In recent years, image processing especially for remote sensing technology has developed rapidly. In the field of remote sensing, the efficiency of processing remote sensing images has been a research hotspot in this field. However, the remote sensing data has some problems when processing by a distributed framework, such as Spark, and the key problems to improve execution efficiency are data skew and data reused. Therefore, in this paper, a parallel acceleration strategy based on a typical deep learning algorithm, deep belief network (DBN), is proposed to improve the execution efficiency of the DBN algorithm in Spark. First, the re-partition algorithm based on the tag set is proposed to the relief data skew problem. Second, the cache replacement algorithm on the basis of characteristics is proposed to automatic cache the frequently used resilient distributed dataset (RDD). By caching RDD, the re-computation time of frequently reused RDD is reduced, which lead to the decrease of total computation time of the job. The numerical and analysis verify the effectiveness of the strategy.

With the emergence of big data era, most of the current performance optimization strategies are mainly used in a distributed computing framework with disks as the underlying storage. They may solve the problems in traditional disk-based distribution, but they are hard to transplant and are not well suitable for performance optimization especially for an in-memory computing framework on account of different underlying storage and computation architecture. In this paper, we first give the definition of the resource allocation model, parallelism degree model, and allocation fitness model on the basis of the theoretical analysis of Spark architecture. Second, based on the model presented, we propose a strategy embedded in the evaluation model which is easy to perform. The optimization strategy selects the worker with a lower load that satisfies requirements to assign the latter tasks, and the worker with a higher load may not be assigned tasks. The experiments consisting of four variance jobs are conducted to verify the effectiveness of the presented strategy.

The purpose of our research is to extend the formal representation of the human mind to the concept of the complex q-rung orthopair fuzzy hypersoft set (Cq-ROFHSS), a more general hybrid theory. A great deal of imprecision and ambiguity can be captured by it, which is common in human interpretations. It provides a multiparameterized mathematical tool for the order-based fuzzy modeling of contradictory two-dimensional data, which provides a more effective way of expressing time-period problems as well as two-dimensional information within a dataset. Thus, the proposed theory combines the parametric structure of complex q-rung orthopair fuzzy sets and hypersoft sets. Through the use of the parameter q, the framework captures information beyond the limited space of complex intuitionistic fuzzy hypersoft sets and complex Pythagorean fuzzy hypersoft sets. By establishing basic set-theoretic operations, we demonstrate some of the fundamental properties of the model. To expand the mathematical toolbox in this field, Einstein and other basic operations will be introduced to complex q-rung orthopair fuzzy hypersoft values. The relationship between it and existing methods demonstrates its exceptional flexibility. The Einstein aggregation operator, score function, and accuracy function are used to develop two multi-attribute decision-making algorithms, which prioritize based on the score function and accuracy function to ideal schemes under Cq-ROFHSS, which captures subtle differences in periodically inconsistent data sets. The feasibility of the approach will be demonstrated through a case study of selected distributed control systems. The rationality of these strategies has been confirmed by comparison with mainstream technologies. Additionally, we demonstrate that these results are compatible with explicit histograms and Spearman correlation analyses. The strengths of each approach are analyzed in a comparative manner. The proposed model is then examined and compared with other theories, demonstrating its strength, validity, and flexibility.

The cubic q-rung orthopair hesitant fuzzy set (Cq-ROHFS) provides greater information and is capable of representing both the interval-valued q-rung orthopair hesitant fuzzy set (IVq-ROHFS) and the q-rung orthopair hesitant fuzzy set (q-ROHFS). The concept of Cq-ROHFS is more flexible when considering the symmetry between two or more objects. In social life, complex decision information is often too uncertain and hesitant to allow precision. The cubic q-rung orthopair hesitant fuzzy sets are a useful tool for representing uncertain and hesitant fuzzy information in uncertain decision situations. Using the least common multiple (LCM) extension method, we propose a decision-making method based on an exponential similarity measure and hesitancy in the cubic q-rung orthopair hesitant fuzzy environment. To represent assessment information more accurately, our proposed method adjusts parameters according to the decision maker’s preferences in the decision-making process. The Cq-ROHFS setting was used to develop a depression rating method based on the similarity measure for depressed patients. Finally, the validity and applicability of the decision method is demonstrated using an example of depression rating assessment. As a result of this study, the scientific community can gain insight into real-world clinical diagnostic problems and treatment options.