ANNOTE: Annotation of time-series events

This paper analyzes the optimization features of machine learning (ML) model training procedures using multi-GPU systems to enhance cyber security in telecommunication networks. A key aspect of the study is the use of data parallelism, which allows the distribution of the training load across multiple GPUs, significantly reducing training time and improving model accuracy-critical factors for rapid threat detection in cyberspace. A novel approach for optimizing data batch size using Mutual Information (MI) is proposed, which harmonizes the utilization of computational resources with the information content of the training data. MI helps to determine the optimal data batch size that minimizes training errors and improves model accuracy without a significant increase in training time. Experimental results demonstrate the substantial advantages of multi-GPU configurations compared to single-GPU setups, providing faster training and improved model accuracy. It was particularly emphasized that MI-guided batch size tuning significantly outperforms traditional manual tuning methods, ensuring higher validation accuracy and reducing training time. The study showed that the MI-based approach is an effective tool for addressing the problem of optimizing ML model training processes in real-world scenarios where cyber security is critical. The proposed methods allow ML models to train faster and more accurately identify potential threats, making them particularly relevant for telecommunication networks where a rapid response to new threats in real time is required. The implementation of modern computational technologies such as multi-GPU systems and MI-optimized training enhances the efficiency and accuracy of machine learning models. This, in turn, improves cyber security measures and ensures a more reliable defence of telecommunication networks against malicious attacks. It is noted that the proposed approaches can be adapted not only for cyber security but also for other areas where high model accuracy and fast training are important. Future research prospects include the development of new machine learning methods, particularly deep neural networks, the exploration of alternative computational architectures such as quantum computing or distributed systems, and their integration into real-time systems. Special attention should be paid to the ethical aspects of implementing automated cyber security systems, particularly in preventing bias in algorithms and ensuring fairness in their application.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

Medical studies are usually time consuming, cumbersome and extremely costly to perform, and for exploratory research, their results are also difficult to predict a priori. This is particularly the case for rare diseases, for which finding enough patients is difficult and usually requires an international-scale research. In this case, the process can be even more difficult due to the heterogeneity of data-protection regulations, making the data sharing process particularly hard. In this short paper, we propose MedCo2 (pronounced MedCo square), a distributed system that streamlines the process of a medical study by bridging and enabling both data discovery and data analysis among multiple databases, while protecting data confidentiality and patients' privacy. MedCo2 relies on interactive protocols, homomorphic encryption and differential privacy. It enables the privacy-preserving computations of multiple statistics such as cosine similarity and variance, and the training of machine learning models, on patients that are obliviously selected according to specific criteria among multiple databases.

Brain-computer interfaces (BCIs) translate brain activity into digital commands for interaction with the physical world. The technology has great potential in several applied areas, ranging from medical applications to entertainment industry, and creates new conditions for basic research in cognitive neuroscience. The BCIs of today, however, offer only crude online classification of the user's current state of mind, and more sophisticated decoding of mental states depends on time-consuming offline data analysis. The present paper addresses this limitation directly by leveraging a set of improvements to the analytical pipeline to pave the way for the next generation of online BCIs. Specifically, we introduce an open-source research framework that features a modular and customizable hardware-independent design. This framework facilitates human-in-the-loop (HIL) model training and retraining, real-time stimulus control, and enables transfer learning and cloud computing for the online classification of electroencephalography (EEG) data. Stimuli for the subject and diagnostics for the researcher are shown on separate displays using web browser technologies. Messages are sent using the Lab Streaming Layer standard and websockets. Real-time signal processing and classification, as well as training of machine learning models, is facilitated by the open-source Python package Timeflux. The framework runs on Linux, MacOS, and Windows. While online analysis is the main target of the BCI-HIL framework, offline analysis of the EEG data can be performed with Python, MATLAB, and Julia through packages like MNE, EEGLAB, or FieldTrip. The paper describes and discusses desirable properties of a human-in-the-loop BCI research platform. The BCI-HIL framework is released under MIT license with examples at: bci.lu.se/bci-hil (or at: github.com/bci-hil/bci-hil).

