Automated chart summarization is crucial for enhancing data accessibility and enabling efficient information extraction from visual data. While recent advances in visual-language models (VLMs) have demonstrated promise, existing methods often suffer from limitations in matching the generated summary to the chart data and in reasoning about complex chart patterns. This paper introduces End-to-End Visual Chain-of-Thought (V-CoT) for chart summarization, a novel approach optimized for Large Vision-Language Models (LVLMs). Our method directly trains an LVLM to process chart images and generate textual summaries in an end-to-end fashion, eliminating the need for explicit chart parsing modules. We incorporate a visual Chain-of-Thought mechanism through instruction fine-tuning, implicitly guiding the LVLM to perform visual reasoning steps during summary generation. Evaluated on the large-scale Chart-Sum-QA dataset, our V-CoT method significantly outperforms state-of-the-art baselines across a range of automatic metrics, including BLEU, BLEURT, CIDEr, and CS, and demonstrates superior matching degree and reasoning correctness in human evaluations. Ablation studies and detailed analyses further validate the effectiveness and robustness of our proposed approach, establishing a new benchmark for end-to-end chart summarization.

We introduce Visual Premise Proving (VPP), a novel task tailored to refine the process of chart question answering by deconstructing it into a series of logical premises. Each of these premises represents an essential step in comprehending a chart's content and deriving logical conclusions, thereby providing a granular look at a model's reasoning abilities. This approach represents a departure from conventional accuracy-based evaluation methods, emphasizing the model's ability to sequentially validate each premise and ideally mimic human analytical processes. A model adept at reasoning is expected to demonstrate proficiency in both data retrieval and the structural understanding of charts, suggesting a synergy between these competencies. However, in our zero-shot study using the sophisticated MATCHA model on a scientific chart question answering dataset, an intriguing pattern emerged. The model showcased superior performance in chart reasoning (27\%) over chart structure (19\%) and data retrieval (14\%). This performance gap suggests that models might more readily generalize reasoning capabilities across datasets, benefiting from consistent mathematical and linguistic semantics, even when challenged by changes in the visual domain that complicate structure comprehension and data retrieval. Furthermore, the efficacy of using accuracy of binary QA for evaluating chart reasoning comes into question if models can deduce correct answers without parsing chart data or structure. VPP highlights the importance of integrating reasoning with visual comprehension to enhance model performance in chart analysis, pushing for a balanced approach in evaluating visual data interpretation capabilities.

Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches proposed so far in the literature have severe limitations: they either require prior domain knowledge used to design the anomaly discovery algorithms, or become cumbersome and expensive to use in situations with recurrent anomalies of the same type. In this work, we address these problems, and propose an unsupervised method suitable for domain agnostic subsequence anomaly detection. Our method, Series2Graph, is based on a graph representation of a novel low-dimensionality embedding of subsequences. Series2Graph needs neither labeled instances (like supervised techniques) nor anomaly-free data (like zero-positive learning techniques), and identifies anomalies of varying lengths. The experimental results, on the largest set of synthetic and real datasets used to date, demonstrate that the proposed approach correctly identifies single and recurrent anomalies without any prior knowledge of their characteristics, outperforming by a large margin several competing approaches in accuracy, while being up to orders of magnitude faster. This paper has appeared in VLDB 2020.

Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many applications. Convolutional neural networks perform well for the data series classification task; though, the explanations provided by this type of algorithm are poor for the specific case of multivariate data series. Addressing this important limitation is a significant challenge. In this paper, we propose a novel method that solves this problem by highlighting both the temporal and dimensional discriminant information. Our contribution is two-fold: we first describe a convolutional architecture that enables the comparison of dimensions; then, we propose a method that returns dCAM, a Dimension-wise Class Activation Map specifically designed for multivariate time series (and CNN-based models). Experiments with several synthetic and real datasets demonstrate that dCAM is not only more accurate than previous approaches, but the only viable solution for discriminant feature discovery and classification explanation in multivariate time series. This paper has appeared in SIGMOD'22.

