ARTICLE | doi:10.20944/preprints202011.0451.v1
Subject: Mathematics & Computer Science, Algebra & Number Theory Keywords: Explainable AI; Cluster Analysis; Swarm Intelligence; Machine Learning System; High-Dimensional Data Visualization; Decision Trees
Online: 17 November 2020 (14:01:33 CET)
The understanding of water quality and its underlying processes is important for the protection of aquatic environments enabling the rare opportunity of access to a domain expert. Hence, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series resulting in explanations that are interpretable by a domain expert. The XAI combines in three steps a data-driven choice of a distance measure with explainable cluster analysis through supervised decision trees. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The XAI does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two comparable decision-based XAIs were unable to provide meaningful and relevant explanations from the multivariate time series data. Open-source code in R for the three steps of the XAI framework is provided.
ARTICLE | doi:10.20944/preprints202208.0387.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: explainable artificial intelligence; high-level explainable feature; entropy; plant stress; early diagnosis
Online: 22 August 2022 (15:47:02 CEST)
The article is devoted to solving the problem of searching for universal explainable features that can remain explainable for a wide class of objects and phenomena and become an integral part of Explainable AI (XAI). The study is implemented on the example of an applied problem of early diagnostics of plant stress, using Thermal IR (TIR) and HSI, presented by 8 vegetation indices/channels. Each such index was presented by 5 statistical values. A Single-Layer-Perceptron classifier was used as the main instrument. TIR turned out to be the best of the indices in terms of efficiency in the field and sufficient to detect all 7 key days with 100% accuracy. Our study shows also that there are a number of indices, inluding NDVI, and usual color channels Red, Green, Blue, which are close to TIR possibilities in early plant stress detection with 100% accurasy or near, and can be used for wide class of plants and in different conditions their treatment. The stability of the stress classification in our study was maintained when the training set was reduced up to 10% of the dataset volume. The entropy-like feature of (max-min) for any indices/channels have determined as a leadersheep universal high-level explainable feature for the plant stress detection, which used in interaction with some of other statistical features.
ARTICLE | doi:10.20944/preprints202111.0186.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Explainable AI; Convolutional Neural Network; Network Compression
Online: 9 November 2021 (15:03:27 CET)
Model understanding is critical in many domains, particularly those involved in high-stakes decisions, i.e., medicine, criminal justice, and autonomous driving. Explainable AI (XAI) methods are essential for working with black-box models such as Convolutional Neural Networks. This paper evaluates the traffic sign classifier of Deep Neural Network (DNN) from the Programmable Systems for Intelligence in Automobiles (PRYSTINE) project for explainability. The results of explanations were further used for the CNN PRYSTINE classifier vague kernels` compression. After all, the precision of the classifier was evaluated in different pruning scenarios. The proposed classifier performance methodology was realised by creating the original traffic sign and traffic light classification and explanation code. First, the status of the kernels of the network was evaluated for explainability. For this task, the post-hoc, local, meaningful perturbation-based forward explainable method was integrated into the model to evaluate each kernel status of the network. This method enabled distinguishing high and low-impact kernels in the CNN. Second, the vague kernels of the classifier of the last layer before the fully connected layer were excluded by withdrawing them from the network. Third, the network's precision was evaluated in different kernel compression levels. It is shown that by using the XAI approach for network kernel compression, the pruning of 5% of kernels leads only to a 1% loss in traffic sign and traffic light classification precision. The proposed methodology is crucial where execution time and processing capacity prevail.
