Decision Logic Research Articles

Improved Accuracy In Data Mining Decision Tree Classification Using Adaptive Boosting (Adaboost)

The Decision Tree algorithm is a data mining method algorithm that is often applied as a solution to a problem for a classification. The Decision Tree C5.0 algorithm has several weaknesses, including: the C5.0 algorithm and several other decision tree methods are often biased towards modeling whose features have many levels, some problems for the model can occur such as over-fit or under-fit challenges, big changes to decision logic can result in small changes to data training, C5.0 can experience modeling inconvenience, data imbalance causes low accuracy in C5.0 algorithm. The boosting algorithm is an iterative algorithm that gives different weights to the distribution of training data in each iteration. Each iteration of boosting adds weight to examples of misclassification and decreases weight to examples of correct classification, thereby effectively changing the distribution of the training data. One example of a boosting algorithm is adaboost. The purpose of this research is to improve the performance of the Decision Tree C5.0 classification method using adaptive boosting (adaboost) to predict hepatitis disease using the Confusion matrix. Tests that have been carried out with the Confusion Matrix use the Hepatitis dataset in the Decision Tree C5.0 classification which has an accuracy rate of 80.58% with a classification error rate of 19.15%. Whereas in the Decision Tree C5.0 classification Adaboost has a higher accuracy rate of 82.98%, a classification error rate of 17.02%. This difference is caused by the adaboost algorithm, because the adaboost algorithm is able to change a weak classifier into a strong classifier by increasing the weight of the observations, and adaboost is also able to reduce the classifier error rate.

The Brushing Game in Online Marketplaces

ABSTRACT We study a pervasive fraudulent strategy, called “brushing,” employed by retailers operating in e-commerce platforms: Retailers place fake orders of their own products to inflate sales and boost the visibility of their store links in search results. Using a duopolistic pricing game with heterogeneous consumer search behavior, we show that the retailer at a more prominent position in product listing enjoys greater profit as well as an advantage in future position allocation if the platform charges a per-sale commission fee and uses a sales-based ranking mechanism to display store-link positions. To fight for better visibility, retailers may employ brushing to boost their sales metrics. We characterize the equilibrium brushing behavior for the position competition game between the retailers. Under a sufficiently high commission rate, the game has a pure-strategy equilibrium and entails no-brushing outcome. Otherwise, retailers fully engage in brushing activity and the brushing equilibrium exists only in mixed strategies. Model extensions incorporating heterogeneities in wholesale cost and product quality show that retailers with cost and quality advantages are able to gain profit improvement at a less prominent position and thereby have less incentive to invest in brushing. Our results provide platform managers and retailers with economic insights to better understand the logic for brushing fraud and strategic decisions in online marketplaces.

Prediction-Uncertainty-Aware Threat Detection for ADAS: A Case Study on Lane-Keeping Assistance

Advanced driver assistance systems typically support the driver in cases where the driver is likely to fail the driving task. The challenge, from a system perspective, is to accurately detect those cases. Recently, machine learning-based prediction models that are able to estimate the prediction uncertainty in real-time have successfully been introduced for this purpose. However, very little effort has been made on using the prediction uncertainty in the decision-making logic to improve the system's robustness, especially in cases where the input data is affected by noise or anomalies that are not presented in the training data. In this work, four threat-detection methods using uncertainty estimates are proposed and evaluated using a real-world data set. The methods use different strategies for leveraging uncertainty information, where the goal is to ensure that the intervention decision is based on trustworthy predictions. The threat-detection methods' performances are evaluated, using five different learning-based prediction models, in the context of a lane-keeping assistance application.

FalsifAI: Falsification of AI-Enabled Hybrid Control Systems Guided by Time-Aware Coverage Criteria

