Mach. Learn. Knowl. Extr., Volume 2, Issue 4 (December 2020) – 16 articles

Link prediction in complex networks has attracted considerable attention from interdisciplinary research communities, due to its ubiquitous applications in biological networks, social networks, transportation networks, telecommunication networks, and, recently, knowledge graphs. Numerous studies utilized link prediction approaches in order sto find missing links or predict the likelihood of future links as well as employed for reconstruction networks, recommender systems, privacy control, etc. This work presents an extensive review of state-of-art methods and algorithms proposed on this subject and categorizes them into four main categories: similarity-based methods, probabilistic methods, relational models, and learning-based methods. Additionally, a collection of network data sets has been presented in this paper, which can be used in order to study link prediction. We conclude this study with a discussion of recent developments and future research directions. Full article

Follicular lymphoma (FL) is the second most common lymphoma in Western countries. FL is characterized by being incurable, usually having an indolent clinical course with frequent relapses, and an eventual patient’s death or transformation to Diffuse Large B-cell Lymphoma. The immune response and the tumoral immune microenvironment, including FOXP3+Tregs, PD-1+TFH cells, TNFRSF14 (HVEM), and BTLA play a role in the pathogenesis. We aimed to analyze the gene expression of FL by Artificial Intelligence (machine learning, deep learning), to identify genes associated with the prognosis of the patients and with the microenvironment in terms of overall survival (OS). A series of 184 cases of the GSE16131 dataset was analyzed by multilayer perceptron (MLP) and radial basis function (RBF) neural networks. In the analysis, MLP and RBF had a synergistic effect. From an initial set of 22,215 genes probes, a final set of 43 genes was highlighted. These 43 genes predicted the OS and correlated with the immune microenvironment: in a multivariate Cox analysis, 18 genes were associated with a poor prognosis (namely, MED8, KRT19, CDC40, SLC24A2, PRB1, KIAA0100, EVA1B, KLK10, TMEM70, BTN2A3P, TRPM4, MED6, FRYL, CBFA2T2, RANBP9, BNIP2, PTP4A2 and ALDH1L1) and 25 genes were associated with a good prognosis of the patients. Gene set enrichment analysis (GSEA) confirmed these findings and showed a typical sinusoidal-like shape. Some of the most relevant genes for poor OS were EVA1B, KRT19, BTN2A3P, KLK10, TRPM4, TMEM70, and SLC24A2 (hazard risk = from 1.7 to 4.3, p < 0.005) and for good OS, these were TDRD12 and ZNF230 (HR = 0.34 and 0.28, p < 0.001). EVA1B, KRT19, BTN2AP3, KLK10, and TRPM4 also associated with M2-like macrophage markers including CD163, MRC1 (CD206), and IL10 in the core enrichment for dead OS outcome by GSEA and to poor OS by Kaplan–Meier with Log rank test. The scientific literature showed that some of these genes also play a role in other types of cancer. In conclusion, by Artificial Intelligence, we have identified new biomarkers with prognostic relevance in FL. Full article

Feature analysis is a fundamental research area in computer graphics; meanwhile, meaningful and part-aware feature bases are always demanding. This paper proposes a framework for conducting feature analysis on a three-dimensional (3D) model by introducing modified Non-negative Matrix Factorization (NMF) model into the graphical feature space and push forward further applications. By analyzing and utilizing the intrinsic ideas behind NMF, we propose conducting the factorization on feature matrices constructed based on descriptors or graphs, which provides a simple but effective way to raise compressed and scale-aware descriptors. In order to enable part-aware model analysis, we modify the NMF model to be sparse and constrained regarding to both bases and encodings, which gives rise to Sparse and Constrained Non-negative Matrix Factorization (SAC-NMF). Subsequently, by adapting the analytical components (including hidden variables, bases, and encodings) to design descriptors, several applications have been easily but effectively realized. The extensive experimental results demonstrate that the proposed framework has many attractive advantages, such as being efficient, extendable, and so forth. Full article

