Search

A life-cycle assessment (LCA) model was developed to comparatively analyze the use of manual and automated mining equipment in underground copper mine sites. Processes and key variables that were determined to contribute to the environmental impact of operations were identified for six mine sites in a range of geographical locations around the world. Our model successfully calculated carbon dioxide (CO2 eq.) emissions to within 4.9% of the reported annual emissions from the site’s respective companies. The implementation of automation was found to decrease global warming potential by a range of 11.4%–18.0% or 3.9–17.9 kg CO2 eq./t ore. The model was also used to estimate the average reductions across several impact potentials including, acidification (11.9%–17.8%), eutrophication (7.6%–13.7%), and human toxicity (16.0%–20.0%). World-wide the mining industry is moving toward introducing significantly more automation to enhance productivity and safety. This novel work demonstrates an important third dimension that can support this move, reduced environmental impact.

Design contexts are factors that shape a design, and whilst they are recognised by developers, they are typically tacit. Unlike software requirements, software engineering researchers have paid little attention to design contexts and there is little or no systematic research on how design contexts influence design. In this paper, we conduct an empirical investigation using Stack Overflow with the aim of mining design context knowledge that is related to design patterns. We chose to study design patterns because they are clear and identifiable. In this work, we develop a new taxonomy of design context terms related to design patterns. We introduce a new automated mining approach, DPC Miner, for mining design context knowledge from Stack Overflow. Finally, we analyse the Stack Overflow posts and present how design context impacts decisions about design patterns in practice.

Assertion - based verification has become a viable solution for functional verification. Manual definition of assertions is costly and needs human expertise. On the other hand, the automatic approaches are still struggling with generating high -quality assertion sets in terms of accuracy, and readability. To overcome the mentioned shortcomings, this paper exceeds the state-of-the-art by introducing a new fully automated approach to generate a set of complete and accurate assertions. Moreover, the mined assertions are readable thereby, easy to understand by the verification engineer. Furthermore, the method is equipped with a feature that communicates with users to select the assertions related to a specific block based on the user's need for further debugging and design analysis. Experimental results present the effectiveness of the proposed approach by showing that it generates significantly more compact assertion sets than the state-of-the-art while achieving 100% detection of the injected mutants.

Feature annotation based on preprocessor directives is the most common mechanism in Highly-Configurable Software Systems (HCSSs) to manage variability. However, it is challenging to understand, maintain, and evolve feature fragments guarded by #ifdef directives. Yet, despite HCSSs being implemented in Version Control Systems, the support for evolving features in space and time is still limited. To extend the knowledge on this topic, we analyze the feature life cycle in space and time. Specifically, we introduce an automated mining approach and apply it to four HCSSs, analyzing commits of their entire development life cycle (13 to 20 years and 37,500 commits). This goes beyond existing studies, which investigated only differences between specific releases or entire systems. Our results show that features undergo frequent changes, often with substantial modifications of their code. The findings of our empirical analyses stress the need for better support of system evolution in space and time at the level of features. In addition to these analyses, we contribute an automated mining approach for the analysis of system evolution at the level of features. Furthermore, we also make available our dataset to foster new studies on feature evolution in HCSSs.

For any molecule, network, or process of interest, to keep up with new publications on these, is becoming increasingly difficult. For many cellular processes, molecules and their interactions that need to be considered can be very large. Automated mining of publications can support large scale molecular interaction maps and database curation. Text mining and Natural Language Processing (NLP)-based techniques are finding their applications in mining the biological literature, handling problems such as Named Entity Recognition (NER) and Relationship Extraction (RE). Both rule-based and machine learning (ML)-based NLP approaches have been popular in this context, with multiple research and review articles examining the scope of such models in Biological Literature Mining (BLM). In this review article, we explore self-attention based models, a special type of neural network (NN)-based architectures that have recently revitalized the field of NLP, applied to biological texts. We cover self-attention models operating either at a sentence level or an abstract level, in the context of molecular interaction extraction, published from 2019 onwards. We conduct a comparative study of the models in terms of their architecture. Moreover, we also discuss some limitations in the field of BLM that identifies opportunities for the extraction of molecular interactions from biological text.

