Search

Design methodologies for approximation of medium to large-scale accelerators have largely relied on search-based design space exploration. Due to the enormously sized solution space, Artificial Intelligence (AI) based heuristic search has remained one of the most common techniques to explore cost and performance trade-offs. As a sub-class of AI techniques, Monte Carlo Tree Search (MCTS) has recently shown great potential as an intelligent stochastic search algorithm to solve computational problems with large branching factors. MCTS employs reinforced learning that combines past statistics and stochastic processes to traverse new paths in the search tree. Inspired by the success of MCTS in the games domain (AlphaGo), it has been recently applied to explore the solution space of approximate circuits. In this paper, a modified MCTS-based intelligent search technique is proposed that can handle huge search space for approximation of fairly large benchmark circuits. The proposed learning-based heuristic for MCTS directs the search towards deeper nodes in the search tree resulting in a rather asymmetric tree to efficiently utilize the search budget on the exploration of more promising nodes in the design space. The modified MCTS algorithm is based on reinforced learning where an agent uses past information to improve the overall gain. Experimental results confirm that the proposed heuristics can reach out to deeper nodes in the search tree which account for larger area savings in the context of approximate computing. The modified search algorithm enables 34.23% more area savings than the original search algorithm.

The effectiveness of managing an enterprise or institution to some extent depends on how intelligently the document flow is organized in it. After all, document flow and management activities are closely related to each other. The speed of obtaining the information necessary for making a management decision depends on how quickly the movement, processing of documents and their transfer to execution is carried out. In order to improve the efficiency of working with electronic documents due to their automated intellectual analysis, a comprehensive approach to the development of a subsystem for managing electronic documents in CASE-systems, which allow dynamic adjustment under changing operating conditions and user needs, is proposed. Agent and ontological approaches are used to analyze documents. Ontologies allow you to explicitly represent the semantics and structure of a document. The use of agents allows you to simplify the analysis process, make it extensible and scalable. The results of the intelligent search and processing of documents obtained from heterogeneous sources can be used not only for automatic classification and cataloging of documents in the information system in a user-friendly form, but also for reducing the complexity of the stage of analysis of the subject area of the information system, its design, as well as to intellectualize the processes of creating reporting documents based on information placed in the system database. The research provides an opportunity to create CASE technology, designed to create an information system that is dynamically adjusted and has unique adaptation capabilities to changing operating conditions based on "feedback" and intelligent document analysis. [ABSTRACT FROM AUTHOR]

The development of power grid dispatching and monitoring business brings forward new requirements for the digitization and intelligence of dispatching systems. In combination with the power grid regulation data and business characteristics, this paper studies the intelligent search framework for power grid dispatching and monitoring, as well as the key technologies such as power domain thesaurus modeling, power feature word segmentation algorithm, multi-factor correlation sorting algorithm, power knowledge map correlation modeling, etc. The grid intelligent search application for regulation cloud is developed to realize the search of grid equipment model, equipment operation, monitoring events, and services, which can comprehensively, accurately, quickly and intelligently retrieve the monitoring and operation data of massive dispatching equipment, and provide strong support for the business management and decision-making of dispatching equipment monitoring.

With the rapid development of the smart grid technology and the advent of the big data era of informatization, data labels have become a new evaluation standard to measure the informatization level of the industry, which also have a great impact on the construction direction of industry informatization, automation, and intelligent system in the later stage. With the promotion of new technology, the power grid dispatching industry is also carrying out a new generation of digital reform around data and business. This paper proposes a construction method of regulation ontology label system suitable for the search application of power grid regulation micro scene, which starts with the power grid regulation micro scene, divides and automatically reorganizes the business scene of the power grid. On this basis, by creating corresponding regulatory ontology labels and corresponding label dimensions, it innovatively proposes the construction method of label library suitable for regulatory ontology, and puts forward the construction process of regulatory ontology label system with sharing, security, service, and statistics as the core. Finally, the rationality and correctness of the construction method are verified by the application of regulation ontology label system in power grid micro scene intelligent search.

