Usage Of Heuristics Research Articles

Explainable Optimisation through Online and Offline Hyper-heuristics

Abstract - Research in the explainability of optimisation techniques has largely focused on metaheuristics and their movement of solutions around the search landscape. Hyper-heuristics create a different challenge for explainability as they make use of many more operators, or low-level heuristics and learning algorithms which modify their probability of selection online. This paper describes a set of methods for explaining hyper-heuristics decisions in both online and offline scenarios using selection hyper-heuristics as an example. These methods help to explain various aspects of the function of hyper-heuristics both at a particular juncture in the optimisation process and through time. Visualisations of each method acting on sequences provide an understanding of which operators are being utilised and when, and in which combinations to produce a greater understanding of the algorithm-problem nexus in hyper-heuristic search. These methods are demonstrated on a range of problems including those in operational research and water distribution network optimisation. They demonstrate the insight that can be generated from optimisation using selection hyper-heuristics, including building an understanding of heuristic usage, useful combinations of heuristics and heuristic parameterisations. Furthermore the dynamics of heuristic utility are explored throughout an optimisation run and we show that it is possible to cluster problem instances according to heuristic selection alone, providing insight into the perception of problems from a hyper-heuristic perspective.

Search symbols, trading performance, and investor participation

We investigate the relationships among search symbols, trading performance, and investor participation. We use two specific datasets from Google Trends’ search volume index. The search volume by number ticker significantly predicts high returns and high investor participation when applied by active retail investors investing in large firms. This does not hold true for less active retail investors who use Chinese company name tickers as their search terms. Our results indicate that the heuristic usage of number tickers to search for company information helps active retail investors to obtain better trading performance compared with less active retail investors who use Chinese company name tickers.

Numerological Heuristics and Credit Risk in Peer-to-Peer Lending

People often use heuristics as mental shortcuts when making financial decisions. Although the literature typically considers heuristics as behavior biases, we explore how different types of heuristics differ from one another. Through peer-to-peer lending data, we observe that borrowers who use limited attention when applying for loans tend to choose round loan amounts, simplifying the decision-making process but compromising accuracy. This round-number heuristic decreases their funding success rate and increases the probability of default. On the other hand, some borrowers select loan amounts in “lucky numbers” that superstitious lenders favor. This lucky-number heuristic caters to the lenders’ preference, thus increasing the borrowers’ funding success rates and reducing the likelihood of default. Our paper demonstrates that borrowers select heuristics based on their motives, leading to varying consequences. We also show that heuristics are not all the same, and people’s choice of heuristics provides insight into their characteristics and can predict decision outcomes. For instance, factoring in heuristic usage information improves default prediction accuracy in our setting. Our findings can be beneficial to practitioners in refining the underwriting and screening of borrowers and loans.

Solving Hub Location Problems With Profits Using Variable Neighborhood Search

This paper proposes variable neighborhood search (VNS) heuristics to solve hub network design problems with profits, which are uncapacitated hub location problems with incomplete hub networks. These problems seek to locate hub facilities, design hub networks, and assign spokes to hubs to maximize total profits. Six problems consisting of multiple allocation, single allocation, and r-allocation strategies, with optional direct connections, are solved. Unlike hub location problems that minimize costs satisfying all service demands, the operators can choose to satisfy a subset of travel demands to maximize profits. Although exact methods and heuristics are both commonly used for solving hub location problems, the problems with profits are mainly solved by the former. Therefore, VNS-based heuristics are proposed to solve six variants of hub location problems. The proposed heuristics have the same shaking procedure to escape local optima, while neighborhood structures in the improvement procedure depend on the allocation strategies. To evaluate the heuristics, this study also designs enhanced Benders decomposition methods which are exact algorithms. Computational experiments on existing benchmark datasets reveal an extraordinary performance of the heuristics. For the instances that can be solved by exact methods, the heuristics solve over 90% to optimality while being one to three orders of magnitude faster than the commercial solver CPLEX and Benders decomposition. Given the outstanding accuracy, with significantly reduced computational cost, the study contributes to the usage of heuristics for hub location problems with profits, especially for larger-scale networks, where exact methods cannot be executed because of limited computational resources.

