Exploiting Machine Learning Techniques Research Articles

Fusing image and physical data for fatigue life prediction of nickel-based single crystal superalloys

This paper introduces a method for predicting the fatigue life of single crystals, which fuses image data and physical data by exploiting machine learning techniques. The proposed approach establishes a comprehensive study by progressively contributing a new database to the field, enabling the inference of service conditions, including temperature and σmax, as well as inherent material properties from fracture images, such as crystal orientation. We evaluate the effectiveness of the proposed method via its application to the fatigue life prediction of DD6 alloy, which achieves promising performance across various crystal orientations. The extensive experimental analysis and evaluation suggest that our proposed method has high predictive accuracy and computational efficiency of our proposed method. These results show that our approach holds promise for enhancing our understanding of material fatigue and improving predictive precision in failure analysis.

A Framework for Detection of Malicious Code by Exploiting Machine Learning Techniques on Portable Executables

Executable files coming from the internet bring along with them many potential hazards and vul- nerabilities in the form of malware to computer systems. The executables can be of form raw binaries, mnemonics, libraries, and function calls/APIs. They can misguide many of the conventional malware detection techniques. This paper explores the potential of Machine Learning- based methods for malware detection problems. The scope of the work here is currently limited to Static Anal- ysis of Executable files. Various feature selection tech- niques are implemented to reduce the size of the training data. Machine learning algorithms like K-Nearest Neigh- bors and Random Forest Classifier were trained on the curated feature sets. The outperforming experiment re- sult was shown by the Random Forest Classifier having an accuracy of 99.5%. We have developed a framework as a two-step module; in the first step, a list of features are extracted from a given executable file, and then for the next step, trained algorithm is integrated into the framework which will classify whether the given executa- ble file is malicious or not. This framework is demon- strated in the form of a Webapp developed in Python. Furthermore, this framework is evaluated based on its performance on a small dataset containing 35 portable executables (.exe) files and it is observed to be retaining the accuracy of the trained algorithm.

Surfactant Layers on Gold Nanorods.

ConspectusGold nanorods (Au NRs) are an exceptionally promising tool in nanotechnology due to three key factors: (i) their strong interaction with electromagnetic radiation, stemming from their plasmonic nature, (ii) the ease with which the resonance frequency of their longitudinal plasmon mode can be tuned from the visible to the near-infrared region of the electromagnetic spectrum based on their aspect ratio, and (iii) their simple and cost-effective preparation through seed-mediated chemical growth. In this synthetic method, surfactants play a critical role in controlling the size, shape, and colloidal stability of Au NRs. For example, surfactants can stabilize specific crystallographic facets during the formation of Au NRs, leading to the formation of NRs with specific morphologies.The process of surfactant adsorption onto the NR surface may result in various assemblies of surfactant molecules, such as spherical micelles, elongated micelles, or bilayers. Again, the assembly mode is critical toward determining the further availability of the Au NR surface to the surrounding medium. Despite its importance and a great deal of research effort, the interaction between Au NPs and surfactants remains insufficiently understood, because the assembly process is influenced by numerous factors, including the chemical nature of the surfactant, the surface morphology of Au NPs, and solution parameters. Therefore, gaining a more comprehensive understanding of these interactions is essential to unlock the full potential of the seed-mediated growth method and the applications of plasmonic NPs. A plethora of characterization techniques have been applied to reach such an understanding, but many open questions remain.In this Account, we review the current knowledge on the interactions between surfactants and Au NRs. We briefly introduce the state-of-the-art methods for synthesizing Au NRs and highlight the crucial role of cationic surfactants during this process. The self-assembly and organization of surfactants on the Au NR surface is then discussed to better understand their role in seed-mediated growth. Subsequently, we provide examples and elucidate how chemical additives can be used to modulate micellar assemblies, in turn allowing for a finer control over the growth of Au NRs, including chiral NRs. Next, we review the main experimental characterization and computational modeling techniques that have been applied to shed light on the arrangement of surfactants on Au NRs and summarize the advantages and disadvantages for each technique. The Account ends with a "Conclusions and Outlook" section, outlining promising future research directions and developments that we consider are still required, mostly related to the application of electron microscopy in liquid and in 3D. Finally, we remark on the potential of exploiting machine learning techniques to predict synthetic routes for NPs with predefined structures and properties.

