Human Expert Knowledge Research Articles

The Next Generation of Medical Decision Support: A Roadmap Toward Transparent Expert Companions.

Increasing quality and performance of artificial intelligence (AI) in general and machine learning (ML) in particular is followed by a wider use of these approaches in everyday life. As part of this development, ML classifiers have also gained more importance for diagnosing diseases within biomedical engineering and medical sciences. However, many of those ubiquitous high-performing ML algorithms reveal a black-box-nature, leading to opaque and incomprehensible systems that complicate human interpretations of single predictions or the whole prediction process. This puts up a serious challenge on human decision makers to develop trust, which is much needed in life-changing decision tasks. This paper is designed to answer the question how expert companion systems for decision support can be designed to be interpretable and therefore transparent and comprehensible for humans. On the other hand, an approach for interactive ML as well as human-in-the-loop-learning is demonstrated in order to integrate human expert knowledge into ML models so that humans and machines act as companions within a critical decision task. We especially address the problem of Semantic Alignment between ML classifiers and its human users as a prerequisite for semantically relevant and useful explanations as well as interactions. Our roadmap paper presents and discusses an interdisciplinary yet integrated Comprehensible Artificial Intelligence (cAI)-transition-framework with regard to the task of medical diagnosis. We explain and integrate relevant concepts and research areas to provide the reader with a hands-on-cookbook for achieving the transition from opaque black-box models to interactive, transparent, comprehensible and trustworthy systems. To make our approach tangible, we present suitable state of the art methods with regard to the medical domain and include a realization concept of our framework. The emphasis is on the concept of Mutual Explanations (ME) that we introduce as a dialog-based, incremental process in order to provide human ML users with trust, but also with stronger participation within the learning process.

Computer Vision and Deep Learning Techniques for the Analysis of Drone-Acquired Forest Images, a Transfer Learning Study

Unmanned Aerial Vehicles (UAV) are becoming an essential tool for evaluating the status and the changes in forest ecosystems. This is especially important in Japan due to the sheer magnitude and complexity of the forest area, made up mostly of natural mixed broadleaf deciduous forests. Additionally, Deep Learning (DL) is becoming more popular for forestry applications because it allows for the inclusion of expert human knowledge into the automatic image processing pipeline. In this paper we study and quantify issues related to the use of DL with our own UAV-acquired images in forestry applications such as: the effect of Transfer Learning (TL) and the Deep Learning architecture chosen or whether a simple patch-based framework may produce results in different practical problems. We use two different Deep Learning architectures (ResNet50 and UNet), two in-house datasets (winter and coastal forest) and focus on two separate problem formalizations (Multi-Label Patch or MLP classification and semantic segmentation). Our results show that Transfer Learning is necessary to obtain satisfactory outcome in the problem of MLP classification of deciduous vs evergreen trees in the winter orthomosaic dataset (with a 9.78% improvement from no transfer learning to transfer learning from a a general-purpose dataset). We also observe a further 2.7% improvement when Transfer Learning is performed from a dataset that is closer to our type of images. Finally, we demonstrate the applicability of the patch-based framework with the ResNet50 architecture in a different and complex example: Detection of the invasive broadleaf deciduous black locust (Robinia pseudoacacia) in an evergreen coniferous black pine (Pinus thunbergii) coastal forest typical of Japan. In this case we detect images containing the invasive species with a 75% of True Positives (TP) and 9% False Positives (FP) while the detection of native trees was 95% TP and 10% FP.

Mobile robot automatic navigation control algorithm based on fuzzy neural network in industrial Internet of things environment

Mobile robot is an important developing direction in the field of robotics, it is widely used in Industrial Internet of Things (IIoT) environment, agriculture, military, transportation, services with the coming of 5G wireless communication technology. Automatic navigation control technology is the core in these research areas, which is also the key technology for mobile robot to achieve intelligentization and autonomation.The article discusses and researches the neural network technology and its application in mobile robot navigation control. For the characteristics and research of mobile robot navigation problem, it finds the way to improve the mobile robot intelligentization, level of the self-organization, self-learning and adaptive capability. The combination of neural network with other intelligent algorithms solves autonomous navigation problem of the mobile robot in the complex uncertain environments and unknown variable environments. The mobile robot navigation control problem using fuzzy neural network can achieve a more effective real-time navigation control performance through amending the network weights by self-study according to the navigation priori knowledge of human experts.

