Intelligent PI control for trajectory regulation in autonomous vehicles using a voting-based ensemble of statistical learning models

This study presents a field-programmable gate array (FPGA)-based mechatronic design and real-time fuzzy control method with computational intelligence optimization for omni-Mecanum-wheeled autonomous vehicles. With the advantages of cuckoo search (CS), an evolutionary CS-based fuzzy system is proposed, called CS-fuzzy. The CS’s computational intelligence was employed to optimize the structure of fuzzy systems. The proposed CS-fuzzy computing scheme was then applied to design an optimal real-time control method for omni-Mecanum-wheeled autonomous vehicles with four wheels. Both vehicle model and CS-fuzzy optimization are considered to achieve intelligent tracking control of Mecanum mobile vehicles. The control parameters of the Mecanum fuzzy controller are online-adjusted to provide real-time capability. This methodology outperforms the traditional offline-tuned controllers without computational intelligences in terms of real-time control, performance, intelligent control and evolutionary optimization. The mechatronic design of the experimental CS-fuzzy based autonomous mobile vehicle was developed using FPGA realization. Some experimental results and comparative analysis are discussed to examine the effectiveness, performance, and merit of the proposed methods against other existing approaches.

We analyzed a data set containing functional brain images from 6 healthy controls and 196 individuals with Parkinson's disease (PD), who were divided into five stages according to illness severity. The goal was to predict patients' PD illness stages by using their functional brain images. We employed the following prediction approaches: multivariate statistical methods (linear discriminant analysis, support vector machine, decision tree, and multilayer perceptron [MLP]), ensemble learning models (random forest [RF] and adaptive boosting), and deep convolutional neural network (CNN). For statistical and ensemble models, various feature extraction approaches (principal component analysis [PCA], multilinear PCA, intensity summary statistics [IStat], and Laws' texture energy measure) were employed to extract features, the synthetic minority over‐sampling technique was used to address imbalanced data, and the optimal combination of hyperparameters was found using a grid search. For CNN modeling, we applied an image augmentation technique to increase and balance data sizes over different disease stages. We adopted transfer learning to incorporate pretrained VGG16 weights and architecture into the model fitting, and we also tested a state‐of‐the‐art machine learning model that could automatically generate an optimal neural architecture. We found that IStat consistently outperformed other feature extraction approaches. MLP and RF were the analytic approaches with the highest prediction accuracy rate for multivariate statistical and ensemble learning models, respectively. Overall, the deep CNN model with pretrained VGG16 weights and architecture outperformed other approaches; it captured critical features from imaging, effectively distinguished between normal controls and patients with PD, and achieved the highest classification accuracy.