Modern Cyber-Physical Systems (CPSs) that need to perform complex control tasks (e.g., autonomous driving) are increasingly using AI-enabled controllers, mainly based on deep neural networks (DNNs). The quality assurance of such types of systems is of vital importance. However, their verification can be extremely challenging, due to their complexity and uninterpretable decision logic. Falsification is an established approach for CPS quality assurance, which, instead of attempting to prove the system correctness, aims at finding a time-variant input signal violating a formal specification describing the desired behavior; it often employs a search-based testing approach that tries to minimize the <i>robustness</i> of the specification, given by its quantitative semantics. However, guidance provided by robustness is mostly black-box and only related to the system output, but does not allow to understand whether the temporal internal behavior determined by multiple consecutive executions of the neural network controller has been explored sufficiently. To bridge this gap, in this paper, we make an early attempt at exploring the temporal behavior determined by the repeated executions of the neural network controllers in hybrid control systems and first propose eight time-aware coverage criteria specifically designed for neural network controllers in the context of CPS, which consider different features by design: the simple temporal activation of a neuron, the continuous activation of a neuron for a given duration, and the differential neuron activation behavior over time. Secondly, we introduce a falsification framework, named <inline-formula><tex-math notation="LaTeX">$\mathtt {FalsifAI}$</tex-math></inline-formula>, that exploits the coverage information for better falsification guidance. Namely, inputs of the controller that increase the coverage (so improving the <i>exploration</i> of the DNN behaviors), are prioritized in the <i>exploitation</i> phase of robustness minimization. Our large-scale evaluation over a total of 3 typical CPS tasks, 6 system specifications, 18 DNN models and more than 12,000 experiment runs, demonstrates 1) the advantage of our proposed technique in outperforming two state-of-the-art falsification approaches, and 2) the usefulness of our proposed time-aware coverage criteria for effective falsification guidance.

Combination of Decision Logics for Green Innovations in Saudi Arabian based Small and Medium Enterprises Experience

Combination of Decision Logics for Green Innovations in Saudi Arabian based Small and Medium Enterprises Experience

Modus Ponens and the Logic of Decision

This article presents and discusses a prima facie counterexample to modus ponens. To appropriately theorize the case, I argue for conceptualizing the notions of logical consequence and logical commitment in “normative” terms, so that logical commitment does not attach to the premises of a spurious dominance argument—and, more generally, does not attach to unreasonable decision states, or to syntactically specified classes thereof. I also suggest that there is a logical motivation for the restriction to “well-formed” decision states that is characteristic of Savage-style logics of decision.

RNNCon: Contribution Coverage Testing for Stacked Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are applied in safety-critical fields such as autonomous driving, aircraft collision detection, and smart credit. They are highly susceptible to input perturbations, but little research on RNN-oriented testing techniques has been conducted, leaving a threat to a large number of sequential application domains. To address these gaps, improve the test adequacy of RNNs, find more defects, and improve the performance of RNNs models and their robustness to input perturbations. We aim to propose a test coverage metric for the underlying structure of RNNs, which is used to guide the generation of test inputs to test RNNs. Although coverage metrics have been proposed for RNNs, such as the hidden state coverage in RNN-Test, they ignore the fact that the underlying structure of RNNs is still a fully connected neural network but with an additional "delayer" that records the network state at the time of data input. We use the contributions, i.e., the combination of the outputs of neurons and the weights they emit, as the minimum computational unit of RNNs to explore the finer-grained logical structure inside the recurrent cells. Compared to existing coverage metrics, our research covers the decision mechanism of RNNs in more detail and is more likely to generate more adversarial samples and discover more flaws in the model. In this paper, we redefine the contribution coverage metric applicable to Stacked LSTMs and Stacked GRUs by considering the joint effect of neurons and weights in the underlying structure of the neural network. We propose a new coverage metric, RNNCon, which can be used to guide the generation of adversarial test inputs. And we design and implement a test framework prototype RNNCon-Test. 2 datasets, 4 LSTM models, and 4 GRU models are used to verify the effectiveness of RNNCon-Test. Compared to the current state-of-the-art study RNN-Test, RNNCon can cover a deeper decision logic of RNNs. RNNCon-Test is not only effective in identifying defects in Deep Learning (DL) systems but also in improving the performance of the model if the adversarial inputs generated by RNNCon-Test are filtered and added to the training set to retrain the model. In the case where the accuracy of the model is already high, RNNCon-Test is still able to improve the accuracy of the model by up to 0.45%.

A collaborative collision avoidance strategy for autonomous ships under mixed scenarios

AbstractShip collision avoidance has always been one of the classic topics in the field of marine research. In traditional encounter situations, officers on watch (OOWs) usually use a very high frequency (VHF) radio to coordinate each other. In recent years, with the continuous development of autonomous ships, there will be a mixed situation where ships of different levels of autonomy coexist at the same time. Under such a scenario, different decision makers have different perceptions of the current scene and different decision-making logic, so conventional collision avoidance methods may not be applicable. Therefore, this paper proposes a collaborative collision avoidance strategy for multi-ship collision avoidance under mixed scenarios. It builds a multi-ship cooperative network to determine cooperative objects and timing, at the same time. Based on a cooperative game model, a global collision avoidance responsibility distribution that satisfies group rationality and individual rationality is realised, and finally achieves a collaborative strategy according to the generalised reciprocal velocity obstacle (GRVO) algorithm. Case studies show that the strategy proposed in this paper can make all ships pass each other clearly and safely.