Mutation effect estimation on protein–protein interactions using deep contextualized representation learning

The functional impact of protein mutations is reflected on the alteration of conformation and thermodynamics of protein–protein interactions (PPIs). Quantifying the changes of two interacting proteins upon mutations is commonly carried out by computational approaches. Hence, extensive research efforts have been put to the extraction of energetic or structural features on proteins, followed by statistical learning methods to estimate the effects of mutations on PPI properties. Nonetheless, such features require extensive human labors and expert knowledge to obtain, and have limited abilities to reflect point mutations. We present an end-to-end deep learning framework, MuPIPR (Mutation Effects in Protein–protein Interaction PRediction Using Contextualized Representations), to estimate the effects of mutations on PPIs. MuPIPR incorporates a contextualized representation mechanism of amino acids to propagate the effects of a point mutation to surrounding amino acid representations, therefore amplifying the subtle change in a long protein sequence. On top of that, MuPIPR leverages a Siamese residual recurrent convolutional neural encoder to encode a wild-type protein pair and its mutation pair. Multi-layer perceptron regressors are applied to the protein pair representations to predict the quantifiable changes of PPI properties upon mutations. Experimental evaluations show that, with only sequence information, MuPIPR outperforms various state-of-the-art systems on estimating the changes of binding affinity for SKEMPI v1, and offers comparable performance on SKEMPI v2. Meanwhile, MuPIPR also demonstrates state-of-the-art performance on estimating the changes of buried surface areas. The software implementation is available at https://github.com/guangyu-zhou/MuPIPR.

Proposal of an Architecture for the Integration of a Chatbot with Artificial Intelligence in a Smart Campus for the Improvement of Learning

Traditional teaching based on masterclasses or techniques where the student develops a passive role has proven to be inefficient methods in the learning process. The use of technology in universities helps to generate active learning where the student’s interest improves making him the main actor in his education. However, implementing an environment where active learning takes place requires a great deal of effort given the number of variables involved in this objective. To identify these variables, it is necessary to analyze the data generated by the students in search of patterns that allow them to be classified according to their needs. Once these needs are identified, it is possible to make decisions that contribute to the learning of each student; for this, the use of artificial intelligence is considered. These techniques emulate the processes of human thought using structures that contain knowledge and experience of human experts.

Deep learning-based cross-domain adaptation for gearbox fault diagnosis under variable speed conditions

Existing intelligent gearbox fault diagnosis approaches have two shortcomings: (a) their performance is mostly confined to manual handcrafted features, and (b) they follow a general assumption that the distribution of the data in the source domain (labeled data on which the model is trained) is similar to the target domain (unlabeled data on which the model is tested), which might not be the case in real-world applications. Substantial human expertise and domain knowledge is required for manual feature extraction, and moreover, deploying the same model for a target domain whose distribution is different from the source domain would lead to poor generalization. Since deep learning methods can automatically learn high dimensional feature representations from raw measurement data, this paper proposes a novel deep learning-based domain adaptation (DA) method for gearbox fault diagnosis under significant speed variations. A deep convolutional neural network is used as the main architecture. The paper proposes to minimize the summation of cross-entropy loss (between the labeled source domain data) and maximum mean discrepancy loss (between the labeled source and unlabeled target datasets) simultaneously to adapt the source domain model to be applied in the target domain. The proposed deep learning DA approach is evaluated using experimental data from a gearbox under variable speeds and multiple health conditions. An appropriate benchmarking with both traditional machine learning methods and other DA methods demonstrate the superiority of the proposed method.

Identification of Li-ion battery models through monotonic echo serial networks for coarse data

Abstract Monotone transformation models are extended to inaccurate data and are combined with recurrent neural networks in a new battery model that is able to ascertain the health of rechargeable batteries for automotive applications. The presented method exploits the information contained in the vehicle’s operational records better than other cutting-edge models and uses a minimum amount of human expert knowledge. The experimental validation of the technique includes a comparative analysis of batteries in different health conditions, comprising first-principles models and different machine learning procedures.

Identification of Synthetic Activators of Cancer Cell Migration by Hybrid Deep Learning.

