Search

Purpose: The purpose of this review was to evaluate the effects of physical activity on children's free recall, cued recall, and recognition episodic memory and to explore potential moderating factors. Methods: The following databases were searched: PubMed, ERIC, APA Psych Info, CINHAL, SPORTDiscus, and Google Scholar. Studies were included if: (1) participants were aged 4–18 years, (2) participants were typically developed, (3) participants were randomized to groups, (4) interventions employed gross movements, (5) sedentary group was used for control, (6) memory tests were quantitative, and (7) employed acute or chronic intervention. Results: 14 studies met inclusion criteria resulting in the analysis of data from 7 free recall, 7 cued recall, and 8 recognition memory tests. Physical activity was found to have a positive influence on tests free (g = 0.56), cued recall (g = 0.67), and no influence on tests of recognition (g = 0.06). While some moderator analyses were significant, the authors do not consider these results to be meaningful in application. Conclusions: The effects of acute and chronic physical activity enhance specific aspects of long-term episodic memory. These findings suggest physical activity interventions developed for children may be expected to benefit some, but not all, types of memory processing. [ABSTRACT FROM AUTHOR]

Nanowires (NWs) composed of 2,4-bis[(4-diethylamino)-2-hydroxyphenyl] squaraine were prepared by evaporation-induced self-assembly (EISA). NWs were ∼560 nm wide (aspect ratios: 10–90). X-ray diffraction analysis indicated polymorphism (monoclinic/triclinic). Optical data reported the triclinic phase with energetic disorder. Given the favorable alignment of the Au work function and squaraine HOMO energy, symmetric, unipolar metal–insulator–metal devices were formed by the EISA of NW meshes on inter-digitated Au electrodes. Room temperature DC I–V characteristics displayed hysteretic I–V loops, indicating memristive behavior. At low bias, data indicated Ohmic transport with carrier extraction facilitated by thermionic emission. At high biases, devices exhibited space-charge-limited conduction in the presence of shallow traps. At 77 K, data indicated Ohmic transport at low bias with carrier extraction by thermionic emission while, at high biases, trap-limited space-charge-limited conduction in the presence of traps distributed in energy, with carrier extraction by Fowler–Nordheim tunneling, was observed. The I–V hysteresis was eliminated at 77 K and attenuated by fast scan rates at room temperature, suggesting that carrier trapping/de-trapping underpinned the hysteresis. In impedance measurements, the device response fitted a Randles equivalent circuit indicating purely electronic conduction. By applying voltage waveforms, I–V hysteresis and analog resistive switching (memristive) functionality were observed. Device conductance could be increased sweep by sweep, giving conductance tuning through distinct states, with wait time- or voltage-erase options, consistent with trap filling/emptying effects. Repeated erase–write–read of multiple distinct states over many voltage cycles during continuous use in air was demonstrated. Finally, synaptic functions, e.g., pulse-dependent plasticity, and short- to long-term memory transition, were successfully emulated. [ABSTRACT FROM AUTHOR]

Local diffusivity of a protein depends crucially on the conformation, and the conformational fluctuations are often non-Markovian. Here, we investigate the Langevin equation with non-Markovian fluctuating diffusivity, where the fluctuating diffusivity is modeled by a generalized Langevin equation under a double-well potential. We find that non-Markovian fluctuating diffusivity affects the global diffusivity, i.e., the diffusion coefficient obtained by the long-time trajectories when the memory kernel in the generalized Langevin equation is a power-law form. On the other hand, the diffusion coefficient does not change when the memory kernel is exponential. More precisely, the global diffusivity obtained by a trajectory whose length is longer than the longest relaxation time in the memory kernel is not affected by the non-Markovian fluctuating diffusivity. We show that these non-Markovian effects are the consequences of an everlasting effect of the initial condition on the stationary distribution in the generalized Langevin equation under a double-well potential due to long-term memory. [ABSTRACT FROM AUTHOR]