Melting the Psychological Boundary: How Interactive and Sensory Affordance Influence Users’ Adoption of Digital Heritage Service

As a result of the post-pandemic situation, enhancing digital heritage services has become one of the key issues for the recovery of tourism. Disruptive innovation in human–computer interaction technology has brought new opportunities for digitalization and intelligent transformation in the contemporary cultural tourism industry. Existing research on the adoption behavior of digital heritage services primarily focuses on users’ assessments of behavior results. There is a considerable gap in research about the interaction and value co-creation between users and digital intelligence services and users’ cognitive construction logic of digital heritage services. Following reciprocal determinism, we propose a conceptual model to deconstruct the detailed transmission path of interactive affordance and sensory affordance to digital heritage adoption. In Study 1, a lab experiment in an AI-assisted smart screen digital heritage service context revealed that interactive affordance and user adoption of digital heritage services were partially mediated by psychological distance. Findings from a between-subject online experiment in Study 2 confirmed that embodied cognition and psychological distance play a parallel intermediary role in the impact of sensory affordance on adoption. In Study 3, a lab experiment in a VR-based digital museum context further verified that information overload moderates the influence of embodied cognition on psychological distance. This research reveals the deep-bounded, rational decision-making logic of digital heritage service adoption and provides significant practical enlightenment for the optimization of the affordance experience.

A value-based approach to the adoption of cryptocurrencies

The use of cryptocurrencies offers attractive business opportunities, in the context of financial services, smart contracts and token-based business models. The objective of this study is to provide a value-based understanding of what drives people to use cryptocurrencies for value exchange. Based on the users’ perceived value of the technology, as logic of decision making, we explore the role of perceived financial value and the perceived emotional value in the intention to use the technology. The unified technology adoption theory provides the potential drivers of these value concepts, which are extended accounting for sustainability. Furthermore, to capture users’ evolving experience with blockchain technologies, we propose the concept of the cryptocurrency knowledge path, capturing the scope and depth of users’ knowledge on the applicability of cryptocurrencies, as potential influence on the value concepts in the decision to actively use cryptocurrencies. For the analysis, a structural model is set up and estimated using partial least square analysis (PLS-SEM). We identify a positive effect of both value concepts, financial and emotional value, on the intention to use cryptocurrencies. However, interestingly, we find that the emotional value assessment is fully mediated through the knowledge path. Furthermore, we find that environmental sustainability considerations are fully mediated through either of the two value concepts. These results provide guidance for a customer-centric, sustainable design and marketing of crypto-projects.

Clinical Spasticity Assessment Assisted by Machine Learning Methods and Rule-Based Decision

The Modified Ashworth Scale (MAS) is commonly used to assess spasticity in clinics. The qualitative description of MAS has resulted in ambiguity during spasticity assessment. This work supports spasticity assessment by providing measurement data acquired from wireless wearable sensors, i.e., goniometers, myometers, and surface electromyography sensors. Based on in-depth discussions with consultant rehabilitation physicians, eight (8) kinematic, six (6) kinetic, and four (4) physiological features were extracted from the collected clinical data from fifty (50) subjects. These features were used to train and evaluate the conventional machine learning classifiers, including but not limited to Support Vector Machine (SVM) and Random Forest (RF). Subsequently, a spasticity classification approach combining the decision-making logic of the consultant rehabilitation physicians, SVM, and RF was developed. The empirical results on the unknown test set show that the proposed Logical-SVM-RF classifier outperforms each individual classifier, reporting an accuracy of 91% compared to 56-81% achieved by SVM and RF. A data-driven diagnosis decision contributing to interrater reliability is enabled via the availability of quantitative clinical data and a MAS prediction.

AI-Enhanced Hybrid Decision Management

The Decision Model and Notation (DMN) modeling language allows the precise specification of business decisions and business rules. DMN is readily understandable by business users involved in decision management. However, as the models get complex, the cognitive abilities of humans threaten manual maintainability and comprehensibility. Proper design of the decision logic thus requires comprehensive automated analysis of e.g., all possible cases the decision shall cover; correlations between inputs and outputs; and the importance of inputs for deriving the output. In the paper, the authors explore the mutual benefits of combining human-driven DMN decision modeling with the computational power of Artificial Intelligence for DMN model analysis and improved comprehension. The authors propose a model-driven approach that uses DMN models to generate Machine Learning (ML) training data and show, how the trained ML models can inform human decision modelers by means of superimposing the feature importance within the original DMN models. An evaluation with multiple real DMN models from an insurance company evaluates the feasibility and the utility of the approach.

