Reasoning Capabilities Research Articles

Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing

Reasoning is a dynamic process. In cognitive theories, the dynamics of reasoning refers to reasoning states over time after successive state transitions. Modeling the cognitive dynamics is of utmost importance to simulate human reasoning capability. In this paper, we propose to learn the reasoning dynamics of visual relational reasoning by casting it as a path routing task. We present a reinforced path routing method that represents an input image via a structured visual graph and introduces a reinforcement learning based model to explore paths (sequences of nodes) over the graph based on an input sentence to infer reasoning results. By exploring such paths, the proposed method represents reasoning states clearly and characterizes state transitions explicitly to fully model the reasoning dynamics for accurate and transparent visual relational reasoning. Extensive experiments on referring expression comprehension and visual question answering demonstrate the effectiveness of our method.

A fuzzy model for predicting burn patients’ intravenous fluid resuscitation rate

One of the critical areas in the medical field is the burn treatment management that helps to rescue patient’s life by dramatically minimizing the after-burn progression and severity. Initial acute burn treatment involves intravenous fluid resuscitation, which must be administered meticulously to restore fluid loss and maintain essential organ function. A number of factors must be addressed quickly to make a decision for determining the required rate of intravenous fluid. Traditional methods with manual calculation reflects slow response and inaccurate estimation in most of the cases, thus requires random adjustments. Some automated and artificially intelligent systems can be found which still use the traditional formulas showing high fluctuation in the calculation of required rate. Therefore, this research proposes a fuzzy logic based model to predict the adequate intravenous fluid resuscitation rate for a burn patient. Fuzzy systems are treated as intelligent system close to human reasoning capabilities and for this application it ensures smooth transition of required rate without showing any high fluctuations for any adjustment. To attain the objective, a fuzzy logic system has been developed aggregating the clinical burn protocol as the knowledge base of the fuzzy inference engine where the %TBSA and HUO measurements are considered as inputs and intravenous fluid rate is the output. Multiple forms of fuzzy membership functions and different types of defuzzification methods have been applied to the proposed system to compile a comparative study. To explore the best approach, ten different test cases have been simulated employing both the manual calculation and the proposed fuzzy model. Results have presented that the proposed fuzzy based system shows to predict the optimum amount of intravenous fluid rate necessary for burn patient’s resuscitation.

A Method for Expanding Predicates and Rules in Automated Geometry Reasoning System

Predicates and rules are usually enclosed as built-in functions in automated geometry reasoning systems, meaning users cannot add any predicate or rule, thus resulting in a limited reasoning capability of the systems. A method for expanding predicates and rules in automated geometry reasoning systems is, thus, proposed. Specifically, predicate and rule descriptions are transformed to knowledge trees and forests based on formal representations of geometric knowledge, and executable codes are dynamically and automatically generated by using “code templates”. Thus, a transformation from controlled natural language descriptions to mechanization algorithms is completed, and finally, the dynamic expansion of predicates and rules in the reasoning system is achieved. Moreover, the method has been implemented in an automated geometry reasoning system for Chinese college entrance examination questions, and the practicality and effectiveness of the method were tested. In conclusion, the enclosed setting, which is a shortcoming of traditional reasoning systems, is avoided, the user-defined dynamic expansion of predicates and rules is realized, the application scope of the reasoning system is extended, and the reasoning capability is improved.