Electronic invoicing has been mandatory for Italian companies since January 2019. All the invoices are structured in a predefined xml template which facilitates the extraction of the information. The main aim of this paper is to exploit the information contained in electronic invoices to build an intelligent system which can simplify accountants’ work. More precisely, this contribution shows how it is possible to automate part of the accounting process: all the invoices of a company are classified into specific codes which represent the economic nature of the financial transactions. To accomplish this classification task, a multiclass classification algorithm is proposed to predict two different target variables, the account and the VAT codes, which are part of the general ledger entry. To apply this model to real datasets, a multi-step procedure is proposed: first, a matching algorithm is used for the reconstruction of the training set, then input data are elaborated and prepared for the training phase, and finally a classification algorithm is trained. Different classification algorithms are compared in terms of prediction accuracy, including ensemble models and neural networks. The models under comparison show optimal results in the prediction of the target variables, meaning that machine learning classifiers succeed in translating the complex rules of the accounting process into an automated model. A final study suggests that best performances can be achieved considering the hierarchical structure of the account codes, splitting the classification task into smaller sub-problems. Full article

Quantifying the characteristics of public attention is an essential prerequisite for appropriate crisis management during severe events such as pandemics. For this purpose, we propose language-agnostic tweet representations to perform large-scale Twitter discourse classification with machine learning. Our analysis on more than 26 million coronavirus disease 2019 (COVID-19) tweets shows that large-scale surveillance of public discourse is feasible with computationally lightweight classifiers by out-of-the-box utilization of these representations. Full article

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed. Full article

Neural network classifiers (NNCs) are known to be vulnerable to malicious adversarial perturbations of inputs including those modifying a small fraction of the input features named sparse or $L_0$ attacks. Effective and fast $L_0$ attacks, such as the widely used Jacobian-based Saliency Map Attack (JSMA) are practical to fool NNCs but also to improve their robustness. In this paper, we show that penalising saliency maps of JSMA by the output probabilities and the input features of the NNC leads to more powerful attack algorithms that better take into account each input’s characteristics. This leads us to introduce improved versions of JSMA, named Weighted JSMA (WJSMA) and Taylor JSMA (TJSMA), and demonstrate through a variety of white-box and black-box experiments on three different datasets (MNIST, CIFAR-10 and GTSRB), that they are both significantly faster and more efficient than the original targeted and non-targeted versions of JSMA. Experiments also demonstrate, in some cases, very competitive results of our attacks in comparison with the Carlini-Wagner (CW) $L_0$ attack, while remaining, like JSMA, significantly faster (WJSMA and TJSMA are more than 50 times faster than CW $L_0$ on CIFAR-10). Therefore, our new attacks provide good trade-offs between JSMA and CW for $L_0$ real-time adversarial testing on datasets such as the ones previously cited. Full article

Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dataset. To our knowledge, this is the first time that both scalability and accuracy of such a distance-regression model are being compared to this extent. We expect our results to be useful on shedding light on the capabilities of MLM and in assessing what solution algorithms can improve the efficiency of MLM. We conclude that $\left(i\right)$ randomized solvers are an attractive option when the computing time or resources are limited and $\left(ii\right)$ MLM can be used as an out-of-the-box tool especially for high-dimensional problems. Full article

Uncertainty is ubiquitous and happens in every single prediction of Machine Learning models. The ability to estimate and quantify the uncertainty of individual predictions is arguably relevant, all the more in safety-critical applications. Real-world recognition poses multiple challenges since a model’s knowledge about physical phenomenon is not complete, and observations are incomplete by definition. However, Machine Learning algorithms often assume that train and test data distributions are the same and that all testing classes are present during training. A more realistic scenario is the Open Set Recognition, where unknown classes can be submitted to an algorithm during testing. In this paper, we propose a Knowledge Uncertainty Estimation (KUE) method to quantify knowledge uncertainty and reject out-of-distribution inputs. Additionally, we quantify and distinguish aleatoric and epistemic uncertainty with the classical information-theoretical measures of entropy by means of ensemble techniques. We performed experiments on four datasets with different data modalities and compared our results with distance-based classifiers, SVM-based approaches and ensemble techniques using entropy measures. Overall, the effectiveness of KUE in distinguishing in- and out-distribution inputs obtained better results in most cases and was at least comparable in others. Furthermore, a classification with rejection option based on a proposed combination strategy between different measures of uncertainty is an application of uncertainty with proven results. Full article