PurposeCryptocurrency markets are gaining popularity, with over 23,000 cryptocurrencies in 2023 and a total market valuation of 870.81 billion USD in 2023. With its increasing popularity, cryptocurrencies are also susceptible to volatility. Predicting the price with the least fallacy or more accuracy has become the need of the hour as it significantly influences investment decisions.Design/methodology/approachThis study aims to create a dynamic forecasting model using the ensemble method and test the forecasting accuracy of top 15 cryptocurrencies’ prices. Statistical and econometric model prediction accuracy is examined after hyper tuning the parameters. Drawing inferences from the statistical model, an ensemble model using machine learning (ML) algorithms is developed using gradient-boosted regressor (GBR), random forest regressor (RFR), support vector regression (SVR) and multi-layer perceptron (MLP). Validation curves are utilized to optimize model parameters and boost prediction accuracy.FindingsIt is found that when the price movement exhibits autocorrelation, the autoregressive integrated moving average (ARIMA) model and the ensemble model performed better. ARIMA, simple linear regression (SLR), random forest (RF), decision tree (DT), gradient boosting (GB) and multi-model regression (MLR) ensemble models performed well with coins, showing that trends, seasonality and historical price patterns are prominent. Furthermore, the MLR approach produces more accurate predictions for coins with higher volatility and irregular price patterns.Research limitations/implicationsAlthough the dataset includes crisis period data, anomalies or outliers are yet to be explicitly excluded from the analysis. The models employed in this study still demonstrate high accuracy in predicting cryptocurrency prices despite these outliers, suggesting that the models are robust enough to handle unexpected fluctuations or extreme events in the market. However, the lack of specific analysis on the impact of outliers on model performance is a limitation of the study, as it needs to fully explore the resilience of the forecasting models under adverse market conditions.Practical implicationsThe present study contributes to the body of literature on ensemble methods in forecasting crypto price in general, potentially influencing future studies on price forecasting. The study motivates the researchers on empirical testing of our framework on various asset classes. As a result, on the prediction ability of ensemble model, the study will significantly influence the decision-making process of traders and investors. The research benefits the traders and investors to effectively develop a model to forecast cryptocurrency price. The findings highlight the potential of ensemble model in predicting high volatile cryptocurrencies and other financial assets. Investors can design the investment strategies and asset allocation decisions by understanding the relationship between market trends and consumer behavior. Investors can enhance portfolio performance and mitigate risk by incorporating these insights into their decision-making processes. Policymakers can use this information to design more effective regulations and policies promoting economic stability and consumer welfare. The study emphasizes the need for using diversified model to understand the market dynamics and improving trading strategies.Originality/valueThis research, to the best of our knowledge, is the first to use the above models to develop an ensemble model on the data for which the outliers have not been adjusted, and the model still outperformed the other statistical, econometric, ML and deep learning (DL) models.

Many regions in Iran are currently experience water crisis, largely driven by frequent droughts and expanding agricultural land combined with over abstraction of groundwater. Therefore, it is extremely important to identify potential groundwater recharge (GWR) zones to help in prevent water scarcity. The key objective of this research is to applying different scenarios for GWR potential mapping by means of a classifier ensemble approach, namely a combination of Maximum Entropy (ME) and Frequency Ratio (FR) models in a semi-arid mountainous, Marboreh Watershed of Iran. To consider the ensemble effect of these models, 15 input layers were generated and used in two models and then the models were combined in seven scenarios. According to marginal response curves (MRCs) and the Jackknife technique, quaternary formations (Qft1 and Qft2) of lithology, sandy-clay-loam (Sa. Cl. L) class of soil, 0–4% class of slope, and agriculture & rangeland classes of land use, offered the highest percolation potential. Results of the FR model showed that the highest weight belonged to Qft1 rocks and Sa. Cl. L textures. Seven scenarios were used for GWR potential maps by different ensembles based on basic mathematical operations. Correctly Classified Instances (CCI), and the AUC indices were applied to validate model predictions. The validation indices showed that scenarios 5 had the best performance. The combination of models by different ensemble scenarios enhances the efficiency of these models. This study serves as a basis for future investigations and provides useful information for prediction of sites with groundwater recharge potential through combination of state-of-the-art statistical and machine learning models. The proposed ensemble model reduced the machine learning and statistical models’ limitations gaps and promoted the accuracy of the model where combining, especially for data-scarce areas. The results of present study can be used for the GWR potential mapping, land use planning, and groundwater development plans.