KSPMI: A Knowledge-based System for Predictive Maintenance in Industry 4.0

In the context of Industry 4.0, smart factories use advanced sensing and data analytic technologies to understand and monitor the manufacturing processes. To enhance production efficiency and reliability, statistical Artificial Intelligence (AI) technologies such as machine learning and data mining are used to detect and predict potential anomalies within manufacturing processes. However, due to the heterogeneous nature of industrial data, sometimes the knowledge extracted from industrial data is presented in a complex structure. This brings the semantic gap issue which stands for the lack of interoperability among different manufacturing systems. Furthermore, as the Cyber-Physical Systems (CPS) are becoming more knowledge-intensive, uniform knowledge representation of physical resources and real-time reasoning capabilities for analytic tasks are needed to automate the decision-making processes for these systems. These requirements highlight the potential of using symbolic AI for predictive maintenance. To automate and facilitate predictive analytics in Industry 4.0, in this paper, we present a novel Knowledge-based System for Predictive Maintenance in Industry 4.0 (KSPMI). KSPMI is developed based on a novel hybrid approach that leverages both statistical and symbolic AI technologies. The hybrid approach involves using statistical AI technologies such as machine learning and chronicle mining (a special type of sequential pattern mining approach) to extract machine degradation models from industrial data. On the other hand, symbolic AI technologies, especially domain ontologies and logic rules, will use the extracted chronicle patterns to query and reason on system input data with rich domain and contextual knowledge. This hybrid approach uses Semantic Web Rule Language (SWRL) rules generated from chronicle patterns together with domain ontologies to perform ontology reasoning, which enables the automatic detection of machinery anomalies and the prediction of future events’ occurrence. KSPMI is evaluated and tested on both real-world and synthetic data sets.

Handling temporality in human activity reasoning

Human-aware Artificial Intelligent systems are goal directed autonomous systems that are capable of interacting, collaborating, and teaming with humans. Activity reasoning is a formal reasoning approach that aims to provide common sense reasoning capabilities to these interactive and intelligent systems. This reasoning can be done by considering evidences –which may be conflicting–related to activities a human performs. In this context, it is important to consider the temporality of such evidence in order to distinguish activities and to analyse the relations between activities. Our approach is based on formal argumentation reasoning, specifically, Timed Argumentation Frameworks (TAF), which is an appropriate technique for dealing with inconsistencies in knowledge bases. Our approach involves two steps: local selection and global selection. In the local selection, a model of the world and of the human’s mind is constructed in form of hypothetical fragments of activities (pieces of evidences) by considering a set of observations. These hypothetical fragments have two kinds of relations: a conflict relation and a temporal relation. Based on these relations, the argumentation attack notion is defined. We define two forms of attacks namely the strong and the weak attack. The former has the same characteristics of attacks in TAF whereas for the latter the TAF approach has to be extended. For determining consistent sets of hypothetical fragments, that are part of an activity or are part of a set of non-conflicting activities, extension-based argumentation semantics are applied. In the global selection, the degrees of fulfillment of activities is determined. We study some properties of our approach and apply it to a scenario where a human performs activities with different temporal relations.

Enabling Morally Sensitive Robotic Clarification Requests

The design of current natural language-oriented robot architectures enables certain architectural components to circumvent moral reasoning capabilities. One example of this is reflexive generation of clarification requests as soon as referential ambiguity is detected in a human utterance. As shown in previous research, this can lead robots to (1) miscommunicate their moral dispositions and (2) weaken human perception or application of moral norms within their current context. We present a solution to these problems by performing moral reasoning on each potential disambiguation of an ambiguous human utterance and responding accordingly, rather than immediately and naively requesting clarification. We implement our solution in the Distributed Integrated Cognition Affect and Reflection robot architecture, which, to our knowledge, is the only current robot architecture with both moral reasoning and clarification request generation capabilities. We then evaluate our method with a human subjects experiment, the results of which indicate that our approach successfully ameliorates the two identified concerns.

Effectiveness of model ASEAN meeting in enhancing critical thinking: a Colombia case study

ABSTRACT This Article analyses the effectiveness of Simulation-Based Learning Model ASEAN Meeting in enhancing critical thinking skills and academic performance compared to the conventional teaching method among 216 International Relations undergraduate students on the north coast of Colombia. A t–student test, Welch test, and the Kendall Tau correlation coefficient were used to analyses the perceptions and academic performance from 216 undergraduate Asia Pacific Politics courses for two years. A pre-test, post-test, and achievement of academic objectives questionnaire were applied, as well as a verification test of previous knowledge and focus groups at the end of the courses. It was found that simulations fostered an inquiry-based attitude to represent a countrýs agenda not achieved through the conventional method, thus enhancing deductive and inductive reasoning, recognizing assumptions, and drawing inferences capabilities.

