Knowledge-based Search Research Articles

Operation optimization of ventilated floor heating system in nearly-zero-energy building

As the share of renewable energy sources increases and building energy systems become more complex, optimizing system operation is necessary to fully improve economic, environmental, renewable penetration and thermal comfort performance. Most current studies focus on single-objective or multi-objective optimization of building systems, but the impact of different objectives and their combinations on operation is unclear. In this study, optimal schedules for a ventilated heating floor in a nearly-zero-energy building were determined using an improved particle swarm optimization algorithm coupled with prior knowledge-based search accelerating strategy. System performance was investigated under different combinations of optimization objectives, including reducing operational costs and carbon emissions, increasing wind power penetration, and improving thermal comfort. The results show that under the influence of prior knowledge, stochastic algorithm converges quickly with reasonable results even when the solution space is large. The performance of some single-objective optimization cases is unsatisfactory due to the exclusion of some control variables. In contrast, multi-objective optimization yields optimization problems better, which finds better dynamic operation status and leads to better system performance. Specifically, co-optimization of operational cost, wind power penetration and environmental cost together produces the most reasonable solution.

USING FORWARD CHAINING METHODS TO DIAGNOSE CHOLESTEROL DISEASE USING THE WEB

Cholesterol disease can attack humans, both young and adult, in this case it is necessary to do a quick diagnosis to provide basic knowledge about cholesterol disease to sufferers. Advances in expert systems can overcome this problem, namely by designing a web-based computer system that is integrated with databases and programming languages ​​such as PHP-MySQL so that it can help cholesterol patients to diagnose the disease. The expert system application in its decision making uses a forward chaining inference engine where the goal driven data will start a search on the initial node to the goal node until it gets results. The results of the implementation of the system, namely the system provides questions in the form of symptoms that must be answered by the patient based on the symptoms experienced by the patient and the results of the process the system will provide information on what type of cholesterol disease he is experiencing in order to get a solution with treatment and handling. System that works with a knowledge base search that is able to provide decisions by utilizing an expert knowledge base.

Rapid Evolution of a Fragment-like Molecule to Pan-Metallo-Beta-Lactamase Inhibitors: Initial Leads toward Clinical Candidates.

With the emergence and rapid spreading of NDM-1 and existence of clinically relevant VIM-1 and IMP-1, discovery of pan inhibitors targeting metallo-beta-lactamases (MBLs) became critical in our battle against bacterial infection. Concurrent with our fragment and high-throughput screenings, we performed a knowledge-based search of known metallo-beta-lactamase inhibitors (MBLIs) to identify starting points for early engagement of medicinal chemistry. A class of compounds exemplified by 11, discovered earlier as B. fragilis metallo-beta-lactamase inhibitors, was selected for in silico virtual screening. From these efforts, compound 12 was identified with activity against NDM-1 only. Initial exploration on metal binding design followed by structure-guided optimization led to the discovery of a series of compounds represented by 23 with a pan MBL inhibition profile. In in vivo studies, compound 23 in combination with imipenem (IPM) robustly lowered the bacterial burden in a murine infection model and became the lead for the invention of MBLI clinical candidates.

A novel adaptive optimization framework for SVM hyper-parameters tuning in non-stationary environment: A case study on intrusion detection system

Building an Intrusion Detection System (IDS) in non-stationary environment is challenging because, in such an environment, intrusion-related data grow every day. A machine learning model trained in a stationary environment where training data does not change, often fails to retain its performance in real world environment. This is because dynamism in data makes the hyper-parametric values of the underlying classifier shift in the search space. For making such a model work for intrusion detection in non-stationary environment, one must have to run hyper-parametric optimization algorithm again and again at various time instances. But the expansion of the existing data in non-stationary environment, makes such a way of tunning the hyper-parameters computationally expensive. So, there is a requirement of more adaptive and computationally efficient optimization frameworks for hyper-parameters to build IDS in non-stationary environment. This paperwork proposes a novel framework to train a Support Vector Machine (SVM) for intrusion detection by optimizing its hyper-parameters C and γ dynamically. For designing this framework, we have used Moth-Flame Optimization (MFO) as the base optimization algorithm which can be run with random initialization. Further, for utilizing the knowledge generated by running the base optimization algorithm, we have introduced two algorithms- a Lightweight MFO and a simple Knowledge-Based Search. The Lightweight MFO uses the knowledge for initializing the starting solutions and the Knowledge-Based Search uses the knowledge as search space. Based on the result of a drift detection module, the proposed framework identifies the most appropriate algorithm to be used at a particular time instance when re-training of the model is required due to the change in the data. Results have shown a significant reduction in the average time complexity of the hyper-parametric optimization process. We have evaluated our proposed framework on benchmark NSL-KDD dataset and got significantly encouraging convergence rate and detection performance. The obtained average accuracy for IDS built using our proposed framework is 97.5%. Further, we have also compared our framework by considering other metaheuristic algorithms as base optimization algorithms and found that our proposed framework, which uses MFO as a base optimization algorithm outperforms the others.