SumMER: Structural Summarization for RDF/S KGs

Knowledge graphs are becoming more and more prevalent on the web, ranging from small taxonomies, to large knowledge bases containing a vast amount of information. To construct such knowledge graphs either automatically or manually, tools are necessary for their quick exploration and understanding. Semantic summaries have been proposed as a key technology enabling the quick understanding and exploration of large knowledge graphs. Among the methods proposed for generating summaries, structural methods exploit primarily the structure of the graph in order to generate the result summaries. Approaches in the area focus on identifying the most important nodes and usually employ a single centrality measure, capturing a specific perspective on the notion of a node’s importance. Moving from one centrality measure to many however, has the potential to generate a more objective view on nodes’ importance, leading to better summaries. In this paper, we present SumMER, the first structural summarization technique exploiting machine learning techniques for RDF/S KGs. SumMER explores eight centrality measures and then exploits machine learning techniques for optimally selecting the most important nodes. Then those nodes are linked formulating a subgraph out of the original graph. We experimentally show that combining centrality measures with machine learning effectively increases the quality of the generated summaries.

The Causal Plausibility Decision in Healthcare.

The explosion of interest in exploiting machine learning techniques in healthcare has brought the issue of inferring causation from observational data to centre stage. In our work in supporting the health decisions of the individual person/patient-as-person at the point of care, we cannot avoid making decisions about which options are to be included or excluded in a decision support tool. Should the researcher's routine injunction to use their findings 'with caution', because of methodological limitations, lead to inclusion or exclusion? The task is one of deciding, first on causal plausibility, and then on causality. Like all decisions these are both sensitive to error preferences (trade-offs). We engage selectively with the Artificial Intelligence (AI) literature on the causality challenge and on the closely associated issue of the 'explainability' now demanded of 'black box' AI. Our commitment to embracing 'lifestyle' as well as 'medical' options for the individual person, leads us to highlight the key issue as that of who is to make the preference- sensitive decisions on causal plausibility and causality.

Precinct Vaticinator on Social-Media using Machine Learning Techniques

Precinct vaticinator of users from online social media brings considerable research these days. Automatic recognition of precinct related with or referenced in records has been investigated for decades. As a standout amongst the online social network organization, Social-Media has pulled in an extensive number of users who send a millions of tweets on regular schedule. Because of the worldwide inclusion of its users and continuous tweets, precinct vaticinator on Social-Media has increased noteworthy consideration in these days. Tweets, the short and noisy and rich natured texts bring many challenges in research area for researchers. In proposed framework, a general picture of precinct vaticinator using tweets is studied. In particular, tweet precinct is predicted from tweet contents. By outlining tweet content and contexts, it is fundamentally featured that how the issues rely upon these text inputs. In this work, we predict the precinct of user from the tweet text exploiting machine learning techniques namely naïve bayes, Support Vector Machine and Decision Tree.

A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection

Background: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respiratory sounds in an automatic way. The aim is to show the effectiveness of machine learning techniques in respiratory sound analysis. A feature vector is gathered directly from breath audio and, thus, by exploiting supervised machine learning techniques, we detect if the feature vector is related to a patient affected by a lung disease. Moreover, the proposed method is able to characterise the lung disease in asthma, bronchiectasis, bronchiolitis, chronic obstructive pulmonary disease, pneumonia, and lower or upper respiratory tract infection. Results: A retrospective experimental analysis on 126 patients with 920 recording sessions showed the effectiveness of the proposed method. Conclusion: The experimental analysis demonstrated that it is possible to detect lung disease by exploiting machine learning techniques. We considered several supervised machine learning algorithms, obtaining the most interesting performance with the neural network model, with an F-Measure of 0.983 in lung disease detection and equal to 0.923 in lung disease characterisation, increasing the state-of-the-art performance.

