International Journal of Intelligent Systems最新文献

Vanilla Transformers focus on semantic relevance between mid- to high-level features and are not good at extracting smoke features, as they overlook subtle changes in low-level features like color, transparency, and texture, which are essential for smoke recognition. To address this, we propose the cross contrast patch embedding (CCPE) module based on the Swin Transformer. This module leverages multiscale spatial contrast information in both vertical and horizontal directions to enhance the network’s discrimination of underlying details. By combining cross contrast with the transformer, we exploit the advantages of the transformer in the global receptive field and context modeling while compensating for its inability to capture very low-level details, resulting in a more powerful backbone network tailored for smoke recognition tasks. In addition, we introduce the separable negative sampling mechanism (SNSM) to address supervision signal confusion during training and release the SKLFS-WildFire test dataset, the largest real-world wildfire test set to date, for systematic evaluation. Extensive testing and evaluation on the benchmark dataset FIgLib and the SKLFS-WildFire test dataset show significant performance improvements of the proposed method over baseline detection models.

Container-based cloud brokers are third-party services that act as an intermediate entity between users and multiple cloud providers. The cloud brokers intended to perform discovery and provisioning of cloud services with an affordable pricing scheme. As cloud services can be provisioned on-demand basis for multiple users, the cloud brokers are unable to provide the most suited services to the users on time. To address this issue, the proposed work introduces a novel approach for efficient cloud service provisioning by utilizing container-based cloud service brokerage and implementing service arbitrage across various cloud providers. A microservice architecture-based service discovery mechanism is developed which incorporates a service registry for tracking newly available services from the providers. Docker containers are employed to orchestrate the services, which ensures streamlined management and deployment of offered services. Further, the proposed system recommends and evaluates the services to the cloud users based on probability matrices, mapping matrices, and user feedback. The performance of the proposed model is compared with existing techniques, namely, rough multidimensional matrix (RMDM) and similarity-enhanced hybrid group recommendation approach (HGRA). Experimental results show that the proposed model outperforms the existing models in terms of clustering accuracy and execution time.

As an effective addition to the hesitant fuzzy set (HFS), a probabilistic dual hesitant fuzzy set (PDHFS) has been designed in this paper. PDHFS would be an improved version of the dual hesitant fuzzy set (DHFS) where both membership and nonmembership hesitant quality is considered for all its probability of existence. Additional information on the degree of acceptance or rejection contains such allocated probabilities. More conveniently, we create a comprehensive type of PDHFS called interval-valued PDHFS (IVPDHFS) to interpret the probability data that exist in the hesitancy. This study describes several basic operating laws by stressing the advantages and enriching the utility of IVPDHFS in MAGDM. To aggregate IVPDHF information in MAGDM problems and extend its applications, we present the Muirhead mean (MM) operator of IVPDHFSs and study some attractive properties of the suggested operator. Besides that, in order to compute attribute weights, a new organizational framework is designed by using partial knowledge of the decision makers (DMs). Subsequently, a standardized technique with the suggested operator for MAGDM is introduced, and the realistic usage of the operator is illustrated by the use of a problem of regenerative energy source selection. We discuss the influence of the parameter vector on the ranking results. Finally, to address the benefits and limitations of the recommended MAGDM approach, the findings of the proposal are contrasted with other approaches.

In the digital currency market, including Bitcoin, price prediction using artificial intelligence (AI) and machine learning (ML) is critical but challenging. Conventional methods such as technical analysis (based on historical market data) and fundamental analysis (based on economic variables) suffer from data noise, processing delays, and insufficient data. To make predictions more accurate, faster, and able to handle more data, the suggested method combines several steps: extracting important information, labeling it, choosing the best features, merging different models, and fine-tuning the model settings. Based on the price data, this approach initially generates 5 labels with a new labeling method based on the percentage of average price changes in several days and generates signals (hold, buy, sell, strong sell, and strong buy). Thereafter, it extracts 768 features from technical studies using the TA-Lib library and from an authoritative site. The TLBOA algorithm, which does not get stuck in the local optimum with two updates, was used to select and reduce features to 15 to avoid overfitting. A variety of ML models, including support vector machine and Naive Bayes, use these selected features for training. By using the evolutionary DE algorithm to optimize the XGBoost meta-parameters, we increased the accuracy by 1%–4%. The proposed strategy has performed better than other models, such as XGBoost with 85.66% and gradient boosting with 84.15%, and has achieved an accuracy of 91%–92%.