ABSTRACT Data augmentation is crucial for training deep learning models in breast cancer detection and segmentation, but conventional methods can cause annotation errors and visual artefacts, which harm instance‐level localisation, generalisation and clinical reliability. This study aims to develop an annotation‐aware, real‐time data augmentation framework that preserves spatial and clinical integrity during geometric transformations to improve model robustness and performance. A real‐time augmentation framework dynamically recalculates bounding box coordinates and segmentation masks during cropping and rotation. Instance‐level annotation correction is performed on‐the‐fly within the training pipeline, without offline preprocessing, additional storage, or generative modelling and is evaluated on the DDSM, INbreast and BUSI datasets. Experimental results show consistent performance gains across all datasets and models, with detection metrics improving by an average of 4.2–4.4% and segmentation accuracy increasing by up to 9.3%. The real‐time implementation achieves low preprocessing latency (≈0.12 s per batch, 3.75 ms per image), enabling high‐throughput training without added computational overhead. By preserving annotation integrity during geometric transformations, the proposed framework provides a computationally efficient and easily integrable solution for breast cancer imaging, with broader applicability to other medical image analysis tasks requiring precise spatial annotations.

The growth of telecommunication technologies, especially 5G, the growing popularity of smart mobile devices, the emergence of smart cities and Internet of Things (IoT), and the easy use of these equipments have led the cloud users to utilize their various services. Real-time applications and the use of big data have caused cloud service providers (CSPs) to move their servers to the edge of the network and in the vicinity of users to maintain the quality of their services. For this purpose, the concept of mobile-edge computing (MEC) was formed. Applications often have heavy computing complexity on mobile devices or require a lot of data to process. Moreover, in order to save energy consumption of the batteries of this equipment, offloading them on the network resources can transfer the computational complexity from the users’ equipment to the network resources. The resource placement (RP) is one of the major challenges in this area. Improper resource topology upsets their load balancing and increases access latency. In the proposed method of this article, the cellular mobile network is divided into smaller areas and using the coral reefs optimization (CRO) algorithm, the optimal placement of resources in each of these areas will be locally performed. The deep$Q$-network (DQN) and Markov game (MG) are used to optimize global RP to reduce global latency and to improve resource load balancing as its two objectives. The results of the experiments show that the proposed method has significantly improved its objectives and server’s energy efficiency, compared to some similar works in this area.

Abstract The service‐oriented software engineering approach has been increasingly utilized to design and develop complex distributed systems. Exploiting semantic web technologies to increase utilization of the web services at the semantic level leads to create semantic web services (SWSs). This paper proposes a model‐driven architecture (MDA) to model the SWS and to transform it from a high‐level modeling language, such as the Unified Modeling Language (UML), to a low‐level semantic description, such as the Web Service Modeling Language (WSML). To annotate all aspects of the SWS, a UML profile is provided by extending the UML metamodel. Some stereotypes and tagged values are also defined to support WSML. Therefore, the structure aspects of the SWS are modeled with a class diagram based on stereotypes that are defined in the UML profile. The logical and behavioral aspects of the SWS are modeled and expressed using activity diagrams, sequence diagrams, and Object Constraint Language (OCL). Experimental results show that the proposed approach not only increases the level of independence, accuracy, expressiveness, understandability, and machine processability but also significantly reduces the complexity and heterogeneity. Moreover, the proposed method is also evaluated in comparison with the previous methods of the literature, and the results will show that the proposed method outperforms the other methods in terms of expressiveness, understandability, scalability, level of independence, and accuracy.

The process of extracting data from different heterogeneous data sources, transforming them into an integrated, unified and cleaned repository, and storing the result as a single entity leads to the construction of a data warehouse (DW), which facilitates access to data for the users of information systems and decision support systems. Due to their enormous volumes of data, processing of analytical queries of decision support systems need to scan very large amounts of data, which has a negative effect on the systems’ response time. Because of the special importance of online analytical processing (OLAP) in these systems, to enhance the performance and improve the query response time of the system, an appropriate number of views of the DW are selected for materialization and will be utilized for responding to the analytical queries, instead of direct access to the base relations. Memory constraint and views maintenance overhead are two main limitations that make it impossible, in most cases, to materialize all views of the DW. Selecting a proper set of views of DW for materialization, called materialized view selection (MVS) problem, is an important research issue that has been focused in various papers. In this paper, we have proposed a method, called P-SA, to select an appropriate set of views using an improved version of simulated annealing (SA) algorithm that utilizes a proper neighborhood selection strategy. P-SA uses the multiple view processing plan (MVPP) structure for selecting the views. Data and queries of a benchmark DW have been used in experimental results for evaluating the introduced method. The experimental results show better performance of the P-SA compared to other SA-based MVS methods for increasing the number of queries, in terms of the total cost of view maintenance and query processing. Moreover, the total cost of queries in the P-SA is also better than the other important SA-based MVS methods of the literature when the size of the DW is increased.

Various problems are just rising with regard to mining in massive datasets, among which finding similar documents can be pinpointed. The Shingling method converts this problem to a set-based problem. Some of existing methods have used min-hashing to compress the results already driven from the shingling method and then have exploited LSH method to find candidate pairs for similarity search from all pairs of documents. In this paper, an apriori-based method is proposed for finding similar documents based on frequent itemset mining approach. To this end, the apriori algorithm is modified and is customized for similarity search problem. Modeling the similarity search problem as a frequent pattern mining problem, using a modified version of apriori, and dynamic selection the minimum support threshold are the most important advantages of the proposed method, which lead to its appropriate execution time and high quality results. The proposed method finds similar documents in less time than the combined method and MCVM method because it generates fewer candidate pairs for finding similar documents. Furthermore, experimental results show the high quality of the answers of the proposed methods.