Examining the Predictive Capability of Advanced Software Fault Prediction Models – An Experimental Investigation Using Combination Metrics

Background: Fault prediction is a key problem in software engineering domain. In recent years, an increasing interest in exploiting machine learning techniques to make informed decisions to improve software quality based on available data has been observed. Aim: The study aims to build and examine the predictive capability of advanced fault prediction models based on product and process metrics by using machine learning classifiers and ensemble design. Method: Authors developed a methodological framework, consisting of three phases i.e., (i) metrics identification (ii) experimentation using base ML classifiers and ensemble design (iii) evaluating performance and cost sensitiveness. The study has been conducted on 32 projects from the PROMISE, BUG, and JIRA repositories. Result: The results shows that advanced fault prediction models built using ensemble methods show an overall median of F-score ranging between 76.50% and 87.34% and the ROC(AUC) between 77.09% and 84.05% with better predictive capability and cost sensitiveness. Also, non-parametric tests have been applied to test the statistical significance of the classifiers. Conclusion: The proposed advanced models have performed impressively well for inter project fault prediction for projects from PROMISE, BUG, and JIRA repositories.

A babel of web-searches: Googling unemployment during the pandemic

Researchers are increasingly exploiting web-searches to study phenomena for which timely and high-frequency data are not readily available. We propose a data-driven procedure which, exploiting machine learning techniques, solves the issue of identifying the list of queries linked to the phenomenon of interest, even in a cross-country setting. Queries are then aggregated in an indicator which can be used for causal inference. We apply this procedure to construct a search-based unemployment index and study the effect of lock-downs during the first wave of the covid-19 pandemic. In a Difference-in-Differences analysis, we show that the indicator rose significantly and persistently in the aftermath of lock-downs. This is not the case when using unprocessed (raw) web search data, which might return a partial figure of the labour market dynamics following lock-downs.

Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis: A Multi-Cohort Study.

This pilot study aims at exploiting machine learning techniques to extract color Doppler ultrasound (CDUS) features and to build an artificial neural network (ANN) model based on these CDUS features for improving the diagnostic performance of thyroid cancer classification. A total of 674 patients with 712 thyroid nodules (TNs) (512 from internal dataset and 200 from external dataset) were randomly selected in this retrospective study. We used ANN to build a model (TDUS-Net) for classifying malignant and benign TNs using both the automatically extracted quantitative CDUS features (whole ratio, intranodular ratio, peripheral ratio, and number of vessels) and gray-scale ultrasound (US) features defined by the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS). Then, we compared the diagnostic performance of the model, the performance of another ANN model based on the gray-scale US features alone (TUS-Net), and that of radiologists. The TDUS-Net (0.898, 95% CI: 0.868-0.922) achieved a higher area under the curve (AUC) than that of TUS-Net (0.881, 95% CI: 0.850-0.908) in the internal tests. Compared with radiologists, TDUS-Net (AUC: 0.925, 95% CI: 0.880-0.958) performed better than radiologists (AUC: 0.810, 95% CI: 0.749-0.862) in the external tests. Applying a machine learning model by combining both gray-scale US features and CDUS features can achieve comparable or even higher performance than radiologists in classifying TNs.

Q-Learning based Routing Protocol to Enhance Network Lifetime in WSNs

In resource constraint Wireless Sensor Networks (WSNs), enhancement of network lifetime has been one of the significantly challenging issues for the researchers. Researchers have been exploiting machine learning techniques, in particular reinforcement learning, to achieve efficient solutions in the domain of WSN. The objective of this paper is to apply Q-learning, a reinforcement learning technique, to enhance the lifetime of the network, by developing distributed routing protocols. Q-learning is an attractive choice for routing due to its low computational requirements and additional memory demands. To facilitate an agent running at each node to take an optimal action, the approach considers node’s residual energy, hop length to sink and transmission power. The parameters, residual energy and hop length, are used to calculate the Q-value, which in turn is used to decide the optimal next-hop for routing. The proposed protocols’ performance is evaluated through NS3 simulations, and compared with AODV protocol in terms of network lifetime, throughput and end-to-end delay.