Identifying feature requests and bug reports in user comments holds great potential for development teams. However, automated mining of RE-related information from social media and app stores is challenging since (1) about 70% of user comments contain noisy, irrelevant information, (2) the amount of user comments grows daily making manual analysis unfeasible, and (3) user comments are written in different languages. Existing approaches build on traditional machine learning (ML) and deep learning (DL), but fail to detect feature requests and bug reports with high Recall and acceptable Precision which is necessary for this task. In this paper, we investigate the potential of transfer learning (TL) for the classification of user comments. Specifically, we train both monolingual and multilingual BERT models and compare the performance with state-of-the-art methods. We found that monolingual BERT models outperform existing baseline methods in the classification of English App Reviews as well as English and Italian Tweets. However, we also observed that the application of heavyweight TL models does not necessarily lead to better performance. In fact, our multilingual BERT models perform worse than traditional ML methods.

We present new constraints on the cosmic cold molecular gas evolution out to redshift 6 based on systematic mining of the public ALMA archive in the COSMOS field (A3 COSMOS). Our A3 COSMOS dataset contains ∼ 700 galaxies (0.3 ≲ z ≲ 6) with high-confidence ALMA detection and multi-wavelength SEDs. Combining with ∼ 1,200 CO-observed galaxies at 0 ≲ z ≲ 4 (75% at z < 0.1) in the literature, we parameterize galaxies’ molecular gas depletion time and gas fraction each as a function of stellar mass, offset from the star-forming main-sequence and cosmic age. We propose a new functional form which provides a better fit and implies a “downsizing” effect and “mass-quenching”. By adopting galaxy stellar mass functions and applying our gas fraction function, we obtain a cosmic cold molecular gas density evolution in agreement with recent CO blind field surveys as well as semi-analytic modeling. These together provide us a coherent picture of galaxy cold molecular gas, SFR and stellar mass evolution.

Mineral demand rapidly increases; as a result, underground mining activities gradually dig into the earth’s crust to deeper levels. For instance, the depth of coal mines has reached 1500 m, whereas the depth of mines for nonferrous metals has already achieved around 4500 m. Deep mining faces a number of technical and environmental challenges, first of all, great rock mass stresses, high temperature and long winding distance. The traditional technologies are hardly capable to provide the development and extraction efficiency and safety. That is why the need in developing and implementation of new modern mining technologies arose. In roadheading, TBM (tunnelboring machine) method is gradually introduced. A TBM combines the functions of rock breaking, support installation, mucking and conveying rock. In mining industry, smart mining based on mechanized and automated mining methods is successfully implemented at coal mines. Besides, a technical concept of fluidized mining for deepseated mineral resources (6000 m and more) was proposed. This paper presents the review of the current global status of deep mining and highlights some of the newest technological achievements in roadheading and the mineral extraction processes.

Many implied programming patterns are contained in large-scale software. Most of the implied programming patterns are missing proper documentation. Defects would be brought into the software, if any of the patterns is violated by programmers. To alleviate this problem, many works are proposed to find defects by mining programming patterns from the software. However, a great many of candidate patterns and defects are reported by these approaches. These patterns and defects need to be manually confirmed, and the applicability and scalability of these approaches are restricted by this problem. In view of this problem, this paper proposes an approach to automated mining, confirming, filtering function call sequence patterns (FCSPs), and detecting defects which violate the patterns. At first, FCSPs are mined from a previous stable version and an update version under analyzing, respectively; then, the FCSPs are confirmed by analyzing correlations; after that, useful FCSPs are filtered with respect to the FCSPs mined from the previous version; finally, the version under analyzing is scanned for suspicious defects against the filtered FCSPs. 3 open source projects are selected as the experimental subjects to evaluate the approach. As the experimental result shows, the efficiency of defect detection is improved by the proposed approach. It confirms programming candidate FCSPs with 82% F1-measure and 77% accuracy, and eliminates 55% suspicious defects without sacrificing the performance.

