New Methods Enhance the Processing of Permanent Gauge Data

A developing practice: OSINT by the Dutch police As a result of citizens’ use of the internet and smartphones, an increasing amount of information is becoming available online, which may be relevant to police work. To monitor developments in society and detect criminal offences, the police must make use of online data. For this reason, police organizations worldwide have invested in OSINT (open source intelligence). This also applies to the police in the Netherlands. This article maps out how the Dutch police use OSINT and what current issues arise in this context. OSINT by the police is used in criminal investigations and intelligence work. Within investigations, there are significant differences in its use between types of offences and organizational units. OSINT is still a relatively new investigative method and is not yet common practice for all investigators. In this respect, investigations in the Netherlands are not yet fully “up to date.” In the field of intelligence, OSINT contributes to building an intelligence position that provides insight into what is happening and what may potentially occur. This takes place in various contexts, including phenomenon analyses, real-time intelligence, and threat assessments for protection and security. At present, several issues and developments are relevant to OSINT by the police. These include the validation of information in an era of synthetic media and deepfakes, the legal mismatch between practice and available statutory powers, the growing use of closed online environments such as encrypted messaging groups, and the massive data volumes generated during large-scale events. The article concludes that OSINT by the police is an emergent, increasingly indispensable practice. However, the expansion of powers raises fundamental questions about privacy, civil liberties, and the future role of the police in democratic society.

As operators move towards intelligent wells and fields, data management systems need to be adapted to support the transformation. With technology advancements and a growing network of sensors that enable faster and higher frequency data gathering, there is a need to sustainably scale data management systems to the level required to handle higher volumes of data and faster processing response. The most comprehensive systems, however, are those that support efficient decision making. A Middle Eastern operator embarked on a project to enhance the existing well integrity data management system to add new capabilities and extend the system to other fields in the Arabian Gulf. The updated well integrity management standards were also incorporated to reflect the operator's latest business principles. The system was further integrated with a geographical information system and well integrity business workflows were developed. The system automatically monitors data and sends notifications on abnormal well conditions. This is being supported by a single repository of all necessary data, historical inspection, pressure trends and well intervention histories. Through continuous monitoring of operating conditions by the system and automatic task assignment when conditions indicate the rise of well problems, engineers can work more proactively and manage a growing number of assets. Automated monitoring relieves engineers from the efforts previously exerted on manual processes and allows them to focus on the engineering analysis. Having a single repository with historical inspection, safety critical equipment test data, full pressure trends and well intervention histories, provides a wealth of information from which to make informed decisions. A benefit of having such methodology, from a management viewpoint, is that there is a common approach to well integrity indicators and key performance indicators for all assets. This allows benchmarking from field to field so that a consistent decision making approach can be made and resources of different types properly focused on those places where the challenges and demands are higher. In a period where the industry has gone through some substantial rationalization, the fact that staff can be assigned to different assets through the use of a common system with which they are familiar helps them to quickly understand, analyze and tackle well problems. This paper examines the application of intelligent software analytics and a robust system to optimize resources and enhance efficiency and performance. By collecting a wider range of data with increased frequency and applying intelligent software analytics, the operator has been able to greatly improve the asset management coverage, thus improving efficiency and performance; satisfying regulatory requirements and achieving production targets.

Although the properties of geomaterials vary spatially, geotechnical site investigations often take sparse measurements from a limited number of locations. To estimate geotechnical properties at unsampled locations, interpolation is often needed. This paper presents a Bayesian supervised learning method for interpolation of site-specific geotechnical data from sparse measurements. The interpolation is considered as a supervised learning problem and is solved under a Bayesian framework. Numerical examples are used to evaluate performance of the proposed method and to provide a comparative study with ordinary kriging, a popular interpolation method in geosciences applications. Results show that when the available measurement points are sparse and limited, the Bayesian supervised learning method performs better than kriging. When the number of measurement points is large, results from the proposed method and kriging are almost identical. In addition, the proposed method is data-driven and nonparametric. It does not require a detrending process when dealing with nonstationary data, and it bypasses estimation of a parametric form of autocorrelation structure (e.g., semivariogram in conventional kriging interpolation). A well-known challenge in kriging is the selection of a suitable semivariogram function form or a suitable trend function form for detrending, given sparse geotechnical data. The proposed Bayesian supervised learning method bypasses these challenges and is particularly suitable for nonstationary geotechnical data. Standard preprocessing steps such as outlier removal and noise reduction apply to Bayesian supervised learning.