Adoption Factors of Artificial intelligence in Human Resources Management

The phenomenon of artificial intelligence has been widely studied in several areas. In opposite, in terms of AI in HRM, the literature shows limited research on the adoption factors of artificial intelligence (AI) in HRM. AI has been enrolled in several HRM’s areas starting from staffing till management performance or compensation. A set of suggestions on how to adopt AI in HRM has been raised. This piece of research aims to identify the adoption factors of six scenarios of AI in HRM. These scenarios are turnover prediction with artificial neural networks, candidate search with knowledge-based search engines, staff rostering with genetic algorithms, HR sentiment analysis with text mining, résumé data acquisition with information extraction and employee self-service with interactive voice response. As a result, compatibility, relative advantage, complexity, managerial support, government involvement, and vendor partnership are determinants affected factors of AI adoption in HRM. This paper tries to address new insights for practitioners and academics by minimizing the risks associated with AI adoption in some areas of HRM through exploring determinant factors of adoption.

Structured encryption for knowledge graphs

We investigate the problem of structured encryption (STE) for knowledge graphs (KGs) where the knowledge of data can be efficiently and privately queried. Presently, the application of natural language processing (NLP) for knowledge-based search is gradually emerging. Compared with the traditional search based only on keywords of documents—symmetric searchable encryption (SSE), the knowledge-based search system transforms the latent knowledge contained in documents into a semantic network as a knowledge base, which greatly improves the accuracy and relevance of search results. In order to develop a knowledge-based search, the contents of documents are analyzed and extracted using KG techniques (e.g. multi-relational graph (MG) and property graph (PG)), and then all encrypted nodes and edges in a KG constitute the entire index table and database. This paper proposes the first STE for KGs with CQA2-security to search on protected knowledge, where KGs include MGs and PGs. In general, the latter is more complex than the former, but it can represent more abundant knowledge. Experimental results show that the index construction time of our schemes is about 1.9s and the query time is about 190 ms. Our sensitivity analysis shows that the performance of our proposed schemes is greatly influenced by the number of edges and nodes, but less by the number of properties.

Patient and Graph Embeddings for Predictive Diagnosis of Drug Iatrogenesis.

In the context of the IA.TROMED project we intend to develop and evaluate original algorithmic methods that will rely on semantic enrichment of embeddings by combining new deep learning algorithms, such as models founded on transformers, and symbolic artificial intelligence. The documents' embeddings, the graphs' embeddings of biomedical concepts, and patients' embeddings, all of them semantically enriched with aligned formal ontologies and semantic networks, will constitute a layer that will play the role of a queryable and searchable knowledge base that will supply the IA.TROMED's clinical, predictive, and iatrogenic diagnosis support module.

