Search Accuracy Research Articles

Advanced computational strategy for damage identification of offshore jacket platforms

AbstractIn this study, an efficient surrogate‐assisted grey wolf optimizer (GWO) is presented by combining Kriging‐based active learning to identify damages in jacketed platforms based on modal analysis. The use of active learning in parallel with GWO significantly reduced the number of calls to the objective function and increased the accuracy of the algorithm's search in the problem space. The proposed approach was first evaluated on four benchmark problems, and its performance was validated against original GWO, particle swarm optimization (PSO), and genetic algorithm (GA) techniques. Then, by generating artificial damage scenarios on a real jacket platform in ABAQUS software, it was evaluated for the identification of damaged members. The results indicated high accuracy in estimation and an appropriate convergence rate in solving the high‐dimensional and complicated problem of damage detection of jacketed platforms. In such a way that the error rate of damage severity estimation in scenarios 1 and 2 was, on average, 3% and 5%, respectively. Meanwhile, the damage position was correctly estimated, and the call rate of the function was reduced by 50%. The efficiency of the proposed approach shows that it can be used for further works on the reliability‐based design of jacket structures.

A Prediction Model for Methane Concentration in the Buertai Coal Mine Based on Improved Black Kite Algorithm–Informer–Bidirectional Long Short-Term Memory

Accurate prediction of methane concentration in mine roadways is crucial for ensuring miner safety and enhancing the economic benefits of mining enterprises in the field of coal mine safety. Taking the Buertai Coal Mine as an example, this study employs laser methane concentration monitoring sensors to conduct precise real-time measurements of methane concentration in coal mine roadways. A prediction model for methane concentration in coal mine roadways, based on an Improved Black Kite Algorithm (IBKA) coupled with Informer-BiLSTM, is proposed. Initially, the traditional Black Kite Algorithm (BKA) is enhanced by introducing Tent chaotic mapping, integrating dynamic convex lens imaging, and adopting a Fraunhofer diffraction search strategy. Experimental results demonstrate that the proposed improvements effectively enhance the algorithm’s performance, resulting in the IBKA exhibiting higher search accuracy, faster convergence speed, and robust practicality. Subsequently, seven hyperparameters in the Informer-BiLSTM prediction model are optimized to further refine the model’s predictive accuracy. Finally, the prediction results of the IBKA-Informer-BiLSTM model are compared with those of six reference models. The research findings indicate that the coupled model achieves Mean Absolute Errors (MAE) of 0.00067624 and 0.0005971 for the training and test sets, respectively, Root Mean Square Errors (RMSE) of 0.00088187 and 0.0008005, and Coefficient of Determination (R2) values of 0.9769 and 0.9589. These results are significantly superior to those of the other compared models. Furthermore, when applied to additional methane concentration datasets from the Buertai Coal Mine roadways, the model demonstrates R2 values exceeding 0.95 for both the training and test sets, validating its excellent generalization ability, predictive performance, and potential for practical applications.

A Line of Sight/Non Line of Sight Recognition Method Based on the Dynamic Multi-Level Optimization of Comprehensive Features.

With the advent of the 5G era, high-precision localization based on mobile communication networks has become a research hotspot, playing an important role in indoor emergency rescue in shopping malls, smart factory management and tracking, as well as precision marketing. However, in complex environments, non-line-of-sight (NLOS) propagation reduces the measurement accuracy of 5G signals, causing large deviations in position solving. In order to obtain high-precision position information, it is necessary to recognize the propagation state of the signal before distance measurement or angle measurement. In this paper, we propose a dynamic multi-level optimization of comprehensive features (DMOCF) network model for line-of-sight (LOS)/NLOS identification. The DMOCF model improves the expression ability of the deep model by adding a res2 module to the time delay neural network (TDNN), so that fine-grained feature information such as weak reflections or noise in the signal can be deeply understood by the model, enabling the network to realize layer-level feature processing by adding Squeeze and Excitation (SE) blocks with adaptive weight adjustment for each layer. A mamba module with position coding is added to each layer to capture the local patterns of wireless signals under complex propagation phenomena by extracting local features, enabling the model to understand the evolution of signals over time in a deeper way. In addition, this paper proposes an improved sand cat search algorithm for network parameter search, which improves search efficiency and search accuracy. Overall, this new network architecture combines the capabilities of local feature extraction, global feature preservation, and time series modeling, resulting in superior performance in the 5G channel impulse response (CIR) signal classification task, improving the accuracy of the model and accurately identifying the key characteristics of multipath signal propagation. Experimental results show that the NLOS/LOS recognition method proposed in this paper has higher accuracy than other deep learning methods.