This study comprehensively assesses various recurrent neural networks (RNNs) for decoding the elbow angle from electromyogram (EMG) signals, a crucial aspect in myoelectric interfaces. EMG signals from the shoulder girdle and arm were recorded during goal-directed reaching movements, and linear envelopes were continuously mapped to the elbow angle by three RNN architectures: nonlinear autoregressive exogenous (NARX), Elman, and long-term short memory (LSTM). All three approaches effectively captured the complex dynamics of the multi-input to a single-output regression problem. Regarding within-subject variability, the NARX, Elman, and LSTM demonstrated superior accuracy and robustness compared to dynamic feedforward neural networks like time-delay neural networks. Notably, there was no statistically significant distinction among NARX, Elman, and LSTM estimation performances. Elman and LSTM exhibited an advantage in decoding latent information dependencies through their context layers, leading to improved estimation performance in inter-subject variability analysis, particularly with increased training data volume and variability. Furthermore, the LSTM, with its complex architecture capable of learning long-term temporal dependencies, exhibited the highest performance among the considered RNNs. Consequently, selecting the optimal RNN structure is recommended based on the complexity of the data at hand. The RNN-based decoding model holds potential applications in prosthetics, robotic assistants, and exoskeletons, enabling intention detection and real-time assessment of active rehabilitation progress. [ABSTRACT FROM AUTHOR]

Introduction: Learning is a long-term memory process heavily influenced by the control processes implemented by working memory, including recognition of semantic properties of items by which subjects generate a semantic structure of engrams. Aim: The aim of this study is to investigate the verbal learning strategies of patients affected by a tumor in the left frontal lobe to highlight the role of area 9. Method: Ten patients with frontal low-grade gliomas and ten healthy control subjects, matched for age, sex and education, were recruited and then evaluated with a two-part verbal learning test: multi-trial word list learning in free recall, and multi-trial word list learning preceded by an explicit semantic strategy cue. Frontal patients were divided into two groups: those either with frontal lesions involving or sparing area 9. Results: In comparison to healthy control subjects, frontal patients with lesions involving area 9 memorized fewer words and displayed difficulty in using semantic strategies. When the strategy was suggested by the examiner, their performance improved, but to a lesser extent than the healthy control. Conversely, frontal patients with lesions sparing area 9 showed similar results to healthy control subjects. Conclusion: The results suggested that, while the identification of the categorical criterion requires the integrity of the entire dorsolateral prefrontal area, only area 9, and not the surrounding areas, could be responsible for the effective use of semantic strategies in learning tasks. [ABSTRACT FROM AUTHOR]

Accumulating evidence suggests that rhythmic temporal cues in the environment influence the encoding of information into long-term memory. Here, we test the hypothesis that these mnemonic effects of rhythm reflect the coupling of high-frequency (gamma) oscillations to entrained lower-frequency oscillations synchronized to the beat of the rhythm. In Study 1, we first test this hypothesis in the context of global effects of rhythm on memory, when memory is superior for visual stimuli presented in rhythmic compared with arrhythmic patterns at encoding [Jones, A., & Ward, E. V. Rhythmic temporal structure at encoding enhances recognition memory, Journal of Cognitive Neuroscience, 31, 1549–1562, 2019]. We found that rhythmic presentation of visual stimuli during encoding was associated with greater phase-amplitude coupling (PAC) between entrained low-frequency (delta) oscillations and higher-frequency (gamma) oscillations. In Study 2, we next investigated cross-frequency PAC in the context of local effects of rhythm on memory encoding, when memory is superior for visual stimuli presented in-synchrony compared with out-of-synchrony with a background auditory beat [Hickey, P., Merseal, H., Patel, A. D., & Race, E. Memory in time: Neural tracking of low-frequency rhythm dynamically modulates memory formation. Neuroimage, 213, 116693, 2020]. We found that the mnemonic effect of rhythm in this context was again associated with increased cross-frequency PAC between entrained low-frequency (delta) oscillations and higher-frequency (gamma) oscillations. Furthermore, the magnitude of gamma power modulations positively scaled with the subsequent memory benefit for in- versus out-of-synchrony stimuli. Together, these results suggest that the influence of rhythm on memory encoding may reflect the temporal coordination of higher-frequency gamma activity by entrained low-frequency oscillations. [ABSTRACT FROM AUTHOR]

