Relevant Temporal Patterns Research Articles

A deep fusion model for stock market prediction with news headlines and time series data

Time series forecasting models are essential decision support tools in real-world domains. Stock market is a remarkably complex domain, due to its quickly evolving temporal nature, as well as the multiple factors having an impact on stock prices. To date, a number of machine learning-based approaches have been proposed in the literature to tackle stock trend prediction. However, they typically tend to analyze a single data source or modality, or consider multiple modalities in isolation and rely on simple combination strategies, with a potential reduction in their modeling power. In this paper, we propose a multimodal deep fusion model to predict stock trends, leveraging daily stock prices, technical indicators, and sentiment in daily news headlines published by media outlets. The proposed architecture leverages a BERT-based model branch fine-tuned on financial news and a long short-term memory (LSTM) branch that captures relevant temporal patterns in multivariate data, including stock prices and technical indicators. Our experiments on 12 different stock datasets with prices and news headlines demonstrate that our proposed model is more effective than popular baseline approaches, both in terms of accuracy and trading performance in a portfolio analysis simulation, highlighting the positive impact of multimodal deep learning for stock trend prediction.

IJCM_305A: Forecasting Dengue and Chikungunya incidence using Time Series Analysis Modelling

Background: In recent years, the rise in vector-borne diseases, particularly Dengue and Chikungunya, has posed a significant public health challenge globally. Epidemiological data from the Integrated Disease Surveillance Program (IDSP) is a useful resource for forecasting and early outbreak identification by applying effective models like Sessional Autoregressive Integrated Moving Average (SARIMA) models has proven effective in capturing temporal dependencies in various fields. Objective: To forecast the dengue and chikungunya cases in India using Seasonal Autoregressive Integrated Moving Average models. Methodology: we preprocessing the IDSP dataset to extract relevant temporal patterns and trends. Subsequently, SARIMA models are applied to capture the time dependent dynamics of disease occurrences. The model’s performance is evaluated through rigorous validation processes, including cross-validation techniques, to ensure its reliability and generalizability. Results: This study considered a secondary data set of weekly dengue and chikungunya cases over the period of 2019 to 2023. The time plot shows several spikes in the data, indicating periods where the number of dengue cases increased significantly in the most recent years. Forecast of the future dengue and chikungunya cases was done for the next one year (2024). we observed that the number of dengue and chikungunya cases has fluctuated over time but has generally remained within a certain range. The forecast predicts a significant increase in cases as we move towards the latter half of 2024, with a very sharp spike towards the end of the forecast period. Conclusion: In conclusion, utilizing a secondary dataset spanning from 2019 to 2023, this study employed time series analysis to forecast future Dengue and Chikungunya cases. The forecast predicts a significant increase in dengue cases during 2024 which can lead to potential implications for public health practitioners, policymakers, and researchers involved in infectious disease management.

Temporal pattern mining for knowledge discovery in the early prediction of septic shock

Temporal pattern mining can be employed to detect patterns and trends in a patient's health status as it evolves over time. However, these methods often produce an overwhelming number of patterns, impeding knowledge discovery and practical implementation in acute care settings. To address this, we propose a framework that focuses on identifying a concise set of relevant temporal patterns and static variables from electronic health records for the early prediction of septic shock. Sepsis is caused by an adverse immune response to infection that triggers widespread inflammation throughout the body, which can progress to septic shock and ultimately result in death if not treated promptly. The analysis of health state patterns in sepsis patients over time offers the potential to predict septic shock prior to its onset, enabling proactive healthcare interventions. Our framework incorporates a temporal pattern mining method and four feature selection techniques. We discover that selecting features based on a model-based wrapper approach yields the highest prediction performance among these techniques. On the other hand, the use of information value identifies more multi-state patterns with abnormal health states, providing healthcare providers with valuable indicators of patient deterioration.

