Fixed-length Vector Research Articles

AABBA Graph Kernel: Atom-Atom, Bond-Bond, and Bond-Atom Autocorrelations for Machine Learning.

Graphs are one of the most natural and powerful representations available for molecules; natural because they have an intuitive correspondence to skeletal formulas, the language used by chemists worldwide, and powerful, because they are highly expressive both globally (molecular topology) and locally (atom and bond properties). Graph kernels are used to transform molecular graphs into fixed-length vectors, which, based on their capacity of measuring similarity, can be used as fingerprints for machine learning (ML). To date, graph kernels have mostly focused on the atomic nodes of the graph. In this work, we developed a graph kernel based on atom-atom, bond-bond, and bond-atom (AABBA) autocorrelations. The resulting vector representations were tested on regression ML tasks on a data set of transition metal complexes; a benchmark motivated by the higher complexity of these compounds relative to organic molecules. In particular, we tested different flavors of the AABBA kernel in the prediction of the energy barriers and bond distances of the Vaska's complex data set (Friederich et al., Chem. Sci., 2020, 11, 4584). For a variety of ML models, including neural networks, gradient boosting machines, and Gaussian processes, we showed that AABBA outperforms the baseline including only atom-atom autocorrelations. Dimensionality reduction studies also showed that the bond-bond and bond-atom autocorrelations yield many of the most relevant features. We believe that the AABBA graph kernel can accelerate the exploration of large chemical spaces and inspire novel molecular representations in which both atomic and bond properties play an important role.

Particle Swarm Optimization for Efficiently Evolving Deep Convolutional Neural Networks Using an Autoencoder-Based Encoding Strategy

Deep convolutional neural networks (DCNNs) have achieved surpassing success in the field of computer vision, and a number of elaborately designed networks refresh the performance records in benchmark datasets. Recently, evolutionary neural architecture search (ENAS) has become an emerging area, which could employ an evolutionary computation (EC) technique to automatically construct promising network architectures without human intervention. However, existing algorithms still have limitations: most standard EC approaches cannot process flexible-length architecture representations directly, and most fitness evaluation processes suffer from the exhibitive computational cost and the unreliable prediction results. To overcome these shortcomings, we propose an efficient particle swarm optimization (PSO)-based neural architecture search algorithm to search for appropriate dense blocks on image classification tasks, named EAEPSO. EAEPSO addresses the first limitation by designing an autoencoder to encode variable-length network representations as fixed-length latent vectors, which converts the original search space to a latent space that can facilitate the downstream search. Besides, an efficient and effective hierarchical fitness evaluation method is designed to guide the search process to address the second limitation. The experimental results show that EAEPSO is a very competitive ENAS algorithm that achieves an error rate of 2.74% on CIFAR-10 and 16.17% on CIFAR-100, and reduces the computational cost from hundreds or thousands of GPU-days to only 2.2 and 4 GPU-days, respectively. Further analyses investigate the reduced training data’s effect and confirm the effectiveness of both the proposed autoencoder and the proposed hierarchical fitness evaluation method.

PLM-T3SE: Accurate Prediction of Type III Secretion Effectors Using Protein Language Model Embeddings.

The Type III secretion effectors (T3SEs) are bacterial proteins synthesized by Gram-negative pathogens and delivered into host cells via the Type III secretion system (T3SS). These effectors usually play a pivotal role in the interactions between bacteria and hosts. Hence, the precise identification of T3SEs aids researchers in exploring the pathogenic mechanisms of bacterial infections. Since the diversity and complexity of T3SE sequences often make traditional experimental methods time-consuming, it is imperative to explore more efficient and convenient computational approaches for T3SE prediction. Inspired by the promising potential exhibited by pre-trained language models in protein recognition tasks, we proposed a method called PLM-T3SE that utilizes protein language models (PLMs) for effective recognition of T3SEs. First, we utilized PLM embeddings and evolutionary features from the position-specific scoring matrix (PSSM) profiles to transform protein sequences into fixed-length vectors for model training. Second, we employed the extreme gradient boosting (XGBoost) algorithm to rank these features based on their importance. Finally, a MLP neural network model was used to predict T3SEs based on the selected optimal feature set. Experimental results from the cross-validation and independent test demonstrated that our model exhibited superior performance compared to the existing models. Specifically, our model achieved an accuracy of 98.1%, which is 1.8%-42.4% higher than the state-of-the-art predictors based on the same independent data set test. These findings highlight the superiority of the PLM-T3SE and the remarkable characterization ability of PLM embeddings for T3SE prediction.