In this paper, we present a survey of modeling and simulation approaches to describe information retrieval basics. We investigate its methods, its challenges, its models, its components and its applications. Our contribution is twofold: on the one hand, reviewing the literature on discovery some search techniques that help to get pertinent results and reach an effective search, and on the other hand, discussing the different research perspectives for study and compare more techniques used in information retrieval. This paper will also shedding the light on some of the famous AI applications in the legal field. [ABSTRACT FROM AUTHOR]

Objectives: Geometric misalignment is one of the key problems for orthophoto mosaicking. To solve this problem, this paper proposes a regional seamline detection algorithm based on dense optical flow. Methods: Firstly, the cost image is constructed with dense optical flow, gradient information and gray information. And the cost image is regarded as a weighted undirected graph. Secondly, the principle of maximum flow and minimum cut is used to search for seamline based on graph‑cut model. Results: The experiment results show that the seamline cost of the sparse building area greater than 100 pixels obtained by the proposed method only accounts for 0.7% of the path length. And the search efficiency of the proposed method is increased by 17% compared with OrthoVista software. Conclusions: The proposed method can automatically avoid passing the building area and the areas with large projection in digital orthophoto map, greatly reduce the probability of geometric dislocation phenomenon of image mosaicking, and realize the intelligence of orthophoto seamline searching. [ABSTRACT FROM AUTHOR]

The efficiency and reliability of heterogeneous multi-processors can meet the requirements of increasingly complex signal processing tasks. Therefore, layered heterogeneous system has become the new research trend of signal processing platform. In order to improve the real-time performance of the platform and solve the problem of high throughput, the software and hardware modules and architecture of the hierarchical heterogeneous signal processing platform are studied, and a directed acyclic graph is used to model component tasks and hardware resources. The proposed scheduling algorithms are classified according to task types, scheduling objectives, scheduling processes and research methods, and the concept of combinatorial optimization algorithms is proposed according to the latest research progress of task scheduling. By comparing and analyzing the performance of classical heuristic algorithm, intelligent search algorithm, machine learning algorithm and combinatorial optimization algorithm, it is found that the combined optimization algorithm can meet the requirements of task scheduling of the platform. [ABSTRACT FROM AUTHOR]

Trajectory planning and obstacle avoidance play essential roles in the cooperative flight of multiple unmanned aerial vehicles (UAVs). In this paper, a unified framework for onboard distributed trajectory planning is proposed, which takes full advantage of intelligent discrete and continuous search algorithms. Firstly, the Monte Carlo tree search (MCTS) is used as the task allocation algorithm to solve the cooperative obstacle avoidance problem. Taking the task allocation decisions as the constraint, knowledge-based particle swarm optimization (Know-PSO) is used as the optimization algorithm to solve the onboard distributed cooperative trajectory planning problem. Simulation results demonstrate that the proposed intelligent MCTS-PSO search framework is effective and flexible for multiple UAVs to conduct the cooperative trajectory planning and obstacle avoidance. Further, it has been applied in practical experiments and achieved promising results.

With the progress of science and technology, artificial intelligence as the emerging tool has been deeply into our lives. The application of modern intelligent equipment is more and more extensive, and also inseparable from our lives. The mobile intelligent terminal represented by smart phone is a powerful intelligent computing and networking device, which has more perception and interaction capabilities. Due to the emergence of a large number of application software, it is not easy to find and get the app that you really need. Therefore, this paper uses speech recognition technology to build an app intelligent search and recommendation system. We designed the system from the levels of speech information extraction, analysis and finalized recommendation. Experimental results show that the proposed method is more efficient and intelligent. [ABSTRACT FROM AUTHOR]