The sensory recruitment hypothesis conceptualizes information in working memory as being activated representations of information in long-term memory. Accordingly, changes made to an item in working memory would be expected to influence its subsequent retention. Here, we tested the hypothesis that suppressing information from working memory, which can reduce short-term access to that information, may also alter its long-term neural representation. We obtained fMRI data (n = 25; 13 female / 12 male participants) while participants completed a working memory removal task with scene images as stimuli, followed by a final surprise recognition test of the examined items. We applied a multivariate pattern analysis to the data to quantify the engagement of suppression on each trial, to track the contents of working memory during suppression, and to assess representational changes afterward. Our analysis confirms previous reports that suppression of information in working memory involves focused attention to target and remove unwanted information. Furthermore, our findings provide new evidence that even a single dose of suppression of an item in working memory can (if engaged with sufficient strength) produce lasting changes in its neural representation, particularly weakening the unique, item-specific features, which leads to forgetting. Our study sheds light on the underlying mechanisms that contribute to the suppression of unwanted thoughts and highlights the dynamic interplay between working memory and long-term memory. [ABSTRACT FROM AUTHOR]

Software-defined networking (SDN) is a new network paradigm, which is highly decoupled compared to traditional networks, and makes it easier to operate by separating the data and control planes of the network, promoting logical centralization of network control, and introducing the ability to program the network. Due to the feature of logically centralized control, the attack on the controller will lead to the paralysis of the entire network, so the intrusion detection is particularly important for SDN. With the rise of artificial intelligence network, machine learning technology and deep learning technology have been applied in all aspects of life. Due to the advantages of high accuracy, light weight, and fast response speed, deep learning is beneficial for intrusion detection. However, the methods proposed at this stage are mainly concentrated in traditional networks, and they are often used to detect DDoS (Distributed Denial of Service) attacks only, which cannot be applied to SDN directly to classify different attack types specific to this new network paradiam. In this work, we propose a hybrid Long Short Term Memory (LSTM)-based multi-class intrusion detection method, i.e., Convolutional Neural Network with Attention (CNNA)-BiLSTM to detect 8 common intrusion types on the InSDN dataset. Firstly, a feature selection method is proposed for the high-dimensional data of SDN network data traffic to extract the positive features that are effective for model decision-making, reduce the misleading of the model by unfavorable and negative features, and decrease the computational cost. Secondly, a multi-class intrusion detection model based on multi-output nodes and hybrid BiLSTM with attention is proposed to improve the accuracy of the model for emerging detection. The proposed deep learning model provides a better classification result in two-class and multi-class problems compared with other methods. It achieves an accuracy of 99.86% and 99.31% on two-class and multi-class scenarios, respectively. Moreover, our proposed model can accurately detect each category in multi-classification detection, while other standard models cannot detect Botnet, Web, and U2R attacks accurately because of their small sample scales. [ABSTRACT FROM AUTHOR]

In engineering practice, deep learning is commonly used for small-sample fault diagnosis of mechanical equipment under heavy noise interference. In recent years, many researchers have used attentional neural operators based on CNNs to extract feature representations from complex data. However, the current attentional neural operator-based fault diagnosis method still has the following limitations: (1) CNN performs poorly in global feature extraction and is unable to capture the global dependencies of long sequential signals. (2) Neural operators have a serious information loss problem in multi-level feature computation, which is unfavorable for processing sensor signals that are long and contain complex noise. To address these problems, we innovatively design an efficient attentional neural operator, and also propose a new lightweight model called CSDANet. Firstly, the spatial interaction between local and global in vibration signals is facilitated by introducing a multi-level convolution and layer scaling strategies; secondly, We designed a feature channel with long-term memory capacity to cope with the adverse effects of information loss on the model; Finally, a vibration signal feature extractor is proposed to obtain richer feature mapping from the original one-dimensional sensor signals, which significantly improves the ability of the attention module to perceive multi-frequency domain noise features while consuming less computational resources. The results of two experiments demonstrate that the proposed approach accommodates advantages of lightweight and robustness in small-sample fault diagnosis tasks, compared to the existing mainstream Transformer and CNN fault diagnosis frameworks. [ABSTRACT FROM AUTHOR]