Institutional design beyond democratic innovations

ABSTRACT Steffen Ganghof’s Beyond Presidentialism and Parliamentarism can improve existing typologies in comparative government and has great potential for discussions about democratic innovation and reform. So far, democratic innovations like deliberative mini-publics have remained mostly additive, leaving the underlying decision-making logics of representative political systems unchanged. Ganghof’s ideas can move debates about how deliberative democracy is to be institutionalized forward. Semi-parliamentary government constitutes an intriguing option to meet both demands for legislative flexibility and responsiveness to citizens’ concerns and demands for stability and accountability. At the same time, I identify a limitation of the book in the fact that Ganghof’s normative theory of democracy remains thin. To appeal to citizens in constitutional reform processes, proposals for semi-parliamentary reform need to do more than reconcile conflicting visions of majority rule. They need to speak to democracy’s central promises of equal autonomy and rationality.

The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests

Symbolic learning is the logic-based approach to machine learning, and its mission is to provide algorithms and methodologies to extract logical information from data and express it in an interpretable way. Interval temporal logic has been recently proposed as a suitable tool for symbolic learning, specifically via the design of an interval temporal logic decision tree extraction algorithm. In order to improve their performances, interval temporal decision trees can be embedded into interval temporal random forests, mimicking the corresponding schema at the propositional level. In this article we consider a dataset of cough and breath sample recordings of volunteer subjects, labeled with their COVID-19 status, originally collected by the University of Cambridge. By interpreting such recordings as multivariate time series, we study the problem of their automated classification using interval temporal decision trees and forests. While this problem has been approached with the same dataset as well as with other datasets, in all cases, non-symbolic learning methods (usually, deep learning-based) have been applied to solve it; in this article we apply a symbolic approach, and show that it does not only outperform the state-of-the-art obtained with the same dataset, but its results are also superior to those of most non-symbolic techniques applied on other datasets. As an added bonus, thanks to the symbolic nature of our approach, we are also able to extract explicit knowledge to help physicians characterize typical COVID-positive cough and breath.

Research on combat simulation agent modelling methods combined with reinforcement learning

Agent-based combat simulation is an important research method in the field of military science and system simulation. Behaviour decision model plays the key role in the design of combat simulation agents. The behaviour tree (BT) designed by nonplayer characters (NPCs) in the game provides an efficient and concise method for the construction of combat simulation agents and has been widely used. Because the rationality of BT construction directly affects the rationality of agent decision logic, designing a reasonable BT has become a crucial step. The design of the operational agent BT not only relies on rich tactical experience but also needs to repeatedly adjust and optimize the BT according to the operational deduction and simulation results. To avoid unreasonable BT design caused by lack of experience and eliminate the process of repeated debugging, a modelling method of a combat simulation agent that combines reinforcement learning and the BT method was proposed. This method not only makes the design process of BT more automatic but also simplifies the experience requirements of the combat simulation agent designers. Experiments show that RL-BT effectively integrates the reinforcement learning method and can endow combat simulation agents with battlefield learning ability while making independent decisions. The agent based on RL-BT for decision modelling can continuously adjust and optimize the decision process through experience accumulation, and its performance in combat simulation is significantly better than that of the agent using the original BT.

Interpretable boosted-decision-tree analysis for the Majorana Demonstrator

The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

Fog-cloud architecture-driven Internet of Medical Things framework for healthcare monitoring.