Techno-regulation and intelligent safeguards

The growth of Internet and the pervasiveness of ICT have led to a radical change in social relationships. One of the drawbacks of this change is the exposure of individuals to threats during online activities. In this context, the techno-regulation paradigm is inspiring new ways to safeguard legally interests by means of tools allowing to hamper breaches of law. In this paper, we focus on the exposure of individuals to specific online threats when interacting with smartphones. We propose a novel techno-regulatory approach exploiting machine learning techniques to provide safeguards against threats online. Specifically, we study a set of touch-based gestures to distinguish between underages or adults who is accessing a smartphone, and so to guarantee protection. To evaluate the proposed approach’s effectiveness, we developed an Android app to build a dataset consisting of more than 9000 touch-gestures from 147 participants. We experimented both single-view and multi-view learning techniques to find the best combination of touch-gestures able of distinguishing between adults and underages. Results show that the multi-view learning combining scrolls, swipes, and pinch-to-zoom gestures, achieves the best ROC AUC (0.92) and accuracy (88%) scores.

Googling Unemployment During the Pandemic: Inference and Nowcast Using Search Data

Researchers are increasingly exploiting web-searches to study phenomena for which timely and high-frequency data are not readily available. We propose a data-driven procedure which, exploiting machine learning techniques, solves the issue of identifying the list of queries linked to the phenomenon of interest, even in a cross-country setting. Queries are then aggregated in an indicator which can be used for causal inference. We apply this procedure to construct a search-based unemployment index and study the effect of lock-downs during the covid-19 pandemic. In a Difference-in-Differences analysis, we show that the indicator rose significantly and persistently in the aftermath of lock-downs.

Constraining the astrophysics and cosmology from 21 cm tomography using deep learning with the SKA

ABSTRACT Future Square Kilometre Array (SKA) surveys are expected to generate huge data sets of 21 cm maps on cosmological scales from the Epoch of Reionization. We assess the viability of exploiting machine learning techniques, namely, convolutional neural networks (CNNs), to simultaneously estimate the astrophysical and cosmological parameters from 21 cm maps from seminumerical simulations. We further convert the simulated 21 cm maps into SKA-like mock maps using the detailed SKA antennae distribution, thermal noise, and a recipe for foreground cleaning. We successfully design two CNN architectures (VGGNet-like and ResNet-like) that are both efficiently able to extract simultaneously three astrophysical parameters, namely the photon escape fraction (fesc), the ionizing emissivity power dependence on halo mass (Cion), and the ionizing emissivity redshift evolution index (Dion), and three cosmological parameters, namely the matter density parameter (Ωm), the dimensionless Hubble constant (h), and the matter fluctuation amplitude (σ8), from 21 cm maps at several redshifts. With the presence of noise from SKA, our designed CNNs are still able to recover these astrophysical and cosmological parameters with great accuracy ($R^{2} \gt 92{{\ \rm per\ cent}}$), improving to $R^{2} \gt 99{{\ \rm per\ cent}}$ towards low-redshift and low neutral fraction values. Our results show that future 21 cm observations can play a key role to break degeneracy between models and tightly constrain the astrophysical and cosmological parameters, using only few frequency channels.

Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films

Materials informatics exploiting machine learning techniques, e.g., Bayesian optimization (BO), have the potential to reduce the number of thin-film growth runs for optimization of thin-film growth conditions through incremental updates of machine learning models in accordance with newly measured data. Here, we demonstrated BO-based molecular beam epitaxy (MBE) of SrRuO3, one of the most intensively studied materials in the research field of oxide electronics, mainly owing to its unique nature as a ferromagnetic metal. To simplify the intricate search space of entangled growth conditions, we ran the BO for a single condition while keeping the other conditions fixed. As a result, high-crystalline-quality SrRuO3 film exhibiting a high residual resistivity ratio of over 50 as well as strong perpendicular magnetic anisotropy was developed in only 24 MBE growth runs in which the Ru flux rate, growth temperature, and O3-nozzle-to-substrate distance were optimized. Our BO-based search method provides an efficient experimental design that is not as dependent on the experience and skills of individual researchers, and it reduces experimental time and cost, which will accelerate materials research.