ARTICLE | doi:10.20944/preprints202209.0196.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Autonomous Vehicles; Reinforcement Learning; Explainable Reinforcement Learning; XRL
Online: 14 September 2022 (08:13:44 CEST)
While machine learning models are powering more and more everyday devices, there is a growing need for explaining them. This especially applies to the use of Deep Reinforcement Learning in solutions that require security, such as vehicle motion planning. In this paper, we propose a method of understanding what the RL agent’s decision is based on. The method relies on conducting statistical analysis on a massive set of state-decisions samples. It indicates which input features have an impact on the agent’s decision and the relationships between decisions, the significance of the input features, and their values. The method allows us for determining whether the process of making a decision by the agent is coherent with human intuition and what contradicts it. We applied the proposed method to the RL motion planning agent which is supposed to drive a vehicle safely and efficiently on a highway. We find out that making such analysis allows for a better understanding agent’s decisions, inspecting its behavior, debugging the ANN model, and verifying the correctness of input values, which increases its credibility.
ARTICLE | doi:10.20944/preprints202101.0346.v1
Subject: Engineering, Other Keywords: Chronic wound classification; transfer learning; explainable artificial intelligence.
Online: 18 January 2021 (14:28:04 CET)
Artificial Intelligence (AI) has seen increased application and widespread adoption over the past decade despite, at times, offering a limited understanding of its inner working. AI algorithms are, in large part, built on weights, and these weights are calculated as a result of large matrix multiplications. Computationally intensive processes are typically harder to interpret. Explainable Artificial Intelligence (XAI) aims to solve this black box approach through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies chronic wounds through the use of transfer learning and fully connected layers. Classified chronic wound images serve as input to the XAI model for an explanation. Interpretable results can help shed new perspectives to clinicians during the diagnostic phase. The proposed method successfully provides chronic wound classification and its associated explanation. This hybrid approach is shown to aid with the interpretation and understanding of AI decision-making processes.
ARTICLE | doi:10.20944/preprints202209.0276.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Sensor fusion; Camera and LiDAR fusion; Odometry; Explainable AI
Online: 19 September 2022 (10:27:42 CEST)
Recent deep learning frameworks draw a strong research interest in the application of ego-motion estimation as they demonstrate a superior result compared to geometric approaches. However, due to the lack of multimodal datasets, most of these studies primarily focused on a single sensor-based estimation. To overcome this challenge, we collect a unique multimodal dataset named LboroAV2, using multiple sensors including camera, Light Detecting And Ranging (LiDAR), ultrasound, e-compass and rotary encoder. We also propose an end-to-end deep learning architecture for fusion of RGB images and LiDAR laser scan data for odometry application. The proposed method contains a convolutional encoder, a compressed representation and a recurrent neural network. Besides feature extraction and outlier rejection, the convolutional encoder produces a compressed representation which is used to visualise the network's learning process and to pass useful sequential information. The recurrent neural network uses this compressed sequential data to learn the relation between consecutive time steps. We use the LboroAV2 and KITTI VO datasets to experiment and evaluate our results. In addition to visualising the network's learning process, our approach gives superior results compared to other similar methods. The code for the proposed architecture is released in GitHub and accessible publicly.
ARTICLE | doi:10.20944/preprints202206.0186.v1
Subject: Medicine & Pharmacology, Oncology & Oncogenics Keywords: screening model; breast cancer; explainable model; machine learning; Asian women
Online: 13 June 2022 (11:06:10 CEST)
This study aimed to determine the feasibility of the development of an over-the-counter (OTC) screening model using machine learning for breast cancer screening in the Asian women population. Data were retrospectively collected from women who came to the Hospital Universiti Sains Malaysia, Malaysia. Five screening models were developed based on machine learning methods; random forest, artificial neural network (ANN), support vector machine (SVM), elastic-net logistic regression and extreme gradient boosting (XGBoost). Features used for the development of the screening models were limited to information from the patients’ registration form. The model performance was assessed across the dense and non-dense groups. SVM had the best sensitivity while elastic-net logistic regression had the best specificity. In terms of precision, both random forest elastic-net logistic regression had the best performance, while, in terms of PR-AUC, XGBoost had the best performance. Additionally, SVM had a more balanced performance in terms of sensitivity and specificity across the mammographic density groups. The three most important features were age at examination, weight and number of children. In conclusion, OTC models developed from machine learning methods can improve the prognostic process of breast cancer in Asian women.