With the rapid growth of research publications, empowering scientists to keep an oversight over scientific progress is of paramount importance. In this regard, the leaderboards facet of information organization provides an overview on the state-of-the-art by aggregating empirical results from various studies addressing the same research challenge. Crowdsourcing efforts like PapersWithCode among others are devoted to the construction of leaderboards predominantly for various subdomains in Artificial Intelligence. Leaderboards provide machine-readable scholarly knowledge that has proven to be directly useful for scientists to keep track of research progress – their construction could be greatly expedited with automated text mining.

In the last decade, mining software repositories (MSR) has become one of the most important sources to feed machine learning models. Especially open-source projects on platforms like GitHub are providing a tremendous amount of data and make them easily accessible. Nevertheless, there is still a lack of standardized pipelines to extract data in an automated and fast way. Even though several frameworks and tools exist which can fulfill specific tasks or parts of the data extraction process, none of them allow neither building an automated mining pipeline nor the possibility for full parallelization. As a consequence, researchers interested in using mining software repositories to feed machine learning models are often forced to re-implement commonly used tasks leading to additional development time and libraries may not be integrated optimally. This preliminary study aims to demonstrate current limitations of existing tools and Git itself which are threatening the prospects of standardization and parallelization. We also introduce the multi-dimensionality aspects of a Git repository and how they affect the computation time. Finally, as a proof of concept, we define an exemplary pipeline for predicting refactoring operations, assessing its performance. Finally, we discuss the limitations of the pipeline and further optimizations to be done.

BackgroundOur previous infodemiological study was performed by manually mining health-effect data associated with electronic cigarettes (ECs) from online forums. Manual mining is time consuming and limits the number of posts that can be retrieved.ObjectiveOur goal in this study was to automatically extract and analyze a large number (>41,000) of online forum posts related to the health effects associated with EC use between 2008 and 2015.MethodsData were annotated with medical concepts from the Unified Medical Language System using a modified version of the MetaMap tool. Of over 1.4 million posts, 41,216 were used to analyze symptoms (undiagnosed conditions) and disorders (physician-diagnosed terminology) associated with EC use. For each post, sentiment (positive, negative, and neutral) was also assigned.ResultsSymptom and disorder data were categorized into 12 organ systems or anatomical regions. Most posts on symptoms and disorders contained negative sentiment, and affected systems were similar across all years. Health effects were reported most often in the neurological, mouth and throat, and respiratory systems. The most frequently reported symptoms and disorders were headache (n=939), coughing (n=852), malaise (n=468), asthma (n=916), dehydration (n=803), and pharyngitis (n=565). In addition, users often reported linked symptoms (eg, coughing and headache).ConclusionsOnline forums are a valuable repository of data that can be used to identify positive and negative health effects associated with EC use. By automating extraction of online information, we obtained more data than in our prior study, identified new symptoms and disorders associated with EC use, determined which systems are most frequently adversely affected, identified specific symptoms and disorders most commonly reported, and tracked health effects over 7 years.

The concept of autonomous mobile robots (AMR) has gained much popularity in recent years, particularly in commercial settings where the name industrial autonomous mobile robot (IAMR) is proposed. In addition to automatic guided vehicles and automated mining trucks, IAMR also includes autonomous merchant ships. AMR is an old concept which was first introduced in the 1980s. Although the concept of AMRs is old and broadly used, there is still no common definition of autonomy when mobile robots are concerned. This paper will review some of the most known definitions and develop a taxonomy for autonomy in mobile autonomous robots. This will be used to compare the different definitions of robotic autonomy. This paper will mainly look at industrial autonomous mobile robots, i.e. systems that are designed to operate with a clear commercial objective in mind and which are normally supported by a remote control centre. This means that the robot is not fully autonomous, but to varying degrees dependent on humans in some control and monitoring functions.