The new coronavirus disease (COVID-19) has increased the need for new technologies such as the Internet of Medical Things (IoMT), Wireless Body Area Networks (WBANs), and cloud computing in the health sector as well as in many areas. These technologies have also made it possible for billions of devices to connect to the internet and communicate with each other. In this study, an Internet of Medical Things (IoMT) framework consisting of Wireless Body Area Networks (WBANs) has been designed and the health big data from WBANs have been analyzed using fog and cloud computing technologies. Fog computing is used for fast and easy analysis, and cloud computing is used for time-consuming and complex analysis. The proposed IoMT framework is presented with a diabetes prediction scenario. The diabetes prediction process is carried out on fog with fuzzy logic decision-making and is achieved on cloud with support vector machine (SVM), random forest (RF), and artificial neural network (ANN) as machine learning algorithms. The dataset produced in WBANs is used for big data analysis in the scenario for both fuzzy logic and machine learning algorithm. The fuzzy logic gives 64% accuracy performance in fog and SVM, RF, and ANN have 89.5%, 88.4%, and 87.2% accuracy performance respectively in the cloud for diabetes prediction. In addition, the throughput and delay results of heterogeneous nodes with different priorities in the WBAN scenario created using the IEEE 802.15.6 standard and AODV routing protocol have been also analyzed. Fog-Cloud architecture-driven for IoMT networks • An IoMT framework is designed with important components and functions such as fog and cloud node capabilities. •Real-time data has been obtained from WBANs in Riverbed Modeler for a more realistic performance analysis of IoMT. •Fuzzy logic and machine learning algorithms (RF, SVM, and ANN) are used for diabetes predictions. •Intra and Inter-WBAN communications (IEEE 802.15.6 standard) are modeled as essential components of the IoMT framework with all functions.

Does TMT internationalization promote corporate digital transformation? A study based on the cognitive process mechanism

PurposeCorporate digital transformation (DT) and top management team (TMT) internationalization seem to be concomitant phenomena in recent years, the former is a major change and a thorough transformation requiring continuously new technologies and ideas. Excitingly, the latter shows a relatively broad vision, a large risk appetite and interest in new things. Does TMT internationalization promote DT? This question is essential for DT. Given that, this article will aim to discuss and examine whether and how TMT internationalization affects corporate DT.Design/methodology/approachThis article takes China's A-share listed manufacturing companies from 2011 to 2019 as a sample. The quantitative text analysis method is used to measure attention related to digitalization. This paper discusses: (1) The decision-making logic and cognitive process mechanism of “TMT internationalization–attention related to digitalization–corporate DT”. (2) The moderating effect of shared corporate mission of the TMT on the cognitive process of decision-making, that is, the social process of transforming individual cognition into team cognition, and the social process of transforming team cognition into corporate decision-making.FindingsTMT internationalization promotes DT. As an external manifestation of team cognition, attention plays a positive role as an intermediary mechanism. Specifically, executives with overseas experience have higher urgency assessment and manageable assessment, thus affecting their attention to digitalization positively, thereby promoting DT. This article does not demonstrate the moderating effect of shared corporate mission on the cognitive process, but it promotes DT directly, and only plays a role in the precognitive stage.Originality/valueThis article is the first one to study the relationship between TMT internationalization and corporate DT, which has practical guiding significance for DT and the “going out” strategies of the TMT. Also, the combination of upper echelons theory and cognitive theory opens up the black box of the strategic process. Lastly, this research explores the formation process of team cognition, which is always neglected by previous studies of the TMT demographic characteristics.

The Influence of Prior Experience on Entrepreneurs' Decision-making Logic: The Moderating Effect of Environmental Uncertainty

The Influence of Prior Experience on Entrepreneurs' Decision-making Logic: The Moderating Effect of Environmental Uncertainty

SYSTEM OF ENSURING NATIONAL SECURITY AS COMPONENT OF PUBLIC ADMINISTRATION OF THE COUNTRY

The article is devoted to the development of a methodology for building a public administration system that would most adequately correspond to the conditions of functioning of the system ensuring national security and the logic of decision-making in this area. The basis of the methodology for building a system of public management of national security provision is the comprehensive use of elements of the dynamic model of management of the system of national security provision. The main functional subsystems of the national security system and their purpose are shown. The spheres of state activity are directly transformed into spheres (directions) of public administration. One of the important areas of public administration is ensuring national security. The concept of public policy of ensuring national security (PPZNB), its content and principles, as well as the main goals of achieving its effectiveness are presented. It is emphasized that an important feature of public management of ensuring national security is that it is a category of strategic public management that is perspective-oriented, a conceptual plan for improving the management system. The most complex type of strategic management is called «strategic management on a real-time scale» and is usually associated with solving strategic tasks that arise suddenly. In fact, the organization should simultaneously be engaged in clarifying the strategy and solving emerging strategic tasks. It is the system of public management of ensuring national security that is such. This system of strategic public management is at the stage of formation, therefore its components have not yet been definitively determined. Improving the foundations of the public policy of ensuring national security, substantiating its goals, principles and priority areas, mechanisms for achieving the specified goals is impossible without modeling the processes of management decision-making in this area. Modeling also makes it possible to predict the possible negative consequences of management decisions made in various spheres of the state’s life.