An ontological modelling of multi-attribute criticality analysis to guide Prognostics and Health Management program development

Digital technologies are becoming more pervasive and industrial companies are exploiting them to enhance the potentialities related to Prognostics and Health Management (PHM). Indeed, PHM allows to evaluate the health state of the physical assets as well as to predict their future behaviour. To be effective in developing PHM programs, the most critical assets should be identified so to direct modelling efforts. Several techniques could be adopted to evaluate asset criticality; in industrial practice, criticality analysis is amongst the most utilised. Despite the advancement of artificial intelligence for data analysis and predictions, the criticality analysis, which is built upon both quantitative and qualitative data, has not been improved accordingly. It is the goal of this work to propose an ontological formalisation of a multi-attribute criticality analysis in order to i) fix the semantics behind the terms involved in the analysis, ii) standardize and uniform the way criticality analysis is performed, and iii) take advantage of the reasoning capabilities to automatically evaluate asset criticality and associate a suitable maintenance strategy. The developed ontology, called MOCA, is tested in a food company featuring a global footprint. The application shows that MOCA can accomplish the prefixed goals; specifically, high priority assets towards which direct PHM programs are identified. In the long run, ontologies could serve as a unique knowledge base that integrate multiple data and information across facilities in a consistent way. As such, they will enable advanced analytics to take place, allowing to move towards cognitive Cyber Physical Systems that enhance business performance for companies spread worldwide.

The delay and window size problems in rule-based stream reasoning

In recent years, there has been an increasing interest in extending stream processing engines with rule-based temporal reasoning capabilities. To ensure correctness, such systems must be able to output results over the partial data received so far as if the entire (infinite) stream had been available; furthermore, these results must be streamed out as soon as the relevant data is received, thus incurring the minimum possible delay; finally, due to memory limitations, systems can only keep a limited history of previous facts in memory to perform further computations. These requirements pose significant theoretical and practical challenges since temporal rules can derive new information and propagate it both towards past and future time points; as a result, streamed answers can depend on data that has not yet been received, as well as on data that arrived far in the past. Towards developing a solid foundation for practical rule-based stream reasoning, we propose and study in this paper a suite of decision problems that can be exploited by stream reasoning algorithms to tackle the aforementioned challenges, and provide tight complexity bounds for a core temporal extension of Datalog. All of the problems we consider can be solved at design time (under reasonable assumptions), prior to the processing of any data. Solving these problems enables the use of reasoning algorithms that process the input streams incrementally using a sliding window, while at the same time supporting an expressive rule-based knowledge representation language and minimising both latency and memory consumption.

Evaluating the Clinical Reasoning of Student Health Professionals in Placement and Simulation Settings: A Systematic Review.

(1) Background: Clinical reasoning is essential to the effective practice of autonomous health professionals and is, therefore, an essential capability to develop as students. This review aimed to systematically identify the tools available to health professional educators to evaluate students’ attainment of clinical reasoning capabilities in clinical placement and simulation settings. (2) Methods: A systemic review of seven databases was undertaken. Peer-reviewed, English-language publications reporting studies that developed or tested relevant tools were included. Searches included multiple terms related to clinical reasoning and health disciplines. Data regarding each tool’s conceptual basis and evaluated constructs were systematically extracted and analysed. (3) Results: Most of the 61 included papers evaluated students in medical and nursing disciplines, and over half reported on the Script Concordance Test or Lasater Clinical Judgement Rubric. A number of conceptual frameworks were referenced, though many papers did not reference any framework. (4) Conclusions: Overall, key outcomes highlighted an emphasis on diagnostic reasoning, as opposed to management reasoning. Tools were predominantly aligned with individual health disciplines and with limited cross-referencing within the field. Future research into clinical reasoning evaluation tools should build on and refer to existing approaches and consider contributions across professional disciplinary divides.