To accommodate surrounding rock structure stability control problem in underground mining, we study the coupling effect principle between hydraulic support and surrounding rock, and develop a series of longwall mining technology and equipment, which solves four common technical problems that significantly undermine coal mining safety, efficiency, and high recovery and extraction rates. Based on the coupling characteristic between mining-induced stress field and supporting stress field of hydraulic support, we identify six controllable factors in the application of hydraulic support to surrounding rock, and further reveal the relationship between hydraulic support and surrounding rock in terms of the strength, the stiffness, and the stability coupling. Our findings provide a plausible solution to the longwall mining technical problem with 6–8 m mining height. By analyzing the dynamic disequilibrium characteristics between hydraulic support and surrounding rock, we propose the intelligent top coal caving control method and the high-coal-recovery-rate technology for fully mechanized caving faces. With the invention of this technology, China is likely to lead the world in terms of the fully mechanized top coal caving mining technology. We are also the first to employ the intelligent coupling technology between hydraulic support and surrounding rock, and automated mining mode, and supporting system cooperative control with automatic organization. We develop the comprehensive multi-index intelligence adjusting height decision-making mechanism and three-dimensional navigation automatic adjusting straightness technology based on shearer cutting height memory association, cutting power parameters, vibration, and video information, leading to the first set of intelligent longwall mining technology and equipment for thin seam. Our innovation makes a solid contribution to the revolution of intelligence mining technology. With the innovative use of three-dimensional coupling control principle for surrounding rock, we successfully resolve the technological difficulties of longwall mining equipment and surrounding rock control for steep dipping seam, making a breakthrough of longwall mining technology with steep dipping seam.

Maintenance is crucial to ensure production/output and customer satisfaction in the mining sector. The cost of maintenance of mechanised and automated mining systems is very high, necessitating efforts to enhance the effectiveness of maintenance systems and organisation. For effective maintenance planning, it is important to have a good understanding of the reliability and availability characteristics of the systems. Determining the Mean Residual Life (MRL) of systems allows organisations to more effectively plan maintenance tasks. In this paper, we use a statistical approach to estimate MRL and consider a Weibull proportional hazard model (PHM) with time-independent covariates to model the hazard function so that the operating environment could be integrated into the reliability analysis. The paper explains our methods for calculating the conditional reliability function and computing the MRL as a function of the current conditions. The model is verified and validated using data from the hydrauli...

With the increasing amount of program source code data in the development of the open source community, there are reusable program patterns in the vast amount of code data. The existing program pattern mainly relies on manual extraction and there are problems such as high labor cost and a small number of acquired modes. This paper proposes a program code mining method for this problem. Automated mining of program pattern by this method saves labor costs and time costs and can more accurately mine more program patterns. In the mining process, the pre-processing is performed to convert the code data into a digital sequence and then the SPADE algorithm is used for automatic mining to obtain a reusable program pattern. After comparison with PrefixSpan and GSP mining algorithms, the results show that the method is effective.

Despite significant advances over decades, gold and silver mining still involves the old paradigm with a significant amount of waste management during haulage, processing, and disposal.

This paper describes the design and implementation of Sensorland, an immersive environment developed to support an existing policy making framework. In particular, our aim was to visualise future application scenarios for sensor systems in two different contexts: (1) A highly automated mining environment, and (2) A natural disaster response situation. For this purpose, two virtual reality (VR) environments for HTC Vive were created using Unity 3D game engine. Finally, the opportunities and pitfalls of the VR medium for presenting information to support policy making are discussed. We make several recommendations for the future development of the content creation process, and consider its applicability in other contexts.

Automation and intelligent coal mining comprise the most important fields in coal mining technology research. The key to automation and intelligent coal mining is the automated mining of the working face, and accurate positioning of the shearer is one of the most important technologies in the automated mining process. However, significant defects in non-inertial navigation system (INS)-based methods have led to low positioning accuracy. In this paper, we propose a new shearer positioning technology to further improve the positioning accuracy of the shearer and monitor the shearer position in real time. The shearer positioning system proposed is based on the strapdown inertial navigation system (SINS). We conducted shearer positioning experiments with gyroscopes, accelerometers, and other inertial navigation instruments. The experimental results are thoroughly studied on the basis of error compensation techniques such as inertial instrument zero bias compensation and Kalman filter compensation. Compared with traditional shearer positioning technology, the experimental results show that the shearer positioning system based on SINS can achieve more accurate positioning of the shearer and can accurately reflect the running characteristics of the shearer working the mining face.