The paper considers the hybrid intellectualization that is attained through a two-level metasystem dividing the area of production tasks into a large number of zones, in each of which special knowledge is concentrated. An intellectual problem has been solved, for which up to seven intelligent technologies are involved in parallel or in series that makes it possible to increase the multidimensionality and speed of decision-making. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes a Neurocomputing application that reorders the Web results obtained from different Web Search Engines emulating the way our brain takes decisions. The proposed application is based on the Random Neural Network with Deep Learning Clusters that evaluates and adapts Web result relevance by associating independently each Deep Learning Cluster to a specific Web Search Engine. In addition, this paper presents a Deep Learning Cluster to perform as a Management Cluster that decides the final result relevance based on the inputs from each independent Deep Learning cluster. The performance of the proposed Management Cluster is evaluated when included as an additional layer to the Deep Learning Clusters. On average; the proposed Deep Learning cluster structure improves Smart Search performance. [ABSTRACT FROM AUTHOR]

Online news media websites and mobile news applications can report hot events in real time. With the change of news duration, we urgently need a tool that can automatically extract hot events from massive data and show how events change dynamically with time. In this paper, the authors analyze the news transmission mode based on fuzzy data classification and neural network simulation. Due to the limitation of BP neural network algorithm, there are some problems in the prediction of information transmission. Therefore, we use fuzzy algorithm to optimize BP neural network, which is easy to fall into local minimum and slow convergence speed, so that BP neural network has higher prediction accuracy. The simulation results show that after the introduction of the neural network model, the features of neural network with richer semantic information can be used, and the new event line can be processed at the same time. The training speed of news content processing is much faster than that of probability graph model. It can be seen that under the influence of new media, news communication shows new characteristics, which further affects people's news reading habits. [ABSTRACT FROM AUTHOR]

Gyrator transform has been widely used for image encryption recently. For gyrator transform-based image encryption, the rotation angle used in the gyrator transform is one of the secret keys. In this paper, by analyzing the properties of the gyrator transform, an improved particle swarm optimization (PSO) algorithm was proposed to search the rotation angle in a single gyrator transform. Since the gyrator transform is continuous, it is time-consuming to exhaustedly search the rotation angle, even considering the data precision in a computer. Therefore, a computational intelligence-based search may be an alternative choice. Considering the properties of severe local convergence and obvious global fluctuations of the gyrator transform, an improved PSO algorithm was proposed to be suitable for such situations. The experimental results demonstrated that the proposed improved PSO algorithm can significantly improve the efficiency of searching the rotation angle in a single gyrator transform. Since gyrator transform is the foundation of image encryption in gyrator transform domains, the research on the method of searching the rotation angle in a single gyrator transform is useful for further study on the security of such image encryption algorithms.

At present, there are some problems in the course of software engineering and experiment teaching, such as the obsolete textbooks, the backward experimental equipment, the difficulty in introducing the latest software technology into the classroom, and the inconsistency between experimental courses and the needs of the enterprises. In this paper, we carry out experiment teaching exploration of software design method based on search algorithms. Through analysis and comparison of the various programming methods, it is found that the search-based programming method is the latest technology and software developing trend. Then , we explore and build the experimental teaching environment based on program of search algorithm, which is an innovative content of software engineering experiment teaching. Teaching practice shows that students welcome the reform. [ABSTRACT FROM AUTHOR]

Search Engine (SE) is the most preferred information retrieval tool ubiquitously used. In spite of vast scale involvement of users in SE’s, their limited capabilities to understand the user/searcher context and emotions places high cognitive, perceptual and learning load on the user to maintain the search momentum. In this regard, the present work discusses a Cognitive Agent (CA) based approach to support the user in Web-based search process. The work suggests a framework called Secured Cognitive Agent based Multi-strategic Intelligent Search System (CAbMsISS) to assist the user in search process. It helps to reduce the contextual and emotional mismatch between the SE’s and user. After implementation of the proposed framework, performance analysis shows that CAbMsISS framework improves Query Retrieval Time (QRT) and effectiveness for retrieving relevant results as compared to Present Search Engine (PSE). Supplementary to this, it also provides search suggestions when user accesses a resource previously tagged with negative emotions. Overall, the goal of the system is to enhance the search experience for keeping the user motivated. The framework provides suggestions through the search log that tracks the queries searched, resources accessed and emotions experienced during the search. The implemented framework also considers user security. [ABSTRACT FROM AUTHOR]