The outbreak of COVID-19 has caused more than 200,000 deaths so far in the USA alone, which instigates the necessity of initial screening to control the spread of the onset of COVID-19. However, screening for the disease becomes laborious with the available testing kits as the number of patients increases rapidly. Therefore, to reduce the dependency on the limited test kits, many studies suggested a computed tomography (CT) scan or chest radiograph (X-ray) based screening system as an alternative approach. Thereby, to reinforce these approaches, models using both CT scan and chest X-ray images need to develop to conduct a large number of tests simultaneously to detect patients with COVID-19 symptoms. In this work, patients with COVID-19 symptoms have been detected using eight distinct deep learning techniques, which are VGG16, InceptionResNetV2, ResNet50, DenseNet201, VGG19, MobilenetV2, NasNetMobile, and ResNet15V2, using two datasets: one dataset includes 400 CT scan and another 400 chest X-ray images. Results show that NasNetMobile outperformed all other models by achieving an accuracy of 82.94% in CT scan and 93.94% in chest X-ray datasets. Besides, Local Interpretable Model-agnostic Explanations (LIME) is used. Results demonstrate that the proposed models can identify the infectious regions and top features; ultimately, it provides a potential opportunity to distinguish between COVID-19 patients with others. Full article

Hybrid simulation (HS) is an advanced simulation method that couples experimental testing and analytical modeling to better understand structural systems and individual components’ behavior under extreme events such as earthquakes. Conducting HS and real-time HS (RTHS) can be challenging with complex analytical substructures due to the nature of direct integration algorithms when the finite element method is employed. Thus, alternative methods such as machine learning (ML) models could help tackle these difficulties. This study aims to investigate the quality of the RTHS tests when a deep learning algorithm is used as a metamodel to represent the dynamic behavior of a nonlinear analytical substructure. The compact HS laboratory at the University of Nevada, Reno was utilized to conduct exclusive RTHS tests. Simulating a braced frame structure, the RTHS tests combined, for the first time, linear brace model specimens (physical substructure) along with nonlinear ML models for the frame (analytical substructure). Deep long short-term memory (Deep-LSTM) networks were employed and trained to develop the metamodels of the analytical substructure using the Python environment. The training dataset was obtained from pure analytical finite element simulations for the complete structure under earthquake excitation. The RTHS evaluations were first conducted for virtual RTHS tests, where substructuring was sought between the LSTM metamodel and virtual experimental substructure. To validate the proposed RTHS testing methodology and full system, several actual RTHS tests were conducted. The results from ML-based RTHS were evaluated for different ML models and compared against results from conventional RTHS with finite element models. The paper demonstrates the potential of conducting successful experimental RTHS using Deep-LSTM models, which could open the door for unparalleled new opportunities in structural systems design and assessment. Full article

The integration of Environmental, Social and Governance (ESG) considerations into business decisions and investment strategies have accelerated over the past few years. It is important to quantify the extent to which ESG-related conversations are carried out by companies so that their impact on business operations can be objectively assessed. However, profiling ESG language is challenging due to its multi-faceted nature and the lack of supervised datasets. This research study aims to detect historical trends in ESG discussions by analyzing the transcripts of corporate earning calls. The proposed solution exploits recent advances in neural language modeling to understand the linguistic structure in ESG discourse. In detail, firstly we develop a classification model that categorizes the relevance of a text sentence to ESG. A pre-trained language model is fine-tuned on a small corporate sustainability reports dataset for this purpose. The semantic knowledge encoded in this classification model is then leveraged by applying it to the sentences in the conference transcripts using a novel distant-supervision approach. Extensive empirical evaluations against various pretraining techniques demonstrate the efficacy of the proposed transfer learning framework. Our analysis indicates that in the last 5 years, nearly 15% of the discussions during earnings calls pertained to ESG, implying that ESG factors are integral to business strategy. Full article

