Proposed Inference Model Research Articles

A Real-Time Shipping Container Accident Inference System Monitoring the Alignment State of Shipping Containers in Edge Environments

Along with the recent development of artificial intelligence technology, convergence services that apply technology are undergoing active development in various industrial fields. In particular, artificial intelligence-based object recognition technologies are being widely applied to the development of intelligent analysis services based on image data and streaming video data. As such, in the port yard, these object recognition technologies are being used to develop port safety services in smart ports. Accidents are a frequent occurrence in port yards due to misaligned loading of ship containers. In order to prevent such accidents, various studies using artificial intelligence technology are underway. In this paper, we propose a real-time shipping container accident inference edge system that can analyze the ship container’s loading status from a safety point of view to prevent accidents in advance. The proposed system includes the collection of video data of the ship container, inferring the safety level of the alignment status of the ship container, and transmitting the inference results for the safety level. In this paper, the proposed inference model is implemented with YOLOv3, YOLOv4 and YOLOv7 networks and can be used in video monitoring to realize the accurate classification and positioning of three different safety levels (safe, caution, and danger) in real time. In the performance evaluation, the detection accuracy of the inference model implemented with the YOLOv4 network was greater than 0.95. Its performance was also significantly better than that of the inference model implemented with the YOLOv3 and YOLOv7 networks. Although it was slightly inferior to the YOLOv4 network in terms of the accuracy, the inference model implemented with the YOLOv3 network had a faster inference speed than the model implemented with the YOLOv4 and YOLOv7 networks. Because of the port safety scenario, in which the inference accuracy is more important than the inference speed, we applied the YOLOv4 algorithm to the inference model of the system.

An ensemble federated learning framework for privacy-by-design mobility behaviour inference in smart cities

Inferring the travel behaviour of users in their GPS trajectories, while protecting their privacy is a significant issue for smart and sustainable cities. To address this challenge, we use Federated Learning (FL), a privacy-preserving machine learning technique that aims at collaboratively training a robust global model by accessing users’ locally trained models, but not their data. Specifically, we design a novel eNsemble federATed leArning for mobiLity InfErence (NATALIE) framework. The ensemble method combines the outputs from different DNN models learned via FL and shows an accuracy that surpasses comparable models reported in the literature. Extensive benchmarking experiments on open-access MTL Trajét and GeoLife GPS datasets demonstrate that the proposed inference model can achieve comparable accuracy in the identification of mode of travel without compromising privacy. The evaluation of the proposed model against non-i.i.d. data at varying sample sizes and different worker numbers shows improved performance. Findings are expected to contribute to the advancement of the transportation sector in smart and sustainable cities.

MODEL ADAPTIV NEURO-FUZZY PENTRU SISTEMUL DE CONTROL AL PROCESULUI DE MACINARE A CLINKERULUI IN MORILE CU BILE DIN FABRICILE DE CIMENT

The main purpose of this study consisted in the realization of the development model of a decision support system for the cement grinding process in ball mills, including the acquisition, processing and analysis subsystems of data regarding the progress of the technological process, based on hardware technologies and intelligent software. To create the decision-making models, the graphic environment for the development of adaptive neuro-fuzzy systems from the Matlab program package was used. The paper presents a model based on the techniques proposed and developed with the application of fuzzy logic and artificial neural networks. The input/output variables, the linguistic qualifiers and the membership functions specific to each shredding batch were identified. The inference rules were defined. A standard defuzzification method was applied to defuzzify the results obtained from the inference process. At the same time, the results of the simulations of the proposed models in the Matlab environment were also presented. The testing and verification of the data obtained with the proposed inference model was carried out by comparison with the experimental data.

A Basic Study on Herding a Flock of Sheep through Deep Reinforcement Learning in a Continuous Space

Strömbom et al. elucidated an algorithm in which a sheepdog can skillfully control a flock of sheep to guide them to a destination. This is called the Herding Algorithm, and it models the behavior of a sheepdog in two ways: “driving”, which guides a flock of sheep to a destination, and “collecting”, which brings the sheep together into one flock. In this model, Go et al. showed that an agent (sheepdog) could herd a flock of sheep with an inference model generated by reinforcement learning (RL). However, in their previous study, RL learned only the movement behavior to the positions at which the agent performs “driving” and “collecting” in the discretized environmental state and behavioral space. In this study, we have assumed a continuous environmental state and behavioral space. We have confirmed that even if the agent's herding behavior is the learning target, the proposed inference model generated by deep RL can herd sheep.

Numerical Markov Logic Network: A Scalable Probabilistic Framework for Hybrid Knowledge Inference

In recent years, the Markov Logic Network (MLN) has emerged as a powerful tool for knowledge-based inference due to its ability to combine first-order logic inference and probabilistic reasoning. Unfortunately, current MLN solutions cannot efficiently support knowledge inference involving arithmetic expressions, which is required to model the interaction between logic relations and numerical values in many real applications. In this paper, we propose a probabilistic inference framework, called the Numerical Markov Logic Network (NMLN), to enable efficient inference of hybrid knowledge involving both logic and arithmetic expressions. We first introduce the hybrid knowledge rules, then define an inference model, and finally, present a technique based on convex optimization for efficient inference. Built on decomposable exp-loss function, the proposed inference model can process hybrid knowledge rules more effectively and efficiently than the existing MLN approaches. Finally, we empirically evaluate the performance of the proposed approach on real data. Our experiments show that compared to the state-of-the-art MLN solution, it can achieve better prediction accuracy while significantly reducing inference time.

