Soft Computing最新文献

Indoor positioning systems and Air Quality (AQ) monitoring play a crucial role in creating smart environments that promote human well-being and sustainable living.This research paper explores the integration of Software-Defined Networking (SDN) with a Pozyx-based indoor positioning system for advanced AQ monitoring. By addressing the current challenges in network management, scalability, and Quality of Service (QoS) provisioning for indoor AQ monitoring systems, we propose a novel SDN-based routing protocol. Our findings reveal significant enhancements in energy efficiency and Packet Error Rate (PER), showcasing the potential of merging Pozyx and SDN technologies for creating smarter and sustainable living environments. This study contributes to the domain of indoor positioning and AQ monitoring, marking a step forward towards the realization of intelligent environmental monitoring systems.

Encryption of a plaintext involves a secret key. The secret key of classical cryptosystems can be successfully determined by utilizing metaheuristic techniques. Monoalphabetic cryptosystem is one of the famous classical cryptosystems. In this paper, we determine the secret key of the monoalphabetic cryptosystem using a recently proposed metaheuristic technique, namely, red deer algorithm. The existing red deer algorithm framework has been tailored to solve the above considered problem. Performance of the developed red deer algorithm is compared with the following metaheuristic techniques: tabu search, genetic algorithm, and cuckoo search using three criteria, namely, effectiveness, efficiency, and accuracy. The results obtained show that the proposed red deer algorithm can compete with all the above three algorithms with respect to all the criteria. This signifies the importance of the proposed red deer algorithm is that it can be utilized to solve the similar problems effectively, efficiently, and with more accuracy.

The categorical concepts, tools, and techniques advanced not only the theory of automata and languages but also developed the theory of fuzzy automata and languages and played a significant role in many other branches of theoretical computer science. Unlike theory of classical/fuzzy automata with output and their languages, this paper aims to incorporate the concept of fuzziness and roughness together in the theory of automata with output and their languages, to introduce the concepts of crisp deterministic automata with fuzzy rough output, and fuzzy rough language and study their categorical aspects. We have shown that the crisp deterministic automata with fuzzy rough outputs and fuzzy rough languages, along with their morphisms, respectively, form categories CDAFRO and FRL. We have also shown the existence of a functor between the categories CDAFRO and FRL. The categorical concepts of product and coproduct of a subfamily of object-class, equalizer, and coequalizer of a pair of parallel morphisms in category CDAFRO are studied. Finally, for a given fuzzy rough language, a minimal crisp deterministic automaton having fuzzy rough output recognizing it is constructed using the fuzzy generalization of foremost Myhill–Nerode’s theory of automata and languages.

In this paper, the potential of the five latest artificial intelligence (AI) predictive techniques, namely multiple linear regression (MLR), multi-layer perceptron neural network (MLPNN), Bayesian regularized neural network (BRNN), generalized feed-forward neural networks (GFFNN), extreme gradient boosting (XGBoost), and their ensemble soft computing models were evaluated to predict of the maximum peak load (PL) and displacement (DP) values resulting from pull-out tests. For this, 34 samples of the fully cementitious grouted rock bolts were prepared and cast. After conducting pull-out tests and building a dataset, twenty-four tests were randomly considered as a training dataset, and the remaining measurements were chosen to test the models’ performance. The input parameters were water-to-grout ratio (%) and curing time (day), while peak loads and displacement values were the outputs. The results revealed that the ensemble XGBoost model was superior to the other models. It was because having higher values of R² (0.989, 0.979) and VAF (99.473, 98.658) and lower values of RMSE (0.0201, 0.0435) were achieved for testing the dataset of PL and DP’ values, respectively. Besides, sensitivity analysis proved that curing time was the most influential parameter in estimating values of peak loads and displacements. Also, the results confirmed that the ensemble XGBoost method was positioned to predict the axial-bearing capacity of the fully cementitious grouted rock bolting system with extreme performance and accuracy. Eventually, the results of the ensemble XGBoost modeling technique suggested that this novel model was more economical, less time-consuming, and less complicated than laboratory activities.

The Chinese postman problem (CPP) is a widely recognized combinatorial optimization problem with numerous real-world applications. Modeling such real-world applications often involves considering uncertain variables. Robust optimization is one of the prominent approaches for solving optimization problems when uncertainties are present in the parameters of the optimization problem. In this paper, we delve into the realm of the uncertain multi-objective Chinese postman problem, incorporating budget constraints while simultaneously optimizing profit maximization and time minimization, all within the framework of robust optimization methodology. We formulate the deterministic form of uncertain multi-objective CPP for three different types of uncertainty sets: ellipsoidal, polyhedral, and budgeted. To tackle these formulations, we employ four established multi-objective solution strategies: the global criteria approach, the fuzzy programming method, (epsilon )-constraint, and the Genetic algorithm. Subsequently, we conduct numerical experiments to verify the proposed models.