Acquisition of temporal patterns from electronic health records: an application to multimorbid patients

BackgroundThe exponential growth of digital healthcare data is fueling the development of Knowledge Discovery in Databases (KDD). Extracting temporal relationships between medical events is essential to reveal hidden patterns that can help physicians find optimal treatments, diagnose illnesses, detect drug adverse reactions, and more. This paper presents an approach for the extraction of patient evolution patterns from electronic health records written in Catalan and/or Spanish.MethodsWe propose a robust formulation for extracting Temporal Association Rules (TARs) that goes beyond simple rule extraction by considering the sequence of multiple visits. Our highly configurable algorithm leverages this formulation to extract Temporal Association Rules from sequences of medical instances. We can generate rules in the desired format, content, and temporal factors while accounting for different levels of abstraction of medical instances. To demonstrate the effectiveness of our methodology, we applied it to extract patient evolution patterns from clinical histories of multimorbid patients suffering from heart disease and stroke who visited Primary Care Centers (CAP) in Catalonia. Our main objective is to uncover complex rules with multiple temporal steps, that comprise a set of medical instances.ResultsAs we are working with real-world, error-prone data, we propose a process of validation of the results by expert practitioners in primary care. Despite our limited dataset, the high percentage of patterns deemed correct and relevant by the experts is promising. The insights gained from these patterns can inform preventive measures and help detect risk factors, ultimately leading to better treatments and outcomes for patients.ConclusionOur algorithm successfully extracted a set of meaningful and relevant temporal patterns, especially for the specific type of multimorbid patients considered. These patterns were evaluated by experts and demonstrated the ability to predict risk factors that are commonly associated with certain diseases. Moreover, the average time gap between the occurrence of medical events provided critical insight into the term of these risk factors. This information holds significant value in the context of primary healthcare and preventive medicine, highlighting the potential of our method to serve as a valuable medical tool.

Spike timing-dependent plasticity alters electrosensory neuron synaptic strength in vitro but does not consistently predict changes in sensory tuning in vivo.

How do sensory systems optimize detection of behaviorally relevant stimuli when the sensory environment is constantly changing? We addressed the role of spike timing-dependent plasticity (STDP) in driving changes in synaptic strength in a sensory pathway and whether those changes in synaptic strength could alter sensory tuning. It is challenging to precisely control temporal patterns of synaptic activity in vivo and replicate those patterns in vitro in behaviorally relevant ways. This makes it difficult to make connections between STDP-induced changes in synaptic physiology and plasticity in sensory systems. Using the mormyrid species Brevimyrus niger and Brienomyrus brachyistius, which produce electric organ discharges for electrolocation and communication, we can precisely control the timing of synaptic input in vivo and replicate these same temporal patterns of synaptic input in vitro. In central electrosensory neurons in the electric communication pathway, using whole cell intracellular recordings in vitro, we paired presynaptic input with postsynaptic spiking at different delays. Using whole cell intracellular recordings in awake, behaving fish, we paired sensory stimulation with postsynaptic spiking using the same delays. We found that Hebbian STDP predictably alters sensory tuning in vitro and is mediated by NMDA receptors. However, the change in synaptic responses induced by sensory stimulation in vivo did not adhere to the direction predicted by the STDP observed in vitro. Further analysis suggests that this difference is influenced by polysynaptic activity, including inhibitory interneurons. Our findings suggest that STDP rules operating at identified synapses may not drive predictable changes in sensory responses at the circuit level.NEW & NOTEWORTHY We replicated behaviorally relevant temporal patterns of synaptic activity in vitro and used the same patterns during sensory stimulation in vivo. There was a Hebbian spike timing-dependent plasticity (STDP) pattern in vitro, but sensory responses in vivo did not shift according to STDP predictions. Analysis suggests that this disparity is influenced by differences in polysynaptic activity, including inhibitory interneurons. These results suggest that STDP rules at synapses in vitro do not necessarily apply to circuits in vivo.