A Data-Flow Oriented Deep Ensemble Learning Method for Real-Time Surface Defect Inspection

Real-time surface defect inspection plays an important role in the quality control of automated production. For the surface defect inspection, flowing data are a common data form in the automated pipeline production. Although flowing data provide rich information for surface defect inspection, there are still a lot of dynamic distribution challenges caused by the flowing data, such as the domain shift phenomenon and imbalanced training data. However, many existing industrial inspection solutions still use static strategies. To determine the dynamic distribution influence on the data flow domain, this article proposes a new deep ensemble learning method with domain fluctuation adaptation. Specifically, a new distribution discrepancy identifier based on estimation of the data set distribution and data characteristic is proposed. It utilizes advantages of both the deep convolutional neural network (CNN) and the shallow feature-based learning method to achieve higher robustness and fine-grained detection in streaming data scenes. In order to validate the proposed method, an inspection bench test system, as a part of a real industrial surface mount technology production line, is designed and fabricated. The proposed inference model is successfully applied to an embedded terminal with a hybrid and heterogeneous computing architecture. At last, the method is validated on the data collected from the manufacturer. The result suggests that the proposed method possesses a competitive mean average precision (mAP) rate with good adaptation and robustness in industrial streaming data scenes.

Critical Temperature Prediction for a Superconductor: A Variational Bayesian Neural Network Approach

Much research in recent years has focused on using empirical machine learning approaches to extract useful insights on the structure-property relationships of superconductor material. Notably, these approaches are bringing extreme benefits when superconductivity data often come from costly and arduously experimental work. However, this assessment cannot be based solely on an open black-box machine learning, which is not fully interpretable, because it can be counter-intuitive to understand why the model may give an appropriate response to a set of input data for superconductivity characteristic analyses, e.g., critical temperature. The purpose of this study is to describe and examine an alternative approach for predicting the superconducting transition temperature $T_c$ from SuperCon database obtained by Japan's National Institute for Materials Science. We address a generative machine-learning framework called Variational Bayesian Neural Network using superconductors chemical elements and formula to predict $T_c$ . In such a context, the importance of the paper in focus is twofold. First, to improve the interpretability, we adopt a variational inference to approximate the distribution in latent parameter space for the generative model. It statistically captures the mutual correlation of superconductor compounds and; then, gives the estimation for the $T_c$ . Second, a stochastic optimization algorithm, which embraces a statistical inference named Monte Carlo sampler, is utilized to optimally approximate the proposed inference model, ultimately determine and evaluate the predictive performance. As a result, in comparison with the standard evaluation metrics, the results are promising and also agree with the existing models prevalent in the field. The $R^2$ value obtained is very close to the best model (0.94), whereas a considerable improvement is seen in the RMSE value (3.83 K). Notably, the proposed model is known as the first of its kind for predicting a superconductor's $T_c$ .

Semigroup of fuzzy automata and its application for fast accurate fault diagnosis on machine and anti-fatigue control

In order to carry out machine fault diagnosis earlier and more accurately such as the automatic detection for the ship’s level scale, and the existing literatures didn’t discuss these until now. However, for solving the problem, this paper presents a semigroup of fuzzy automata and its properties, constructs a fuzzy inference system on the semigroup of fuzzy automata, and discusses its application on machine fault diagnosis and the anti-fatigue driving reminder device. At the same time, the comparison between this inference model and the existing diagnosis methods is discussed. The experimental results show that the diagnosis speed and the average precision of the proposed inference model are faster and higher than those of traditional methods, which their maximum diagnosis precision is 95.98%.

A Conflict Decision Model Based on Game Theory for Intelligent Vehicles at Urban Unsignalized Intersections

This article proposed a novel conflict decision model for intelligent vehicles based on game theory with analyzing the interaction behaviors between vehicles at urban unsignalized intersections. The proposed model can help intelligent vehicles cross intersections safely and more efficiently. Firstly, we developed an inference model for types of interactions among vehicles based on fuzzy logic. Then, the driving data was collected at urban unsignalized intersections by subgrade sensors and a retrofit intelligent vehicle and it was used in verifying the proposed inference model. After that, a conflict decision model considering safety, efficiency and comfort for intelligent vehicles based on game theory, was proposed to select the optimal driving strategies. Finally, a simulation and verification platform was built using Matlab/Simulink & Prescan. And the validity and effectiveness of the model were proved by simulation experiments. The results show the decision model can effectively help vehicles avoid conflicts and save their time spent in crossing intersections by 15 percent.