Major companies like Google, Tesla, and Uber have invested heavily in autonomous technology, testing them in countries like the US, China, and Germany. Autonomous vehicle (AV) technology has advanced significantly, with deep learning algorithms, high-definition mapping systems, and vehicle-to-everything (V2X) communication. Sensor technology like lidar, radar, and cameras has also been developed for safe navigation. Recent advancements in intelligent control technology have improved performance and capabilities, with artificial intelligence (AI) and machine learning (ML) playing a crucial role in developing intelligent control systems. Researchers are developing algorithms for safe navigation, sensor fusion techniques, predictive modeling, and advanced planning algorithms to enhance navigation, lane changes, and intersection handling. Safety in AV control requires rigorous testing, cybersecurity, redundancy, and failsafe mechanisms. This review synthesizes a wide range of methodologies, such as statistical analysis, simulation-based approaches, deep learning models, reinforcement learning algorithms, and genetic algorithms, that have been used throughout many studies on Autonomous Vehicles (AVs). These techniques have greatly improved the performance of AVs, especially in terms of maximizing mixed traffic flow, strengthening sensor integration, and honing decision-making in challenging situations. Research findings show significant advancements; for instance, deep learning improves vehicle control and pedestrian recognition in difficult situations, while simulation-based models emphasize the benefits of autonomous vehicles on traffic efficiency. The optimization of AV routing and traffic management has been demonstrated by the successful combination of genetic algorithms and reinforcement learning. Despite these developments, a number of significant challenges still need to be overcome, including the requirement for flexible and scalable infrastructure as well as policy frameworks, sensor susceptibilities to inclement weather, and security and privacy concerns. The necessity for more reliable fixes for these vulnerabilities and the incorporation of AVs into the current transportation infrastructure are too prominent research needs. Numerous studies also stress how important it is to have sophisticated governance frameworks in place to handle the moral, legal, and security issues related to the use of AVs. The review identifies that AV research predominantly focuses on improving communication technologies, AI-enabled decision-making, and sensor integration. Future research directions should explore AV interactions with urban infrastructure, develop equitable policy adaptations, and implement advanced safety measures in the absence of connectivity. Overall, this review provides comprehensive insights into the current state, challenges, and future potential of AV technologies, guiding researchers and policymakers in addressing critical gaps to accelerate the global development and adoption of AV systems.

<p>Water is an essential elixir for several living organisms to function and survive. But it gets contaminated through several sources such as industrial wastes, oil spills, marine dumping, etc. With a growing population, availability of good quality water is of grave importance. This has become the motivation to probe into analysis of water quality from the outcomes of Statistical and Ensemble methods and to find the best working models from both methods. Research has been done to predict water quality analysis using standalone statistical and ensemble models. So, this research focuses on obtaining the best Statistical and Ensemble model separately among the models tried. The statistical models implemented for comparison are Principal Component Analysis (PCA), Hierarchical Clustering Analysis (HCA), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA). The Ensemble models used are Bagging, Boosting and Stacking. The models are then combined to build a Hybrid model to observe the comparisons between the three. The performance metrics used are Confusion Matrix, Accuracy, Precision, Recall, F1-score and ROC curve. While comparing the models, it is observed that Hybrid model produces the most accurate results, hence proving that the combination of Statistical and Ensemble model is efficient.</p>

Perceptions of vulnerable roadway users on autonomous vehicle regulations

PID controllers are very common in industrial systems applications. Tuning of parameters of the controllers is governed by system nonlinearities and continuous parameter variations. In this paper, a complete and rigorous comparison is made between two tuning algorithms. PI controller was used in a speed control loop through a field oriented Control (FOC) of an induction motor. AC machine was primarily controlled via classical PI, whereas an intelligent fuzzy PI controller provides a satisfactory outcome. The latter will be in use when a sudden change in the load torque is applied. The simulation result shows the performance of the proposed controller in terms of the speed and the parameter variations.

In order to systematically understand the operational forecast performance of current numerical, statistical, and ensemble models for O3 in Beijing–Tianjin–Hebei and surrounding regions, a comprehensive evaluation was conducted for the 30 model sets regarding O3 forecasts in June–July 2023. The evaluation parameters for O3 forecasts in the next 1–3 days were found to be more reasonable and practically meaningful than those for longer lead times. When the daily maximum 8 h average concentration of O3 was below 100 μg/m3 or above 200 μg/m3, a significant decrease in the percentage of accurate models was observed. As the number of polluted days in cities increased, the overall percentage of accurate models exhibited a decreasing trend. Statistical models demonstrated better overall performance in terms of metrics such as root mean square error, standard mean bias, and correlation coefficient compared to numerical and ensemble models. Numerical models exhibited significant performance variations, with the best-performing numerical model reaching a level comparable to that of statistical models. This finding suggests that the continuous tuning of operational numerical models has a more pronounced practical effect. Although the best statistical model had higher accuracy than numerical and ensemble models, it showed a significant overestimation when O3 concentrations were low and a significant underestimation when concentrations were high. In particular, the underestimation rate for heavy polluted days was significantly higher than that for numerical and ensemble models. This implies that statistical models may be more prone to missing high-concentration O3 pollution events.