With the explosive growth of internet data and the increasing user demand, the traditional search methods has been difficult to meet user's needs in the mobile search field. In order to achieve the intelligent search based on semantic understanding, it is urgent to improve the level of search from word-based to semantic-based. Facing to the open internet data resources, an intelligent search pattern on “dynamic knowledge network + calculation operator”was proposed. Then, dynamic knowledge network was described in detail, which included theoretical basis, structure model, system model and features. Furthermore, it was presented about the basic structure of intelligent search based on dynamic knowledge network, which provided the support about theory and model for intelligent search. Finally, the main problems and challenges in the future were explained.

The modern power grid is becoming vulnerable to a variety of cyber-physical attacks, and an intelligent attacker could choose an appropriate combination of components and trip them simultaneously to cause significant damage to the power grid. For instance, significant cascading failures may be caused. Such potential consequences call for a comprehensive examination of potential n − k contingencies. A main problem related to the n − k analysis lies in the tremendous number of possible contingencies for a bulk power system. Thus, it is crucial to develop an efficient method to find the critical contingencies able to cause undesirable cascading failures. In this study, we develop a state space pruning based intelligent search method to identify these contingencies. First, the random chemistry method is deployed to sample a certain number of typical critical contingencies, which serve as a basis for the criticality analysis of components. Further, based on the criticality of components, the search space will be greatly reduced. Lastly, the particle swarm optimization algorithm is applied to search for the critical multiple contingencies. Case studies are conducted based on several IEEE bulk systems considering branch failures and bus failures, and the performance and efficiency of the proposed method is validated. The obtained collection of critical contingencies can provide useful information for making informed decisions to ensure secure power system operations. [ABSTRACT FROM AUTHOR]

Copyright of Revista Electrónica Redes de Ingeniería is the property of Universidad Distrital Francisco Jose de Caldas, Facultad de Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper addresses an application of Teaching-Learning-Based Optimization method for the optimal allocation of Distributed Generations (DGs) in radial distribution systems. The problem is formulated to maximize annual energy loss reduction while maintaining better node voltage profiles using penalty function approach. A piecewise linear multi-level load pattern is considered, and the distribution network is reconfigured after optimal placement of DGs in the distribution network. A probability-based heuristic intelligent search (IS) is suggested to enhance the accuracy and convergence of the optimization techniques. IS directs optimization techniques to efficiently scan the problem search space in such a way that a fair candidature is available to all decision variables of the problem. It virtually squeezes the search space while maintaining adequate diversity in population. The proposed method is investigated on the benchmark IEEE 33-bus, 69-bus test distribution systems, and 83-bus real distribution system. The application results show that the proposed optimization methodology provides substantial improvement in convergence characteristics and quality of solutions. [ABSTRACT FROM PUBLISHER]

The active and reactive power flow in distribution networks can be effectively controlled by optimally placing Shunt Capacitors (SCs) and Distributed Generators (DGs). This paper presents improved versions of three evolutionary or swarm-based search algorithms, namely, Improved Genetic Algorithm (IGA), Improved Particle Swarm Optimization (IPSO) and Improved Cat Swarm Optimization (ICSO) to efficiently handle the problem of simultaneous allocation of SCs and DGs in radial distribution networks while considering variable load scenario. The benefit of network reconfiguration has also been taken into account after optimal allocation of these devices. Several algorithm specific modifications are suggested in the standard forms of GA, PSO and CSO to overcome their inherent drawbacks. In addition, an intelligent search approach is proposed to enhance overall performance of proposed algorithms. The proposed methods are investigated on IEEE 33-bus and 69-bus test distribution systems showing promising results when compared with other recently established methods. Application results also show a marked improvement in the performance of these algorithms while compared with their respective standard counterparts. [ABSTRACT FROM AUTHOR]