Various big data sets are recorded on the server side of computer system. The big data are well defined as a volume, variety, and velocity (3V) model. The 3V model has been proposed by Gartner, Inc. as a first press release. 3V model means the volume, variety, and velocity in terms of data. The big data have 3V in well balance. Then, there are various categories in terms of the big data, e.g., sensor data, log data, customer data, financial data, weather data, picture data, movie data, and so on. In particular, the fault big data are well-known as the characteristic log data in software engineering. In this paper, we analyze the fault big data considering the unique features that arise from big data under the operation of open source software. In addition, we analyze actual data to show numerical examples of reliability assessment based on the results of multiple regression analysis well-known as the quantification method of the first type. Full article

Most existing studies of tourist attraction recommendations have specifically emphasized analyses of popular sites. However, recommending such spots encourages crowds to flock there in large numbers, making tourists feel uncomfortable. Furthermore, some studies have discovered that quite a few tourists dislike crowded destinations and prefer to avoid them. A ready solution is discovery and publicity of less-known tourist attractions. Especially, this study specifically examines discovery of less-known Japanese tourist destinations that are attractive and merit increased visits. Using this approach, crowds can not only be dispersed from popular tourist attractions, but more diverse spots can be provided for travelers to choose from. By analyzing geo-tagged photographs on Flickr, we propose a formula that incorporates different aspects such as image quality assessment (IQA), comment sentiment, and tourist attraction popularity for ranking tourist attractions. We investigate Taiwanese and Japanese people to assess their familiar Japanese cities and remove them from ranking results of tourist attractions. The remaining spots are less-known tourist attractions. As reported from results of verification experiments, most less-known tourist attractions are known by only a few people. They appeal to participants. Additionally, we examined some factors that might affect respondents when they decide whether a spot is attractive to them or not. This study can benefit tourism industries worldwide in the process of discovering potential tourist attractions. Full article

In this paper, we study how to extract visual concepts to understand landscape scenicness. Using visual feature representations from a Convolutional Neural Network (CNN), we learn a number of Concept Activation Vectors (CAV) aligned with semantic concepts from ancillary datasets. These concepts represent objects, attributes or scene categories that describe outdoor images. We then use these CAVs to study their impact on the (crowdsourced) perception of beauty of landscapes in the United Kingdom. Finally, we deploy a technique to explore new concepts beyond those initially available in the ancillary dataset: Using a semi-supervised manifold alignment technique, we align the CNN image representation to a large set of word embeddings, therefore giving access to entire dictionaries of concepts. This allows us to obtain a list of new concept candidates to improve our understanding of the elements that contribute the most to the perception of scenicness. We do this without the need for any additional data by leveraging the commonalities in the visual and word vector spaces. Our results suggest that new and potentially useful concepts can be discovered by leveraging neighbourhood structures in the word vector spaces. Full article

The random nature of traffic conditions on freeways can cause excessive congestion and irregularities in the traffic flow. Ramp metering is a proven effective method to maintain freeway efficiency under various traffic conditions. Creating a reliable and practical ramp metering algorithm that considers both critical traffic measures and historical data is still a challenging problem. In this study we use simple machine learning approaches to develop a novel real-time ramp metering algorithm. The proposed algorithm is computationally simple and has minimal data requirements, which makes it practical for real-world applications. We conduct a simulation study to evaluate and compare the proposed approach with an existing traffic-responsive ramp metering algorithm. Full article