside passive speed limit mode lacks traffic management, and thus which indirectly leads to the inconsistency or even sudden change of vehicle behaviors in time and space, thereby affects the traffic efficiency and safety. Focusing on the proactive speed limit mode at vehicle side, a utility evaluation and recommendation method is proposed, which carries out the multi-scenario traffic simulation for varied proactive and passive speed limit considering road line types, traffic flow and vehicle type proportion. From the two perspectives of safety and efficiency, the utility evaluation indicators and weights are extracted …

Simulation On Flood Disaster In Urban Building Complex System Based On Lbm, Shen Zhang, Zewang Yang, Yifan Wang, Liang Sun, Ming Cheng, Fankai Meng, Ting Li

Journal of System Simulation

Abstract: Because of the extreme climate change, the potential flood disaster risk in the southeast coastal areas of China can not be ignored. Based on lattice Boltzmann computational fluid dynamics method, a three-dimensional simulation study of waterlogging process in tsunami impact scenario is carried out for a coastal city building complex system, and the reliability and accuracy of the numerical simulation method for the flood impact test of an ideal building complex are verified. The results show that the buildings along rivers and coastlines have obvious cloaking effect, while the buildings inside the city are less affected by floods. The …

Research On Modeling And Simulation Technology Of Microwave Radar High Precision Tracking Loop, Jiaji Lou, Jing Ma, Xiaowei Li, Yue Zhao, Youbin Song

Journal of System Simulation

Abstract: Aiming at the key problem of high-precision tracking loop design of a measurement radar for the weak signal (low carrier to noise ratio signal) in dynamic environment, the design and optimization methods of carrier tracking loop and code tracking loop are focused on. A signal structure with a single carrier as a pilot is proposed, and the loop structure of the frequency-locked loop and the phase-locked loop working together is studied. The modeling and simulation on the two structures show that for the week signal tracking in a dynamic environment, the loop combination structure of the frequency-serial auxiliary …

Research On Parameter Construction Method Of Blue Army Equipment Model Based On A Deep Network, Boyuan Zhang, Guanghong Gong, Ze Wang, Ni Li

Journal of System Simulation

Abstract: The modeling of blue army equipment is an indispensable part of adversarial simulation environment construction. Aiming at the limited available parameters of "information-poor" and "small sample" characteristics to the blue system, a deep network-based method is proposed to generate the parameters of blue army equipment model. By injecting the information into the simulation model of the blue army equipment, the simulation data is generated and trained in the deep neural network. The obtained network has a certain generalization ability to the unknown parameters prediction of the same type of equipment and can be used directly in prediction or be …

Multi-Robot Path Planning Based On Cbs Algorithm, Qiao Qiao, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: Aiming at the long multi-robot planning path and long one-way search running time of conflict-based search(CBS) in the multi-agent path finding(MAPF), an improved CBS algorithm is proposed, which in a two-way A^* focus search is used to optimize the search direction and search method. The suboptimal factorωis introduced into the underlying search function of the CBS algorithm to improve the efficiency of path search. The one-way search in the conflict search algorithm is optimized to a two-way A^* search. The experimental results show that the path cost of the improved CBS algorithm is shortened …

Research On Emotional Contagion And Intervention Strategy Of Indoor Evacuation Based On Risk Perception, Yang Zeng, Jinling Li, Haixiang Guo, Weiming Chen

Journal of System Simulation

Abstract: Aiming at the panic emotion contagion in the indoor emergency evacuation with multi-exit and multi-obstacle, an emotional contagion model is constructed on personality traits, risk perception differences of age and gender, and consciousness regulation. The simulation is carried out by using AnyLogic, which combines individual emotions with evacuation speed to realize the real-time updating of emotional state and speed. That personnel intervention in the process of evacuation can effectively alleviate the spread of panic emotion, is verified and can provide the theoretical basis for panic contagion in the process of emergency evacuation. The results show that the degree of …

Research On Complex Combat Network Dynamic Evolution Based On Information Entropy, Lianyi Zhang, Xisheng Shen, Duzheng Qing, Han Zhang, Min Zhou, Xifu Wang

Journal of System Simulation

Abstract: Network-centric warfare, distributed and decentralized command and control gradually replace separately the traditional platform-centric warfare and centralized command and control, and information has become a combat capability. Based on the new information weapon equipment system operation loop, a complex combat network model based on information entropy is constructed, and the combat capability measurement method is proposed. On the basis of the combat capability upgrade being the network driving force, the dynamic evolution rule of the complex combat network is designed and the preferential evolution and stochastic evolution models are constructed. According to a typical system combat example, the influence …

Sis-Based Modeling And Simulation Analysis On Exercise Benefit Perception Transmission, Lei Wang, Jinhai Sun, Tuojian Li