With the increasing volume of temporal data and the expanding range of application domains, research on temporal knowledge graph completion (TKGC) has become a prominent topic in the fields of artificial intelligence and data science. The primary objective of TKGC methods is to infer and model missing entities and relations, thereby enhancing the completeness and accuracy of knowledge graphs to provide more reliable and comprehensive information for various downstream tasks. Existing methods fail to adequately consider the importance of query-relevant historical information when balancing local and global historical data. Moreover, they lack effective modeling of the underlying relationships and periodic features among events in snapshots at specific times. To address these issues, we propose a completion method based on temporal-aware encoding and entity attention contrast (TEEAC). The TEEAC model employs a local–global encoder to encode local and global historical information separately, thereby capturing different types of dependencies in temporal knowledge graphs. On this basis, a temporal entity encoder is introduced to capture query-relevant historical information and explore the influence of temporal periodicity on historical snapshot events. Additionally, the TEEAC model incorporates an entity attention encoder that dynamically adjusts the embedding weights of different entities within historical information, enhancing the model’s ability to capture query-relevant historical information. Furthermore, by adopting local–global contrastive learning, the model effectively distinguishes entities with high relevance from historical information, thereby achieving improved prediction performance in the extrapolation task. Finally, comparative experiments conducted on four public datasets validate the effectiveness of the proposed TEEAC model.

Navigating the Digital Twin Network landscape: A survey on architecture, applications, privacy and security

Nowadays, the prediction of student performance is still complicated to analyze the talent of individuals and the effort to improve their academic performance. Moreover, the researchers are performed to analyze the outcomes of student performance but the educational database consists of a huge data volume, which is hard to train the small sample. In this research work, a new hybrid deep learning model with optimized entropy rough set theory is developed to predict the student’s performance accurately. The preprocessing phase is performed with outlier removal and the data-filling method. The features are mined from the preprocessed data by Entropy weighted Rough set-based feature mining. A novel meta-heuristic hybrid Galactic Rider Swarm Optimization (GRSO) algorithm is developed for feature mining. A hybrid deep learning-based Convolutional Recurrent Network (CRN) is implemented for prediction, where the classification performance is improved by the GRSO algorithm. Here, the hyperparameters of the Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are optimized by the GRSO algorithm. Here, the sensitivity and accuracy rate of the recommended GRSO-CRN method attain 94% and 93%. The simulation outcome of the proposed GRSO-CRN model achieves enriched performance.

With the rapid development of intelligent medical digitization and people's aspirations for a healthy life, the issue of medical data security has become increasingly prominent. The sensitivity and value of medical data demand that we take effective measures to safeguard data security. This not only pertains to the risks of data leakage and personal information abuse but also to issues of social stability. To address the problem of medical data security, the advantages and characteristics of the distributed architecture of fog computing are primarily utilized, and RSA algorithm technology is integrated. This enables the effective processing and storage of the large volume of heterogeneous data generated by medical service systems in the context of the Internet of Things at fog nodes, achieving low-latency processing and efficient storage of medical data and ensuring the data security of data sources. Simultaneously, technical means such as identity authentication and access control, fine-grained permission management, and data encryption in intelligent medical service systems are employed to enhance data security protection. Research has demonstrated that the integration of fog computing and RSA algorithm technology can effectively reduce computational costs, ensure the security of medical data flow, protect patient privacy, and prevent improper information access and abuse. The intelligent medical data security technology based on fog computing is of great significance for protecting patient privacy and data security. Meanwhile, it plays an important role in safeguarding medical data, improving service quality, and promoting industry development, and it represents an important research direction in the future intelligent medical field.

Chapter 13 - Multiscale Agent-Based Computer Models in Skeletal Tissue Regeneration

Data visualization is an indispensable part of data analysis, transforming abstract data into intuitive information through charts, images and other forms to help people better understand the laws and trends behind the data. As the volume of data continues to increase, people need to understand and analyze data more intuitively and effectively. As a result, data visualization becomes a powerful tool that can help people extract useful information from massive amounts of data and present it in an intuitive way. This paper will focus on the concept, technology and application of data visualization to discuss the importance and development trend of data visualization in the field of enterprise intelligence.

The contributed volume aims to explicate and address the difficulties and challenges that of seamless integration of the two core disciplines of computer science, i.e., computational intelligence and data mining. Data Mining aims at the automatic discovery of underlying non-trivial knowledge from datasets by applying intelligent analysis techniques. The interest in this research area has experienced a considerable growth in the last years due to two key factors: (a) knowledge hidden in organizations databases can be exploited to improve strategic and managerial decision-making; (b) the large volume of data managed by organizations makes it impossible to carry out a manual analysis. The book addresses different methods and techniques of integration for enhancing the overall goal of data mining. The book helps to disseminate the knowledge about some innovative, active research directions in the field of data mining, machine and computational intelligence, along with some current issues and applications of related topics.