A dynamic framework for tuning SVM hyper parameters based on Moth-Flame Optimization and knowledge-based-search

In the real world, most of the collections of data are dynamic in nature, i.e. their size may grow with time. This dynamic nature of the data not only reduces the performance of the classifiers but also demands more optimized models for retaining the performance. Due to this, machine learning models developed in a static environment cannot be deployed efficiently to solve the real-world problems. Nowadays, maximum existing works consider only the static behaviour of the data for the training of machine learning models where the size of the collection of training data does not change over time. This paperwork imposes Support Vector Machine (SVM) in a dynamic environment. It has been identified that shifting of the optimum values of two hyper-parameters C (Penalty Parameter) and γ (Kernel Parameter) in the search space is one of the primary reasons for the performance degradation of SVM in dynamic environment. This paper proposes a novel framework that uses a new optimization module Knowledge-Based-Search (KBS) along with Moth –Flame Optimization (MFO) to optimize C and γ in a dynamic environment to train SVM efficiently. KBS uses knowledge gathered at various instances of time, which are the bi-products of MFO. MFO in our framework is the base optimization algorithm which works underneath KBS. The experiments have shown that KBS helps in controlling the exponential growth of the time complexity of the optimization process where only MFO is used to optimize C andγ. Integration of KBS with MFO brings down the time complexity to a large extent. To validate the proposed framework we have used a simulated dynamic environment for profit/loss classification problem for organizations. The experiments have also shown that KBS's integration with MFO outperforms integration of KBS with other modern optimization techniques such as Particle Swarm Optimization (PSO), Multi-Verse Optimization (MVO), Grey-Wolf Optimization (GWO), Cuckoo Search (CS), Whale Optimization Algorithm (WOA), Genetic Algorithm (GA), Fire-Fly Algorithm (FFA) and Salp Swarm Algorithm (SSA).

An optimal algorithm for the robotic assembly system design problem: An industrial case study

The design process of flow-oriented assembly systems is characterized by being both highly complex and time consuming. Especially those design processes categorized into robotic and multi variant encountered in the automotive body-in-white production stages. Unlike established manual and template-based assembly system design models, which are currently applied in industry, the here presented novel approach uses a knowledge-based search algorithm and automatically generates optimal assembly system configurations. The algorithm has been implemented in a software prototype and the results have been validated against different large-size industrial scenarios in the automotive field of body-in-white production.

A Knowledge-Based Cooperative Algorithm for Energy-Efficient Scheduling of Distributed Flow-Shop

Facing increasingly serious ecological problems, sustainable development and green manufacturing have attracted much attention. Meanwhile, with the development of globalization, distributed manufacturing is becoming widespread. This paper addresses an energy-efficient scheduling of the distributed permutation flow-shop (EEDPFSP) with the criteria of minimizing both makespan and total energy consumption. Considering the distributed and multiobjective optimization complexity, a knowledge-based cooperative algorithm (KCA) is proposed to solve the EEDPFSP. First, a cooperative initialization scheme is presented with both extended energy-efficient Nawaz–Enscore–Ham heuristic and slowest allowable speed rule that are specially designed to produce good initial solutions with certain diversity. Second, several properties of the nondominated solutions are investigated based on the characteristics of the bi-objective problem, which are used to develop the knowledge-based search operators. Third, a cooperative search strategy of multiple operators is designed for the solutions with different characteristics to tradeoff two objectives. Fourth, a knowledge-based local intensification is used for exploiting better nondominated solutions sufficiently. Moreover, an energy saving method based on the critical path is used to further improve the performance. The effect of parameter setting on the KCA is investigated with the Taguchi method of design-of-experiment. Extensive computational tests and comparisons are carried out, which verify the effectiveness of the special designs of the KCA in solving the EEDPFSP.

A Novel Knowledge-based Semantic Search Engine

A Novel Knowledge-based Semantic Search Engine

Benchmarking fold detection by DaliLite v.5.

Protein structure comparison plays a fundamental role in understanding the evolutionary relationships between proteins. Here, we release a new version of the DaliLite standalone software. The novelties are hierarchical search of the structure database organized into sequence based clusters, and remote access to our knowledge base of structural neighbors. The detection of fold, superfamily and family level similarities by DaliLite and state-of-the-art competitors was benchmarked against a manually curated structural classification. Database search strategies were evaluated using Fmax with query-specific thresholds. DaliLite and DeepAlign outperformed TM-score based methods at all levels of the benchmark, and DaliLite outperformed DeepAlign at fold level. Hierarchical and knowledge-based searches got close to the performance of systematic pairwise comparison. The knowledge-based search was four times as efficient as the hierarchical search. The knowledge-based search dynamically adjusts the depth of the search, enabling a trade-off between speed and recall. http://ekhidna2.biocenter.helsinki.fi/dali/README.v5.html. Supplementary data are available at Bioinformatics online.