Anomaly detection based on system text logs of virtual network functions

In virtual network environments building secure and effective systems is crucial for its correct functioning, and so the anomaly detection task is at its core. To uncover and predict abnormalities in the behavior of a virtual machine, it is desirable to extract relevant information from system text logs. The main issue is that text is unstructured and symbolic data, and also very expensive to process. However, recent advances in deep learning have shown remarkable capabilities of handling such data. In this work, we propose using a simple LSTM recurrent network on top of a pre-trained Sentence-BERT, which encodes the system logs into fixed-length vectors. We trained the model in an unsupervised fashion to learn the likelihood of the represented sequences of logs. This way, the model can trigger a warning with an accuracy of 81% when a virtual machine generates an abnormal sequence. Our model approach is not only easy to train and computationally cheap, it also generalizes to the content of any input.

HashGAT-VCA: A vector cellular automata model with hash function and graph attention network for urban land-use change simulation

Vector cellular automata (VCA) models, which excel at representing spatiotemporal dynamics of irregularly shaped land parcels, have been widely employed in land use change simulations. However, current research faces the following issues: (1) most VCA models neglect the spatial heterogeneity of driving factors within each land parcel when evaluating the environmental driving effects; (2) when calculating the neighborhood effects, simple statistics of land use types in neighboring parcels are often used, overlooking the influence of driving factors within neighboring parcels; (3) the ability to explore the interactions between land parcels is often limited. To address the aforementioned issues, this study proposes a HashGAT-VCA model for investigating urban land use changes. The model utilizes a Hash function to encode the non-uniform distribution of each driving factor within each irregularly shaped land parcel into a fixed-length vector, and constructs a graph structure between land parcels based on their spatial topological relationships. By employing a Graph Attention Network (GAT), the model explores the mechanisms of environmental driving effects and inter-parcel interactions to calculate the probability of land use change for each parcel. The proposed HashGAT-VCA model was applied to simulate urban land use changes in Shenzhen, China, from 2009 to 2012. Compared to other VCA models, the HashGAT-VCA demonstrated higher simulation accuracy. The results indicated that HashGAT-VCA can effectively capture the impacts of the heterogeneously distributed driving factors and the interactions between land parcels on land use changes. Additionally, this study simulated land use patterns for the years 2025 and 2030 under ecological control strategies, providing decision support for urban planning.

Learning semi-supervised enrichment of longitudinal imaging-genetic data for improved prediction of cognitive decline

BackgroundAlzheimer’s Disease (AD) is a progressive memory disorder that causes irreversible cognitive decline. Given that there is currently no cure, it is critical to detect AD in its early stage during the disease progression. Recently, many statistical learning methods have been presented to identify cognitive decline with temporal data, but few of these methods integrate heterogeneous phenotype and genetic information together to improve the accuracy of prediction. In addition, many of these models are often unable to handle incomplete temporal data; this often manifests itself in the removal of records to ensure consistency in the number of records across participants.ResultsTo address these issues, in this work we propose a novel approach to integrate the genetic data and the longitudinal phenotype data to learn a fixed-length “enriched” biomarker representation derived from the temporal heterogeneous neuroimaging records. Armed with this enriched representation, as a fixed-length vector per participant, conventional machine learning models can be used to predict clinical outcomes associated with AD.ConclusionThe proposed method shows improved prediction performance when applied to data derived from Alzheimer’s Disease Neruoimaging Initiative cohort. In addition, our approach can be easily interpreted to allow for the identification and validation of biomarkers associated with cognitive decline.

Passage-aware Search Result Diversification

Research on search result diversification strives to enhance the variety of subtopics within the list of search results. Existing studies usually treat a document as a whole and represent it with one fixed-length vector. However, considering that a long document could cover different aspects of a query, using a single vector to represent the document is usually insufficient. To tackle this problem, we propose to exploit multiple passages to better represent documents in search result diversification. Different passages of each document may reflect different subtopics of the query and comparison among the passages can improve result diversity. Specifically, we segment the entire document into multiple passages and train a classifier to filter out the irrelevant ones. Then the document diversity is measured based on several passages that can offer the information needs of the query. Thereafter, we devise a passage-aware search result diversification framework that takes into account the topic information contained in the selected document sequence and candidate documents. The candidate documents’ novelty is evaluated based on their passages while considering the dynamically selected document sequence. We conducted experiments on a commonly utilized dataset, and the results indicate that our proposed method performs better than the most leading methods.