Computational cell metabolism models seek to provide metabolic explanations of cell behavior under different conditions or following genetic alterations, help in the optimization of in vitro cell growth environments, or predict cellular behavior in vivo and in vitro. In the extremes, mechanistic models can include highly detailed descriptions of a small number of metabolic reactions or an approximate representation of an entire metabolic network. To date, all mechanistic models have required details of individual metabolic reactions, either kinetic parameters or metabolic flux, as well as information about extracellular and intracellular metabolite concentrations. Despite the extensive efforts and the increasing availability of high-quality data, required in vivo data are not available for the majority of known metabolic reactions; thus, mechanistic models are based primarily on ex vivo kinetic measurements and limited flux information. Machine learning approaches provide an alternative for derivation of functional dependencies from existing data. The increasing availability of metabolomic and lipidomic data, with growing feature coverage as well as sample set size, is expected to provide new data options needed for derivation of machine learning models of cell metabolic processes. Moreover, machine learning analysis of longitudinal data can lead to predictive models of cell behaviors over time. Conversely, machine learning models trained on steady-state data can provide descriptive models for the comparison of metabolic states in different environments or disease conditions. Additionally, inclusion of metabolic network knowledge in these analyses can further help in the development of models with limited data.This chapter will explore the application of machine learning to the modeling of cell metabolism. We first provide a theoretical explanation of several machine learning and hybrid mechanistic machine learning methods currently being explored to model metabolism. Next, we introduce several avenues for improving these models with machine learning. Finally, we provide protocols for specific examples of the utilization of machine learning in the development of predictive cell metabolism models using metabolomic data. We describe data preprocessing, approaches for training of machine learning models for both descriptive and predictive models, and the utilization of these models in synthetic and systems biology. Detailed protocols provide a list of software tools and libraries used for these applications, step-by-step modeling protocols, troubleshooting, as well as an overview of existing limitations to these approaches.

Artificial intelligence (AI) has huge potential to accelerate drug discovery, but challenges remain in implementing AI algorithms that can be used by the broad scientific community. Identification of molecular features and their subsequent use in training of machine learning models may permit prediction of new molecules with enhanced properties. Predictive modeling is particularly applicable to analysis of structure-activity relationships (SARs) and would be a useful tool in the hands of laboratory medicinal chemists. This requires a software platform that is chemically intuitive while providing the user with access to AI methods. The KNIME platform provides such an environment through inclusion of broad chemical toolsets and a user-friendly approach for utilization of machine learning for analysis of SAR data. Here, we illustrate use of KNIME for this purpose, with a focus on discovery of features of highly potent tau inhibitors from a series of structurally diverse polyphenols. Workflows are described that enable implementation of AI tools in KNIME for diverse SAR projects.

The future 6G network will be able to connect massive and various unmanned vehicles (UxVs) into the network, bringing novel requirements toward UxV network security and data privacy. Deploying machine learning (ML)-based intrusion detection on UxVs can be one promising approach. The conventional approach cannot fulfill security and privacy requirements, as the structure can be more flexible, and there may be a lack of a central node in the 6G-based UxV network. Moreover, UxV clients can exhibit high heterogeneity with extremely class-imbalanced training samples. With the presence of federated learning (FL), UxVs can collaborate to train and update ML models while preserving data privacy in the UxV security critical scenario. However, most past works focused on centralized approaches, using cloud servers to assist intrusion detection and service deployments. This article introduces an FL framework with a decentralized design for training ML models on UxVs using intrusion detection as a study case. This scheme can be more flexible, as UxV clients can collaborate to train and synchronize models without the central server. Simulation experiments were conducted to evaluate the efficiency of the proposed approach. Experimental results and theoretical analysis confirm that the proposed method outperforms baseline models with FedAvg and local-trained client models.

Forecasting demand for assets and services can be addressed in various markets, providing a competitive advantage when the predictive models used demonstrate high accuracy. However, the training of machine learning models incurs high computational costs, which may limit the training of prediction models based on available computational capacity. In this context, this paper presents an approach for training demand prediction models using quantum neural networks. For this purpose, a quantum neural network was used to forecast demand for vehicle financing. A classical recurrent neural network was used to compare the results, and they show a similar predictive capacity between the classical and quantum models, with the advantage of using a lower number of training parameters and also converging in fewer steps. Utilizing quantum computing techniques offers a promising solution to overcome the limitations of traditional machine learning approaches in training predictive models for complex market dynamics.