Understanding and improving ontology reasoning efficiency through learning and ranking

Ontologies are the fundamental building blocks of the Semantic Web and Linked Data. Reasoning is critical to ensure the logical consistency of ontologies, and to compute inferred knowledge from an ontology. It has been shown both theoretically and empirically that, despite decades of intensive work on optimising ontology reasoning algorithms, performing core reasoning tasks on large and expressive ontologies is time-consuming and resource-intensive. In this paper, we present the meta-reasoning framework R2O2* to tackle the important problems of understanding the source of TBox reasoning hardness and predicting and optimising TBox reasoning efficiency by exploiting machine learning techniques. R2O2* combines state-of-the-art OWL 2 DL reasoners as well as an efficient OWL 2 EL reasoner as components, and predicts the most efficient one by using an ensemble of robust learning algorithms including XGBoost and Random Forests. A comprehensive evaluation on a large and carefully curated ontology corpus shows that R2O2* outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.

Rapid trajectory design in complex environments enabled by reinforcement learning and graph search strategies

Designing trajectories in dynamically complex environments is challenging and easily becomes intractable. Recasting the problem may reduce the design time and offer global solutions by leveraging phase space mapping patterns available as accessible regions, and the application of search techniques from combinatorics. A computationally efficient search process produces potential trajectory concepts to meet unique design requirements over a broad range of mission types, including low-thrust scenarios. A successful framework is summarized in terms of four components: (i) Accessible regions — establishing reachable regions within the design space for a given thruster/engine capability: (ii) Database exploitation — discretization of well known dynamical structures to form a searchable 2D or 3D volume or map: (iii) Automated pathfinding — exploiting machine learning techniques to determine the transport sequence to deliver an efficient path: (iv) Convergence/optimization — once the transport sequence is determined as a globally efficient concept, it is optimized locally by traditional numerical strategies.

Improved adaptive sampling method utilizing Gaussian process regression for prediction of spectral peak structures

Materials informatics exploiting machine learning techniques has the potential to afford high-throughput experiments. In the various spectroscopies widely used in the research fields of materials science and physics, detailed peak structures provide vitally important information. Here, we propose an improved adaptive sampling method for such spectroscopies, which utilizes Gaussian process regression with a new heuristic evaluation function. Application of this method to various spectroscopies reveals that it enables prediction of detailed peak structures using fewer sampling points while preserving the required accuracy. Our method reduces the measurement time and cost and thus increases the throughput of sample characterization.

ABCD: agent based model for document classification

Document classification is the task of analysing, identifying and categorising collection of documents into their annotated classes based on their contents. This paper presents ABCD as an agent-based classifier for documents. ABCD is autonomous by depending on software agents in collecting and distributing documents, and smart by exploiting machine learning techniques to train the underlying classifier. As such, the system consists of two essential components, namely, the agent component and the classification component. To be comprehensive and to facilitate comparative results, five statistical classifiers are exploited. These classifiers are based on Naive Bayes (NB), Hidden Markov Model (HMM), Repeated Incremental Pruning to Produce Error Reduction (RIPPER), Support Vector Machine (SVM) and Random Forest (RF) algorithms. The proposed model is experimentally tested on both BBC news articles dataset and News Aggregator dataset from artificial intelligence lab. The obtained results indicate the superiority of the Random Forest algorithm for classifying unimodal documents.

A Novel Intrusion Detection Systems based on Genetic Algorithms-suggested Features by the Means of Different Permutations of Labels’ Orders

Intrusion detection systems (IDS) by exploiting Machine learning techniques are able to diagnose attack traffics behaviors. Because of relatively large numbers of features in IDS standard benchmark dataset, like KDD CUP 99 and NSL_KDD, features selection methods play an important role. Optimization algorithms like Genetic algorithms (GA) are capable of finding near-optimum combination of the features intended for construction of the final model. This paper proposes an innovative method called chain method, for evaluation of the given test record. The main intuition of our method is to concentrate merely on one attack type at every stage. In the beginning, datasets with the proposed features by GA based on different labels will be assembled. Based on a specific sequence– which is found on different permutation of four existed labels- the test record will be entered the chain module. If the first stage –which is correlated to the input sequence-, is able to diagnose the first label, the final output has been indicated. If is not, the records will pass through the next stage until the final output be obtained. Simulations on proposed chain method, illustrate this technique is able to outperform other conventional methods especially in R2L and U2R detection with the accuracy of 98.83% and 98.88% respectively.