Encrypted Network Traffic Classification Using Deep and Parallel Network-In-Network Models

Network traffic classification analyzes received data packets to identify distinct application or traffic kinds. This research describes a neural network model that uses deep and parallel network-in-network (NIN) architectures to classify encrypted network data. In comparison to typical convolutional neural networks (CNN), NIN uses a micro network after each convolution layer to improve local modeling. Furthermore, NIN uses global average pooling instead of traditional fully connected layers before final classification, resulting in a considerable reduction in the number of model parameters. Our suggested solution uses deep NIN models with several MLP convolutional layers to map fixed-length packet vectors to application or traffic labels. Furthermore, a parallel decision method is created to build two sub-networks to process packet headers and packet bodies separately, taking into account that they may include different types of evidence for classification. Our investigations on the ''ISCX VPN-nonVPN'' encrypted traffic dataset demonstrate that NIN models can achieve a better balance between classification accuracy and model complexity than standard CNNs. The parallel decision technique can increase the accuracy of a single NIN model for classifying encrypted network data. Finally, the test set F1 scores of 0.983 and 0.985 are obtained for traffic characterisation and application identification, respectively

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-Based Similarity

Graph representation learning (GRL) methods, such as graph neural networks and graph transformer models, have been successfully used to analyze graph-structured data, mainly focusing on node classification and link prediction tasks. However, the existing studies mostly only consider local connectivity while ignoring long-range connectivity and the roles of nodes. In this paper, we propose Unified Graph Transformer Networks (UGT) that effectively integrate local and global structural information into fixed-length vector representations. First, UGT learns local structure by identifying the local sub-structures and aggregating features of the k-hop neighborhoods of each node. Second, we construct virtual edges, bridging distant nodes with structural similarity to capture the long-range dependencies. Third, UGT learns unified representations through self-attention, encoding structural distance and p-step transition probability between node pairs. Furthermore, we propose a self-supervised learning task that effectively learns transition probability to fuse local and global structural features, which could then be transferred to other downstream tasks. Experimental results on real-world benchmark datasets over various downstream tasks showed that UGT significantly outperformed baselines that consist of state-of-the-art models. In addition, UGT reaches the third-order Weisfeiler-Lehman power to distinguish non-isomorphic graph pairs.

On the optimality of quantum circuit initial mapping using reinforcement learning

Quantum circuit optimization is an inevitable task with the current noisy quantum backends. This task is considered non-trivial due to the varying circuits’ complexities in addition to hardware-specific noise, topology, and limited connectivity. The currently available methods either rely on heuristics for circuit optimization tasks or reinforcement learning with complex unscalable neural networks such as transformers. In this paper, we are concerned with optimizing the initial logical-to-physical mapping selection. Specifically, we investigate whether a reinforcement learning agent with simple scalable neural network is capable of finding a near-optimal logical-to-physical mapping, that would decrease as much as possible additional CNOT gates, only from a fixed-length feature vector. To answer this question, we train a Maskable Proximal Policy Optimization agent to progressively take steps towards a near-optimal logical-to-physical mapping on a 20-qubit hardware architecture. Our results show that our agent coupled with a simple routing evaluation is capable of outperforming other available reinforcement learning and heuristics approaches on 12 out of 19 test benchmarks, achieving geometric mean improvements of 2.2% and 15% over the best available related work and two heuristics approaches, respectively. Additionally, our neural network model scales linearly as the number of qubits increases.

A Deep Long-Term Joint Temporal-Spectral Network for Spectrum Prediction.

Spectrum prediction is a promising technique to release spectrum resources and plays an essential role in cognitive radio networks and spectrum situation generating. Traditional algorithms normally focus on one-dimensional or predict spectrum values in a slot-by-slot manner and thus cannot fully perceive the spectrum states in complex environments and lack timeliness. In this paper, a deep learning-based prediction method with a simple structure is developed for temporal-spectral and multi-slot spectrum prediction simultaneously. Specifically, we first analyze and construct spectrum data suitable for the model to simultaneously achieve long-term and multi-dimensional spectrum prediction. Then, a hierarchical spectrum prediction system is developed that takes advantage of the advanced Bi-ConvLSTM and the seq2seq framework. The Bi-ConvLSTM captures time-frequency characteristics of spectrum data, and the seq2seq framework is used for long-term spectrum prediction. Furthermore, the attention mechanism is used to address the limitations of the seq2seq framework that compresses all inputs into fixed-length vectors, resulting in information loss. Finally, the experimental results have shown that the proposed model has a significant advantage over the benchmark schemes. Especially, the proposed spectrum prediction model achieves 6.15%, 0.7749, 1.0978, and 0.9628 in MAPE, MAE, RMSE, and R2, respectively, which is better than all the baseline deep learning models.

Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records.

Transformation of patient data extracted from a database into fixed-length numerical vectors requires expertise in topical medical knowledge as well as data manipulation-thus, manual feature design is labor-intensive. In this study, we propose a machine learning-based method to for this purpose applicable to electronic medical data recorded during hospitalization, which utilizes unsupervised feature extraction based on graph embedding. Unsupervised learning is performed on a heterogeneous graph using Graph2Vec, and the inclusion of clinically useful data in the obtained embedding representation is evaluated by predicting readmission within 30 days of discharge based on it. The embedded representations are observed to improve predictive performance significantly as the information contained in the graph increases, indicating the suitability of the proposed method for feature design corresponding to clinical information.

Emotion generation method in online physical education teaching based on data mining of teacher-student interactions.

Different from conventional educational paradigms, online education lacks the direct interplay between instructors and learners, particularly in the sphere of virtual physical education. Regrettably, extant research seldom directs its focus toward the intricacies of emotional arousal within the teacher-student course dynamic. The formulation of an emotion generation model exhibits constraints necessitating refinement tailored to distinct educational cohorts, disciplines, and instructional contexts. This study proffers an emotion generation model rooted in data mining of teacher-student course interactions to refine emotional discourse and enhance learning outcomes in the realm of online physical education. This model includes techniques for data preprocessing and augmentation, a multimodal dialogue text emotion recognition model, and a topic-expanding emotional dialogue generation model based on joint decoding. The encoder assimilates the input sentence into a fixed-length vector, culminating in the final state, wherein the vector produced by the context recurrent neural network is conjoined with the preceding word's vector and employed as the decoder's input. Leveraging the long-short-term memory neural network facilitates the modeling of emotional fluctuations across multiple rounds of dialogue, thus fulfilling the mandate of emotion prediction. The evaluation of the model against the DailyDialog dataset demonstrates its superiority over the conventional end-to-end model in terms of loss and confusion values. Achieving an accuracy rate of 84.4%, the model substantiates that embedding emotional cues within dialogues augments response generation. The proposed emotion generation model augments emotional discourse and learning efficacy within online physical education, offering fresh avenues for refining and advancing emotion generation models.

PseAAC2Vec protein encoding for TCR protein sequence classification

The classification and prediction of T-cell receptors (TCRs) protein sequences are of significant interest in understanding the immune system and developing personalized immunotherapies. In this study, we propose a novel approach using Pseudo Amino Acid Composition (PseAAC) protein encoding for accurate TCR protein sequence classification. The PseAAC2Vec encoding method captures the physicochemical properties of amino acids and their local sequence information, enabling the representation of protein sequences as fixed-length feature vectors. By incorporating physicochemical properties such as hydrophobicity, polarity, charge, molecular weight, and solvent accessibility, PseAAC2Vec provides a comprehensive and informative characterization of TCR protein sequences. To evaluate the effectiveness of the proposed PseAAC2Vec encoding approach, we assembled a large dataset of TCR protein sequences with annotated classes. We applied the PseAAC2Vec encoding scheme to each sequence and generated feature vectors based on a specified window size. Subsequently, we employed state-of-the-art machine learning algorithms, such as support vector machines (SVM) and random forests (RF), to classify the TCR protein sequences. Experimental results on the benchmark dataset demonstrated the superior performance of the PseAAC2Vec-based approach compared to existing methods. The PseAAC2Vec encoding effectively captures the discriminative patterns in TCR protein sequences, leading to improved classification accuracy and robustness. Furthermore, the encoding scheme showed promising results across different window sizes, indicating its adaptability to varying sequence contexts.

Structural Outlier Detection and Zernike-Canterakis Moments for Molecular Surface Meshes-Fast Implementation in Python.