The subject matter of the article is the forecasting of time series of sea ice extent using statistical and deep learning methods. Sea ice extent is one of the most important indicators of climate change. Today, there are trends towards melting glaciers, which leads to a rise in sea level and, in turn, creates a significant threat of flooding of coastal regions around the globe. In addition, melting glaciers affect the flora and fauna of the Arctic and Antarctic regions, as well as economic stability in the world, covering economic development and food security. The spheres of agriculture, tourism, logistics are directly dependent on climate change, therefore, forecasting future changes is critically important for stability and sustainable development. The article analyzes the main trends in the change in sea ice extent. The goal of the study is to increase the reliability of long-term forecasting by designing a framework that covers the full forecasting cycle from data analysis to the use of predictive statistical methods and deep learning techniques. The tasks of the article are to conduct a comparative analysis of statistical methods and deep learning methods and their evaluation for the task of forecasting the area of sea ice distribution. The study used forecasting methods based on statistical models and deep learning. A study was conducted on the use of different approaches to forecasting future changes in a time series based on statistical methods, deep learning methods and ensemble models. The results obtained allow to evaluate the performance of models in the short term and an approach to long-term forecasting was formed. The use of autoregressors and deep learning methods is proposed to create a reliable long-term forecast. The comparison of the performance of the methods was carried out for the Northern and Southern Hemispheres. Conclusions. The scientific novelty of the results obtained is as follows: the method of forecasting time series of sea ice distribution using statistical methods and deep learning methods has been further developed. It was propose a generalizable forecasting framework that links time-series characteristics to model class selection and ensemble construction. The use of ensemble approaches allows us to ensure both the consideration of the main trends and the recognition of hidden patterns. The results obtained allow for a comprehensive assessment of time series for the Northern and Southern Hemispheres and indicate the feasibility of using both statistical forecasting methods for data with clearly defined patterns, such as the Arctic region, and deep learning methods to recognize hidden patterns observed in time series data for the Antarctic region.

Validation and verification (V&V) is an integral part of system design that allows the designer to establish the correctness of a system as well as analyze its robustness in the presence of disturbances and failures. V&V is especially critical in the development of autonomous vehicles. The pursuer-evader problem is a particularly challenging topic in autonomous vehicle research because it includes several different problems such as path planning, target assignment, and collision avoidance. In this paper, we describe the foundation of a model-based V&V framework that enables validation and verification of certain aspects of the performance of autonomous pursuer vehicles. In particular, we concentrate on the verification and analysis of a collision-avoidance strategy employed to prevent collisions between pursuers. The work presented in this paper was conducted at the Lockheed Martin Advanced Technology Center and is part of the ongoing VVIACS project (validation and verification of intelligent and adaptive control systems) as presented in G. Tallant et al. (2004).

Ensemble engineering and statistical modeling for parameter calibration towards optimal design of microbial fuel cells

The objective of this work was to better understand pedestrians' understanding, trust, comfort, and acceptance of autonomous vehicle (AV) external human-machine interfaces (eHMIs). A link between mechanical engineering (i.e., automotive engineering) and civil engineering (i.e., multimodal transportation systems) is necessary to understand the effectiveness of varying AV-to-human communication strategies. Using a within-subject experiment design, 47 participants interacted with AVs possessing one of four eHMIs in a virtual reality (VR) environment. We administered a Likert scale survey to measure participants' perceptions of the eHMIs and used ordinal logistic regressions to analyze the results. We also accounted for participants' gender and stated interest in AVs, novel contributions to this field of research. The presence of an eHMI was found to improve participants' perceptions of AVs. Although females generally reported higher levels of understanding, trust, comfort, and acceptance, males' scores increased more significantly with the introduction of an eHMI. Text eHMIs outperformed nontextual interfaces, with participants noting the best perceptions with the text eHMI located on the AV's grille. Participants' understanding and identification of right-of-way (ROW) were most improved by the eHMIs while trust and comfort were most impacted by the participants' stated interest in AVs. Acceptance had little response to the eHMIs or stated AV interest and gender had little impact in the statistical models. This research supports the development of a standard, uniform AV-pedestrian communication strategy and strengthens the connection between humans and AVs.