Septic shock prediction and knowledge discovery through temporal pattern mining

Sepsis is the body's adverse response to infection which can lead to septic shock and eventually death if not treated in a timely manner. Analyzing patterns in sepsis patients' health status over time can help predict septic shock before its onset allowing healthcare providers to be more proactive. Temporal pattern mining methods can be used to identify trends in a patient's health status over time. If these methods return too many patterns, however, this can hinder knowledge discovery and practical implementation at the bedside in acute care settings. We propose a framework to find a small number of relevant temporal patterns in electronic health records for the early prediction of septic shock. Our framework consists of a temporal pattern mining method and three pattern selection techniques based on non-contrasted group support (PST1), contrasted group support (PST2), and model predictive power (PST3, PST4). We find that model-based feature selection approaches PST3 and PST4 yield the best prediction performance among these techniques. However, PST2 identifies more multi-state patterns with abnormal health states, which can give healthcare providers indicators of patient deterioration towards septic shock. Hence, from a knowledge discovery perspective, it may be worthwhile to sacrifice a small amount of prediction power for actionable patient health information through the implementation of PST2.

Intracortical depth analyses of frequency-sensitive regions of human auditory cortex using 7T fMRI

Despite recent advances in auditory neuroscience, the exact functional organization of human auditory cortex (AC) has been difficult to investigate. Here, using reversals of tonotopic gradients as the test case, we examined whether human ACs can be more precisely mapped by avoiding signals caused by large draining vessels near the pial surface, which bias blood-oxygen level dependent (BOLD) signals away from the actual sites of neuronal activity. Using ultra-high field (7T) fMRI and cortical depth analysis techniques previously applied in visual cortices, we sampled 1mm isotropic voxels from different depths of AC during narrow-band sound stimulation with biologically relevant temporal patterns. At the group level, analyses that considered voxels from all cortical depths, but excluded those intersecting the pial surface, showed (a) the greatest statistical sensitivity in contrasts between activations to high vs. low frequency sounds and (b) the highest inter-subject consistency of phase-encoded continuous tonotopy mapping. Analyses based solely on voxels intersecting the pial surface produced the least consistent group results, even when compared to analyses based solely on voxels intersecting the white-matter surface where both signal strength and within-subject statistical power are weakest. However, no evidence was found for reduced within-subject reliability in analyses considering the pial voxels only. Our group results could, thus, reflect improved inter-subject correspondence of high and low frequency gradients after the signals from voxels near the pial surface are excluded. Using tonotopy analyses as the test case, our results demonstrate that when the major physiological and anatomical biases imparted by the vasculature are controlled, functional mapping of human ACs becomes more consistent from subject to subject than previously thought.

Behavioral and Single-Neuron Sensitivity to Millisecond Variations in Temporally Patterned Communication Signals.

In many sensory pathways, central neurons serve as temporal filters for timing patterns in communication signals. However, how a population of neurons with diverse temporal filtering properties codes for natural variation in communication signals is unknown. Here we addressed this question in the weakly electric fish Brienomyrus brachyistius, which varies the time intervals between successive electric organ discharges to communicate. These fish produce an individually stereotyped signal called a scallop, which consists of a distinctive temporal pattern of ∼8-12 electric pulses. We manipulated the temporal structure of natural scallops during behavioral playback and in vivo electrophysiology experiments to probe the temporal sensitivity of scallop encoding and recognition. We found that presenting time-reversed, randomized, or jittered scallops increased behavioral response thresholds, demonstrating that fish's electric signaling behavior was sensitive to the precise temporal structure of scallops. Next, using in vivo intracellular recordings and discriminant function analysis, we found that the responses of interval-selective midbrain neurons were also sensitive to the precise temporal structure of scallops. Subthreshold changes in membrane potential recorded from single neurons discriminated natural scallops from time-reversed, randomized, and jittered sequences. Pooling the responses of multiple neurons improved the discriminability of natural sequences from temporally manipulated sequences. Finally, we found that single-neuron responses were sensitive to interindividual variation in scallop sequences, raising the question of whether fish may analyze scallop structure to gain information about the sender. Collectively, these results demonstrate that a population of interval-selective neurons can encode behaviorally relevant temporal patterns with millisecond precision. The timing patterns of action potentials, or spikes, play important roles in representing information in the nervous system. However, how these temporal patterns are recognized by downstream neurons is not well understood. Here we use the electrosensory system of mormyrid weakly electric fish to investigate how a population of neurons with diverse temporal filtering properties encodes behaviorally relevant input timing patterns, and how this relates to behavioral sensitivity. We show that fish are behaviorally sensitive to millisecond variations in natural, temporally patterned communication signals, and that the responses of individual midbrain neurons are also sensitive to variation in these patterns. In fact, the output of single neurons contains enough information to discriminate stereotyped communication signals produced by different individuals.