Data-driven modeling of 600 MW supercritical unit under full operating conditions based on Transformer-XL.

Improving the flexible and deep peak shaving capability of supercritical (SC) unit under full operating conditions to adapt a larger-scale renewable energy integrated into the power grid is the main choice of novel power system. However, it is particularly challenging to establish an accurate SC unit model under large-scale variable loads and deep peak shaving. To this end, a data-driven modeling strategy combining Transformer-Extra Long (Transformer-XL) and quantum chaotic nutcracker optimization algorithm is proposed. Firstly, three models of the SC unit under once-through/recirculation/shut-down are built via analyzing its mechanism of the operation process, respectively. Secondly, the superior performance of Transformer-XL in obtaining global feature information is employed to effectively solve the problem of high information dependence caused by the strong coupling and nonlinearity of SC unit. Then, the improved quantum chaotic nutcracker optimization algorithm with higher search accuracy is proposed to obtain the optimal parameters of Transformer-XL based on the logistic chaotic mapping and quantum thinking. Feature information dependencies and optimal parameter settings are fully considered in the proposed modeling scheme, which results in an accurate model of SC unit under full operating conditions. Finally, various simulations and comparisons are conducted based on the on-site data of 600 MW SC unit to demonstrate the superiority of the proposed data-driven modeling strategy. According to the improved Transformer-XL, the mean square errors of the proposed SC unit model under once-through/recirculation/shut-down modes are less than 2.500E-03, which verifies the high accuracy of the model. Consequently, the developed model is suitable for application in the controller designing and the operating efficiency and flexibility improvement of SC unit.

Position-Aware Metric Normalization: A Hierarchical Framework for Context-Sensitive Evaluation of Search and Recommendation Systems

Position bias and creative format effects significantly impact the evaluation accuracy of modern search and recommendation systems, yet traditional metrics often fail to account for these complex interaction patterns. The article presents a comprehensive evaluation framework that implements sophisticated normalization techniques to address these challenges. The framework introduces a hierarchical correction model that accounts for vertical and horizontal position bias while simultaneously considering viewport visibility patterns and scrolls depth distribution. The system implements a creative-aware correction model that captures format-specific engagement baselines, cross-format interaction effects, and temporal attention patterns. By integrating fine-grained viewport tracking and precise interaction event collection, the framework enables more accurate performance assessment by normalizing metrics across multiple dimensions. Experimental results demonstrate that the approach significantly improves evaluation accuracy compared to traditional metrics, leading to more informed optimization decisions in search and recommendation systems. The framework's adaptive nature, powered by automated learning of interaction patterns and dynamic adjustment of normalization factors, makes it particularly suitable for contemporary applications where user behavior patterns continuously evolve.

Network Security Intrusion Detection Methods Combining Optimization Algorithms and Neural Networks

Cyber-attacks are becoming increasingly common and sophisticated, and the security of net-works is a pressing concern for companies everywhere. To spot and stop attempts to access network resources without authorization, intrusion. There is, however, a problem that many traditional IDS methods can generate a lot of false alarms. This means that it misidentifies safe activity as a threat and is not readily accepted by security teams for which real issues. Scalability and resistance to evolving threats a hybrid approach of a neural network combined with an adaptive algorithm was used in this paper focuses on improvement the performance and accuracy of the intrusion detection system proposed by us. Combining genetic algorithms and particle swarm optimization with neural networks using a framework optimized for comprehensive performance is present in this tutorial. More to the point, parameters and training procedures for Deep learning models in intrusion detection tasks. The objective of this research paper model is to make a false alarm the rate should be decreased, search accuracy increased and in real-time network environments, the system should adapt easily. Experimental results show that the combination of optimization algorithms and neural networks outperforms traditional IDS methods.