Cloud database failure prediction using multi agent system

We have proposed a new method of fault tolerance mechanism in modern cloud database. Cloud database is important for big enterprises and have strict service level agreement (SLA) so any downtime is costly. All databases have their own fault tolerance mechanism by means of clustering technique, standby, backup recovery strategies with almost no data loss. The above methods are either costly or time consuming. If any measurement can be taken which can predict cloud database failure well ahead of it actually happens, suggest reason for the failure and also provide solution for the problem from knowledge database will not only reduce cost and time problem mentioned above but also will add a new dimension to fault tolerance technology. In this paper we have tried to develop an idea of failure prediction for a cloud database with the help of multi agent system and probable solution based on knowledge base search.

Cloud database failure prediction using multi agent system

We have proposed a new method of fault tolerance mechanism in modern cloud database. Cloud database is important for big enterprises and have strict service level agreement (SLA) so any downtime is costly. All databases have their own fault tolerance mechanism by means of clustering technique, standby, backup recovery strategies with almost no data loss. The above methods are either costly or time consuming. If any measurement can be taken which can predict cloud database failure well ahead of it actually happens, suggest reason for the failure and also provide solution for the problem from knowledge database will not only reduce cost and time problem mentioned above but also will add a new dimension to fault tolerance technology. In this paper we have tried to develop an idea of failure prediction for a cloud database with the help of multi agent system and probable solution based on knowledge base search.

Payoffs and pitfalls in using knowledge-bases for consumer health search

Consumer health search (CHS) is a challenging domain with vocabulary mismatch and considerable domain expertise hampering peoples’ ability to formulate effective queries. We posit that using knowledge bases for query reformulation may help alleviate this problem. How to exploit knowledge bases for effective CHS is nontrivial, involving a swathe of key choices and design decisions (many of which are not explored in the literature). Here we rigorously empirically evaluate the impact these different choices have on retrieval effectiveness. A state-of-the-art knowledge-base retrieval model—the Entity Query Feature Expansion model—was used to evaluate these choices, which include: which knowledge base to use (specialised vs. general purpose), how to construct the knowledge base, how to extract entities from queries and map them to entities in the knowledge base, what part of the knowledge base to use for query expansion, and if to augment the knowledge base search process with relevance feedback. While knowledge base retrieval has been proposed as a solution for CHS, this paper delves into the finer details of doing this effectively, highlighting both payoffs and pitfalls. It aims to provide some lessons to others in advancing the state-of-the-art in CHS.

Evaluating the impact of Idea-Inspire 4.0 on analogical transfer of concepts

AbstractThe biological domain has the potential to offer a rich source of analogies to solve engineering design problems. However, due to the complexity embedded in biological systems, adding to the lack of structured, detailed, and searchable knowledge bases, engineering designers find it hard to access the knowledge in the biological domain, which therefore poses challenges in understanding the biological concepts in order to apply these concepts to engineering design problems. In order to assist the engineering designers in problem-solving, we report, in this paper, a web-based tool called Idea-Inspire 4.0 that supports analogical design using two broad features. First, the tool provides access to a number of biological systems using a searchable knowledge base. Second, it explains each one of these biological systems using a multi-modal representation: that is, using function decomposition model, text, function model, image, video, and audio. In this paper, we report two experiments that test how well the multi-modal representation in Idea-Inspire 4.0 supports understanding and application of biological concepts in engineering design problems. In one experiment, we use Bloom's method to test “analysis” and “synthesis” levels of understanding of a biological system. In the next experiment, we provide an engineering design problem along with a biological-analogous system and examine the novelty and requirement-satisfaction (two major indicators of creativity) of resulting design solutions. In both the experiments, the biological system (analogue) was provided using Idea-Inspire 4.0 as well as using a conventional text-image representation so that the efficacy of Idea-Inspire 4.0 is tested using a benchmark.