ARTICLE | doi:10.20944/preprints202206.0115.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: Explainable machine learning; COVID-19; Vaccination uptake; Shapley values; Feature importance.
Online: 8 June 2022 (05:30:18 CEST)
COVID-19 vaccine hesitancy is considered responsible for the lower rate of acceptance of vaccines in many parts of the world. However, sources of this hesitancy are rooted in many social, political, and economic factors. This paper strives to find the most important variables in predicting the COVID-19 vaccination uptake. We introduce an explainable machine learning (ML) framework to understand the COVID-19 vaccination uptake around the world. To predict vaccination uptake, we have trained a random forest (RF) regression model using a number of sociodemographic and socioeconomic data. The traditional decision tree (DT) regression model is also implemented as the baseline model. We found that the RF model performed better than the DT model since RF is more robust to handle nonlinearity and multi-collinearity. Also, we have presented feature importance based on impurity measure, permutation, and Shapley values to provide the most significant unbiased features. It is found that electrification coverage and Gross Domestic Product are the strongest predictors for higher vaccination uptake, whereas the Fragile state index (FI) contributed to lower vaccination uptake. These findings suggest addressing issues that are found responsible for lower vaccination uptake to combat any future public health crisis.
ARTICLE | doi:10.20944/preprints201907.0110.v1
Subject: Arts & Humanities, Philosophy Keywords: causality; deep learning; machine learning; counterfactual; explainable AI; blended cognition; mechanisms; system
Online: 8 July 2019 (08:10:29 CEST)
Causality is the most important topic in the history of Western Science, and since the beginning of the statistical paradigm, it meaning has been reconceptualized many times. Causality entered into the realm of multi-causal and statistical scenarios some centuries ago. Despite of widespread critics, today Deep Learning and Machine Learning advances are not weakening causality but are creating a new way of finding indirect factors correlations. This process makes possible us to talk about approximate causality, as well as about a situated causality.
ARTICLE | doi:10.20944/preprints202209.0190.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: green coffee bean; lightweight framework; deep convolutional neural network; explainable model; random optimization
Online: 14 September 2022 (04:04:05 CEST)
In recent years, the demand for coffee has increased tremendously. During the production process, green coffee beans are traditionally screened manually for defective beans before they are packed into coffee bean packages; however, this method is not only time-consuming but also increases the rate of human error due to fatigue. Therefore, this paper proposed a lightweight deep convolutional neural network (LDCNN) for the quality detection system of green coffee beans, which combined depthwise separable convolution (DSC), squeeze-and-excite block (SE block), skip block, and other frameworks. To avoid the influence of low parameters of the lightweight model caused by the model training process, rectified Adam (RA), lookahead (LA), and gradient centralization (GC) were included to improve efficiency; the model was also put into the embedded system. Finally, the local interpretable model-agnostic explanations (LIME) model was employed to explain the predictions of the model. The experimental results indicated that the accuracy rate of the model could reach up to 98.38% and the F1 score could be as high as 98.24% when detecting the quality of green coffee beans. Hence, it can obtain higher accuracy, lower computing time, and lower parameters. Moreover, the interpretable model verified that the lightweight model in this work is reliable, providing the basis for screening personnel to understand the judgment through its interpretability, thereby improving the classification and prediction of the model.
ARTICLE | doi:10.20944/preprints202110.0375.v1
Subject: Engineering, Biomedical & Chemical Engineering Keywords: Brain-Computer Interface (BCI), Convolutional neural network (CNN), Electroencephalogram (EEG), Explainable artificial intelligence (XAI)
Online: 26 October 2021 (11:45:00 CEST)
Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.