A decision support engine for infill drilling attractiveness evaluation using rule-based cognitive computing under expert uncertainties

Optimally drilling new wells in a developed reservoir is an essential strategy to potentially tap remaining oil for a complete life circle of oilfield development. Further, the determination of optimal infill drilling targets is a challenging issue which involves the integration of data, experts' knowledge and human decisions. The decision process can be essentially regarded as a systematic evaluation of drilling attractiveness. To automate drilling attractiveness evaluation, we develop a decision support engine using rule-based cognitive computing to rank and recommend drilling candidates. Such drilling candidates are chosen by the quantification of regional drilling attractiveness. Then we use two cases with different settings to show its general applicability and human-like reasoning abilities. The reasoning process considers expertise and human-involved uncertainties. The expertise is characterized by certain representation of fuzzy rules sets. Our results highlight the potential of our recommendation engine in pinpointing the most productive drilling location. And our method avoids the expensive reservoir simulation runs. Moreover, fuzzy drilling attractiveness evaluation can serve as an alternative initialization method of model-based infill well optimization, which avoids local optimum problem and greatly saves iteration time. Our approach extends human's reasoning capability and accelerates human's decision-making process with very low computational cost.

Relation Matters: Foreground-Aware Graph-Based Relational Reasoning for Domain Adaptive Object Detection.

Domain Adaptive Object Detection (DAOD) focuses on improving the generalization ability of object detectors via knowledge transfer. Recent advances in DAOD strive to change the emphasis of the adaptation process from global to local in virtue of fine-grained feature alignment methods. However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected. In this case, only seeking one-vs-one alignment does not necessarily ensure the precise knowledge transfer. Moreover, conventional alignment-based approaches may be vulnerable to catastrophic overfitting regarding those less transferable regions (e.g., backgrounds) due to the accumulation of inaccurate localization results in the target domain. To remedy these issues, we first formulate DAOD as an open-set domain adaptation problem, in which the foregrounds and backgrounds are seen as the "known classes" and "unknown class" respectively. Accordingly, we propose a new and general framework for DAOD, named Foreground-aware Graph-based Relational Reasoning (FGRR), which incorporates graph structures into the detection pipeline to explicitly model the intra- and inter-domain foreground object relations on both pixel and semantic spaces, thereby endowing the DAOD model with the capability of relational reasoning beyond the popular alignment-based paradigm. FGRR first identifies the foreground pixels and regions by searching reliable correspondence and cross-domain similarity regularization respectively. The inter-domain visual and semantic correlations are hierarchically modeled via bipartite graph structures, and the intra-domain relations are encoded via graph attention mechanisms. Through message-passing, each node aggregates semantic and contextual information from the same and opposite domain to substantially enhance its expressive power. Empirical results demonstrate that the proposed FGRR exceeds the state-of-the-art performance on four DAOD benchmarks.

WEB PAGE RECOMMENDATION SYSTEM BY INTEGRATING ONTOLOGY AND STEMMING ALGORITHM

In this research, we offer a customized-recommendation system that uses item representations and user profiles based on the ontologies that provide personalized services to semantic applications. To develop and implement the personalized-recommendation system, a system that uses the representations of the items and the user profiles based on the ontologies to provide the semantic applications with personalized services. Recommendation systems can use semantic reasoning capabilities to overcome present system limits and increase the quality of recommendations. The recommender makes use of domain ontologies to improve personalization: on the one hand, a domain-based inference method is used to model user interests more effectively and accurately; on the other hand, a semantic similarity method is used to improve the stemmer algorithm, which is used by our content-based filtering approach, which provides a measure of the affinity between an item and the user. In recommender systems and web personalization, Web Usage Mining is crucial. This study presents an effective recommender system based on ontology and web usage mining. The approach's first step is to extract features from online documents and build on related ideas. Then, they create an ontology for the website using the concepts and relevant terms retrieved from the records. The semantic similarity of web documents is used to group them into multiple semantic themes, each with its own set of preferences. The suggested solution incorporates ontology and semantic knowledge into Web Usage Mining and personalization procedures, as well as a stemming algorithm, and gets an overall accuracy of 90%.

