Equipment monitoring for failure prediction is receiving attention from different sectors of society, such as industry, healthcare, and defense. In the defense domain, assets like military vehicles generate data that ...
Equipment monitoring for failure prediction is receiving attention from different sectors of society, such as industry, healthcare, and defense. In the defense domain, assets like military vehicles generate data that one can use to identify behavior changes and anticipate possible real-time failures, avoiding unnecessary maintenance interventions. Failure anticipation is crucial, as assets operated in the military domain perform critical tasks in which unexpected equipment failures result in high material and human costs. Approaches found in the literature typically deal with failure generation, aiming at analyzing the equipment's behavior. This paper proposes a broader approach called MILPdM. This proposal is a failure prediction architecture covering the whole failure prediction and predictive maintenance procedures. We evaluate MILPdM architecture by analyzing an engine-failure scenario where we train models to predict time series by collecting vibration data that describes the degradation of the vehicle's health. Considering the implementation of an LSTM-based neural network and Random Forest, the acquired results lead to a root mean square error of 0.15015 in the best case, which allows to predict the failure status two minutes in advance with only 3 hours of data history. This result shows that MILPdM is capable of anticipating failures with high assertiveness.
Relevant smart city research involves many highly futuristic applications, such as smart transportation, in which smart roads warn drivers of impending traffic jams, smart parking, which communicates the location of a...
Relevant smart city research involves many highly futuristic applications, such as smart transportation, in which smart roads warn drivers of impending traffic jams, smart parking, which communicates the location of available parking spaces to drivers, and smart environments, which allow homes and workplaces to fully automatically adjust their temperature to save energy. Complexity in the city sensing section is caused by the complexity of urban systems. The enormous number of sensor types and technologies utilized for municipal data collecting provide a problem. Some of the issues in city sensing are node deployment, sensing management, sensor network types, and their derivative variables, necessitating the development of a city sensing architecture capable of contributing to advances in efficiency, accuracy, and real-timeness.
This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the 'performing Scalable Inference' technique to cope with scalability troubles and to expl...
详细信息
Robocup@Home proposes a challenge related to Person Recognition: after presented, a new ‘operator’ should become ‘immediately’ recognizable by the robot. The presentation procedure may require the operator to corr...
Robocup@Home proposes a challenge related to Person Recognition: after presented, a new ‘operator’ should become ‘immediately’ recognizable by the robot. The presentation procedure may require the operator to correctly interact with the robot, following a certain procedure, as instructed by the robot itself (for example, staying in front of the robot, so that the robot can take pictures of this person). In this paper, we propose the use of the KNN (K-Nearest Neighbor) supervised machine learning algorithm to include a new ‘operator’ in a database of persons recognizable by the robot. This algorithm uses information taken from an image segmentation of the face of the operator. The experiment evaluates how long it takes to include a new operator if the robot has from 1 to 12 current operators, evaluating also how long it takes to include this operator based on 1, 2 or more images of the new operator, taken from slightly different points of view. The results confirm that KNN can be used to ‘present to the robot’ up to 13 new operators, with up to 15 images for each operator, in less than 60 seconds.
This paper presents a new algorithm to approximate the nth root of a given real number z. The proposed algorithm is a hybrid algorithm between the Bisection method and the combination of the inverse of sine series and...
详细信息
This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed fra...
详细信息
ISBN:
(数字)9798350351408
ISBN:
(纸本)9798350351415
This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed framework relies on the implementation of a deep learning technique known as Dense Convolutional Networks (DenseNets) in the 6G-enabled IoMT to enhance prediction performance. To validate the performance of DenseNets, we compared it with other deep learning techniques, including Convolutional Neural Networks (CNN) and MobileNet, using real-world datasets. The experimental results show the high performance of DenseNets in predicting MS and ATM compared to other methods, achieving an accuracy of nearly 90 %.
This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique ...
详细信息
ISBN:
(数字)9798350351408
ISBN:
(纸本)9798350351415
This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively.
In recent years, several studies have reported the potential of employing digital games in EFL (English as Foreign Language) courses to promote students' learning motivation. However, scholars have pointed out tha...
详细信息
In recent years, several studies have reported the potential of employing digital games in EFL (English as Foreign Language) courses to promote students' learning motivation. However, scholars have pointed out that students generally lack self-learning ability, which is the key to the success of learning a foreign language. Therefore, it is crucial to foster students' self-learning ability during the game-based learning process. In this study, an expert system was developed to facilitate self-regulated learning in digital game-based learning contexts. To evaluate the effectiveness of the proposed approach, a quasi-experimental design was employed in a university English course. The experimental group students learned with the self-regulated English vocabulary game (SR-EVG) approach, while the control group students learned with the conventional English vocabulary game (C-EVG) approach. The experimental results indicated that the use of the SR-EVG approach could improve learners' English vocabulary achievement and self-regulation compared with the C-EVG approach without increasing students' English learning anxiety. Moreover, through qualitative interviews, it was found that students who used the SR-EVG approach would focus on their learning due to goal-setting in the game and would pay more attention to the learning strategies they used. Practitioner notes: What is already known about this topic Digital game-based learning situates students in a realistic situational environment, enabling students to learn by experiencing and interacting with the situations. Without appropriate scaffolding during digital game-based learning, students may become overly focused on the game, or perform many non-learning behaviors Self-regulated learning refers to students’ ability to learn on their own via goal setting, strategic planning, self-monitoring, and self-adjustment. What this paper adds An expert system-guided self-regulated learning approach was proposed to facilitate EFL s
The capacity to deceptively move in hilly terrains is fundamental to agents in simulation systems for tactical and strategic military training. Such an ability to deceive the adversary can ensure a relevant advantage ...
详细信息
ISBN:
(数字)9798331508296
ISBN:
(纸本)9798331508302
The capacity to deceptively move in hilly terrains is fundamental to agents in simulation systems for tactical and strategic military training. Such an ability to deceive the adversary can ensure a relevant advantage by hiding the real goals of a mission. Using pairs of real and deceptive mission goals, this paper investigates the planning of realistic deceptive routes for simulated agents. With real-world terrain elevation maps, it shows how to explore pathfinding algorithms with relevant path-smoothing characteristics (Theta* and WJPS*, contrasting with the standard $A^{*}$ algorithm) in terrains with pronounced relief features. The study analyzes the effects of terrain elevation costs and the representation of relief contour lines on the determination of more realistic deceptive paths. This work also investigates how users can adjust a Last Topographic Deceptive Point ($L D P_{T}$) calculation to enhance the pathfinding algorithm’s ability to produce more deceptively dense and topographically aware routes. Experimental results for different deceptive topographic path planning strategies are evaluated according to statistical models showing that Theta*, despite being slower than the base $A^{*}$ method in most cases, generated smoothed paths while maintaining a similar deception density for the proposed strategies. On the other hand, WJPS outperformed both in execution time for certain strategies while maintaining the smoothed path characteristic and resulting in a path with lower deceptive capacity.
暂无评论