PALM: Personalized Attention-based Language Model for Long-tail Query Understanding in Enterprise Search Systems

Enterprise search systems face significant challenges in handling long-tail queries, which constitute a substantial portion of search traffic but often receive inadequate attention in traditional systems. This paper introduces PALM (Personalized Attention-based Language Model), a novel framework designed to enhance long-tail query understanding in enterprise search environments. PALM integrates personalization capabilities with an advanced attention mechanism to improve search accuracy for infrequent queries while maintaining high performance on common queries. The framework employs a unique hierarchical architecture that combines user context, query semantics, and organizational knowledge through a sophisticated attention mechanism. The system features an innovative query embedding approach that adapts to individual user contexts while leveraging collective organizational knowledge. Extensive experiments on a large-scale enterprise dataset, comprising over 5 million queries from 50,000 users, demonstrate PALM's superior performance compared to state-of-the-art baselines. The results show significant improvements across multiple metrics, with a 17.5% increase in MAP for ultra-rare queries and a 10.4% overall improvement in NDCG@10. The framework exhibits robust performance across different organizational units and query types, making it particularly valuable for enterprise environments where query patterns are highly diverse and context-dependent. Our ablation studies confirm the effectiveness of each component in the PALM architecture, while case analyses provide insights into the framework's practical applications.

Re-Clustering Documents to Enhance Search Accuracy with Imbalanced Abbreviation Data

Re-Clustering Documents to Enhance Search Accuracy with Imbalanced Abbreviation Data

Hybrid Multi-Strategy Improved Butterfly Optimization Algorithm

To address the issues of poor population diversity, low accuracy, and susceptibility to local optima in the Butterfly Optimization Algorithm (BOA), an Improved Butterfly Optimization Algorithm with multiple strategies (IBOA) is proposed. The algorithm employs SPM mapping and reverse learning methods to initialize the population, enhancing its diversity; utilizes Lévy flight and trigonometric search strategies to update individual positions during global and local search phases, respectively, expanding the search scope of the algorithm and preventing it from falling into local optima; and finally, it introduces a simulated annealing mechanism to accept worse solutions with a certain probability, enriching the diversity of solutions during the optimization process. Simulation experimental results comparing the IBOA with Particle Swarm Optimization, BOA, and three other improved BOA algorithms on ten benchmark functions demonstrate that the IBOA has improved convergence speed and search accuracy.

Novel Colors in Packaging: Boosting Consumers Learning Through Greater Expectation Violation

ABSTRACTCompanies often change product packaging colors to drive innovation and boost sales. However, these changes may violate expectations, resulting in inconsistent associations between new colors and original labels. It remains unclear whether consumers can learn these new associations. This study delved into the effect of expectation violation on consumer learning of color–label (flavor/brand) associations by varying the degree of violation between colors (adjacent and complementary) and labels. To assess associative strength, we compared learning effects under strong (color–flavor) and weak (color–brand) associations. Experiment 1 demonstrated higher accuracy in the visual search for packaging with complementary colors after learning. It was supported in Experiment 2. Between experiments, weaker associations showed greater improvement in response times (RTs). Our results suggest greater expectation violation in packaging color enhances associate learning. However, entrenched strong associations may impede the formation of new ones. These findings advance expectation violation theories and guide companies in using packaging color changes to innovate. Taking complements violating expectations can facilitate consumer learning.