Genome editing technologies hold great promise in fundamental biomedical research, development of treatments for animal and plant diseases, and engineering biological organisms for food and industrial applications. Therefore, a global understanding of the growth of the field is needed to identify challenges, opportunities and biases that could shape the impact of the technology. To address this, this work applies automated literature mining of scientific publications on genome editing in the past year to infer research trends in 2 key genome editing technologies-CRISPR/Cas systems and TALENs. The study finds that genome editing research is disproportionately distributed between and within countries, with researchers in the US and China accounting for 50% of authors in the field whereas countries across Africa are underrepresented. Furthermore, genome editing research is also disproportionately being explored on diseases such as cancer, Duchene Muscular Dystrophy, sickle cell disease and malaria. Gender biases are also evident in genome editing research with considerably fewer women as principal investigators. The results of this study suggest that automated mining of scientific literature could help identify biases in genome editing research as a means to mitigate future inequalities and tap the full potential of the technology.

As an active subfield of Automated Machine Learning, automated structural analysis focuses on extracting the structural information, such as periodicity, from the data automatically, enabling automated data cleaning and feature extraction. Little research, however, has been done on the periodicity mining from numeric data that contain noises and missing points. In this paper, we present a practical and innovative framework to close this gap. To validate our approach, we carry out detailed simulation studies and real data analyses. The experimental results show that our framework is more robust to data granularity with better accuracy and computational efficiency when comparing with baseline methods. Moreover, the results imply that our proposed method is insensitive to data jitters, noise points and missing signal points.

Although much research is devoted to the analysis and prediction of individuals' behavior in social networks, very few studies analyze firms' performance with respect to business networks. Empowered by recent research on the automated mining of business networks, this article illustrates the design of a novel business network-based model called the energy cascading model (ECM) for predicting directional stock price movements of related firms. More specifically, the proposed network-based predictive analytics model considers both influential business relationships and Twitter sentiments to infer a firm's middle to long-term directional stock price movements. The reported empirical experiments are based on a publicly available financial corpus and social media postings that reveal the proposed ECM model to be effective for predicting directional stock price movements. It outperforms the best baseline model, the Pearson correlation-based prediction model, in upward stock price movement prediction by 11.7 percent in terms of F-measure.

The development of off-world sources of critical minerals is creating an opportunity to transform space activity from a consumer of resources into sources of value. This article provides an overview of the rationale for and the feasibility of asteroid mining, based on current technology and information. It concludes that the mining of asteroids is a medium-term to long-term project (20 to 30 years) that requires a stepwise approach. An important step in the development of asteroid mining is the confirmation, through exploration, of the minerals’ abundance on the asteroids. A mission capturing and returning to lunar orbit a single 10-meter-diameter asteroid or a rock off the surface of a larger asteroid accomplishes this goal. This mission would also allow the testing of automated mining and processing equipment, reducing the risks of future large-scale asteroid mining operations. Suggested herein is that asteroids’ exploration be carried out through a partnership between space agencies and private space c...

Drug reactions can be extracted fromuser reviews provided on the Web, and processingthis information in an automated way represents anovel and exciting approach to personalized medicineand wide-scale drug tests. In medical applications,demographic information regarding the authors ofthese reviews such as age and gender is of primaryimportance; however, existing studies usually assumethat this information is available or overlook theissue entirely. In this work, we propose andcompare several approaches to automated mining ofdemographic information from user-generated texts.We compare modern natural language processingtechniques, including feature rich classifiers, extensionsof topic models, and deep neural networks (bothconvolutional and recurrent architectures) for thisproblem.

In order to solve the problem of shearer automation for the automated mining, analysis and processing by a plurality of sensors or observation information sources is the most promising solution to automatically control the shearer’s posture, while there is no vibration sensors with intrinsically safety that can be directly equipped on the shearers under coal mines. In the paper, study on a new intrinsic safe mode vibration sensor to solve the problem, it includes the hardware system designing and data collection programming. At the end, an experiment proves that the intrinsic safe wireless vibration sensor is able to collection the three-dimensional vibration data reliably and in time compared with the other vibration sensors.