Analysis of available sources reveals that situation awareness (SAW) for various objectives is realized through different approaches and techniques. Situation awareness is the perception of the elements in the environment within a volume of time and space, the comprehension of their meaning, and the projection of their status in the near future. The research done showed that results received in the field of artificial intelligence could be used to elaborate real SAW work algorithms. The most developed fields here are artificial neural networks (ANN) and genetic algorithms (GA). New progress and research in informatics, based on information processing implementing protein molecules' immune networks, processing principles appeared under the term of "immunocomputing" (IC). However, precision of situation recognition when using IC method directly depends on the training sample volume and quality, as it happens when using any other pattern recognition method. And yet during analysis it is possible that training data volume could be evidently insufficient for the correct situation recognition. In that case Aggregated Indices Method (AIM) could be used for the situation analysis. In the context of this method it is assumed that the experts assess the factors defining the tactical situation. In the method's framework any process of alternatives' preference estimation by an aggregated preference index may be put into terminological shape of correspondent objects quality estimation by an aggregated quality index. In this paper the combined approach to the tactical situation analysis is offered. The mentioned methods application in the uniform situation analysis system with the purpose of the recognition reliability rate increase is examined.

A core task in statistical analysis, especially in the era of Big Data, is the fitting of flexible, high-dimensional, and non-linear models to noisy data in order to capture meaningful patterns. This can often result in challenging non-linear and non-convex global optimization problems. The large data volume that must be handled in Big Data applications further increases the difficulty of these problems. Swarm Intelligence Methods for Statistical Regression describes methods from the field of computational swarm intelligence (SI), and how they can be used to overcome the optimization bottleneck encountered in statistical analysis. Features Provides a short, self-contained overview of statistical data analysis and key results in stochastic optimization theory Focuses on methodology and results rather than formal proofs Reviews SI methods with a deeper focus on Particle Swarm Optimization (PSO) Uses concrete and realistic data analysis examples to guide the reader Includes practical tips and tricks for tuning PSO to extract good performance in real world data analysis challenges

Assessing soil water content variation in a small mountainous catchment over different time scales and land covers using geographical variables

Deep learning is one of the subsets of machine learning that is widely used in artificial intelligence (AI) field such as natural language processing and machine vision. The deep convolution neural network (DCNN) extracts high-level concepts from low-level features and it is appropriate for large volumes of data. In fact, in deep learning, the high-level concepts are defined by low-level features. Previously, in optimization algorithms, the accuracy achieved for network training was less and high-cost function. In this regard, in this study, AdaptAhead optimization algorithm was developed for learning DCNN with robust architecture in relation to the high volume data. The proposed optimization algorithm was validated in multi-modality MR images of BRATS 2015 and BRATS 2016 data sets. Comparison of the proposed optimization algorithm with other commonly used methods represents the improvement of the performance of the proposed optimization algorithm on the relatively large dataset. Using the Dice similarity metric, we report accuracy results on the BRATS 2015 and BRATS 2016 brain tumor segmentation challenge dataset. Results showed that our proposed algorithm is significantly more accurate than other methods as a result of its deep and hierarchical extraction.

As wildland fires amplify in size in many regions in the western USA, land and water managers are increasingly concerned about the deleterious effects on drinking water supplies. Consequences of severe wildfires include disturbed soils and areas of thick ash cover, which raises the concern of the risk of water contamination via ash. The persistence of ash cover and depth were monitored for up to 90 days post-fire at nearly 100 plots distributed between two wildfires in Idaho and Washington, USA. Our goal was to determine the most ‘cost’ effective, operational method of mapping post-wildfire ash cover in terms of financial, data volume, time, and processing costs. Field measurements were coupled with multi-platform satellite and aerial imagery collected during the same time span. The image types spanned the spatial resolution of 30 m to sub-meter (Landsat-8, Sentinel-2, WorldView-2, and a drone), while the spectral resolution spanned visible through SWIR (short-wave infrared) bands, and they were all collected at various time scales. We that found several common vegetation and post-fire spectral indices were correlated with ash cover (r = 0.6–0.85); however, the blue normalized difference vegetation index (BNDVI) with monthly Sentinel-2 imagery was especially well-suited for monitoring the change in ash cover during its ephemeral period. A map of the ash cover can be used to estimate the ash load, which can then be used as an input into a hydrologic model predicting ash transport and fate, helping to ultimately improve our ability to predict impacts on downstream water resources.