Transcendental Logic-Based Formalism for Semantic Representation of Software Project Requirements Architecture

This article is devoted to the analysis of the situation that has arisen in the practice of using artificial intelligence methods for software development. Nowadays there are many disparate approaches, models, and practices based on the use of narrow intelligence for decision-making at different stages of the life cycle of software products, and an almost complete lack of solutions brought to wide practical use. The article provides a comprehensive overview of the main reasons for the lack of the expected effect from the implementation of Agile and suggests a way to solve this problem based on the use of a self-organizing knowledge model. Based on the heuristic usage of transcendental logic in the terms of "ontological predicates", such a model makes it possible to create a formalism of the semantic representation of the requirements architecture of a software project, which could provide semantic interoperability and an executable semantic framework for automated ontology generation from unstructured informal software requirements text. The main benefit of this model is that it is flexible and ensures the accumulation of knowledge without the need to change the initial infrastructure as well as that the ontology inference engine is the part of the mechanism of collective interaction of active elements of knowledge and not some externally programmed system of rules that imitate the process of thinking.

Investigations of heuristic usage in terms of the accuracy and applicability

Investigations of heuristic usage in terms of the accuracy and applicability

Human-Centered A.I. and Security Primitives

The paper reviews how human-centered artificial intelligence and security primitive have influenced life in the modern world and how it’s useful in the future. Human-centered A.I. has enhanced our capabilities by the way of intelligence, human informed technology. It has created a technology that has made machines and computer intelligently carry their function. The security primitive has enhanced the safety of the data and increased accessibility of data from anywhere regardless of the password is known. This has improved personalized customer activities and filled the gap between the human-machine. This has been successful due to the usage of heuristics which solve belowems by experimental, support vector machine which evaluates and group the data, natural language processing systems which change speech to language. The results of this will lead to image recognition, games, speech recognition, translation, and answering questions. In conclusion, human-centered A.I. and security primitives is an advanced mode of technology that uses statistical mathematical models that provides tools to perform certain work. The results keep on advancing and spreading with years and it will be common in our lives.

Two Novel Current-Mode CNFET-Based Full Adders Using ULPD as Voltage Regulator

This paper presents two novel current-mode Full Adders based on Carbon Nanotube FET (CNFET). They comprise of three main parts: current-to-voltage converter, threshold detector and voltage-to-current converter. While other designs in the literature use either inverter or current source for detecting threshold, the new designs are based on a heuristic usage of an Ultra Low-Power Diode (ULPD) as voltage regulator. The use of diode does not lengthen the critical path and thereby ensuring high-speed operation. It does not increase power consumption significantly either. Simulation results by HSPICE and 32[Formula: see text]nm CNFET technology file demonstrate at least 19% higher performance in terms of energy consumption for the second proposed Full Adder compared to other traditional and state-of-the-art current-mode and mixed-mode designs.

How to Burn a Network or Spread Alarm

This paper compares centrality indices usage within a heuristic method for a fast spread of alarm, or crucial information. Such indices can be used as a core part within more sophisticated optimisation methods, which should determine a graph parameter - burning number, defining, how fast can an alarm spread through all nodes. In this procedure at each time step a new chosen node is alarmed (i.e. burned) “from outside”, and already alarmed nodes at each time step then alarm their neighbours. The procedure ends, when all the nodes are alarmed (i.e. burned). The optimisation heuristic should choose such ordered sequence of nodes, which are to be alarmed “from outside”, that their number, equal the number of time steps (i.e. burning number) necessary to alarm the whole network, is minimised. The NP completeness of the problem necessitates a usage of heuristics. However, even the heuristics can be slower, reaching towards a global optimum, or faster, exchanging part of the quality for a time. This paper studies the usage of centrality indices in a simpler and faster heuristic. It should be useful e.g. for a mobile network of cars or drones, when an optimal solution cannot be computed in advance, or take too much CPU time, since the connections within the dynamic network might not exist any longer. A wide range of centrality indices was tested on selected networks, both real as well as artificially generated. While the performances of indices substantially differ for different types of networks, results show, which centrality indices work well across all tested networks.