A fuzzy based sustainability assessment tool for small island states

The global change between human activities and the natural environment has evolved with technological growth and economic development. Due to their size and small population, small island states have become the most vulnerable to these irreversible changes. These have raised the importance for taking some initiatives for human benefits, economic welfare and environmental protection. Sustainable practices and performance measurement are important for these small island states. The purpose of this paper was to develop a quantitative modelling tool to measure sustainability performance for small island states while considering the three sustainability spheres namely environment, economic and social in an integrated manner. A Sustainability Assessment Tool for Small Island States (SATIS) was developed based on a fuzzy methodological approach which used sustainability indicators for the three dimensions. The research began by identifying the indicators for Mauritius island which were then selected according to their level of importance for this research study through an expert survey. Data was then collected and applied to the proposed model. A Sensitivity analysis was conducted in order to stress on the most influencing factors that were affecting the overall system. The model was then validated using recent data. It was observed that fuzzy logic approach has shown great reasoning capabilities which traditional mathematical tools failed to produce. The fuzzy based methodological approach was found to be a remarkable tool for monitoring sustainability performance in small island states. To conclude, this model is recommended for sustainability assessment. Practitioners can apply this modelling technique to track sustainability performance of Small Island Developing States (SIDS).

Human-Computer Interaction Environment Monitoring and Collaborative Translation Mode Exploration Using Artificial Intelligence Technology.

Artificial intelligence now plays a significant role in both daily life and scientific research because of the rapid advancement of this technology in recent years. Making full use of the phrases in the translation phrase table for translation is challenging since the phrase matching is too accurate when the translation machine decodes. Fully automatic machine translation struggles to meet the expectations of its users since there are more or less translation faults brought on by data bottlenecks. Therefore, we require collaborative assisted translation technology for human-computer interaction. This work strengthens the research on collaborative translation techniques and ways for monitoring the human-computer interaction environment in order to further improve translation quality. This essay investigates and discusses human-computer translation techniques as well as related ideas in collaborative translation and human-computer interaction. The translation similarity model is incorporated into the translation system model together with an overall qualitative knowledge and logical reasoning capability of human-computer interaction to offer fresh strategies and methods for collaborative translation between humans and computers. According to the experimental findings, the accuracy rate of the collaborative translation system for human-computer interaction based on artificial intelligence technology can achieve 98.2% and 95.6%. The quality of the translation is enhanced after human-computer interaction, and the editing gap between the incorrect and auxiliary translations is narrowed, demonstrating the efficiency of the system and demonstrating its viability. In order to enhance the accuracy of system translation and the effectiveness of system operation, it is important to investigate the collaborative translation mode of human-computer interaction based on artificial intelligence technology.

Variational Deep Logic Network for Joint Inference of Entities and Relations

AbstractCurrently, deep learning models have been widely adopted and achieved promising results on various application domains. Despite their intriguing performance, most deep learning models function as black boxes, lacking explicit reasoning capabilities and explanations, which are usually essential for complex problems. Take joint inference in information extraction as an example. This task requires the identification of multiple structured knowledge from texts, which is inter-correlated, including entities, events, and the relationships between them. Various deep neural networks have been proposed to jointly perform entity extraction and relation prediction, which only propagate information implicitly via representation learning. However, they fail to encode the intensive correlations between entity types and relations to enforce their coexistence. On the other hand, some approaches adopt rules to explicitly constrain certain relational facts, although the separation of rules with representation learning usually restrains the approaches with error propagation. Moreover, the predefined rules are inflexible and might result in negative effects when data is noisy. To address these limitations, we propose a variational deep logic network that incorporates both representation learning and relational reasoning via the variational EM algorithm. The model consists of a deep neural network to learn high-level features with implicit interactions via the self-attention mechanism and a relational logic network to explicitly exploit target interactions. These two components are trained interactively to bring the best of both worlds. We conduct extensive experiments ranging from fine-grained sentiment terms extraction, end-to-end relation prediction, to end-to-end event extraction to demonstrate the effectiveness of our proposed method.