Hyperspectral data acquired from field-based platforms present new challenges for their analysis, particularly for complex vertical surfaces exposed to large changes in the geometry and intensity of illumination. The use of hyperspectral data to map rock types on a vertical mine face is demonstrated, with a view to providing real-time information for automated mining applications. The performance of two classification techniques, namely, spectral angle mapper (SAM) and support vector machines (SVMs), is compared rigorously using a spectral library acquired under various conditions of illumination. SAM and SVM are then applied to a mine face, and results are compared with geological boundaries mapped in the field. Effects of changing conditions of illumination, including shadow, were investigated by applying SAM and SVM to imagery acquired at different times of the day. As expected, classification of the spectral libraries showed that, on average, SVM gave superior results for SAM, although SAM performed better where spectra were acquired under conditions of shadow. In contrast, when applied to hypserspectral imagery of a mine face, SVM did not perform as well as SAM. Shadow, through its impact upon spectral curve shape and albedo, had a profound impact on classification using SAM and SVM.

t—Automation is known as one of the most powerful tools for enhancing the mine productivity and safety. Automated mining machineries are so complex and capital intensive assets which need comprehensive maintenance, support and logistic planning to be able to meet their desired production goals. There are several technical, operational and safety challenges in the maintenance of this kind of machinery which force the mining companies to take the advanced solutions for increasing the maintenance quality and reducing the downtimes as much as possible. In this paper firstly the various automation modes of mining machinery are reviewed briefly. Thereafter, regarding to literature review and some field observation, three maintenance challenges are presented and discussed: safety of maintenance crew, maintenance big data and asset integration problems in mine automation systems. Considering the operational difficulties and safety issues the intelligent Reliability Centered Maintenance (iRCM) and eMaintenance as two advanced applicable methods are recommended for maintenance improvement in automated

This paper presents an extended literature review of the human factors impacts of current and future automation in the minerals industry. It begins by defining what is automation and stating why it is being developed and deployed. It then outlines why it is important to consider operators and maintainers when designing and deploying mining automation. To put mining automation into context, lessons learnt from automation in other industries and past problems with automation from a human-element perspective is then presented before specific issues in mining automation are discussed; these include ‘degrees of automation’, automation trends and the deployment issues. Conclusions about the human-element impacts of mining automation are made; these include the likely problems and some potential ways of reducing such problems.

The emergence of the blogosphere has created new challenges for large companies in the management of their corporate reputations, since grass roots blogs can generate negative perceptions about a firm and then spread them rapidly and widely. The blogosphere has also created new opportunities for firms to enhance their reputations, because the informal and personal communication that occurs on blogs may generate significant positive ‘ Internet word of mouth ’ . This paper examines the interaction between the blogosphere and a leading technology company, Dell Computer, over a critical two-year period. Our approach combines two novel techniques: automated mining of blog entries, enabled by parsing software, which generates semantic analysis and network maps of the relevant blog entries; and netnography, a method derived from ethnography for analyzing Internet-based discussions. This study shows that many established reputation management approaches, which were developed during the era of mass media, need to be reshaped to meet new realities in the age of Web 2.0.

With the construction of integrated automated mining monitoring system and its platform, the monitoring data of great capacity from different subsystems were converged in the dispatching room. A high-speed response linkage model for integrated automated monitoring system at coal mine was proposed. In this model, the monitoring data from different subsystems were analyzed intelligently by building the data storage and linkage rules. Also, the uniform dada exchanging formats and data processing mechanism were defined to share monitoring data between different subsystems for united alarms, which provide coal mine with an efficient intelligent dispatching and decision-making method. The simulation results show that this model can meet the demand of high-speed response linkage for integrated monitoring system at coal mine.

Knowledge about the reception of architectural structures is crucial for architects and urban planners. Yet obtaining such information has been a challenging and costly activity. However, with the advent of the Web, a vast amount of structured and unstructured data describing architectural structures has become available publicly. This includes information about the perception and use of buildings (for instance, through social media), and structured information about the building's features and characteristics (for instance, through public Linked Data). Hence, first mining (i) the popularity of buildings from the social Web and (ii) then correlating such rankings with certain features of buildings, can provide an efficient method to identify successful architectural patterns. In this paper we propose an approach to rank buildings through the automated mining of Flickr metadata. By further correlating such rankings with building properties described in Linked Data we are able to identify popular patterns for particular building types (airports, bridges, churches, halls, and skyscrapers). Our approach combines crowdsourcing with Web mining techniques to establish influential factors, as well as ground truth to evaluate our rankings. Our extensive experimental results depict that methods tailored to specific structure types allow an accurate measurement of their public perception.

