With the promotion of cloud computing, a large number of hardware and software systems in the cloud bring massive and complex operation and maintenance (O&M) work. To ensure the O&M efficiency of IT infrastruc...
详细信息
In video games, the validation of design specifications throughout the development process poses a major challenge as the project grows in complexity and scale and purely manual testing becomes very costly. This artic...
详细信息
In video games, the validation of design specifications throughout the development process poses a major challenge as the project grows in complexity and scale and purely manual testing becomes very costly. This article proposes a new approach to design validation regression testing based on a reinforcement learning technique guided by tasks expressed in a formal logic specification language (truncated linear temporal logic) and the progress made in completing these tasks. This requires no prior knowledge of machine learning to train testing bots, is naturally interpretable and debuggable, and produces dense reward functions without the need for reward shaping. We investigate the validity of our strategy by comparing it to an imitation baseline in experiments organized around three use cases of typical scenarios in commercial video games on a 3-D stealth testing environment created in unity. For each scenario, we analyze the agents' reactivity to modifications in common assets to accommodate design needs in other sections of the game, and their ability to report unexpected gameplay variations. Our experiments demonstrate the practicality of our approach for training bots to conduct automated regression testing in complex video game settings.
Intelligent virtual model assistance is a key challenge in cultivating model-driven engineering proliferation and growth. Such assistance will help improve the quality of software models, support education for student...
详细信息
Intelligent virtual model assistance is a key challenge in cultivating model-driven engineering proliferation and growth. Such assistance will help improve the quality of software models, support education for students learning modeling, and lower the entry barriers to new modelers. We present SimIMA, an intelligent modeling assistant for Simulink, which is an extremely popular modeling language in both industry and academia. SimIMA provides modelers with two different forms of data-driven guidance using a knowledge base of configurable repositories and sources. The first form of guidance, SimGESTION, suggests to modelers single-step operations they can perform on their models as they edit them in their modeling environment. These suggestions are based on the machine learning technique of ensemble learning through association rule mining and frequency classification. The second form of guidance, SimXAMPLE, presents modelers with similar/related Simulink systems for modelers to either insert directly into their environments or to view for inspiration. SimXAMPLE accomplishes this through model clone detection. To validate SimIMA, we conduct experiments using an established, open, and curated large set of Simulink models coming from a variety of application domains. Our results show that both of SimIMA's forms of guidance are inferring the appropriate model and element suggestions given SimIMA's knowledge base and that SimIMA is both scalable and efficient. Through our evaluation, SimIMA demonstrates a prediction accuracy of 78.86% for block-level suggestions and 82.04% for full system suggestions.
Food allergy is a growing health issue worldwide and the demand for sensitive,robust and high-throughput analytical methods is *** recent years,mass spectrometry-based methods have been established for multiple food a...
详细信息
Food allergy is a growing health issue worldwide and the demand for sensitive,robust and high-throughput analytical methods is *** recent years,mass spectrometry-based methods have been established for multiple food allergen *** the present study,a novel method was developed for the simultaneous detection of almond,cashew,peanut,and walnut allergens in bakery foods using liquid chromatography–mass *** unique to these four ingredients were extracted,followed by trypsin digestion,quadrupole time-of-flight(Q-TOF)mass spectrometry and bioinformatics *** raw data were processed by de-novo sequencing module plus PEAKS DB(database search)module of the PEAKS software to screen peptides specific to each nut *** thermal stability and uniqueness of these candidate peptides were further verified using triple quadrupole mass spectrometry(QQQ-MS)in multiple reaction monitoring(MRM)*** nut species was represented by four peptides,all of which were validated for label-free quantification(LFQ).Calibration curves were constructed with good linearity and correlation coefficient(r 2)greater than *** limits of detection(LODs)were determined to range from 0.11 to 0.31 mg/kg,and were compared with the reference doses proposed by Voluntary Incidental Trace Allergen Labelling(VITAL).The recoveries of the developed method in incurred bakery food matrices ranged from 72.5%to 92.1%with relative standard deviations(RSD)of<5.2%.The detection of undeclared allergens in commercial bakery food samples confirmed the presence of these *** conclusion,this method provides insight into the qualitative and quantitative detection of trace levels of nut allergens in bakery foods.
AUTOSAR enhances the management of complex automotive electrical and electronic architectures by improving the reusability and interchangeability of software modules between OEMs and suppliers. However, existing AUTOS...