Deep convolutional neural networks (CNNs) are a method of choice for image recognition. Herein a hybrid CNN approach is presented for molecular pattern recognition in drug discovery. Using self-organizing map images of molecular pharmacophores as input, CNN models were trained to identify chemokine receptor CXCR4 modulators with high accuracy. This machine learning classifier identified first-in-class synthetic CXCR4 full agonists. The receptor-activating effects were confirmed by intracellular cAMP response and in a phenotypic spheroid invasion assay of medulloblastoma cell invasion. Additional macromolecular targets of the small molecules were predicted in silico and tested in vitro, revealing modulatory effects on dopamine receptors and CCR1. These results positively advocate the applicability of molecular image recognition by CNNs to ligand-based virtual compound screening, and demonstrate the complementarity of machine intelligence and human expert knowledge.

Finger-Vein Quality Assessment Based on Deep Features From Grayscale and Binary Images

Finger-vein verification is a highly secure biometric authentication that has been widely investigated over the last years. One of its challenges, however, is the possible degradation of image quality, that results in spurious and missing vein patterns, which increases the verification error. Despite recent advances in finger-vein quality assessment, the proposed solutions are limited as they depend on human expertise and domain knowledge to extract handcrafted features for assessing quality. We have proposed, recently, the first deep neural network (DNN) framework for assessing finger-vein quality, that does not require manual labeling of high and low quality images, as is the case for state of the art methods, but infers such annotations automatically based on an objective indicator, the biometric verification decision. This framework has significantly outperformed the existing methods, whether the input image is in grayscale or is binary. Motivated by these performances, we propose, in this work, a representation learning of finger vein image quality, where a DNN takes as input conjointly the grayscale and binary versions of the input image to predict vein quality. Our model allows to learn the joint representation from grayscale and binary images, for quality assessment. The experimental results, obtained on a large public dataset, demonstrates that our proposed method accurately identifies high and low quality images, and outperforms other techniques in terms of equal error rate (EER) minimization, including our previous DNN models, based either on grayscale or binary input.

A Rule-Based Approach Founded on Description Logics for Industry 4.0 Smart Factories

This paper develops a formal framework, founded on description logics, to assist decision making in relation to the manufacturing operation and control in modern enterprises that stand to benefit from the transition to Industry 4.0. The objective is to provide sophisticated support to individuals making decisions in the area of production operations management and in particular, production scheduling and material requirements planning. Using this framework, this paper demonstrates an approach to encode the domain knowledge of human experts managing the production as sets of formal rules. These rules can be implemented in an intelligent system that can assist and empower human experts, reducing difficulty when making decisions in complex manufacturing environments.

Active semi-supervised overlapping community finding with pairwise constraints

Algorithms for finding communities in complex networks are generally unsupervised, relying solely on the structure of the network. However, these methods can often fail to uncover meaningful groupings that reflect the underlying communities in the data, particularly when they are highly overlapping. One way to improve these algorithms is by incorporating human expertise or background knowledge in the form of pairwise constraints to direct the community detection process. In this work, we explore the potential of semi-supervised strategies to improve algorithms for finding overlapping communities in networks. We propose a method, based on label propagation, for finding communities using pairwise constraints. Furthermore, we introduce a new strategy, inspired by active learning, for intelligent constraint selection, which is designed to minimize the level of human annotation required. Extensive evaluations on synthetic and real-world datasets demonstrate the potential of this strategy for effectively uncovering meaningful overlapping community structures, using a limited amount of supervision.

Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases.

An application of explainable artificial intelligence on medical data is presented. There is an increasing demand in machine learning literature for such explainable models in health-related applications. This work aims to generate explanations on how a Convolutional Neural Network (CNN) detects tumor tissue in patches extracted from histology whole slide images. This is achieved using the “locally-interpretable model-agnostic explanations” methodology. Two publicly-available convolutional neural networks trained on the Patch Camelyon Benchmark are analyzed. Three common segmentation algorithms are compared for superpixel generation, and a fourth simpler parameter-free segmentation algorithm is proposed. The main characteristics of the explanations are discussed, as well as the key patterns identified in true positive predictions. The results are compared to medical annotations and literature and suggest that the CNN predictions follow at least some aspects of human expert knowledge.