A Quality Evaluation of Combined Search on a Knowledge Base and Text

We provide a quality evaluation of KB+Text search, a deep integration of knowledge base search and standard full-text search. A knowledge base (KB) is a set of subject–predicate–object triples with a common naming scheme. The standard query language is SPARQL, where queries are essentially lists of triples with variables. KB+Text search extends this by a special occurs-with predicate, which can be used to express the co-occurrence of words in the text with mentions of entities from the knowledge base. Both pure KB search and standard full-text search are included as special cases. We evaluate the result quality of KB+Text search on three different query sets. The corpus is the full version of the English Wikipedia (2.4 billion word occurrences) combined with the YAGO knowledge base (26 million triples). We provide a web application to reproduce our evaluation, which is accessible via http://ad.informatik.uni-freiburg.de/publications .

A Knowledge-Based Search Strategy for Optimally Structuring the Terrain Dependent Rational Function Models

Identifying the optimal structure of terrain dependent Rational Function Models (RFMs) not only decreases the number of Ground Control Points (GCPs) required, but also increases the accuracy of the model, by reducing the multi-collinearity of Rational Polynomials Coefficients (RPCs) and avoiding the ill-posed problem. Global optimization algorithms such as Genetic Algorithm (GA), evaluate the different combinations of parameters effectively. Therefore, they have a high ability to detect the optimal structure of RFMs. However, one drawback of these algorithms is their high computation cost. This article proposes a knowledge-based search strategy to overcome this deficiency. The backbone of the proposed method relies on the technical knowledge about the geometric condition of image at the time of acquisition, as well as the effect of external factors such as terrain relief on the image. This method was evaluated on four different datasets, including a SPOT-1A, a SPOT-1B, an IKONOS-Geo image, and a GeoEye-Geo imagery, using various number of GCPs. Experimental results demonstrate the efficiency of the proposed method to achieve a sub-pixel accuracy using few GCPs (only 4–6 points) in all datasets. The results also indicate that the proposed method improves the computation speed by 140 times when comparing with GA.

Placement of DG for reliability improvement and loss minimization with reconfiguration of radial distribution systems

Purpose – The purpose of the paper is to find the best distributed generators (DGs) location for improving reliability and reducing power loss using distribution system reconfiguration. This is implemented in the presence of the tie-switches. It proposes a search-based algorithm for the reconfiguration problem. Individual DG placement is obtained for all system configurations, and analytical hierarchy process tool is used for finding the overall best location. This is carried out for various system loadings. Design/methodology/approach – This paper proposes a knowledge-based search algorithm which needs the base conditions of the distribution system. A detailed analysis is carried out for finding the best DG locations from the obtained DG placements for various system configurations. Simulations are rigorously carried out with the help of programming. Results from these simulations are further given to analytical hierarchy tool for obtaining the DGs location. Findings – The findings of the paper are the DG placement for various system loadings and various system configurations and to obtain the best DG location for any system configuration. A search-based algorithm is designed for accomplishing it. Originality/value – The proposed method identifies the placement of distributed generation at distribution systems for reliability improvement and power loss reduction which is one of the present day needs for fulfilling the raising power consumers.

Automatic sorting of toxicological information into the IUCLID (International Uniform Chemical Information Database) endpoint-categories making use of the semantic search engine Go3R

The knowledge-based search engine Go3R, www.Go3R.org, has been developed to assist scientists from industry and regulatory authorities in collecting comprehensive toxicological information with a special focus on identifying available alternatives to animal testing. The semantic search paradigm of Go3R makes use of expert knowledge on 3Rs methods and regulatory toxicology, laid down in the ontology, a network of concepts, terms, and synonyms, to recognize the contents of documents. Search results are automatically sorted into a dynamic table of contents presented alongside the list of documents retrieved. This table of contents allows the user to quickly filter the set of documents by topics of interest. Documents containing hazard information are automatically assigned to a user interface following the endpoint-specific IUCLID5 categorization scheme required, e.g. for REACH registration dossiers. For this purpose, complex endpoint-specific search queries were compiled and integrated into the search engine (based upon a gold standard of 310 references that had been assigned manually to the different endpoint categories). Go3R sorts 87% of the references concordantly into the respective IUCLID5 categories. Currently, Go3R searches in the 22million documents available in the PubMed and TOXNET databases. However, it can be customized to search in other databases including in-house databanks.