arXiv subjects

Piotr S. Maciąg

Publications and source records attributed to Piotr S. Maciąg.

7 recordsLinked to original sources

arXiv2026

Hierarchical Specialised Ensembles for Classification of Zebrafish Phenotypes Using the Selected Image Recognition Methods

We propose and evaluate three hierarchical ensemble setups for zebrafish phenotype classification from embryo images. In all setups, stage 1 uses a single four-class classifier to assign images to one of the exclusive phenotypes: Normal, Chorion, Dead, or Other. Images classified as Other are then processed in stage 2, where the ensemble design differs across setups: a single multi-label classifier, two specialized multi-label classifiers, or an ensemble of binary classifiers. We compare these setups using three backbone architectures: ResNet18, ViT, and ConvNeXt. Overall, ConvNeXt achieves the best performance across setups, while the specialized hierarchical ensemble in setup 2 provides the best balance in terms of F1-score. The results show that the proposed specialised hierarchical ensembles are effective for zebrafish phenotype recognition, and suggest that ConvNeXt is particularly useful backbone model.

cs.CV↗

arXiv2026

Discovering Frequent Closed Embedded Sub-DAGs in Spatio-Temporal Event Data

We propose a novel approach to mine patterns in spatio-temporal event data based on discovering frequent closed embedded sub-Directed Acyclic Graphs (DAGs). In our method, event instances are represented as nodes labelled by event types, while edges capture spatio-temporal following relationships. We formally define the considered class of patterns and provide the rationale for focusing on closed sub-DAGs as compact and non-redundant representations of recurring interaction patterns. We implement the DigDag algorithm for mining such patterns and experimentally compare its efficiency with two related approaches: propagation pattern mining using the SLEUTH algorithm and Cascading Spatio-Temporal Pattern mining using the CSTPM algorithm. The experimental results demonstrate that our approach is substantially more efficient while operating under comparable parameter settings. Finally, we present a qualitative analysis of selected discovered patterns.

cs.DB↗

arXiv2026

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG). The proposed architecture consists of four modules: Input, RAG, Generation, and Judging and enables users to specify both a question and a target reading content complexity. RAG is employed to retrieve relevant information from the Internet, enriching and grounding the content produced by three modern LLMs: Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B. Reading materials are generated using three prompting strategies (Chain-of-Thought, zero-shot, and few-shot), and the LLM-as-a-Judge module automatically evaluates answer quality and alignment with the desired readability level. Experimental results show that RAG consistently improves system performance across all models and prompting techniques, increasing relevance and particularly groundedness by up to 26-35 percentage points. Overall, the findings demonstrate that the RAG-augmented architecture effectively produces reading content tailored to user queries and desired textual complexity.

cs.IR↗

arXiv2021

Discovery of Crime Event Sequences with Constricted Spatio-Temporal Sequential Patterns

In this article, we introduce a novel type of spatio-temporal sequential patterns called Constricted Spatio-Temporal Sequential (CSTS) patterns and thoroughly analyze their properties. We demonstrate that the set of CSTS patterns is a concise representation of all spatio-temporal sequential patterns that can be discovered in a given dataset. To measure significance of the discovered CSTS patterns we adapt the participation index measure. We also provide CSTS-Miner: an algorithm that discovers all participation index strong CSTS patterns in event data. We experimentally evaluate the proposed algorithms using two crime-related datasets: Pittsburgh Police Incident Blotter Dataset and Boston Crime Incident Reports Dataset. In the experiments, the CSTS-Miner algorithm is compared with the other four state-of-the-art algorithms: STS-Miner, CSTPM, STBFM and CST-SPMiner. As the results of experiments suggest, the proposed algorithm discovers much fewer patterns than the other selected algorithms. Finally, we provide the examples of interesting crime-related patterns discovered by the proposed CSTS-Miner algorithm.

cs.LG↗

arXiv2021

Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks

Unsupervised anomaly discovery in stream data is a research topic with many practical applications. However, in many cases, it is not easy to collect enough training data with labeled anomalies for supervised learning of an anomaly detector in order to deploy it later for identification of real anomalies in streaming data. It is thus important to design anomalies detectors that can correctly detect anomalies without access to labeled training data. Our idea is to adapt the Online evolving Spiking Neural Network (OeSNN) classifier to the anomaly detection task. As a result, we offer an Online evolving Spiking Neural Network for Unsupervised Anomaly Detection algorithm (OeSNN-UAD), which, unlike OeSNN, works in an unsupervised way and does not separate output neurons into disjoint decision classes. OeSNN-UAD uses our proposed new two-step anomaly detection method. Also, we derive new theoretical properties of neuronal model and input layer encoding of OeSNN, which enable more effective and efficient detection of anomalies in our OeSNN-UAD approach. The proposed OeSNN-UAD detector was experimentally compared with state-of-the-art unsupervised and semi-supervised detectors of anomalies in stream data from the Numenta Anomaly Benchmark and Yahoo Anomaly Datasets repositories. Our approach outperforms the other solutions provided in the literature in the case of data streams from the Numenta Anomaly Benchmark repository. Also, in the case of real data files of the Yahoo Anomaly Benchmark repository, OeSNN-UAD outperforms other selected algorithms, whereas in the case of Yahoo Anomaly Benchmark synthetic data files, it provides competitive results to the results recently reported in the literature.

cs.NE↗

arXiv2017

Discovering Sequential Patterns in Event-Based Spatio-Temporal Data by Means of Microclustering - Extended Report

In the paper, we consider the problem of discovering sequential patterns from event-based spatio-temporal data. The problem is defined as follows: for a set of event types $F$ and for a dataset of events instances $D$ (where each instance in $D$ denotes an occurrence of a particular event type in considered spatio-temporal space), discover all sequential patterns defining the following relation between any event types participating in a particular pattern. The following relation $\rightarrow$ between any two event types, denotes the fact that instances of the first event type attract in their spatial proximity and in considered temporal window afterwards occurrences of instances of the second event type. In the article, the notion of sequential pattern in event-based spatio-temporal data has been defined and the already proposed approach to discovering sequential pattern has been reformulated. We show, it is possible to efficiently and effectively discover sequential patterns in event-based spatio-temporal data.

cs.DB↗

arXiv2017

Efficient Discovering of Top-K Sequential Patterns in Event-Based Spatio-Temporal Data

We consider the problem of discovering sequential patterns from event-based spatio-temporal data. The dataset is described by a set of event types and their instances. Based on the given dataset, the task is to discover all significant sequential patterns denoting some attraction relation between event types occurring in a pattern. Already proposed algorithms discover all significant sequential patterns based on the significance threshold, which minimal value is given by an expert. Due to the nature of described data and complexity of discovered patterns, it may be very difficult to provide reasonable value of significance threshold. We consider the problem of effective discovering of K most important patterns in a given dataset (that is discovering of Top-K patterns).

cs.DB↗