详细信息
ISBN:
(数字)9798331527471
ISBN:
(纸本)9798331527488
AUTOSAR enhances the management of complex automotive electrical and electronic architectures by improving the reusability and interchangeability of software modules between OEMs and suppliers. However, existing AUTOSAR modeling tools need help with non-intuitive representation and complicated architectural relationship modeling processes. In this paper, we propose a visual architecture modeling language to represent based on model-driven development of the system architecture design of vehicles. Our approach addresses these issues by implementing multi-dimensional visualization capabilities, incorporating two-dimensional graphical representations and detailed one-dimensional tabular displays. Furthermore, we introduce a practical'AUTOSAR meeting in the middle modeling method, which allows for separate modeling at different levels. This approach effectively harnesses the expertise of detailed bottom-level designers and high-level architects, improving efficiency in automotive system design. A detailed case study and evaluation substantiate the effectiveness of our modeling language in describing the system architecture.
Deep neural networks have made outstanding achievements in many static tasks, however, when faced with incremental scenario, they suffer from catastrophic forgetting since the previous data is usually inaccessible. St...
详细信息
Deep neural networks have made outstanding achievements in many static tasks, however, when faced with incremental scenario, they suffer from catastrophic forgetting since the previous data is usually inaccessible. Stored data and generative models are commonly used for maintaining model performance, but there exist problems of memory utilization and privacy safety. In this paper, a novel non-exemplar based incremental learning model, Prototype Representation Expansion (PRE), which provides a great degree to retain the feature space of old tasks, is proposed. Firstly, prototypes are generated to meet the stability and robustness. The mean value of feature embedding for each class is used as prototype to maintain the model stability. Meanwhile, PRE also selects prototypes according to their responses of classifier by feature disturbance noise injection, and the decision boundary can better be maintained. Secondly, prototypes of various classes are linearly combined to construct the hybrid prototype with mixed labels. Along with prototype augmentation, they are used for incremental training phase. We conduct extensive experiments on two benchmark datasets, CIFAR-100 and ImageNet-Subset. It shows that PRE can be combined with some non-exemplar based methods to significantly improve their ability and achieve comparable performance to exemplar based methods.
Change detection, an important task in remote sensing image analysis, has been extensively studied in recent years. However, change detection still faces problems such as difficulty in detecting small targets and inco...
详细信息
Change detection, an important task in remote sensing image analysis, has been extensively studied in recent years. However, change detection still faces problems such as difficulty in detecting small targets and incomplete edge detection. Furthermore, pseudo changes such as seasonal changes can also lead to many false detections. In response to these challenges, we propose the Multi-scale Features Mutual Enhancement Network (MFMENet), a simple yet efficient network. MFMENet maximizes feature utilization through mutual guidance and supplementation, enhancing the detection capabilities for small targets and edges. First, we use a lightweight feature extraction network to extract features, which mitigates the information loss caused by continuous downsampling of an overly deep network structure. Then, we design a Context Adaptive Interaction Module (CAIM) to realize the complementarity of feature information at different levels. This facilitates shallow features in gaining more semantic information and deep features in acquiring more texture information, thereby enhancing the model's capability to capture more comprehensive edge features while effectively mitigating interference from pseudo changes. Finally, we introduce a Feature Aggregation Comparison Module (FACM), which uses a combination of aggregation and comparison methods to refine and enhance features. FACM can not only highlight the changed features but also retain more details, improving the model's detection ability of small targets and edge details. The full utilization of features and effective mutual enhancement of information ensure the improvement of MFMENet's performance in small target and edge detection. Extensive experiments on three publicly available datasets (LEVIR, DSIFN, and CDD) demonstrate that our approach achieves superior performance with fewer parameters compared to state-of-the-art methods in recent years. In comparison to these baseline methods, our proposed approach achieves improvem
In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardly accomplish the team task without co...
详细信息
Open Information Extraction (Open IE) provides a method to extract triplets from text, which has become a research frontier and hot topic in recent years. However, the traditional open information extraction approache...
详细信息
software developers can only obtain a very small amount of information from the individual failure-causing inputs, which makes debugging difficult. Therefore, it is necessary to explore additional failure-causing inpu...
详细信息
software developers can only obtain a very small amount of information from the individual failure-causing inputs, which makes debugging difficult. Therefore, it is necessary to explore additional failure-causing inputs (failure regions) using the known failure-causing inputs. In order to accurately and efficiently identify the failure region, we propose a novel two-stage search algorithm, TS-FRI. In the initial exploration stage, a round-robin search identifies several boundary failure-causing points, and the failure region's centroid is estimated. During the main search stage, the boundary failure-causing points are identified through iterative division of the input domain with an equally sized partitioning strategy. This results in the boundary points being as dispersed as possible around the failure-region boundary, with the polytope formed by the points approximating the failure region (e.g., a polygon in two dimensions). The proposed algorithm is validated through simulation and empirical analysis: The experimental results show that the TS-FRI accuracy is at least comparable to the best accuracy of the compared three algorithms, and can be ten times better. In addition, TS-FRI only takes a quarter of the computation time and half the failure-validation cost of the other algorithms.
暂无评论