The increase of the computational power in edge devices has enabled the penetration of distributed machine learning technologies such as federated learning, which allows to build collaborative models performing the training locally in the edge devices, improving the efficiency and the privacy for training of machine learning models, as the data remains in the edge devices. However, in some IoT networks the connectivity between devices and system components can be limited, which prevents the use of federated learning, as it requires a central node to orchestrate the training of the model. To sidestep this, peer-to-peer learning appears as a promising solution, as it does not require such an orchestrator. On the other side, the security challenges in IoT deployments have fostered the use of machine learning for attack and anomaly detection. In these problems, under supervised learning approaches, the training datasets are typically imbalanced, i.e. the number of anomalies is very small compared to the number of benign data points, which requires the use of re-balancing techniques to improve the algorithms' performance. In this paper, we propose a novel peer-to-peer algorithm,P2PK-SMOTE, to train supervised anomaly detection machine learning models in non-IID scenarios, including mechanisms to locally re-balance the training datasets via synthetic generation of data points from the minority class. To improve the performance in non-IID scenarios, we also include a mechanism for sharing a small fraction of synthetic data from the minority class across devices, aiming to reduce the risk of data de-identification. Our experimental evaluation in real datasets for IoT anomaly detection across a different set of scenarios validates the benefits of our proposed approach.

Image processing through machine learning techniques such as neural networks is a field of study that has been advancing for some years, but still has open workspaces. Likewise, Transfer Learning (TL) is a more recent approach that has been developed as an alternative to advance in the solution of some problems associated with the training of machine learning models. In this order of ideas, this work seeks to combine image processing and TL for the creation of a model that allows identifying and categorizing emotions in images taken from recordings of face-to-face classes at the university level. This study seeks to combine the benefits of image processing techniques with the ability to transfer knowledge from previously trained models, which allows a more effective detection of emotions in a variety of educational contexts, initially, classes and activities developed in these contexts. The results show that it is feasible to transfer emotion classification models generated from training models with a generic dataset and then transfer them to a particular case represented in a smaller dataset of images taken from a face-to-face educational context. Regarding the F Score performance metric, the algorithm that delivered the best results was LinInt: Linear Interpolation between SrcOnly and TgtOnly with 83.7% accuracy for the transferred model, this is compared to other models such as RegularTransferNN - Regular Transfer with Neural Networks and RegularTransferLR - Regular Transfer with Linear Regression by Transfer learning techniques tested, and also to classifiers such as SVM - Support Vector Machine and KNN - K-Nearest Neighbors.

<p>Since 2019, ECMWF (European Centre for Medium-Range Weather Forecasts) together with EUMETSAT (European Organisation for the Exploitation of Meteorological Satellites) initiated a project named “<strong>European Weather Cloud</strong>” (https://www.europeanweather.cloud/) expected to become operational in 2022. The strategic goal of this initiative is to build and offer a <strong>community cloud infrastructure</strong> on which Member and Co‐operating States of both organizations can create and manage on demand virtual resources enabling access to the ECMWF’s Numerical Weather Predication (NWP) products and EUMETSAT’s satellite data in a timely, efficient, and configurable fashion. Moreover, one of the main goals is to involve more entities in this initiative in a joint effort to form a federation of clouds/data offered from our Member States, for the maximum benefit of the European Meteorological Infrastructure.</p><p>During the current pilot phase of the project several use cases have been defined, mostly aimed at service developers own organisations. These broad categories of use cases are:</p><ul><li>Web services exploring hosted datasets.</li> <li>Infrastructure allowing the running of an atmospheric dispersion model on ECMWF forecast data.</li> <li>Platform to support the training of machine learning models on archive datasets.</li> <li>Platform to support workshops and training courses (DWD/ICON model training, various ECMWF training courses)</li> <li>Environment facilitating research in collaboration with external partners.</li> </ul><p>Some examples of the use cases currently developed at the European Weather Cloud are:</p><ul><li>The Royal Meteorological Institute of Belgium prepares ECMWF forecast data for use in a local atmospheric dispersion model.</li> <li>The German weather service, which is already feeding maps generated by a server it deployed on the cloud into its public GeoPortal service.</li> <li>The Royal Netherlands Meteorological Institute hosts a climate explorer web application based on KNMI climate explorer data and ECMWF weather and climate reanalyses.</li> <li>EUMETSAT Numerical Weather Prediction Satellite Application Facility (NWP SAF) develops a training module will develop a training module for a fast radiative transfer model (RTTOV) based on ERA5 reanalysis data.</li> <li>EUMETSAT and ECMWF joint use case assess bias correction schemes for the assimilation of radiance data based on several satellite data time series.</li> </ul><p>During the current pilot phase of the project, both organizations have organised user and technical workshops to actively engage with the meteorological community to align the evolution of the European Weather Cloud to reflect and satisfy their goals and needs.</p><p>In this presentation, the status of the project will be analysed describing the existing infrastructure, the offered services and how these are accessed by the end-users along with examples of the existing use cases. The plans, next steps for the evolution and the transition to operations of the European Weather Cloud and its relationship with other projects and initiatives will conclude the presentation.</p>