REVIEW | doi:10.20944/preprints202009.0103.v1
Subject: Medicine & Pharmacology, Other Keywords: climate change; vector-borne disease; artificial intelligence; explainable AI; geospatial modeling; infectious disease; arbovirus
Online: 4 September 2020 (12:21:32 CEST)
As recent history has shown, changing climate not only threatens to increase the spread of known disease, but also the emergence of new and dangerous phenotypes. This occurred most recently with West Nile virus: a virus previously known for mild febrile illness rapidly emerged to become a major cause of mortality and long-term disability throughout the world. As we move forward, into increasingly uncertain times, public health research must begin to incorporate a broader understanding of the determinants of disease emergence – what, how, why, and when. The increasing mainstream availability of high-quality open data and high-powered analytical methods presents promising new opportunities. Up to now, quantitative models of disease outbreak risk have been largely based on just a few key drivers, namely climate and large-scale climatic effects. Such limited assessments, however, often overlook key interacting processes and downstream determinants more likely to drive local manifestation of disease. Such pivotal determinants may include local host abundance, human behavioral variability, and population susceptibility dynamics. The results of such analyses can therefore be misleading in cases where necessary downstream requirements are not fulfilled. It is therefore important to develop models that include climate and higher-level climatic effects alongside the downstream non-climatic factors that ultimately determine individual disease manifestation. Today, few models attempt to comprehensively address such dynamics: up until very recently, the technology simply hasn’t been available. Herein, we present an updated overview of current perspectives on the varying drivers and levels of interactions that drive disease spread. We review the predominant analytical paradigms, discuss their strengths and weaknesses, and highlight promising new analytical solutions. Our focus is on the prediction of arboviruses, particularly West Nile virus, as these diseases represent the pinnacle of epidemiological complexity – solution to which would serve as an effective “gatekeeper”. We present the current state-of-the-art with respect to known drivers of arbovirus outbreak risk and severity, differentially highlighting the impact of climate and non-climatic drivers. The reality of multiple classes of drivers interacting at different geospatial and temporal scales requires advanced new methodologies. We therefore close out by presenting and discussing some promising new applications of AI. Given the reality of accelerating disease risks due to climate change, public health and other related fields must begin the process of updating their research programs to incorporate these much needed, new capabilities.
ARTICLE | doi:10.20944/preprints202204.0073.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Explainable Artificial Intelligence; Human-Centric Artificial Intelligence; Smart Manufacturing; Demand Forecasting; Industry 4.0; Industry 5.0
Online: 8 April 2022 (08:11:56 CEST)
Artificial Intelligence models are increasingly used in manufacturing to inform decision-making. Responsible decision-making requires accurate forecasts and an understanding of the models’ behavior. Furthermore, the insights into models’ rationale can be enriched with domain knowledge. This research builds explanations considering feature rankings for a particular forecast, enriching them with media news entries, datasets’ metadata, and entries from the Google Knowledge Graph. We compare two approaches (embeddings-based and semantic-based) on a real-world use case regarding demand forecasting.
ARTICLE | doi:10.20944/preprints202108.0246.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: Explainable Artificial Intelligence; XAI; Time Series Forecasting; Global Time Series Models; Machine Learning; Artificial Intelligence
Online: 11 August 2021 (10:32:48 CEST)
While increasing empirical evidence suggests that global time series forecasting models can achieve better forecasting performance than local ones, there is a research void regarding when and why the global models fail to provide a good forecast. This paper uses anomaly detection algorithms and Explainable Artificial Intelligence (XAI) to answer when and why a forecast should not be trusted. To address this issue, a dashboard was built to inform the user regarding (i) the relevance of the features for that particular forecast, (ii) which training samples most likely influenced the forecast outcome, (iii) why the forecast is considered an outlier, and (iv) provide a range of counterfactual examples to understand value changes, in the feature vector or the predicted value, can lead to a different outcome. Moreover, a modular architecture and a methodology were developed to iteratively remove noisy data instances from the train set, to enhance the overall global time series forecasting model performance. Finally, to test the effectiveness of the proposed approach, it was validated on two publicly available real-world datasets.