This paper addresses a real-world Integrated Operating Room Planning and Scheduling (IORPS) problem encountered by a local hospital in Naples, characterized by stringent emergency management constraints, requiring treatment initiation within a 20-minute time-window. We tackle this problem by an original Integer Linear Programming formulation, capable of dealing with different operating room management strategies (open, block and block-modified). Our work differs from conventional cost-focused models by adopting a patient-oriented objective function, aligning with public hospitals obligations. The proposed method has been validated using real-world data provided by the hospital. The performed experimentation demonstrates the efficiency of the approach, capable of determining the optimal solution within an acceptable computation time that aligns with hospital requirements. Moreover, it also highlights the relevance of using our optimization approach to reduce delays in emergency responsiveness. This confirms its practical usage as a substitute for the current manual procedure.

In this paper, a novel Snail Homing and Mating Search (SHMS) algorithm is proposed. It is inspired from the biological behaviour of the snails. Snails continuously travel to find food and a mate, leaving behind a trail of mucus that serves as a guide for their return. Snails tend to navigate by following the available trails on the ground and responding to cues from nearby shelter homes. The proposed SHMS algorithm is investigated by solving several unimodal and multimodal functions. The solutions are validated using standard statistical tests such as two-sided and pairwise signed rank Wilcoxon test and Friedman rank test. The solutions obtained from the SHMS algorithm exhibited superior robustness as well as search space exploration capabilities with less computational cost. The real-world application of the SHMS algorithm is successfully demonstrated in the engineering design domain by solving three cases of design and economic optimization Shell and Tube Heat Exchanger (STHE) problem. The objective function value and other statistical results obtained using SHMS algorithm are compared with other well-known metaheuristic algorithms. For Solving STHE Case 1 the SHMS algorithm achieved 0.5–35% minimization of the total cost. For Case 2, 0.6–29% minimization of the total cost has been attained. Furthermore, for Case 3, 0.3%, 0.4% and 52% minimization of total cost is achieved when compared with the ARGA & CI, GA, and original study, respectively. The analysis regarding the convergence of the SHMS algorithm is discussed in detail. The contributions in this paper have opened up several avenues for further applicability of the algorithm for solving complex real-world problems.

NeVer2 is an open-source, cross-platform tool aimed at designing, training, and verifying neural networks. It seamlessly integrates popular learning libraries with our verification backend, offering their functionalities via a graphical interface. Users can design the structure of a neural network by intuitively arranging blocks on a canvas. Subsequently, network training involves specifying dataset sources and hyperparameters through dialog boxes. After training, the verification process entails two steps: (i) incorporating input preconditions and output postconditions via dedicated blocks, and (ii) initiating verification with a simple “push-button” action. To our knowledge, there is currently no other publicly available tool that encompasses all these features. In this paper, we present a comprehensive description of NeVer2, illustrating its complete integration of design, training, and verification through examples. Additionally, we conduct experimental analyses on various verification benchmarks to illustrate the trade-off between completeness and computability using different algorithms. We also include a comparison with state-of-the-art tools such as (alpha ),(beta )-CROWN and NNV for reference.

Current methods for time series ordinal classification (TSOC) methods suffer from low efficiency because the measures used to evaluate the quality of the shapelet need to calculate Information Gain from the Euclidian distances between the shapelet and time series, which incurs tremendous computation for large datasets. This paper introduces a novel method of shapelet discovery for TSOC in which a new measure is adopted, which takes into account the coverage concentration and dominance of shapelet on SAX-represented time series datasets. Moreover, a trie-tree is constructed based on all candidate shapelets and aims to discover a diverse set of high-quality shapelets. The experimental results demonstrated the effectiveness and efficiency when compared to eight SOTA algorithms for time series classification/ordinal classification.

Cyber-Physical Systems (CPS) are complex systems that integrate information control devices with physical resources, which can be automatically and formalized verified by model checking according to the expected requirements in the formal specification. The counterexamples in model checking are witnesses to the violation of the specification properties of the system and can provide important diagnostic information for debugging, controlling, and synthesizing CPS. Designing a rational specification language for CPS and generating effective counterexamples allows security vulnerabilities to be detected and addressed early in the system development. However, CPS involve frequent interactions between cyber and physical systems and often operate in unreliable environments, which poses new challenges for comprehensive modeling and designing specification languages for CPSs with discrete, continuous, time, probabilistic, and concurrent behaviors. Moreover, finding the smallest counterexample of CPS with probabilistic behavior in the shortest possible time has been identified as a Non-Deterministic Polynomial-complete (NP-complete) problem. Although a number of heuristics have been devised to address this challenge, the accuracy and efficiency of the solved counterexamples need to be improved due to the difficulty in determining the heuristic functions. We first provide a comprehensive model for CPS by introducing the Hybrid Probabilistic Time Labeled Transition System (HPTLTS). Subsequently, we design a specification language HPTLTS Temporal Logic (HPTLTS-TL) that can describe the properties of CPS. In addition, we propose an optimization algorithm CACO-A, which combines the Ant Colony Optimization (ACO) algorithm and the A-algorithm to efficiently generate the counterexample of CPS, which is represented as the diagnostic subgraph. Finally, we discuss a typical CPS example to demonstrate the feasibility of our approach.