Automatic and Semantically-Aware 3D UAV Flight Planning for Image-Based 3D Reconstruction

Small-scaled unmanned aerial vehicles (UAVs) emerge as ideal image acquisition platforms due to their high maneuverability even in complex and tightly built environments. The acquired images can be utilized to generate high-quality 3D models using current multi-view stereo approaches. However, the quality of the resulting 3D model highly depends on the preceding flight plan which still requires human expert knowledge, especially in complex urban and hazardous environments. In terms of safe flight plans, practical considerations often define prohibited and restricted airspaces to be accessed with the vehicle. We propose a 3D UAV path planning framework designed for detailed and complete small-scaled 3D reconstructions considering the semantic properties of the environment allowing for user-specified restrictions on the airspace. The generated trajectories account for the desired model resolution and the demands on a successful photogrammetric reconstruction. We exploit semantics from an initial flight to extract the target object and to define restricted and prohibited airspaces which have to be avoided during the path planning process to ensure a safe and short UAV path, while still aiming to maximize the object reconstruction quality. The path planning problem is formulated as an orienteering problem and solved via discrete optimization exploiting submodularity and photogrammetrical relevant heuristics. An evaluation of our method on a customized synthetic scene and on outdoor experiments suggests the real-world capability of our methodology by providing feasible, short and safe flight plans for the generation of detailed 3D reconstruction models.

Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series

We propose a combined method that is based on the fuzzy time series (FTS) and convolutional neural networks (CNN) for short-term load forecasting (STLF). Accordingly, in the proposed method, multivariate time series data which include hourly load data, hourly temperature time series and fuzzified version of load time series, was converted into multi-channel images to be fed to a proposed deep learning CNN model with proper architecture. By using images which have been created from the sequenced values of multivariate time series, the proposed CNN model could determine and extract related important parameters, in an implicit and automatic way, without any need for human interaction and expert knowledge, and all by itself. By following this strategy, it was shown how employing the proposed method is easier than some traditional STLF models. Therefore it could be seen as one of the big difference between the proposed method and some state-of-the-art methodologies of STLF. Moreover, using fuzzy logic had great contribution to control over-fitting by expressing one dimension of time series by a fuzzy space, in a spectrum, and a shadow instead of presenting it with exact numbers. Various experiments on test data-sets support the efficiency of the proposed method.

Picture Fuzzy Petri Nets for Knowledge Representation and Acquisition in Considering Conflicting Opinions

Fuzzy Petri nets (FPNs) have been applied in many fields as a potential modeling tool for knowledge representation and reasoning. However, there exist many deficiencies in the conventional FPNs when applied in the real world. In this paper, we present a new type of FPN, called picture fuzzy Petri nets (PFPNs), to overcome the shortcomings and improve the effectiveness of the traditional FPNs. First, the proposed PFPN model adopts the picture fuzzy sets (PFSs), characterized by degrees of positive membership, neutral membership, and negative membership, to depict human expert knowledge. As a result, the uncertainty, due to vagueness, imprecision, partial information, etc., can be well-handled in knowledge representation. Second, a similarity degree-based expert weighting method is offered for consensus reaching processes in knowledge acquisition. The proposed PFPN model can manage the conflicts and inconsistencies among expert evaluations in knowledge parameters, thus, making the obtained knowledge rules more accurate. Finally, a realistic example of a gene regulatory network is provided to illustrate the feasibility and practicality of the proposed PFPN model.

Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions

Incipient fault diagnosis of a bearing requires robust feature representation for an accurate condition-based monitoring system. Existing fault diagnosis schemes are mostly confined to manual features and traditional machine learning approaches such as artificial neural networks (ANN) and support vector machines (SVM). These handcrafted features require substantial human expertise and domain knowledge. In addition, these feature characteristics vary with the bearing’s rotational speed. Thus, such methods do not yield the best results under variable speed conditions. To address this issue, this paper presents a reliable fault diagnosis scheme based on acoustic spectral imaging (ASI) of acoustic emission (AE) signals as a precise health state. These health states are further utilized with transfer learning, which is a machine learning technique, which shares knowledge with convolutional neural networks (CNN) for accurate diagnosis under variable operating conditions. In ASI, the amplitudes of the spectral components of the windowed time-domain acoustic emission signal are transformed into spectrum imaging. ASI provides a visual representation of acoustic emission spectral features in images. This ensures enhanced spectral images for transfer learning (TL) testing and training, and thus provides a robust classifier technique with high diagnostic accuracy.

