Analysis Of Temporal Features Research Articles

Empower smart cities with sampling-wise dynamic facial expression recognition via frame-sequence contrastive learning

In the construction of smart cities, facial expression analysis plays a crucial role. It can be used in traffic monitoring systems to alleviate traffic pressure by analyzing the emotional states of drivers and passengers. In the field of smart healthcare, it can provide more precise treatment and services to patients. In the realm of social entertainment, it can offer more intelligent and personalized interactions. In summary, the application of emotion computing technology will play an increasingly significant role in the development of smart cities in the future. In the task of dynamic facial expression recognition (DFER), analyzing the spatial–temporal features of video sequences has become a common research approach. However, facial expression sequences often contain a significant number of neutral frames and noisy frames, potentially increasing computational costs and reducing performance. Effectively extracting key frames for spatial–temporal feature analysis is a critical aspect of dynamic facial expression recognition. To address this issue, we proposed a sampling-wise dynamic facial expression recognition via frame-Sequence contrastive learning method, called SW-FSCL. The SW-FSCL method aims to improve the performance of DFER by using intelligent dual-stream sampling strategies and frame-sequence contrastive learning, extract key frame and reduce the impact of neutral frames and noisy frames. We proposed a key frame proposal (KFP) block to analyze the spatial–temporal features of sequences, calculating weight ratios for key frame extraction. Due to potential information loss in long sequences, we introduce a temporal aggregation (TA) block to prevent data loss and ensure the integrity of temporal information. The experimental results provide compelling evidence that the proposed approach not only outperforms all current state-of-the-art algorithms on two widely-used benchmark datasets (DFEW, FERV39k), but also visualization results produces insights into the interpretability of the SW-FSCL method.

An Analysis of Temporal Features in Multivariate Time Series to Forecast Network Events

Analyzing network traffic over time is crucial for understanding the changes in network activity. To properly examine network traffic patterns over time, multiple network events in each timestamp need to be converted to time series data. In this study, we propose a new approach to transform network traffic data into time series formats by extracting temporal features to analyze normal/attack patterns. The normal patterns indicate network traffic occurred without any intrusion-related activities, whereas the attack patterns denote potential threats that deviate from the normal patterns. To evaluate the features, long short-term memory (LSTM) is applied to forecast multi-step network normal and attack events. Visual analysis is also performed to enhance the understanding of key features in the network. We compared the performance differences using time scales of 60 and 120 s. Upon evaluation, we found that the temporal features extracted with the 60 s time scale exhibited better performance in forecasting future network events.

Record-Breaking heavy rainfall around Henan Province in 2021 and future projection of extreme conditions under climate change

A record-breaking extreme precipitation event that occurred in July 2021 over Henan Province is investigated through observations and reanalysis data. Meanwhile, future extreme precipitation conditions are projected through an ensemble projection model using climate model outputs as input. The long duration, the wide range of influence, the extensive amount of accumulated precipitation, and the high intensity of precipitation are the four major characteristics of this event. Further, the physical causes of this event are explored. First of all, the abnormal northward movement of the western North Pacific Subtropical High is quite significant. Secondly, two slow-moving typhoons are found, which intensify inland moisture transport. Thirdly, after encountering the windward slope, the water vapor is violently lifted and continuously accumulated. Future projections of multiple extreme indices show that more extreme precipitation conditions are expected across the entire Henan Province. In addition, the contribution of various sources to the uncertainty of the ensemble projection are quantified. The global climate model is the primary contributing factor. Meanwhile, the effects explained by the interactive effects between global climate models and shared social-economic pathways cannot be neglected. Our study has constructed an analysis framework called the “Four-in-One” (spatial–temporal feature analysis, causal analysis, future projection, and uncertainty quantification). It provides further insight into changes in local extreme precipitation conditions. The overall framework of this study is equally applicable to investigating other types of extreme events.