Summary: Electric vehicles (EVs) are the emerging environmentally friendly approach that is used to minimize greenhouse gases and carbon dioxide (CO2) emissions in the atmosphere. A clear strategy is required for scheduling charging stations (CS) to EVs based on their applications. In this research work, a robust routing and effective charge scheduling approach are devised using a cloud‐assisted Vehicular Ad Hoc NETwork (VANET) for charging EVs. Here, the multi‐objectives, like predicted traffic density, battery power, and distance, are used to identify the optimal routing of EV to CS. The predicted traffic density is evaluated using Deep Long Short Term Memory (DLSTM) and is trained using a developed Jaya Election‐Based Optimization Algorithm (JEBOA), which is the incorporation of Jaya Optimization (Jaya) and Election‐Based Optimization Algorithm (EBOA). Next to optimal routing, the charge scheduling process is carried out using the Fractional Jaya Election‐Based Optimization Algorithm (Fractional JEBOA) by considering the priority, response time, and latency of the EV. The designed Fractional JEBOA is the integration of Fractional Calculus (FC) and the developed JEBOA. Moreover, the various evaluation metrics are considered to calculate the performance of the designed method, which attained a delay of 0.243 ms, distance of 35 km, power of 95 W, response time of 0.441 s and traffic density of 0.664. [ABSTRACT FROM AUTHOR]

In recent years, research on unmanned surface vessels has entered a new phase, demanding the increased accuracy and reliability of integrated navigation and positioning systems. However, in complex environments, due to intermittent sensor failures or communication limitations, Global Navigation Satellite System (GNSS) signals are unreliable. Various errors that emerge in the system make it impossible to complete the measurement update process of filtering algorithms. This study provides a mechanism for improving the accuracy of combined GNSS/Shipborne Inertial Navigation System (SINS) integrated navigation when a GNSS outage occurs. Firstly, a SINS denoising method combining Complementary Ensemble Empirical Mode Decomposition (CEEMD) and an improved wavelet threshold algorithm is proposed. Secondly, a method based on Long Short-Term Memory (LSTM) network assisted GNSS/SINS integrated navigation is proposed to address the issue of poor information fusion performance when GNSS outages occur. The trained LSTM model is combined with SINS data to predict velocity and position during GNSS outages, providing high-precision velocity and position information. This ensures continuous, high-precision, navigation of unmanned surface vessels. Finally, to confirm the validity of the proposed methodology, a sea trial is performed to compare the different methods, and the results reveal the feasibility and effectiveness of the proposed methodology. [ABSTRACT FROM AUTHOR]

The impact of drought builds on all three fronts of economy, environment, and society is devastating. Predicting its arrival and duration is highly important to arrange any sort of mitigation plans. The association of detailed relationship between multiple variables makes drought prediction a highly complex task. Especially influence of global warming, polar sea extent variations and their influence on overall ocean temperature have altered the seasonal rainfall behaviors all over the world. In the midst of it, predictions centered on the history of rainfall levels become inaccurate. The proposed system is an optimized deep learning prediction model integrating indigenous knowledge (IK) is proposed to predict the drought. IK expressed in human language is translated using fuzzy function and fed to an improved Long Short Term Memory (LSTM) model. The LSTM model hyperparameters are optimized using a hybrid of Particle Swarm Optimization (PSO) with firefly to produce the meta-heuristics algorithm which will provide the best performance in presence of integration of IK features into modern meteorological features which solves the problem of local minima in LSTM hyperparameter optimization. The performance of the proposed results were tested compared with the meteorological information gathered by the Karnataka Natural Disaster Monitoring Centre (KNDMC) for the district named Chitradurga of the Karnataka state in India. The proposed system which is Indigenous Knowledge merged along the cross model attention network can produce at least 1.4% higher Nash-Sutcliffe model efficiency coefficient (NSE) and 30% lower Mean Absolute Error (MAE) in the prediction of Standard Precipitation Index (SPI) compared to Convolution Neural Networks (CNN) and LSTM based time series prediction models. [ABSTRACT FROM AUTHOR]