ARTICLE | doi:10.20944/preprints202105.0449.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Explainable Artificial Intelligence; Hopfield Neural Networks; Automatic Video Generation; Data-to-text systems; Software Visualization
Online: 19 May 2021 (14:07:48 CEST)
Hopfield Neural Networks (HNNs) are recurrent neural networks used to implement associative memory. Their main feature is their ability to pattern recognition, optimization, or image segmentation. However, sometimes it is not easy to provide the users with good explanations about the results obtained with them due to mainly the large number of changes in the state of neurons (and their weights) produced during a problem of machine learning. There are currently limited techniques to visualize, verbalize, or abstract HNNs. This paper outlines how we can construct automatic video generation systems to explain their execution. This work constitutes a novel approach to get explainable artificial intelligence systems in general and HNNs in particular building on the theory of data-to-text systems and software visualization approaches. We present a complete methodology to build these kinds of systems. Software architecture is also designed, implemented, and tested. Technical details about the implementation are also detailed and explained. Finally, we apply our approach for creating a complete explainer video about the execution of HNNs on a small recognition problem.
ARTICLE | doi:10.20944/preprints202208.0197.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Deep neural networks; Adversarial Attacks; Poisoning; Backdoors; Trojans; Taxonomy; Ontology; Knowledge Base; Explainable AI; Green AI
Online: 10 August 2022 (09:39:07 CEST)
Deep neural networks (DNN) have successfully delivered a cutting-edge performance in several fields. With the broader deployment of DNN models on critical applications, the security of DNNs becomes an active and yet nascent area. Attacks against DNNs can have catastrophic results, according to recent studies. Poisoning attacks, including backdoor and Trojan attacks, are one of the growing threats against DNNs. Having a wide-angle view of these evolving threats is essential to better understand the security issues. In this regard, creating a semantic model and a knowledge graph for poisoning attacks can reveal the relationships between attacks across intricate data to enhance the security knowledge landscape. In this paper, we propose a DNN Poisoning Attacks Ontology (DNNPAO) that would enhance knowledge sharing and enable further advancements in the field. To do so, we have performed a systematic review of the relevant literature to identify the current state. We collected 28,469 papers from IEEE, ScienceDirect, Web of Science, and Scopus databases, and from these papers, 712 research papers were screened in a rigorous process, and 55 poisoning attacks in DNNs were identified and classified. We extracted a taxonomy of the poisoning attacks as a scheme to develop DNNPAO. Subsequently, we used DNNPAO as a framework to create a knowledge base. Our findings open new lines of research within the field of AI security.
ARTICLE | doi:10.20944/preprints202110.0090.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: artificial intelligence; machine learning; active learning; knowledge acquisition; explainable artificial intelligence; manufacturing; demand forecasting; smart assistant
Online: 5 October 2021 (15:23:46 CEST)
This research work describes an architecture for building a system that guide a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in manufacturing demand forecasting use case and can be extended to other domains. In addition, the system provides means for knowledge acquisition by gathering data from users. Finally, it implements an active learning component and compares multiple strategies to recommend media news to the user. Such media news aims to provide additional context to demand forecasts and enhance judgment on decision-making.
ARTICLE | doi:10.20944/preprints202110.0364.v1
Subject: Engineering, Energy & Fuel Technology Keywords: Artificial Intelligence; Machine Learning; Explainable Artificial Intelligence; Soft Sensors; Industry 4.0; Smart Manufacturing; Cyber-Physical System; Crude Oil Distillation; Debutanization; LPG Purification
Online: 25 October 2021 (15:43:08 CEST)
Refineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predictive machine learning models, enables to provide equipment state monitoring services and to generate decision-making for equipment operations. In this paper, we propose two machine learning models: 1) to forecast the amount of pentane (C5) content in the final product mixture; 2) to identify if C5 content exceeds the specification thresholds for the final product quality. We validate our approach by using a use case from a real-world refinery. In addition, we develop a visualization to assess which features are considered most important during feature selection, and later by the machine learning models. Finally, we provide insights on the sensor values in the dataset, which help to identify the operational conditions for using such machine learning models.