Time-resolved EEG signal analysis for motor imagery activity recognition

Accurately characterizing brain activity requires detailed feature analysis in the temporal, spatial, and spectral domains. While previous research has proposed various spatial and spectral feature extraction methods to distinguish between different cognitive tasks, temporal feature analysis for each separate brain region and frequency band has been largely overlooked. This study introduces two novel approaches for recognizing cognitive activity: temporal entropic profiling and time-aligned common spatio-spectral patterns analysis. These approaches capture and use discriminative short-lived signal segments for motor imagery activity recognition. In Approach-1, we evaluated nine different measures to determine timing parameters that showed altered behavior associated with maximal inter-activity differences, which we then used in a machine-learning framework. In Approach-2, we used the best-performing signal characteristic measures from Approach-1 to determine the optimum latency of each channel at each frequency band for a CSP-based activity recognition strategy. We evaluated both approaches on two online available motor imagery EEG datasets and achieved average recognition accuracy levels of 86%. We compared our methods with four established BCI methods. The performance results show that our approaches exceeded the benchmark methods' performances, with notable improvements in the proposed time-aligned common spatio-spectral patterns approach. This study demonstrates that motor imagery recognition performance is improved when a temporal analysis is adopted alongside spatio-spectral neural feature analysis and that timing parameters associated with the maximal entropic difference of EEG segments to the cognitive tasks varied between different brain regions and subjects.

Gender Neutral Language in (Greater) Buenos Aires, (Greater) La Plata, and Córdoba: An Analysis of Social Context Information Using Textual and Temporal Features.

In this article, I explore Twitter data to analyze Gender Neutral Language (GNL) in (Greater) Buenos Aires, (Greater) La Plata, and Córdoba. The goal is to characterize the social context behind GNL. Social context analysis of social media data is challenging given that this data type does not contain the social characteristics of its users and the circumstances under which the tweets were written. In order to fill this gap, I will derive the social context information from textual and temporal features by analyzing the names of locations, companies, and people used in the text and relating these entities to the message of the tweet. The analysis of temporal features will give us insights into the correlation between language use and social events. Our results show that the general characterization of the social context behind GNL is associated with socio-economically rich areas in city centers. Users of GNL in the investigated areas address certain groups of people with words that express familiarity and close social relationships, such as those meaning “friends” and “neighbors” and that give them information about a political, cultural, or social event or concerning commercial products/services. The temporal analysis by month supports this characterization by showing that certain political and social events induce a higher frequency of GNL. This paper contributes to previous research on GNL in Argentina by testing existing hypotheses quantitatively. The new discovery presented here is that political activism is not the only language context in which GNL is used in social media and that GNL is not exclusively used in big cities of Argentina but also in smaller cities.

Temporal feature analysis method describing for automata models of computation systems

The paper reported the temporal feature analysis method describing for automata models of computation systems. The method is based on from source algorithm to modified algorithm expanding makes it possible to take characteristics of work process related to execution time measurement. The paper considers the transition method from source algorithm representation to modification a final state machine with additional states providing registration of temporal features. The paper demonstrates method usage example on computer system authorization algorithm, approves an algorithm complexity for features registration O(n) for n-states automata algorithm. The method can be used for a large class algorithm, but is recommended to apply it to an algorithm, separated on procedure thus mean of commands amount should be more than 500 for more time measurement accuracy.

Automated cognitive health assessment in smart homes using machine learning

The Internet of Things (IoT) provides smart solutions for future urban communities to address key benefits with the least human intercession. A smart home offers the necessary capabilities to promote efficiency and sustainability to a resident with their healthcare-related, social, and emotional needs. In particular, it provides an opportunity to assess the functional health ability of the elderly or individuals with cognitive impairment in performing daily life activities. This work proposes an approach named Cognitive Assessment of Smart Home Resident (CA-SHR) to measure the ability of smart home residents in executing simple to complex activities of daily living using pre-defined scores assigned by a neuropsychologist. CA-SHR also measures the quality of tasks performed by the participants using supervised classification. Furthermore, CA-SHR provides a temporal feature analysis to estimate if the temporal features help to detect impaired individuals effectively. The goal of this study is to detect cognitively impaired individuals in their early stages. CA-SHR assess the health condition of individuals through significant features and improving the representation of dementia patients. For the classification of individuals into healthy, Mild Cognitive Impaired (MCI), and dementia categories, we use ensemble AdaBoost. This results in improving the reliability of the CA-SHR through the correct assignment of labels to the smart home resident compared with existing techniques.