Active and reactive power flow in distribution networks can be effectively controlled by optimally placing distributed resources like shunt capacitors and distributed generators. This paper presents improved variant of Teaching Learning Based Optimization (TLBO) to efficiently and effectively deal with the problem of simultaneous allocation of these distributed resources in radial distribution networks while considering multi-level load scenario. Several algorithm specific modifications are suggested in the standard form of TLBO to cope against the intrinsic flaws of this technique. In addition, an intelligent search approach is proposed to restrict the problem search space without loss of diversity. This enhances the overall performance of the proposed method. The proposed method is investigated on IEEE 33-bus, 69-bus and 83-bus test distribution systems showing promising results. [ABSTRACT FROM AUTHOR]

ABSTRACT This paper proposes a region sampling based autofocus method for rapid and robust autofocus in microscope. Image content and region size are considered in region sampling criteria. An intelligent search algorithm which employs quartering hill climbing search and golden section search is developed, in which rule-based evaluation of sampled focusing regions is applied. Experimental results demonstrate that the proposed method can significantly improve the performance of image-based autofocus. Microsc. Res. Tech. 78:382-390, 2015. © 2015 Wiley Periodicals, Inc. [ABSTRACT FROM AUTHOR]

This paper presents a multifunctional support system for evidence-based medical technology that permits medical publications and reference information to be searched for in external information resources, makes it possible to formulate questions in medically accepted formats and to perform a critical analysis of publications according to the principles of evidence-based medicine, enables clinical and statistical calculators to be used, and permits answers to clinical questions to be automatically formed and archived. The system has been tested at a multi-profile hospital and demonstrated efficiency in clinical decision-making support. [ABSTRACT FROM AUTHOR]

Social communities of smartphone users have recently gained significant interest due to their wide social penetration. The applications in this domain, however, currently rely on centralized or cloud-like architectures for data sharing and searching tasks, introducing both data-disclosure and performance concerns. In this paper, we present a distributed search architecture for intelligent search of objects in a mobile social community. Our framework, coined SmartOpt, is founded on an in-situ data storage model, where captured objects remain local on smartphones and searches then take place over an intelligent multi-objective lookup structure we compute dynamically. Our MO-QRT structure optimizes several conflicting objectives, using a multi-objective evolutionary algorithm that calculates a diverse set of high quality non-dominated solutions in a single run. Then a decision-making subsystem is utilized to tune the retrieval preferences of the query user. We assess our ideas both using trace-driven experiments with mobility and social patterns derived by Microsoft's GeoLife project, DBLP and Pics 'n' Trails but also using our real Android SmartP2P () system deployed over our SmartLab () testbed of 40+ smartphones. Our study reveals that SmartOpt yields high query recall rates of 95 %, with one order of magnitude less time and two orders of magnitude less energy than its competitors. [ABSTRACT FROM AUTHOR]

Search Engines are the key to finding specific information on the vast expanse of the World Wide Web (WWW). Most of the search engines search for key words to answers the queries from users. There are many of search engines available today, but retrieving meaningful information is difficult. However to overcome this problem in traditional search engines to retrieve meaningful information intelligently, semantic web technologies are phase a vital role. The proposed work is aimed at design of an efficient search engine named as An Efficient Semantic Web Search Engine (AESWSE). [ABSTRACT FROM AUTHOR]

Abstract: This work addresses natural language dialog planning for an intelligent web filtering model, which lets the user filter search results obtained by a traditional search engine and assists them to find what they really are looking for. Unlike state-of-the-art approaches, a stochastic planning model is proposed for a web-driven dialog system which uses Conditional Random Fields to predict next dialog moves. Experiments with real web users and different interaction settings show the promise of the approach to web-based adaptive planning aimed at information filtering. [Copyright &y& Elsevier]