Understanding the response dynamics of plants to biotic stress is essential to improve management practices and breeding strategies of crops and thus to proceed towards a more sustainable agriculture in the coming decades. In this context, hyperspectral imaging offers a particularly promising approach since it provides non-destructive measurements of plants correlated with internal structure and biochemical compounds. In this paper, we present a cascade of data mining techniques for fast and reliable data-driven sketching of complex hyperspectral dynamics in plant science and plant phenotyping. To achieve this, we build on top of a recent linear time matrix factorization technique, called Simplex Volume Maximization, in order to automatically discover archetypal hyperspectral signatures that are characteristic for particular diseases. The methods were applied on a data set of barley leaves (Hordeum vulgare) diseased with foliar plant pathogens Pyrenophora teres, Puccinia hordei and Blumeria graminis hordei. Towards more intuitive visualizations of plant disease dynamics, we use the archetypal signatures to create structured summaries that are inspired by metro maps, i.e. schematic diagrams of public transport networks. Metro maps of plant disease dynamics produced on several real-world data sets conform to plant physiological knowledge and explicitly illustrate the interaction between diseases and plants. Most importantly, they provide an abstract and interpretable view on plant disease progression.

This paper describes new research and development currently being undertaken to advance the automation capability of mining equipment in underground coal mining operations. The research effort targets the development of new inertial navigation solutions that aim to increase roadway development rates and provide a safer working environment for underground mine personnel. Specific developments have been undertaken to develop and integrate navigation, remote control, and visualisation technologies. Results obtained so far show that the navigation solution developed can provide the accuracy necessary for production-level underground mining.

In this paper, a genetic algorithm (GA) is proposed as a search strategy for not only positive but also negative quantitative association rule (AR) mining within databases. Contrary to the methods used as usual, ARs are directly mined without generating frequent itemsets. The proposed GA performs a database-independent approach that does not rely upon the minimum support and the minimum confidence thresholds that are hard to determine for each database. Instead of randomly generated initial population, uniform population that forces the initial population to be not far away from the solutions and distributes it in the feasible region uniformly is used. An adaptive mutation probability, a new operator called uniform operator that ensures the genetic diversity, and an efficient adjusted fitness function are used for mining all interesting ARs from the last population in only single run of GA. The efficiency of the proposed GA is validated upon synthetic and real databases.

This paper describes a navigation system incorporating inertial and two-antenna carrier phase differential global positioning system (GPS) measurements. The major objective is to demonstrate full attitude determination even for a nonaccelerating vehicle. The motivating application for this project is vehicle control. Therefore, the system is designed to operate reliably whether or not GPS measurements are available. The navigation system estimates vehicle position, velocity, acceleration, attitude, and angular rates at 150 Hz with accuracy (standard deviation) of 1.5 cm, 0.8 cm/s, 2.2 cm/s/s, 0.03 deg (pitch and roll), 0.1 deg (yaw), and 0.1 deg/s using a 1.01 m baseline between antennas. The navigation state vector is processed to produce a control state vector at 30 Hz. The control demonstrations involve basic trajectory following as well as trajectory relative maneuvering (i.e., tracking sinusoidal perturbations and performing lane changes). During experimental testing, a magnetic system was available to provide a ground truth reference. The demonstrated accuracy is sufficient for control of vehicles in an automated highway system. Other possible applications include precision farming, aircraft and satellite control, and control or guidance of automated mining or highway maintenance vehicles.

Online service systems have been increasingly popular and important nowadays. Reducing the MTTR (Mean Time to Restore) of a service remains one of the most important steps to assure the user-perceived availability of the service. To reduce the MTTR, a common practice is to restore the service by identifying and applying an appropriate healing action. In this paper, we present an automated mining-based approach for suggesting an appropriate healing action for a given new issue. Our approach suggests an appropriate healing action by adapting healing actions from the retrieved similar historical issues. We have applied our approach to a real-world and large-scale product online service. The studies on 243 real issues of the service show that our approach can effectively suggest appropriate healing actions (with 87% accuracy) to reduce the MTTR of the service. In addition, according to issue characteristics, we further study and categorize issues where automatic healing suggestion faces difficulties.