According to a new KAUST study, machine learning approaches can achieve an assumption-free analysis of epidemic case data with amazingly good prediction accuracy and the flexibility to incorporate new data dynamically. Yasminah Alali, an intern in KAUST's 2021 Saudi Summer Internship (SSI) program, developed a proof of concept that reveals a possible alternative to traditional parameter-driven mechanistic models by removing human bias and assumptions from analysis, revealing the underlying story of the data. Using publicly released COVID-19 incidence and recovery data from India and Brazil, Alali leveraged her experience working with artificial intelligence models to design a framework to fit the characteristics and time-evolving nature of epidemic data in collaboration with KAUST's Ying Sun and Fouzi Harrou. To create an effective Gaussian process regression (GPR) based model for forecasting recovered and confirmed COVID-19 cases in two significantly impacted countries, India and Brazil, the researchers first used Bayesian optimization to modify the Gaussian process regression (GPR) hyperparameters. However, the time dependency in the COVID-19 data series is ignored by machine learning models.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. Durbin Watson is more powerful but there is a catch.

Recognition of anomalous events is a challenging but critical task in many scientific and industrial fields, especially when the properties of anomalies are unknown. In this paper, we present a new anomaly concept called "unicorn" or unique event and present a new, model-independent, unsupervised detection algorithm to detect unicorns. The Temporal Outlier Factor (TOF) is introduced to measure the uniqueness of events in continuous data sets from dynamic systems. The concept of unique events differs significantly from traditional outliers in many aspects: while repetitive outliers are no longer unique events, a unique event is not necessarily outlier in either pointwise or collective sense; it does not necessarily fall out from the distribution of normal activity. The performance of our algorithm was examined in recognizing unique events on different types of simulated data sets with anomalies and it was compared with the standard Local Outlier Factor (LOF). TOF had superior performance compared to LOF even in recognizing traditional outliers and it also recognized unique events that LOF did not. Benefits of the unicorn concept and the new detection method were illustrated by example data sets from very different scientific fields. Our algorithm successfully recognized unique events in those cases where they were already known such as the gravitational waves of a black hole merger on LIGO detector data and the signs of respiratory failure on ECG data series. Furthermore, unique events were found on the LIBOR data set of the last 30 years.

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density estimation techniques. Our empirical findings show that the proposed approach is able to effectively detect adversarial examples crafted by non-adaptive attackers, i.e., not specifically tuned to bypass the detection method. Given our promising results, we plan to extend our analysis to adaptive attackers in future work.

We consider Markov models of stochastic processes where the next-step conditional distribution is defined by a kernel density estimator (KDE), similar to Markov forecast densities and certain time-series bootstrap schemes. The KDE Markov models (KDE-MMs) we discuss are nonlinear, nonparametric, fully probabilistic representations of stationary processes, based on techniques with strong asymptotic consistency properties. The models generate new data by concatenating points from the training data sequences in a context-sensitive manner, together with some additive driving noise. We present novel EM-type maximum-likelihood algorithms for data-driven bandwidth selection in KDE-MMs. Additionally, we augment the KDE-MMs with a hidden state, yielding a new model class, KDE-HMMs. The added state variable captures non-Markovian long memory and signal structure (e.g., slow oscillations), complementing the short-range dependences described by the Markov process. The resulting joint Markov and hidden-Markov structure is appealing for modelling complex real-world processes such as speech signals. We present guaranteed-ascent EM-update equations for model parameters in the case of Gaussian kernels, as well as relaxed update formulas that greatly accelerate training in practice. Experiments demonstrate increased held-out set probability for KDE-HMMs on several challenging natural and synthetic data series, compared to traditional techniques such as autoregressive models, HMMs, and their combinations.

This is part 3 of a multi-part guide on working with time series data in R. You can find the previous parts here: Part 1, Part 2. Generated data like that used in Parts 1 and 2 is great for sake of example, but not very interesting to work with. So let's get some real-world data that we can work with for the rest of this tutorial. There are countless sources of time series data that we can use including some that are already included in R and some of its packages. But I'd like to expand our horizons a bit.