Deep Semantics-Enhanced Neural Code Search

Code search uses natural language queries to retrieve code snippets from a vast database, identifying those that are semantically similar to the query. This enables developers to reuse code and enhance software development efficiency. Most existing code search algorithms focus on capturing semantic and structural features by learning from both text and code graph structures. However, these algorithms often struggle to capture deeper semantic and structural features within these sources, leading to lower accuracy in code search results. To address this issue, this paper proposes a novel semantics-enhanced neural code search algorithm called SENCS, which employs graph serialization and a two-stage attention mechanism. First, the code program dependency graph is transformed into a unique serialized encoding, and a bidirectional long short-term memory (LSTM) model is used to learn the structural information of the code in the graph sequence to generate code vectors rich in structural features. Second, a two-stage attention mechanism enhances the embedded vectors by assigning different weight information to various code features during the code feature fusion phase, capturing significant feature information from different code feature sequences, resulting in code vectors rich in semantic and structural information. To validate the performance of the proposed code search algorithm, extensive experiments were conducted on two widely used code search datasets, CodeSearchNet and JavaNet. The experimental results show that the proposed SENCS algorithm improves the average code search accuracy metrics by 8.30 % (MRR) and 17.85% (DCG) and compared to the best baseline code search model in the literature, with an average improvement of 14.86% in the SR@1 metric. Experiments with two open-source datasets demonstrate SENCS achieves a better search effect than state of-the-art models.

Fuzzy Logic-Driven Natural Language Processing in Pharma Supply Chain Analytics

Fuzzy logic offers a method for handling uncertainty and imprecision, proving valuable in natural language processing (NLP). Fuzzy search, a key component, enhances search functionality by permitting approximate matches. This study examines the application of fuzzy search techniques in wholesale pharmaceutical distribution, where data retrieval accuracy is crucial for public health and safety. We present two case studies, each showcasing specific fuzzy search methods designed to overcome unique data retrieval challenges. A Python implementation demonstrates the practical application of these techniques to enhance search accuracy and efficiency in large pharmaceutical datasets. Our results highlight fuzzy logic's potential to revolutionize information retrieval systems. By offering practical insights and technical guidance, this research aims to enable pharmaceutical industry stakeholders to effectively implement fuzzy search techniques, leading to improved data management and decision-making processes.

Application of Triple Glazing Thickness Optimization Based on Artificial Fish Swarm Algorithm

In response to the growing demand for energy-efficient building designs in cold northern regions, this study explores the optimization of triple glazing thickness to maximize the transmission of solar energy within the wavelength range of 300-2000 nm. The optimization employs the Artificial Fish Swarm Algorithm (AFSA), which is used to iteratively determine the optimal combination of glass thicknesses. A transmittance model of solar radiation through triple glazing is established, where the thicknesses of the three glass layers are treated as variables. The study shows that the optimized thickness combination significantly enhances the indoor heating effect by maximizing solar energy incidence, offering theoretical support and practical guidance for energy-saving building designs in cold climates. Parameter settings of the AFSA, including perception range, step size, and crowding factor, are analyzed to understand their influence on optimization performance. The results suggest that AFSA efficiently addresses complex optimization problems, demonstrating its potential in optimizing material properties for energy-efficient applications. Future directions include multi-objective optimization considering additional factors such as thermal insulation and cost, algorithmic improvements to enhance search accuracy, and experimental validation of the results in real-world conditions. This research provides a scientific foundation for integrating advanced optimization algorithms into the sustainable design of building materials.

Collision Avoidance for Unmanned Surface Vehicles in Multi-Ship Encounters Based on Analytic Hierarchy Process–Adaptive Differential Evolution Algorithm

Path planning and collision avoidance issues are key to the autonomous navigation of unmanned surface vehicles (USVs). This study proposes an adaptive differential evolution algorithm model integrated with the analytic hierarchy process (AHP-ADE). The traditional differential evolution algorithm is enhanced by introducing an elite archive strategy and adaptively adjusting the scale factor F and the crossover factor CR to balance global and local search capabilities, preventing premature convergence and improving the search accuracy. Additionally, the collision risk index (CRI) model is optimized and combined with the quaternion ship domain, enhancing the precision of CRI calculations and USV autonomous collision avoidance capabilities. The improved CRI model, the International Regulations for Preventing Collisions at Sea, and the optimal collision avoidance distance were incorporated as evaluation factors in a fitness function assessment, with weights determined through the AHP to enhance the rationality and accuracy of the fitness function. The proposed AHP-ADE algorithm was compared with the improved particle swarm algorithm, and the performance of the algorithm was comprehensively evaluated using safety, economy, and operational efficiency. Simulation experiments on the MATLAB platform demonstrated that the proposed AHP-ADE algorithm exhibited better performance in scenarios involving multiple ship encounters, thus proving its effectiveness.