Most existing malicious Android app detection approaches rely on manually selected detection heuristics, features, and models. In this paper, we describe a new, complementary system, called DroidMiner, which uses static analysis to automatically mine malicious program logic from known Android malware, abstracts this logic into a sequence of threat modalities, and then seeks out these threat modality patterns in other unknown (or newly published) Android apps. We formalize a two-level behavioral graph representation used to capture Android app program logic, and design new techniques to identify and label elements of the graph that capture malicious behavioral patterns (or malicious modalities). After the automatic learning of these malicious behavioral models, DroidMiner can scan a new Android app to (i) determine whether it contains malicious modalities, (ii) diagnose the malware family to which it is most closely associated, (iii) and provide further evidence as to why the app is considered to be malicious by including a concise description of identified malicious behaviors. We evaluate DroidMiner using 2,466 malicious apps, identified from a corpus of over 67,000 third-party market Android apps, plus an additional set of over 10,000 official market Android apps. Using this set of real-world apps, we demonstrate that DroidMiner achieves a 95.3% detection rate, with only a 0.4% false positive rate. We further evaluate DroidMiner’s ability to classify malicious apps under their proper family labels, and measure its label accuracy at 92%.

We propose an automated mining-based method for explaining concurrency bugs. We use a data mining technique called sequential pattern mining to identify problematic sequences of concurrent read and write accesses to the shared memory of a multi-threaded program. Our technique does not rely on any characteristics specific to one type of concurrency bug, thus providing a general framework for concurrency bug explanation. In our method, given a set of concurrent execution traces, we first mine sequences that frequently occur in failing traces and then rank them based on the number of their occurrences in passing traces. We consider the highly ranked sequences of events that occur frequently only in failing traces an explanation of the system failure, as they can reveal its causes in the execution traces. Since the scalability of sequential pattern mining is limited by the length of the traces, we present an abstraction technique which shortens the traces at the cost of introducing spurious explanations. Spurious as well as misleading explanations are then eliminated by a subsequent filtering step, helping the programmer to focus on likely causes of the failure. We validate our approach using a number of case studies, including synthetic as well as real-world bugs.

Process mining is a domain where computers undoubtedly outperform humans. It is a mathematically complex and computationally demanding problem, and event logs are at too low a level of abstraction to be intelligible in large scale to humans. We demonstrate that if instead the data to mine from are models (not logs), datasets are small (in the order of dozens rather than thousands or millions), and the knowledge to be discovered is complex (reusable model patterns), humans outperform computers. We design, implement, run, and test a crowd-based pattern mining approach and demonstrate its viability compared to automated mining. We specifically mine mashup model patterns (we use them to provide interactive recommendations inside a mashup tool) and explain the analogies with mining business process models. The problem is relevant in that reusable model patterns encode valuable modeling and domain knowledge, such as best practices or organizational conventions, from which modelers can learn and benefit when designing own models.

This article describes the implementation and experimental results of a real-time carrier phase differential Global Positioning System (GPS) aided inertial navigation system (INS). The implementation is the result of a study to analyze the capabilities of such a system relative to the requirements of advanced vehicle control and safety systems for intelligent transportation systems. Such navigation systems have many application possibilities (e,g., aviation and precision flight, automated mining, precision farming, dredging, satellite attitude control). Advantages and disadvantages of the GPS, INS, and differential GPS-aided INS approaches are discussed. The implementation achieves 100-Hz vehicle state estimates with position accuracies at the centimeter level through the use of differential carrier phase GPS techniques.

Human pattern recognition skills are remarkable and in many situations far exceed the ability of automated mining algorithms. By building domain-specific interfaces that present information visually, we can combine human detection with machines‘ far greater computational capacity. We illustrate our ideas by describing a suite of visual interfaces we built for telephone fraud detection.