<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">_</sup> One of the biggest challenges faced in deep learning community is the image data annotation, we know how data is essential for any machine learning problems but when it comes to object detection and segmentation (ODS) problems the data preparation process becomes extremely difficult and time-consuming. The data preparation becomes two steps process, first the data collection itself and second the data annotation. In this paper I present AADGen, a novel way of automatic data collection and annotation (DCA) for text detection and segmentation (TDS) problems. This method reduces the time taken for DCA to almost zero and provides error-free data annotation process. The DCA process will help us in building online learning model training by providing on demand continuous stream of training data. I have done extensive experiments on the data annotation process and achieved more than 99% annotation accuracy. I present a fast, scalable, customizable and error free data annotation approach.

Privacy-preserving training of machine learning models aims to avoid or minimize (mitigate) the exact or similar reproduction (leakage) of information contained in the training data. This chapter introduces pre-processing methods (filtering and de-duplication) that prepare the training data to minimize information leakage, followed by a discussion of training and deployment methods (differentially private fine-tuning, noisy knowledge transfer) that provide empirical or theoretical guarantees for the achieved privacy protection with a focus on Large Language Models (LLMs).

Human Pose Estimation (HPE) is an essential computer vision task that plays a significant role in ergonomics, human-centered design of workplaces, and collaborative robotics, particularly in providing a safe, adaptive, and valuable human-robot collaboration (HRC). Nevertheless, the need for a concise and practical approach to setting up a multicamera and multimodal system for HPE dataset generation remains an open issue in the literature.The main goal of this work is to describe in concise steps a protocol that serves as a guide in the exploratory stage of the approach to construct an extensive multicamera and multimodal dataset used to enhance HRC. In this paper, the proposed protocol specifically addresses the challenge of designing a biomechanical model that can consistently reproduce complex and variable human motion analyses in an assembly task while considering ergonomic factors. Furthermore, the resulting work led to the definition of a marker set for one single-person future pipeline involving the placement of thirty-two reflective markers for 3D motion analysis, specifically emphasizing the upper segments of the human body, including the hands. The future generation of this dataset will hold significant promise for advancing the study of HRC. It will introduce reliable and precise multimodal data collection, such as human kinematics and video data, including depth data, which will then be used for posture metrics analysis. Finally, the dataset will be a valuable resource for the research community, enabling the training of machine learning models. These models will empower collaborative robots (cobots) to learn from human demonstrations, enhancing their efficiency and ergonomic performance in assembly tasks.

The prediction of autism features in relation to age groups has not been definitively addressed, despite the fact that several studies have been conducted using various methodologies. Research in the field of neuroscience has demonstrated that intracranial brain volume and the corpus callosum provide crucial information for the identification of autism spectrum disorder (ASD). Based on these findings, we present Decision Tree-based Autism Prediction System (DT-APS) and Random Forest-based Autism Prediction System (RF-APS) for automatic ASD identification in this paper. These systems utilize characteristics extracted from the corpus callosum and intracranial brain volume, and are based on machine learning techniques. By prioritizing characteristics with the highest discriminatory power for ASD classification, our proposed approaches, DT-APS and RF-APS, have not only enhanced identification accuracy but also simplified the training of machine learning models. The initial step of this method involves dividing each MRI scan into distinct anatomical areas. These areas are adjacent slices in a single 2D image. Each 2D image is mapped to the curvelet space, and the set of GGD parameters characterizes each of the distinct curvelet sub-bands. The AQ-10 dataset was utilized to evaluate the proposed model. When tested on both types of datasets, the suggested prediction model demonstrated superior performance compared to alternative approaches in all relevant metrics, including accuracy, specificity, sensitivity, precision, and false positive rate (FPR).