Sense-making Strategies for the Interpretation of Visualizations—Bridging the Gap between Theory and Empirical Research

Making sense of visualizations is often an open and explorative process. This process is still not very well understood. On the one hand, it is an open question which theoretical models are appropriate for the explanation of these activities. Heuristics and theories of everyday thinking probably describe this process better than more formal models. On the other hand, there are only few detailed investigations of interaction processes with information visualizations. We will try to relate approaches describing the usage of heuristics and everyday thinking with existing empirical studies describing sense-making of visualizations.

Examining student heuristic usage in a hydrogen bonding assessment

This study investigates the role of representational competence in student responses to an assessment of hydrogen bonding. The assessment couples the use of a multiple-select item ("Choose all that apply") with an open-ended item to allow for an examination of students' cognitive processes as they relate to the assignment of hydrogen bonding within a structural representation. Response patterns from the multiple-select item implicate heuristic usage as a contributing factor to students' incorrect responses. The use of heuristics is further supported by the students' corresponding responses to the open-ended assessment item. Taken together, these data suggest that poor representational competence may contribute to students' previously observed inability to correctly navigate the concept of hydrogen bonding. © 2017 by The International Union of Biochemistry and Molecular Biology, 45(5):411-416, 2017.

The Cognitive Underpinnings of Continuous Identity: Higher Episodic Memory Recall and Lower Heuristic Usage Predicts Highest Levels of Self-Continuity

ABSTRACTContinuous identity (CI) is a sense of persistent identity wherein the present self is seen as overlapping with the past and future selves. This study addressed the hypothesis that judgments of CI require successful retrieval of information by examining the relationship between varying levels of CI and two forms of memory recall. The pattern of findings indicated that high levels of cued memory recall combined with low levels of heuristic usage were associated with higher levels of CI, and this occurred for both past-to-present CI and present-to-future CI. We propose that to achieve high levels of CI, individuals need to access and analyze a fund of stored autobiographical information.

Interliminal Design: Understanding cognitive heuristics to mitigate design distortion

Cognitive heuristics are mental shortcuts adapted over time to enable rapid interpretation of our complex environment. They are intrinsic to human cognition and resist modification. Heuristics applied outside the context to which they are best suited are termed cognitive bias, and are the cause of systematic errors in judgment and reasoning. As both a cognitive and intuitive discipline, design by individuals is vulnerable to context-inappropriate heuristic usage. Designing in groups can act positively to counterbalance these tendencies, but is subject to heuristic misuse and biases particular to social environments. Mismatch between desired and actual outcomes– termed here, design distortion – occurs when such usage goes unnoticed and unaddressed, and can affect multiple dimensions of a system. We propose a methodology, interliminal design, emerging from the Program in Collaborative Design at Pacific Northwest College of Art, to specifically address the influence of cognitive heuristics in design. This adaptive approach involves reflective, dialogic, inquiry-driven practices intended to increase awareness of heuristic usage, and identify aspects of the design process vulnerable to misuse on both individual and group levels. By facilitating the detection and mitigation of potentially costly errors in judgment and decision-making that create distortion, such metacognitive techniques can meaningfully improve design.

Architecture of logistics system finding fellow-travellers for drivers

The paper describes an architecture of the logistics system based on application of the smart space idea to finding fellow-travelers for drivers. The ontology formed by mobile devices of the system participants and interconnections between them are presented. The paper also describes algorithms for finding appropriate fellow-travelers for drivers as well as definition of the pick-up and drop-off points meeting requirements of both drivers and passengers. Due to the rather large dimension of the problem, the usage of heuristics significantly reducing the dimension of the task is proposed. To demonstrate the possibilities of the architecture and its underlying components, the software prototype of this system has been developed and described.

Effect of Principal Heuristics on Accuracy of Property Valuation in Nigeria

Valuation inaccuracy has been attributed amongst others to behavioural issues such as the usage of Anchoring and Adjustment Heuristics. There is however a dearth in the research of the other principal heuristics namely availability, representative and positivity. This research is hereby aimed at discovering the effects of these heuristics on the accuracy of property valuation. To accomplish this, the study undertook a cross-sectional questionnaire survey of 159 of the 270 Head Offices of Estate Surveying and Valuation firms in Lagos Metropolis, while 29 and 30 questionnaires were distributed to the Head Offices of the entire Estate Surveying and Valuation Firms in Abuja and Port Harcourt respectively. For ease of coverage, Lagos Metropolis was stratified into six zones; thereafter respondents were selected randomly. The respondents were required to carry out simulated valuations using each of the four types of heuristics and also with supplied current market data. The T-test at the 95 per cent confidence interval was employed to test for inaccuracy in heuristically determined values relative to the sale values (values of the ‘control’ properties). The result reveals that heuristic-determined values, particularly that of representative, are not as accurate as those derived from supplied current market data. The authors recommended more focus on research of representative heuristics while consistent usage of heuristics should be dissuaded, to prevent loss of clients’ confidence in valuation reports.