Object retrieval systems measure the degree of similarity of the shape of 3D models. They search for the elements of the 3D model databases that resemble the query model. In structural bioinformatics, the query model is a protein tertiary/quaternary structure and the objective is to find similarly shaped molecules in the Protein Data Bank. With the ever-growing size of the PDB, a direct atomic coordinate comparison with all its members is impractical. To overcome this problem, the shape of the molecules can be encoded by fixed-length feature vectors. The distance of a protein to the entire PDB can be measured in this low-dimensional domain in linear time. The state-of-the-art approaches utilize Zernike-Canterakis moments for the shape encoding and supply the retrieval process with geometric data of the input structures. The BioZernike descriptors are a standard utility of the PDB since 2020. However, when trying to calculate the ZC moments locally, the issue of the deficiency of libraries readily available for use in custom programs (i.e., without relying on external binaries) is encountered, in particular programs written in Python. Here, a fast and well-documented Python implementation of the Pozo-Koehl algorithm is presented. In contrast to the more popular algorithm by Novotni and Klein, which is based on the voxelized volume, the PK algorithm produces ZC moments directly from the triangular surface meshes of 3D models. In particular, it can accept the molecular surfaces of proteins as its input. In the presented PK-Zernike library, owing to Numba's just-in-time compilation, a mesh with 50,000 facets is processed by a single thread in a second at the moment order 20. Since this is the first time the PK algorithm is used in structural bioinformatics, it is employed in a novel, simple, but efficient protein structure retrieval pipeline. The elimination of the outlying chain fragments via a fast PCA-based subroutine improves the discrimination ability, allowing for this pipeline to achieve an 0.961 area under the ROC curve in the BioZernike validation suite (0.997 for the assemblies). The correlation between the results of the proposed approach and of the 3D Surfer program attains values up to 0.99.

DEEP LEARNING FOR ENLARGING HUMAN MOTION CAPTURE (MOCAP) DATASETS

AbstractOBJECTIVESApplication of deep learning approaches to marker trajectories and ground reaction forces (mocap data), is often hampered by small datasets. Enlarging dataset size is possible using some simple numerical approaches, although these may not be suited to preserving the physiological relevance of mocap data. We propose augmenting mocap data using a deep learning architecture called “generative adversarial networks” (GANs). We demonstrate appropriate use of GANs can capture variations of walking patterns due to subject- and task-specific conditions (mass, leg length, age, gender and walking speed), which significantly affect walking kinematics and kinetics, resulting in augmented datasets amenable to deep learning analysis approaches.METHODSA publicly available (https://www.nature.com/articles/s41597-019-0124-4) gait dataset (733 trials, 21 women and 25 men, 37.2 ± 13.0 years, 1.74 ± 0.09 m, 72.0 ± 11.4 kg, walking speeds ranging from 0.18 m/s to 2.04 m/s) was used as the experimental dataset. The GAN comprised three neural networks: an encoder, a decoder, and a discriminator. The encoder compressed experimental data into a fixed-length vector, while the decoder transformed the encoder's output vector and a condition vector (containing information about the subject and trial) into mocap data. The discriminator distinguished between the encoded experimental data from randomly sampled vectors of the same size. By training these networks jointly using the experimental dataset, the generator (decoder) could generate synthetic data respecting specified conditions from randomly sampled vectors. Synthetic mocap data and lower limb joint angles were generated and compared to the experimental data, by identifying the statistically significant differences across the gait cycle for a randomly selected subset of the experimental data from 5 female subjects (73 trials, aged 26–40, weighing 57–74 kg, with leg lengths between 868–931 mm, and walking speeds ranging from 0.81–1.68 m/s). By conducting these comparisons for this subset, we aimed to assess the synthetic data generated using multiple conditions.RESULTSWe visually inspected the synthetic trials to ensure that they appeared realistic. The statistical comparison revealed that, on average, only 2.5% of the gait cycle showed significantly differences in the joint angles of the two data groups. Additionally, the synthetic ground reaction forces deviated from the experimental data distribution for an average of 2.9% of the gait cycle.CONCLUSIONSWe introduced a novel approach for generating synthetic mocap data of human walking based on the conditions that influence walking patterns. The synthetic data closely followed the trends observed in the experimental data, also in the literature, suggesting that our approach can augment mocap datasets considering multiple conditions, an approach unfeasible in previous work. Creation of large, augmented datasets allows the application of other deep learning approaches, with the potential to generate realistic mocap data from limited and non-lab-based data. Our method could also enhance data sharing since synthetic data does not raise ethical concerns. You can generate and download virtual gait data using our GAN approach from https://thisgaitdoesnotexist.streamlit.app/.Declaration of Interest(b) declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported:I declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research project.