Abstract: Today’s widespread web applications bring many challenges to decision support systems (DSS) research for effectively retrieving useful information from online data sources that are of huge volume. Importantly, in a web search and service environment, search results grouping becomes a crucial issue of DSS functionality and service, where the scale of data is dynamically expanding. This paper proposes an intelligent method that generates equivalence groups (classes) in an incremental manner, so as to deal with the evolving nature of the data in web search. Such equivalence groups are derived from λ-cuts of transitive closure of a closeness matrix for the search elements. The proposed incremental method does not need to redo the whole procedure of grouping each time when the overall search outcome changes, which is common in real applications, rather, it only captures the changes and related elements so that the calculation is minimized in both time and space complexity. Theoretical analysis and data experiments show the advantage and effectiveness of the proposed incremental method. [Copyright &y& Elsevier]

Optimization of process planning is considered as the key technology for computer-aided process planning which is a rather complex and difficult procedure. A good process plan of a part is built up based on two elements: (1) the optimized sequence of the operations of the part; and (2) the optimized selection of the machine, cutting tool and Tool Access Direction (TAD) for each operation. In the present work, the process planning is divided into preliminary planning, and secondary/detailed planning. In the preliminary stage, based on the analysis of order and clustering constraints as a compulsive constraint aggregation in operation sequencing and using an intelligent searching strategy, the feasible sequences are generated. Then, in the detailed planning stage, using the genetic algorithm which prunes the initial feasible sequences, the optimized operation sequence and the optimized selection of the machine, cutting tool and TAD for each operation based on optimization constraints as an additive constraint aggregation are obtained. The main contribution of this work is the optimization of sequence of the operations of the part, and optimization of machine selection, cutting tool and TAD for each operation using the intelligent search and genetic algorithm simultaneously. [ABSTRACT FROM AUTHOR]

Abstract: Intelligent retrieval for best satisfying users search intensions still remains a challenging problem due to the inherent complexity of real-world semantic web applications. Usually, a search request contains not only vagueness or imprecision, but also personalized information goals. This paper presents a novel approach which formulates one’s search request through tightly combining fuzziness together with the user’s subjective weighting importance over multiple search properties. A special ranking mechanism based on the weighed fuzzy query representation is proposed. The ranking method generates a set of “degree of relevance” – an overall score which reflects both fuzzy predicates and the user’s personalized preferences in the search request. Moreover, the ranking method is general and unique rather than arbitrary. Hence, search results shall be properly ordered in terms of their relevance with respect to best matching the search intension. The experimental results show that our approach can effectively capture users information goals and produce much better search results than existing approaches. [Copyright &y& Elsevier]

Adequacy assessment of power-generating systems provides a mechanism to ensure proper system operations in the face of various uncertainties including equipment failures. The integration of time-dependent sources such as wind turbine generators (WTGs) makes the reliability evaluation process more challenging. Due to the large number of system states involved in system operations, it is normally not feasible to enumerate all possible failure states to calculate the reliability indices. Monte Carlo simulation can be used for this purpose through iterative selection and evaluation of system states. However, due to its dependence on proportionate sampling, its efficiency in locating failure states may be low. The simulation may thus be time-consuming and take a long time to converge in some evaluation scenarios. In this paper, as an alternative option, four representative population-based intelligent search (PIS) procedures including genetic algorithm (GA), particle swarm optimization (PSO), artificial immune system (AIS), and ant colony system (ACS) are adopted to search the meaningful system states through their inherent convergence mechanisms. These most probable failure states contribute most significantly to the adequacy indices including loss of load expectation (LOLE), loss of load frequency (LOLF), and expected energy not supplied (EENS). The proposed solution methodology is also compared with the Monte Carlo simulation through conceptual analyses and numerical simulations. In this way, some qualitative and quantitative comparisons are conducted. A modified IEEE Reliability Test System (IEEE-RTS) is used in this investigation. [ABSTRACT FROM AUTHOR]