Application of Self-Organizing Neural Networks to Electrical Fault Classification in Induction Motors

Electrical winding faults, namely stator short-circuits and rotor bar damage, in total constitute around 50% of all faults of induction motors (IMs) applied in variable speed drives (VSD). In particular, the short circuits of stator windings are recognized as one of the most difficult failures to detect because their detection makes sense only at the initial stage of the damage. Well-known symptoms of stator and rotor winding failures can be visible in the stator current spectra; however, the detection and classification of motor windings faults usually require the knowledge of human experts. Nowadays, artificial intelligence methods are also used in fault recognition. This paper presents the results of experimental research on the application of the stator current symptoms of the converter-fed induction motor drive to electrical fault detection and classification using Kohonen neural networks. The experimental tests of a diagnostic setup based on a virtual measurement and data pre-processing system, designed in LabView, are described. It has been shown that the developed neural detectors and classifiers based on self-organizing Kohonen maps, trained with the instantaneous symmetrical components of the stator current spectra (ISCA), enable automatic distinguishing between the stator and rotor winding faults for supplying various voltage frequencies and load torque values.

Modelo de sistema de inferência Fuzzy baseado em matrizes de probabilidade e impacto para classificar riscos em projetos

Projects are essential for organizations to implement their strategies and the success of the projects is crucial for organizations. However, in a context of uncertainties, it is necessary to address risks that threaten this success, allocating resources for its prevention. To decide how to prioritize them and allocate resources, Probability and Impact Matrices (MPIs)are used. MPIs are built with the employment of a human expert, usually the project manager. Although popular, MPIs may have shortcomings, for example, analyzing inaccurate information from the human expert's knowledge and the inability to rank characteristic risks when using discrete classes. Thus, the use of Fuzzy Inference Systems (SIF) in an MPI would allow to address these deficiencies by modeling human knowledge reducing its uncertainty. A general objective of this work was to develop a Fuzzy Inference System based on MPIs to classify risks in projects. In order to reach this objective, we conducted experiments in five stages: (I) Generation of the database containing probability, impact and risk values, varying the correlation between probability-impact, (II) Classification of MPI Conventional and MPI proposed by Cox (2008), (III) Implementation of SIF based on Phase II MPIs rules, (IV) Application of SIF and (V) Analysis of results. It was verified that the SIF model is advantageous, compared to the conventional MPI, allowing the classification of the risks in a continuous scale, which facilitates the prioritization and allocation of resources and the reduction of uncertainty allowing to classify risks in projects.

Design of Fuzzy Logic Controller and its Distinctive Feature

Prof. Lotfi A. Zadeh, who created a new approach to describe a knowledge of a human expert with a natural language, passed away on September 6, 2017. His significant accomplishment was to create a novel artificial intelligence (AI) which exhibits the knowledge of human experts in natural linguistic terms. This system is structured and clear in two points of why a result is obtained and how it is done. The system contrasts with AI systems based on neural networks or deep learning. In this paper, the design of a fuzzy logic controller and its application to controlling of the mouse-platform stabilization are described. In addition, the distinctive features of fuzzy logic control are discussed. The author wants to offer this paper on the altar of Prof. Zadeh.

Review of Deep Learning Methods in Robotic Grasp Detection

For robots to attain more general-purpose utility, grasping is a necessary skill to master. Such general-purpose robots may use their perception abilities to visually identify grasps for a given object. A grasp describes how a robotic end-effector can be arranged to securely grab an object and successfully lift it without slippage. Traditionally, grasp detection requires expert human knowledge to analytically form the task-specific algorithm, but this is an arduous and time-consuming approach. During the last five years, deep learning methods have enabled significant advancements in robotic vision, natural language processing, and automated driving applications. The successful results of these methods have driven robotics researchers to explore the use of deep learning methods in task-generalised robotic applications. This paper reviews the current state-of-the-art in regards to the application of deep learning methods to generalised robotic grasping and discusses how each element of the deep learning approach has improved the overall performance of robotic grasp detection. Several of the most promising approaches are evaluated and the most suitable for real-time grasp detection is identified as the one-shot detection method. The availability of suitable volumes of appropriate training data is identified as a major obstacle for effective utilisation of the deep learning approaches, and the use of transfer learning techniques is proposed as a potential mechanism to address this. Finally, current trends in the field and future potential research directions are discussed.