Evolutionary optimisation of Hénon map control: a black box approach

This paper deals with the usage of heuristics for the optimisation of the control of chaotic system. The main aim of this paper is to show a new approach of solving this problem and constructing new cost functions (CFs) operating in ‘black box mode’ without a previous exact mathematical analysis of the system, thus without knowledge of the stabilising target state. Three proposals of ‘black box’ mode CFs were tested in this paper. As a model of deterministic chaotic system, the two-dimensional Henon map was used. The optimisations were realised in several ways, each one for another desired state of system. Evolutionary algorithms (EAs) self-organising migrating algorithm and differential evolution were used. For each version, repeated simulations were conducted to outline the effectiveness and robustness of the used method and CF.

Can intuitive and analytical decision styles explain managers' evaluation of information technology?

PurposeThe purpose of this paper is to clarify how IT managers' decision styles affect their evaluation of information technology.Design/methodology/approachFour different decision styles were assessed in a leadership test directed towards IT managers. Each style included two dimensions: confidence judgment ability and decision heuristic usage. Participants belonging to each style were interviewed and their answers analysed with regard to their reasoning about central areas of IT management.FindingsResults suggest that a decision style combining intuitive and analytical capabilities lead to better evaluations of information technology.Originality/valeThe results of the present study are valuable for the understanding of how decision styles impact on IT management in everyday life.

The Effects of Choice Context on Decision-Making: An Application to Voter Fatigue

This paper exploits a natural experiment in which choice fatigue is isolated as an explanation for the usage of heuristics in decision-making. The em- pirical application provides evidence that voters who see a given contest relatively further down the ballot are more likely to vote no and to abstain. Within-election exogenous variation in ballot position is primarily due to differences in the set of overlaying local political jurisdictions. My central finding is that lowering a proposi- tion 10 positions on the ballot increases precinct-level no votes and undervotes by 1.3 and 0.7 percentage points, respectively. Interestingly, 8 of 124 statewide propo- sitions in the dataset have winning margins within the range of the no estimate. The empirical analysis employs a unique precinct-level panel dataset of votes cast for the entire menu of federal, state & local ballot choices in primary and general elections between 1992 and 2006 in San Diego County, California. Implications of the results range from the dissemination of information by firms and policy makers to the design of electoral institutions and the strategic use of ballot propositions.

Heuristic use, credit constraints and real estate lending

Presents an investigation into the existence of information processing heuristics in two commercial bank lender types that provide investment and construction loans secured by real estate. Expert real estate banking lenders and expert private banking lenders evidenced different, systematic group specific heuristic usage. Heuristics constrained information cue relevancy and affected the lending decision. Expert private banking lenders mitigated real estate risk by using non‐collateral specific information cues. Real estate lending experts did not mitigate real estate market risk and required favourable collateral specific information cues in order to approve a loan. Concludes that access to credit for real estate investment may be limited by lender expertise because the development of expertise mandates restrictive task interpretation and cue relevance.

Artificial intelligence in photogrammetry

The scope of the discipline of artificial intelligence is reviewed and its relevance for the discipline of photogrammetry is analyzed. The most appropriate artificial-intelligence techniques are delt with more in detail, especially the usage of heuristics in algorithms, rule-based knowledge representation and programming, and also object-oriented programming. Urgent need for using expert-system technology is seen when replacing semiautomatic man-machine systems with fully automatic systems. In building expert systems, especially in gathering of knowledge as rules, a system-analytical approach is considered to be a necessity. It is concluded that the key issue will be the structuring task in the building of complex systems for photogrammetric analysis — also when gathering the knowledge-base for rule-based programming. In the future, it will be increasingly difficult to distinguish between the techniques and methods used in artificial intelligence and, on the other hand, those used in more conventional system design and software engineering.