Self-Organizing Memory Based on Adaptive Resonance Theory for Vision and Language Navigation

Vision and Language Navigation (VLN) is a task in which an agent needs to understand natural language instructions to reach the target location in a real-scene environment. To improve the model ability of long-horizon planning, emerging research focuses on extending the models with different types of memory structures, mainly including topological maps or a hidden state vector. However, the fixed-length hidden state vector is often insufficient to capture long-term temporal context. In comparison, topological maps have been shown to be beneficial for many robotic navigation tasks. Therefore, we focus on building a feasible and effective topological map representation and using it to improve the navigation performance and the generalization across seen and unseen environments. This paper presents a S elf-organizing Memory based on Adaptive Resonance Theory (SMART) module for incremental topological mapping and a framework for utilizing the SMART module to guide navigation. Based on fusion adaptive resonance theory networks, the SMART module can extract salient scenes from historical observations and build a topological map of the environmental layout. It provides a compact spatial representation and supports the discovery of novel shortcuts through inferences while being explainable in terms of cognitive science. Furthermore, given a language instruction and on top of the topological map, we propose a vision–language alignment framework for navigational decision-making. Notably, the framework utilizes three off-the-shelf pre-trained models to perform landmark extraction, node–landmark matching, and low-level controlling, without any fine-tuning on human-annotated datasets. We validate our approach using the Habitat simulator on VLN-CE tasks, which provides a photo-realistic environment for the embodied agent in continuous action space. The experimental results demonstrate that our approach achieves comparable performance to the supervised baseline.

Self-Organizing Neural Scheduler for the Flexible Job Shop Problem With Periodic Maintenance and Mandatory Outsourcing Constraints.

Scheduling is significant in improving the production efficiency and reducing delivery delays for manufacturing enterprises. Unlike the flexible job-shop scheduling problem, two special constraints are encountered in real-world power supply manufacturing systems: 1) periodic maintenance and 2) mandatory outsourcing. As the characteristics of these constraints are not considered in existing scheduling algorithms, schedules generated by most existing approaches are not optimal or even conflict with these constraints. In this article, a self-organizing neural scheduler (SoNS) is proposed to overcome this limitation. A long short-term memory encoder is developed to transform the variable-length structural information into fixed-length feature vectors. Moreover, the reinforcement learning model is proposed to automatically select policies for improving candidate schedules. To validate the effectiveness of the proposed algorithm, extensive experiments are conducted on over 300 problem instances. The nonparametric Kruskal-Wallis tests confirm that the proposed algorithm outperforms several state-of-the-art methods in terms of effectiveness and robustness within a limited computational budget. It demonstrates that the proposed SoNS can solve scheduling problems with the periodic maintenance and mandatory outsourcing constraints effectively.

Development of an Algorithm for Extracting and Encoding Data from Log Messages of a Computing System for Anomaly Detection Systems

This article is devoted to development of an algorithm for automated analysis and transformation of a log message into a list of features in the form of a fixed-length vector and accumulation of the obtained vectors into a single dataset. The resulted dataset is proposed to be used in machine learning based anomaly detection systems. An additional requirement for the algorithm being developed is the diversity of protocols used to collect log messages in a computer system. These goals were achieved by develop of the software package. The software package collect and parse data from log messages in order to isolate and encode the features from log messages. The software package is enable to collect log messages by several protocols: syslog, SNMP, SQL, reading text and binary files. The data extracted from the log messages of the computing system is considered. The support of LUA scripts for data enrichment is applied. The list of features is generated. The method to encode text data extracted from log messages is proposed. The transformation algorithm of an arbitrary log message into a features vector of fixed dimension is proposed. A methodology for the formation of a dataset for subsequent use in machine learning of the anomaly detection system in a computing system is provided. An example of a dataset storage structure is given.

Self-supervised contrastive representation learning for large-scale trajectories

Trajectory representation learning aims to embed trajectory sequences into fixed-length vector representations while preserving their original spatio-temporal feature proximity. Existing works either learn trajectory representations for specific mining tasks or fail to utilize large amounts of unlabeled trajectory data for representation learning. In this work, we propose a self-supervised Trajectory representation learning based on Reconstruction Contrastive Learning called TrajRCL. To be specific, TrajRCL first obtains low-distortion and high-fidelity views of trajectories through trajectory augmentation. Then, TrajRCL leverages a Transformer based encoder–decoder network to reconstruct low-distortion view trajectories to approximate high-fidelity trajectories. Self-supervised contrastive learning is finally used to enhance the consistency of the two view’s trajectory representations. Extensive experiments on two real-world demonstrate the superiority of our model over state-of-the-art baselines and significant efficiency on similarity trajectory search and k-NN query.