Collaborative autonomous vehicles will appear in the near future and will transform deeply road transportation sys- tems, addressing in part many issues such as safety, traffic efficien- cy, etc. Validation and testing of complex scenarios involving sets of autonomous collaborative vehicles are becoming an important challenge. Each vehicle in the set is autonomous and acts asyn- chronously, receiving and processing huge amount of data in real time, coming from the environment and other vehicles. Simulation of such scenarios in real time require huge computing resources. This poster presents a simulation platform combining the real-time OPAL-RT Technologies for processing and parallel computing, and the Pro-SiVIC vehicular simulator from Civitec for realistic simula- tion of vehicles dynamic, road/environment, and sensors behaviors. The two platforms are complementary and their combining allow us to propose a real time simulator of collaborative autonomous sys- tems. The development of embedded sensors and communication technologies, during the last few decades, has affected signifi- cantly the automotive sector, helping to overcome traffic prob- lems and to achieve greater safety on roads and highways. Nowadays, on board active safety systems are essentially designed to avoid collisions rather than only reducing their impact on passengers as with passive systems. Furthermore, augmented night vision, automated park assistance and navi- gation systems are functionalities that are already imple- mented on high-end vehicles (1). Although current ADAS (Advanced Driver Assistance Systems) are built as isolated subsystems that are typically not sharing information within or between vehicles, future generations of ADAS will feature a much higher level of integration as well as extended commu- nication capabilities allowing to exchange information be- tween vehicles. This will lead to fully automated vehicles capable of sharing information and interacting with dynamic environment. Some research efforts are focusing on the coop- erative and optimized behavior of nodes, and Multi-Hop Net- works (2), some specific aspects are introduced in (3) as friends/enemies, dominance, etc. optimize the behavior of multi-hop network. On the other side, some basic scenarios on collaborative autonomous vehicles have been experimented with three collaborative autonomous vehicles at the Griffith University's Intelligent Control Systems Laboratory (ICSL) (4). In these experiments, simple scenarios were considered, such as overtaking, transversal intersection and lane platoon- ing. This poster presents a real-time simulator of collaborative autonomous vehicles on parallel computing tools. We propose a strategy to build a real time simulator architecture of colla- borative autonomous vehicles. This platform allows us to simulate the embedded information processing systems and the brain behind each individual autonomous vehicle, as well as the VANET exchange of information between each vehicle in collaborative scenarios. We provide a brief presen- tation of the Pro-SiVIC simulator and explain our choice due to its high capability to simulate the other essential compo- nents of multi-vehicular collaborative scenarios such as the various sensors, the road environment and the dynamic of each vehicle in real-time. In this work, we propose to interconnect RT-LAB and Pro-SiVIC platforms to complete the required architecture to simulate in real-time scenarios of collaborative autonomous vehicles. We give an example and present some results using a real time ACC (Adaptive Cruise Control) sce- nario with inter-vehicular communication capabilities. As the main embedded processing/control algorithms, we consider a PI controller.

The structure of hardware and software of AI control system of a mobile robot for service use are described. Hardware of the mobile robot described include an autonomous wheel vehicle and a five degree of freedom manipulator. The software of the AI control system is based on soft computing including fuzzy control rules, fuzzy neural network and genetic algorithms. The intelligent control of cooperative motion between the autonomous vehicle and manipulator realises flexible operations such as navigation of a mobile robot in presence of static and dynamic obstacles, processes of opening door in rooms and pushing buttons of an elevator. New hierarchical structure of the AI control system includes direct human-robot communication line based on natural language and cognitive graphics, and a generator of virtual reality for simulation of artificial life conditions for the mobile service robot. Simulation and experimental results of navigation and technical operations with the manipulator mobile service robot used in office building are described.