Journal of System Simulation

Abstract: In order to distinguish the relationship between individual health behavior change and collective health behavior emergence, deal with the challenges of mathematical description of typical health information dissemination processes in social networks and social experiments, SIS(susceptible-infected-susceptible)model is introduced to simulate the dissemination process of classical health information exercise effect perception to meet the requirements of social system complexity, individual diversity and intelligence. To carry out numerical experiments on the propagation process of exercise effect perception to identify the phase change process of the collective health behavior emergence, agent-based modeling and simulation are utilized through NetLogo. Experimental results show …

Low Voltage Ride-Through Modeling For Wind Turbines Based On Neural Odes, Qiping Lai, Tannan Xiao, Dongsheng Li, Chen Shen

Journal of System Simulation

Abstract: Considering the difficulty of equivalent modeling of low voltage ride-through(LVRT) characteristics of a wind farm, a neural ordinary differential equation(ODE)-based wind farm LVRT modeling methodis proposed. The input of the model is the voltage and wind speed of each wind turbine at the grid connection point of wind farm, and the output is the current at the grid connection point. The model can better characterize the strong nonlinear switching process and describe LVRT characteristics of wind farms under different wind speed scenarios. A simulation example of a wind farm including three doubly-fed induction generators(DFIGs) is established on …

Simulation Research On Appearance Detection Of Ampoules Based On Lightweight Network And Model Compression, Zhihao Zhu, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: Aiming at the large scale and redundant parameters of target detection network model, which result in the difficult to deploy the ampoule bottle appearance defect detection model to edge devices, an LC-Faster R-CNN defect detection algorithm based on lightweight network and model compression is proposed. MobileNet-V2 is used as the backbone, and the redundant channels in the convolutional network are trimmed by model pruning strategy. The floating-point parameters are quantized into integers through saturation truncation mapping. Knowledge distillation is used to restore the accuracy of the compressed network. Tested on the self-built ampoule appearance defect dataset, the model volume …

Fast Generation Method Of Multi-Sensing Channel Fusion Virtual Experiment, Jingwei Deng, Hanwu He, Yueming Wu, Jianhao Su

Journal of System Simulation

Abstract: Aiming at the low development efficiency and single experience in traditional virtual experiments, a rapid generation method of multi-sensing channel fusion virtual experiment visualization is proposed. The experimental steps and sequence of experimental steps of the virtual experiment are defined. A parameterized description method of experimental elements based on Petri net is proposed to describe the sequence of experimental steps, which breaks through the constraints the established procedure steps of traditional virtual experiments and supports the exploratory virtual experiments. The visual expression method of the routing graph and the conversion method between the routing graph and the Petri …

Research On Iterative Calculation And Optimization Methods Of Aero-Engine On-Board Model, Xinghua Luo, Jia Geng, Ming Li, Bei Liu, Lei Wang, Zhiping Song

Journal of System Simulation

Abstract: Aeroengine is a complex and time-varying multivariable thermophysical system. The research on the convergence accuracy and rate of the component-level model is of great significance to the model-based engine health management, performance and fault-tolerant control. The existing engine component-level models are generally based on the traditional quasi-Newton method to solve the equilibrium equations simultaneously. Compared with the traditional Newton-Raphson method (N-R method), the convergence speed is optimized, but it is difficult to meet accuracy and real-time requirements of the dynamic model airborne applications within the full envelope. An adaptive variable step factor quasi-Newton method is proposed, which can reduce …

Reliability Parameter Optimization Complex System Simulation Based On R-Vikor Method, Zhiguang Wang, Baiting Liu, Xiaolei Wang, Tao Liu, Zhaowei Yang

Journal of System Simulation

Abstract: The operation of complex simulation system is not isolated, and always affected by multiple external factors and its own performance. In simulation reliability calculation, parameters need to be chosen, and different performance indexes need to be taken into account when comparing with the reference model. The research is transformed into the multi-attribute decision. An system simulation trusted parameter optimization method based on R-VIKOR(resist rank reversal of visekriterijumska optimizacija | kompromisno resenje) is proposed. Multiple sets of aerodynamic parameters of the new model are obtained through model migration theory, and similarity calculation is carried out with the optimal parameters of …

Research On Low Computational Predictive Control Strategy Of Three-Level Four-Arm Apf, Guifeng Wang, Jinxing Guo

Journal of System Simulation

Abstract: Four-arm active power filter(APF) is an ideal device to the power quality of three-phase four-wire distribution network. Owing to the sufficient number of base vectors, three-level four-arm APF has better current tracking performance, but the prediction calculation amount is too large when model predictive current control is applied. A model prediction voltage control strategy based on the idea of space stratification is proposed. Based on the deadbeat control idea and the discrete mathematical model in αβγ coordinate system, the expected reference voltage is predicted from the reference current, and the multiple current predictions are converted into the single voltage …