Adoption of Artificial Intelligence in Public and Private Libraries of China: Determinants, Challenges, and Perceived Benefits

Artificial intelligence (AI) has much significance in different industries, including education. Due to increasing technological advancement, universities show their growing concerns about adopting several facilities linked with AI, specifically in their library management systems. Motivated by such an emerging trend, this research was conducted to examine AI adoption in both public and private libraries in China. The study explored the existing landscape of AI powered services in libraries, the perception of AI benefits, challenges related to AI adoption, and key determinants of such adoption for the targeted libraries. Using a questionnaire technique, the study collected data from different public and private libraries for which a sample of 154 respondents was finalized over the time span of 4.5 weeks. The analysis of the collected data shows that both the situations of launching and planning to launch different AI-related services were observed in Chinese libraries. Moreover, participants also confirmed several benefits of AI, including the enhancement of library operations by improving search accuracy, automating repetitive tasks, offering personalized resource recommendations, revealing usage trends through analytics, curating digital collections, improving cataloging, digitizing rare materials, and providing quick responses via chatbots, thereby allowing librarians to conduct their other more complex tasks. Additionally, the study confirmed several challenges associated with AI adoption. The results also revealed that along with other factors, the support from university administration, maturity and reliability of AI applications, and training and human resource management are positive and significant determinants of AI adoption. On the contrary, funding/cost associated with implementation and innovative services/alignment with technological trends reflected negative coefficients for AI adoption in Chinese libraries.

Gravity data inversion for parameters assessment over geologically faulted structures—A hybrid particle swarm optimization and gravitational search algorithm technique

AbstractInterpreting gravity anomalies caused by fault formations is associated with hydrocarbon systems, mineralized areas and hazardous zones and is the main goal of this research. To achieve an effective and robust model over the geologically faulted structures from gravity anomalies, we present a nature‐inspired hybrid algorithm, which synergizes the physics of the particle swarm optimization and gravitational search algorithm with variable inertia weights. The basic principle of developed particle swarm optimization and gravitational search algorithm method is to synergistically use the exploratory strengths of gravitational search algorithm with the exploitation capacity of particle swarm optimization in order to optimize and enhance the effectiveness by both algorithms. The technique has been tested on synthetic gravity data with varying settings of noises over geologically faulted structure before being applied to field data taken from Ahiri‐Cherla and Aswaraopet master fault present in Pranhita–Godavari valley, India. The optimization process is further refined through normalized Gaussian probability density functions, confidence intervals, histograms and correlation matrices to quantify uncertainty, stability, sensitivity and resolution. When dealing with field data, the true model is never known; in these circumstances, the quality of the outcome can only be inferred from the uncertainty in the mean model. The research utilizes a 68.27% confidence intervals to identify a location where the probability density function is more dominant. This region is then used to evaluate the mean model, which is expected to be more appropriate and closer to the genuine model. Correlation matrices further provide a clear demonstration of the strong connection between layer parameters. The results suggest that particle swarm optimization and gravitational search algorithm is less affected by model parameters and yields geologically more consistent outcomes with little uncertainty in the model, aligning well with the available results. The analysed results show that the method we came up with works well and is stable when it comes to solving the two‐dimensional gravity inverse problem. Future research may involve extending the approach to three‐dimensional inversion problems, with potential improvements in computational efficiency and search accuracy for global optimization methods.