Exploring Discriminative Representations for Image Emotion Recognition With CNNs

Image emotion recognition aims to automatically categorize the emotion conveyed by an image. The potential of deep representation has been demonstrated in recent research on image emotion recognition. To better understand how CNNs work in emotion recognition, we investigate the deep features by visualizing them in this work. This study shows that the deep models mainly rely on the image content but miss the image style information such as color, texture, and shapes that are low-level visual features but are vital for evoking emotions. To form a more discriminative representation for emotion recognition, we propose a novel CNN model that learns and integrates the content information from the high layers of the deep network with the style information from the lower layers. The uncertainty of image emotion labels is also investigated in this paper. Rather than using the emotion labels for training directly, as in previous work, a new loss function is designed by including the emotion labeling quality to optimize the proposed inference model. Extensive experiments on benchmark datasets are conducted to demonstrate the superiority of the proposed representation.

A Self-Adaptive Fuzzy Inference Model Based on Least Squares SVM for Estimating Compressive Strength of Rubberized Concrete

This paper presents an AI approach named as self-Adaptive fuzzy least squares support vector machines inference model (SFLSIM) for predicting compressive strength of rubberized concrete. The SFLSIM consists of a fuzzification process for converting crisp input data into membership grades and an inference engine which is constructed based on least squares support vector machines (LS-SVM). Moreover, the proposed inference model integrates differential evolution (DE) to adaptively search for the most appropriate profiles of fuzzy membership functions (MFs) as well as the LS-SVM’s tuning parameters. In this study, 70 concrete mix samples are utilized to train and test the SFLSIM. According to experimental results, the SFLSIM can achieve a comparatively low MAPE which is less than 2%.

Non‐technical loss and power blackout detection under advanced metering infrastructure using a cooperative game based inference mechanism

To efficiently detect non-technical loss and power blackout in micro-distribution systems, this study proposes using a cooperative game (CG) based inference mechanism under the advanced metering infrastructure technique. Fractional-order Sprott system is designed to extract specific features between the profiled usages and the measurement usages in real time analysis. The fractional-order dynamic errors are positive correlated with the changes in load usages, including normal conditions, electricity fraudulent events, and power blackout events. Then, multiple agents in a game and multiple CG based inference mechanisms are used to locate abnormalities in micro-distribution systems. For energy management applications, the proposed inference mechanism can identify the 2.5–20% irregular usages during normal demand operations. In addition, it can also identify the large changes >20% in usages, while a micro-distribution system is disconnected to operate in the islanded mode within a few hours. This function can address an outage occurrence and then quickly resume service using the service restoration strategy and distributed generations in a local grid. Using a medium-scale micro-distribution system, computer simulations are conducted to show the effectiveness of the proposed inference model.

Fuzzy modelling for selecting headgear types.

The purpose of this study was to develop a computer-assisted inference model for selecting appropriate types of headgear appliance for orthodontic patients and to investigate its clinical versatility as a decision-making aid for inexperienced clinicians. Fuzzy rule bases were created for degrees of overjet, overbite, and mandibular plane angle variables, respectively, according to subjective criteria based on the clinical experience and knowledge of the authors. The rules were then transformed into membership functions and the geometric mean aggregation was performed to develop the inference model. The resultant fuzzy logic was then tested on 85 cases in which the patients had been diagnosed as requiring headgear appliances. Eight experienced orthodontists judged each of the cases, and decided if they 'agreed', 'accepted', or 'disagreed' with the recommendations of the computer system. Intra-examiner agreements were investigated using repeated judgements of a set of 30 orthodontic cases and the kappa statistic. All of the examiners exceeded a kappa score of 0.7, allowing them to participate in the test run of the validity of the proposed inference model. The examiners' agreement with the system's recommendations was evaluated statistically. The average satisfaction rate of the examiners was 95.6 per cent and, for 83 out of the 85 cases, 97.6 per cent. The majority of the examiners (i.e. six or more out of the eight) were satisfied with the recommendations of the system. Thus, the usefulness of the proposed inference logic was confirmed.

Network fault diagnosis using a realistic abductive reasoning model

This paper proposes a method to solve the network fault diagnosis problem using the Realistic Abductive Reasoning Model. This model uses an abductive inference mechanism based on the parsimonious covering theory, and adds some new features to the general model of diagnostic problem-solving. The network fault-diagnosis knowledge is assumed to be represented in the form of causal chaining, namely, a hyper-bipartite graph. A layered graph is constructed from the given hyper-bipartite graph by the addition of a few dummy nodes. Then the diagnostic problem is solved, starting from the lowest layer of the layered graph, as a series of bipartite graphs, until the top-most layer is reached. The inference mechanism uses a Realistic Abductive Reasoning Model to diagnose the faults in a communication network, which is symptom-driven, based on some application programs. The hypothesis-test paradigm is used to refine the solution space. The fault-diagnostic capability of the proposed inference model is demonstrated by considering one node of a given network where the management information would be used to diagnose its local problems and the connectivity of the node in the network. The results obtained by the proposed model substantiate its effectiveness in solving network fault-diagnostic problems.