Automatic statistical evaluation of quality of unit selection speech synthesis with different prosody manipulations

Abstract Quality of speech synthesis is a crucial issue in comparison of various text-to-speech (TTS) systems. We proposed a system for automatic evaluation of speech quality by statistical analysis of temporal features (time duration, phrasing, and time structuring of an analysed sentence) together with standard spectral and prosodic features. This system was successfully tested on sentences produced by a unit selection speech synthesizer with a male as well as a female voice using two different approaches to prosody manipulation. Experiments have shown that for correct, sharp, and stable results all three types of speech features (spectral, prosodic, and temporal) are necessary. Furthermore, the number of used statistical parameters has a significant impact on the correctness and precision of the evaluated results. It was also demonstrated that the stability of the whole evaluation process is improved by enlarging the used speech material. Finally, the functionality of the proposed system was verified by comparison of the results with those of the standard listening test.

Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network.

The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. Four hundred sixty-three patients with gliomas who underwent preoperative MRI were enrolled in the study. All the patients had immunohistopathologic diagnoses of either IDH-wildtype or IDH-mutant gliomas. Tumor subregions were segmented using a convolutional neural network followed by manual correction. DSC perfusion MRI was performed to obtain T2* susceptibility signal intensity-time curves from each subregion of the tumors: enhancing tumor, non-enhancing tumor, peritumoral edema, and whole tumor. These, with arterial input functions, were fed into a neural network as multidimensional inputs. A convolutional long short-term memory model with an attention mechanism was developed to predict IDH genotypes. Receiver operating characteristics analysis was performed to evaluate the model. The IDH genotype predictions had an accuracy, sensitivity, and specificity of 92.8%, 92.6%, and 93.1%, respectively, in the validation set (area under the curve [AUC], 0.98; 95% confidence interval [CI], 0.969-0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% CI, 0.898-0.982). In temporal feature analysis, T2* susceptibility signal intensity-time curves obtained from DSC perfusion MRI with attention weights demonstrated high attention on the combination of the end of the pre-contrast baseline, up/downslopes of signal drops, and/or post-bolus plateaus for the curves used to predict IDH genotype. We developed an explainable recurrent neural network model based on DSC perfusion MRI to predict IDH genotypes in gliomas.

Feature-Based Hand Gesture Recognition Using an FMCW Radar and its Temporal Feature Analysis

In this paper, feature-based gesture recognition in a frequency modulated continuous wave (FMCW) radar system is introduced. We obtain a range-Doppler map (RDM) from raw signals of FMCW radar and generate a variety of features from the RDM. The features are broadly defined to reflect radar-specific characteristics as well as statistical values commonly used in machine learning. Among these radar features, those that are highly correlated with gesture recognition are selected by the proposed feature selection algorithm, which is a wrapper-based feature selection algorithm incorporated with a quantum-inspired evolutionary algorithm (QEA). Furthermore, the information factor based on the minimum redundancy maximum relevance criterion is applied to QEA in order to find feature subsets effectively. The proposed algorithm is able to extract from all feature sets feature subsets related to gesture recognition, and improves the gesture recognition accuracy of the FMCW radar system. In addition, we analyze which features of the radar are helpful for gesture recognition and perform effective gesture recognition using the features determined through feature analysis.

Polarization predictions for inflationary CMB power spectrum features

We conduct a model-independent analysis of temporal features during inflation in the large-scale CMB temperature power spectrum allowing for the possibility of non-negligible tensor contributions. Of 20 principal components of the inflationary history, the suppression of power at low multipoles beginning with a glitch at multipoles $\ell \sim 20-40$ implies deviations in 2-3 of them with 2-3$\sigma$ deviations in each, with larger values reflecting cases where tensors are allowed.If tensors are absent, the corresponding $E$-mode polarization features follow a similar pattern but are predicted to be up to twice as large. They offer the opportunity to soon double the significance of inflationary features or eliminate them as an explanation of temperature features. The tensor degeneracy with features in the temperature power spectrum is broken not only by $B$ but also by $E$-polarization. A precision measurement of $E$-mode polarization at multipoles from $\ell\sim 20-60$ can potentially provide an independent constraint on tensors that is less subject to dust foreground uncertainties.