Solving Paths Search Problems in Complex Graphs

The construction of models of various systems is associated with the enumeration of the values of the parameters of the elements of the structure and taking into account all the characteristics of operation and interaction of components to find a certain set of solutions that determine the configuration of the system. Such tasks belong to enumeration type tasks and imply that some of the next solutions from this set are obtained from the previous solution in a certain order. It is known that any problem of the enumeration type is solved only by methods of exhaustive search, and other methods for their enumeration do not exist yet. The paper presents a new method of searching paths in a graph – the method of node-graph transformation. The proposed method, unlike the existing ones, allows one to search all directed simple paths in an oriented graph of arbitrary structure much faster. In the known graph search methods (Breadth First Search and Depth First Search), the object of the search is a path. The total number of such paths in the graph determines the size of the search space. The main idea of the node-graph transformation method is to significantly reduce the size of the search space by enlarging the search objects. The enlargement of enumeration objects is performed by clustering paths into combinatorial objects that concentrate some set of paths of the same length according to certain rules. These combinatorial objects are called node-graphs. A node-graph refers to center-peripheral combinatorial objects, and specific node-graph transformation operations have been developed to enumerate all paths in the graph, which allow finding new paths based on previous paths. The method can be used as a basic toolkit to reduce the dimensionality of the search space for solutions to NP-complete problems while maintaining the universality and accuracy of the full search.

Identity-based authenticated multi-keyword searchable encryption scheme for cloud-assisted telemedicine information system

In cloud-assisted telemedicine information system (CA-TMIS), patients upload data containing their health metrics to the cloud. Doctors can access the patient’s data through the cloud, thereby alleviating the geographical restrictions in the traditional medical system. To ensure the privacy of the patient, the patient will encrypt the data before uploading the data. How doctors can search through numerous encrypted files to locate specific patients’ relevant data is a topic worthy of research. Searchable encryption technology can fulfill the function of ciphertext retrieval. Some existing searchable encryption schemes use single-keyword for searching, resulting in insufficient search accuracy and increased search costs for doctors. Multi-keyword searchable encryption schemes can address this issue. Therefore, in this paper, we propose an identity-based authenticated multi-keyword searchable encryption scheme, which leverages multiple keywords for combined searching, enhancing search accuracy. The scheme is proven to be resistant to keyword guessing attacks in the standard model. Compared to four other existing schemes, our scheme does not utilize pairing operations and offers higher efficiency advantages. Consequently, our scheme is more suitable for CA-TMIS.

Data Science in Promoting the Participation of SMEs in Public Biddings in Santa Catarina State, Brazil: The Case of BIEL

This paper addresses public bidding from the perspective of developing small and medium-sized enterprises (SMEs). It aims to present a prototype, BIEL, to make it easier for suppliers to locate notices to participate in, increasing their competitiveness and access to public bidding. The context of this research is SMEs’ participation in public biddings in Santa Catarina (SC) State, Brazil, in which suppliers use the SC Purchasing Portal to seek bidding notices. Diagnosing the problem situation requires simplifying the search for notices and allowing suppliers to find those notices that correspond to the items they work with efficiently. The intervention consists of developing an application using web scraping techniques with a dashboard that allows suppliers to search for specific items and obtain a list of corresponding notices. The paper contributes to applying these technologies in public bidding, facilitating SMEs' access to bidding processes. The developed prototype demonstrates promising results, although some limitations can be overcome to improve search accuracy. Making the application's source code available in a public repository on GitHub also contributes to transparency and collaboration in developing technological solutions in the public sector.

A novel hybrid information-based PF-WOA algorithm for gas source localization in 3D space

Abstract In recent years, dangerous gas leakage events occur frequently. Rapid and accurate location of gas leakage sources by mobile robots is the key to avoid the expansion of disasters. In order to solve the problem of discontinuous gas concentration gradient and sparse gas environment in three-dimensional space, particle filter, and whale swarm optimization algorithm are integrated to locate gas source. Firstly, the Z-shape search and comb search are used to locate the plume, and then, the particle filter algorithm is combined with the whale optimization method to guide the particle movement, and the random inertial disturbance term is designed to improve the convergence speed and search accuracy of the algorithm. Experimental results in three-dimensional environment show that the proposed information-driven particle filter whale optimization hybrid algorithm effectively guides the robot in localizing gas source within a certain range, significantly enhancing both the efficiency and accuracy of localization compared to other algorithms.