Genealogical approaches to the temporal origins of the Central American gap: Speciation and divergence in Pacific <i>Chthamalus</i> (Sessilia: Chthamalidae)

A large section of the tropical Eastern Pacific coastline is nearly devoid of reef or consolidated habitat, and is known as the Central American Gap as it is associated with a biogeographic transition in fish and invertebrate species. We analyze phylogeographic data for intertidal barnacles (Chthamalus) to identify relevant temporal patterns that describe the origins of this biogeographic transition (the Mexican-Panamic Transition Zone). These contrasts of populations on either side of the transition zone include two pairs of closely related species (C. panamensis and C. hedgecocki; C. southwardorum and a Southern form of C. southwardorum), as well as gene flow data within one species (C. panamensis) that currently is found on both sides of the boundary between provinces. Using sequence data from a prior phylogenetic study, we used traditional (net nucleotide divergence) measures as well as coalescent analyses that incorporate the isolation-migration model to identify the likely time of separation between Northern and Southern taxa in two species pairs. A total of 67 individuals were sequenced at two mitochondrial (cytochrome c oxidase I, 16S) and one nuclear (elongation factor 1-alpha) gene regions. Our analyses indicate that the regional isolation of these intertidal barnacles occurred approximately 315-400kya, with subsequent expansion of C. panamensis from the Southern region into the North much more recently. There are insufficient survey data to conclusively document the absence of species from this group within the Central American Gap region near the Gulf of Tehuantepec. However, appropriate habitat is quite sparse in this region and other environmental factors, including upwelling and water temperature, are likely to be associated with isolation of many species in the Mexican and Panamic provinces sensu stricto. Some taxa may maintain gene flow across this region, but very few genetic studies have been completed on such taxa. Until further work is done, distinguishing between prior hypotheses of a faunal gap, or a faunal transition zone, is somewhat speculative. Additional taxonomic revision will be necessary in Chthamalus but is beyond the scope of this paper.

Joint projections of North Pacific sea surface temperature from different global climate models

The goal of this work is to develop a general methodology to obtain joint projections of climate indexes, based on ensembles of global climate model (GCM) output and historical records. As a case study, we consider sea surface temperature (SST) in the North Pacific Ocean. We use two ensembles of 17 different GCM results, made available in the fourth assessment report of the Intergovernmental Panel on Climate Change: one corresponds to 20th‐century forcing conditions, and the other corresponds to the A1B emission scenario for the 21st century. Given a representation of the SST spatio‐temporal fields based on a common set of empirical orthogonal functions, we use a hierarchical Bayesian model for the empirical orthogonal function coefficients to estimate a baseline and a set of model discrepancies. These components are all time varying. The model enables us to extract relevant temporal patterns of variability from both the observations and the simulations and obtain common patterns from all 18 series. This is used to obtain unified 21st‐century forecasts of relevant oceanic indexes as well as whole fields of North Pacific SST forecast. We compare the forecast index for different timescales and compare the SST reconstructions with the GCMs for the 21st century. Although the coarser time resolution produces clearer and faster results, we show that finer timescales produce results with structures that are similar to ones obtained at coarser scales. Copyright © 2012 John Wiley & Sons, Ltd.

Timing in the auditory system of the bat.

Echolocating bats use audition to guide much of their behavior. As in all vertebrates, their lower brainstem contains a number of parallel auditory pathways that provide excitatory or inhibitory outputs differing in their temporal discharge patterns and latencies. These pathways converge in the auditory midbrain, where many neurons are tuned to biologically important parameters of sound, including signal duration, frequency-modulated sweep direction, and the rate of periodic frequency or amplitude modulations. This tuning to biologically relevant temporal patterns of sound is created through the interplay of the time-delayed excitatory and inhibitory inputs to midbrain neurons. Because the tuning process requires integration over a relatively long time period, the rate at which midbrain auditory neurons respond corresponds to the cadence of sounds rather than their fine structure and may provide an output that is closely matched to the rate at which motor systems operate.