Detailed analysis of temporal features on contrast enhanced ultrasound may help differentiate intrahepatic cholangiocarcinoma from hepatocellular carcinoma in cirrhosis.

AimTo verify if detailed analysis of temporal enhancement patterns on contrast enhanced ultrasound (CEUS) may help differentiate intrahepatic cholangiocarcinoma (ICC) from hepatocellular carcinoma (HCC) in cirrhosis.MethodsThirty three ICC and fifty HCC in cirrhosis were enrolled in this study. The contrast kinetics of ICC and HCC was analyzed and compared.ResultsStatistical analysis did not reveal significant difference between ICC and HCC in the time of contrast first appearance and arterial peak maximum time. ICC displayed much earlier washout than that of HCC (47.93±26.45 seconds vs 90.86±31.26 seconds) in the portal phase, and most ICC (87.9%) showed washout before 60 seconds than HCC (16.0%). Much more ICC (78.8%) revealed marked washout than HCC (12.0%) while most HCC (88.0%) showed mild washout or no washout in late part of the portal phase (90–120 seconds). Twenty six out of thirty three ICC (78.8%) demonstrated both early washout(<60seconds) and marked washout in late part of the portal phase, whereas, only six of fifty HCC (12.0%)showed these temporal enhancement features (p = 0.000).When both early washout and marked washout in the portal phase are taken as diagnostic criterion for ICC, the diagnostic sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 78.8%,88.0%,81.3%,86.3%,and 84.3% respectively by CEUS.ConclusionsAnalysis of detailed temporal enhancement features on CEUS is helpful differentiate ICC from HCC in cirrhosis.If a nodule in cirrhotic liver displays hyper-enhancement in the arterial phase followed by early and marked washout in the portal phase, the nodule is highly suspicious of ICC rather than HCC.

A Four‐level Focus+Context Approach to Interactive Visual Analysis of Temporal Features in Large Scientific Data

AbstractIn this paper we present a new approach to the interactive visual analysis of time‐dependent scientific data – both from measurements as well as from computational simulation – by visualizing a scalar function over time for each of tenthousands or even millions of sample points. In order to cope with overdrawing and cluttering, we introduce a new four‐level method of focus+context visualization. Based on a setting of coordinated, multiple views (with linking and brushing), we integrate three different kinds of focus and also the context in every single view. Per data item we use three values (from the unit interval each) to represent to which degree the data item is part of the respective focus level. We present a color compositing scheme which is capable of expressing all three values in a meaningful way, taking semantics and their relations amongst each other (in the context of our multiple linked view setup) into account. Furthermore, we present additional image‐based postprocessing methods to enhance the visualization of large sets of function graphs, including a texture‐based technique based on line integral convolution (LIC). We also propose advanced brushing techniques which are specific to the time‐dependent nature of the data (in order to brush patterns over time more efficiently). We demonstrate the usefulness of the new approach in the context of medical perfusion data.

Brainstem mechanisms for analyzing temporal patterns of echolocation sounds: a model for understanding early stages of speech processing?

Because of their stereotyped audio–vocal behavior and highly accessible brainstem circuitry, echolocating bats provide a good model system in which to study the neural mechanisms that underlie the analysis of temporal features of sound. This paper reviews the lower brainstem auditory circuitry and describes selected forms of information processing that are performed in the pathways of the lower brainstem and auditory midbrain (inferior colliculus (IC)). Several examples of neural circuits in echolocating bats point out the ways in which inputs with different properties converge on IC neurons to create selectivity for specific temporal features of sound that are common to speech and echolocation. The initial transformations of auditory nerve input that occur in the lower brainstem pathways include a change in sign from excitatory input to inhibitory output, changes in discharge pattern, and the creation of delay lines. Convergence of multiple inputs on neurons in the IC produces tuning for temporal features of sound including duration, the direction of frequency sweeps, modulation rate, and interstimulus interval. The auditory cortex exerts control over some of this processing by sharpening or shifting neuronal filter properties. The computational processes that occur in the IC result in integration across a time scale that is consistent with the rate at which biological sounds are produced, whether they be echolocation signals or human speech components.