Explainable activity recognition in videos: Lessons learned

AbstractWe consider the following activity recognition task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. This task can be solved using modern deep learning architectures based on neural networks or conventional classifiers such as linear models and decision trees. While neural networks exhibit superior predictive performance as compared with decision trees and linear models, they are also uninterpretable and less explainable. We address thisaccuracy‐explanability gapusing a novel framework that feeds the output of a deep neural network to an interpretable, tractable probabilistic model called dynamic cutset networks, and performs joint reasoning over the two to answer questions. The neural network helps achieve high accuracy while dynamic cutset networks because of their polytime probabilistic reasoning capabilities make the system more explainable. We demonstrate the efficacy of our approach by using it to build three prototype systems that solve human‐machine tasks having varying levels of difficulty using cooking videos as an accessible domain. We describe high‐level technical details and key lessons learned in our human subjects evaluations of these systems.

A computational model of argumentation schemes for multi-agent systems

There are many benefits of using argumentation-based techniques in multi-agent systems, as clearly shown in the literature. Such benefits come not only from the expressiveness that argumentation-based techniques bring to agent communication but also from the reasoning and decision-making capabilities under conditions of conflicting and uncertain information that argumentation enables for autonomous agents. When developing multi-agent applications in which argumentation will be used to improve agent communication and reasoning, argumentation schemes (reasoning patterns for argumentation) are useful in addressing the requirements of the application domain in regards to argumentation (e.g., defining the scope in which argumentation will be used by agents in that particular application). In this work, we propose an argumentation framework that takes into account the particular structure of argumentation schemes at its core. This paper formally defines such a framework and experimentally evaluates its implementation for both argumentation-based reasoning and dialogues.

Model-Based Reasoning in the Deductive Laboratory Work with Arduino and Sensor Module

Laboratory work that has been applied so far is more dominant in deductive laboratory work, but this type of laboratory work is not optimal in stimulating students' reasoning ability. Up to now, model-based reasoning studies on laboratory work have been substantial (especially in measurement and troubleshooting activities) and have not seen overall laboratory activity, including the use of alternative instrumentation such as Arduino and its sensor module. Designing the best laboratory work requires the role of model-based reasoning studies using Arduino devices. A mixed-method research design was used in this study with a theoretical study to obtain a predictive pattern for deductive laboratory work model which was matched with the observations of 50 undergraduate physics education students in laboratory work. Revision activities were shown by students in laboratory work depending on the capabilities of reasoning. The results of this study indicate that revision activities in deductive laboratory work using Arduino can stimulate students' reasoning. Arduino can lead students to explore their thinking and reasoning to solve problems in laboratory work.

Ontology-based modelling of lifecycle underground utility information to support operation and maintenance

Operation and maintenance (O&M) of underground utilities is crucial to ensure normal functionality of utilities by performing different inspection and maintenance activities. A variety of data are required by maintenance staff to evaluate utility condition and make decisions in planning maintenance works. Nevertheless, data required for utility O&M are usually originated from different sources, with various formats or representations. Interpreting and integrating such heterogenous data for utility O&M remains a significant challenge. Therefore, this paper proposes an ontology-based framework for modelling lifecycle utility information such as to facilitate activities and support decision making during utility O&M. The framework consists of (1) a data layer to collect various types of utility lifecycle data, (2) a knowledge layer to extract common mechanisms and methods for utility O&M, (3) an ontology layer where a domain ontology, Utility Operation and Maintenance Ontology (UOMO), is developed with entities and semantic rules to represent different categories of information related to utility projects, (4) an application layer to automate manual tasks and support decision making by leveraging the query and reasoning capability of ontology. To validate the framework, a case study is performed using real-world inspection data where a user interface is developed to allow users to implement different functions without technical knowledge. The case study demonstrates that the framework can, efficiently and automatically, extract and integrate various information to assist different activities, e.g. defect rating, condition assessment and validation, as well as to support decision making in prioritizing maintenance works, and selecting appropriate maintenance methods. This study contributes by proposing the first ontology-based framework for improving efficiency in utility O&M, where the query and semantic reasoning capabilities of the ontology are fully utilized. The developed ontology with lifecycle utility information is expected to facilitate data interoperability in the utility domain and can be extended with other knowledge for large-scale infrastructure management.