Analysis of Temporal Features of Gamma‐Ray Bursts in the Internal Shock Model

In a recent paper we calculated the power density spectrum of gamma-ray bursts arising from multiple shocks in a relativistic wind. The wind optical thickness is one of the factors to which the power spectrum is most sensitive; therefore, we have further developed our model by taking into account the photon downscattering on the cold electrons in the wind. For an almost optically thick wind we identify a combination of ejection features and wind parameters that yield bursts with an average power spectrum in agreement with observations and with an efficiency of converting the wind kinetic energy in 50-300 keV emission of order 1%. For the same set of model features, the interval time between peaks and the pulse fluence have distributions consistent with the lognormal distribution observed in real bursts.

Time coding in the midbrain of mormyrid electric fish. II. Stimulus selectivity in the nucleus exterolateralis pars posterior.

The anterior and posterior exterolateral nuclei (ELa and ELp) of the mormyrid midbrain are thought to play a critical role in the temporal analysis of the electric discharge waveforms of other individuals. The peripheral electroreceptors receiving electric organ discharges (EODs) of other fish project through the brainstem to ELa via a rapid conducting pathway. EODs, composed of brief, but stereotyped waveforms are encoded as a temporal pattern of spikes. From previous work, we know that phase locking is precise in ELa. Here it is shown that evoked potentials recorded from ELp show a similar high degree of phase locking, although the evoked potentials last much longer. Single-unit recordings in ELp reveal two distinct populations of neurons in ELp: type I cells are responsive to voltage step functions, and not tuned for stimulus duration; type II cells are tuned to a specific range of stimulus durations. Type II cells are less responsive than type I cells, tend to respond with bursts of action potentials rather than with single spikes, have a longer latency, show weaker time locking to stimuli, and are more sensitive to stimulus polarity and amplitude. The stimulus selectivity of type II cells may arise from convergence of type I cell inputs. Despite the loss of rapid conduction between ELa and ELp, analysis of temporal features of waveforms evidently continues in ELp, perhaps through a system of labeled lines.

Courtship communication and hearing in an African electric fish

Among sound‐producing fishes, Pollimyrus isidori is of particular interest because of its unusually large repertoire of sounds (5), and because its ears (sacculi) are specialized for sound pressure detection. Males use temporally patterned sounds for courting females, and the male's sonic behavior is elicited by electric signals from the female. The courtship sounds are composed of trains of clicks, and inter‐click interval (ICI) distinguishes the different sounds. The processing of these temporal features is being explored in the brain (mesencephalon) with single unit electrophysiology. The P. isidori auditory system is most sensitive to sounds in the region where amplitude spectrum for the communication sounds peaks (235 Hz), and at a distance of a meter from a sound‐producing male (i.e., about 20 body lengths) many neurons would be at least 20–30 dB above threshold. Most neurons are broadly tuned (Q10dB⩽2), and precisely represent temporal periodicities in their phase‐locked activity. A subpopulation of neurons shows an increased probability of response when the ICI is close to that of one of the courtship sounds. These neurons probably play an important role in the brain's analysis of temporal features of communication sounds. [Work supported by NIH NRSA DC00020‐02 and CDR P50 DC00293‐06.]

An automated technique for analysis of temporal features in animal vocalizations

An automated method is described for quantifying the variation in temporal pattern of the frequency components in animal vocalizations. The tape-recorded signals are electronically preprocessed to enable direct analysis by a digital computer. Several examples of temporal parameter analysis are shown for the mating call of a neotropical frog Eleutherodactylus coqui. The principal advantage of this technique is that it provides a continuous measurement combined with a statistical measure and fine temporal resolution.