BACKGROUND AND OBJECTIVES: In metropolitan settings, the requirement to travel and participate in everyday tasks exposes numerous individuals to the harmful effects of air pollutants, specifically particulate matter 2.5, which has the potential to impact their well-being. Developing precise forecasting models is crucial in mitigating air pollution and providing accurate predictions for the people. Nonetheless, the deficiency in acquiring observable data can frequently lead to unsatisfactory performance of forecasting models in various scenarios. The objective of this study is to address the issue by examining the most effective approaches for predicting the non-linear time-series data of daily particulate matter 2.5 concentration using meteorological inputs. METHODS: The concentration data of particulate matter 2.5 at Central Jakarta and South Jakarta were collected using sensors from the United States of America Embassy in Indonesia and Indonesia's Meteorological, Climatological, and Geophysical Agency. Conversely, the meteorological information was collected through the Merra-2 satellite. This study introduces the long short-term memory deep learning model and contrasts it with the one-dimensional convolution neural network as well as their hybrid counterpart. The dataset is split into 80 percent training and 20 percent testing data. The root mean square and mean absolute error values are then calculated to determine the performance of the models. FINDINGS: A combination of long short-term memory and fully connected layers using dropouts and early stopping patience techniques has been successfully developed to model the non-linear time-series data of daily particulate matter 2.5 concentration. The model effectively captured the patterns present in the historical data, resulting in outcomes that exhibited similar patterns. The long short-term memory model demonstrates an overall root mean square error and mean absolute error values of 18.53 micrograms per cubic meter and 14.92 micrograms per cubic meter in Central Jakarta and 19.4 micrograms per cubic meter and 15.61 micrograms per cubic meter in South Jakarta, where the best seasonal data were found to be in the June-July-August and December-January-February seasons respectively. CONCLUSION: The air pollution forecasting models, which were created using both seasonal and overall time-series data, have the ability to predict air pollution levels by utilizing historical pollution data and meteorological inputs. The proposed long short-term memory model outperforms the one-dimensional convolution network and their hybrid combination. It has effectively surpassed the constraint of collecting observable data, attaining minimal error values on both sensors and satellite data, signifying a noteworthy progression compared to previous studies. Therefore, it might benefit areas lacking sufficient data, providing a valuable tool for air pollution mitigation. [ABSTRACT FROM AUTHOR]

The escalating incidence of breast cancer (BC) in women underscores its grave health threat. Current molecular insights into BC's post-adjuvant therapy cure remain elusive, necessitating active treatment explorations. Immunotherapy, notably chemotherapy-induced immunogenic cell death (ICD), has emerged as a promising BC therapy. ICD harnesses chemotherapeutics to activate anti-tumor immunity via DAMPs, fostering long-term T-cell memory and primary BC cure. Besides chemotherapy drugs, Nanodrugs, traditional Chinese medicine (TCM) and ICIs also induce ICD, boosting immune response. ICIs, like PD-1/PD-L1 inhibitors, revolutionize cancer treatment but face limited success in cold tumors. Thus, ICD induction combined with ICIs is studied extensively for BC immunotherapy. This article reviews the mechanism of ICD related drugs in BC and provides reference for the research and development of BC treatment, in order to explore more effective clinical treatment of BC, we hope to explore more ICD inducers and make ICIs more effective vaccines. [ABSTRACT FROM AUTHOR]

Introduction: Tomatoes are sensitive to low temperatures during their growth process, and low temperatures are one of the main environmental limitations affecting plant growth and development in Northeast China. Chlorophyll fluorescence imaging technology is a powerful tool for evaluating the efficiency of plant photosynthesis, which can detect and reflect the effects that plants are subjected to during the low temperature stress stage, including early chilling injury. Methods: This article primarily utilizes the chlorophyll fluorescence image set of tomato seedlings, applying the dung beetle optimization (DBO) algorithm to enhance the deep learning bidirectional long short term memory (BiLSTM) model, thereby improving the accuracy of classification prediction for chilling injury in tomatoes. Firstly, the proportion of tomato chilling injury areas in chlorophyll fluorescence images was calculated using a threshold segmentation algorithm to classify tomato cold damage into four categories. Then, the features of each type of cold damage image were filtered using SRCC to extract the data with the highest correlation with cold damage. These data served as the training and testing sample set for the BiLSTM model. Finally, DBO algorithm was applied to enhance the deep learning BiLSTM model, and the DBO-BiLSTM model was proposed to improve the prediction performance of tomato seedling category labels. Results: The results showed that the DBO-BiLSTM model optimized by DBO achieved an accuracy, precision, recall, and F1 score with an average of over 95%. Discussion: Compared to the original BiLSTM model, these evaluation parameters improved by 9.09%, 7.02%, 9.16%, and 8.68%, respectively. When compared to the commonly used SVM classification model, the evaluation parameters showed an increase of 6.35%, 7.33%, 6.33%, and 6.5%, respectively. This study was expected to detect early chilling injury through chlorophyll fluorescence imaging, achieve automatic classification and labeling of cold damage data, and lay a research foundation for in-depth research on the cold damage resistance of plants themselves and exploring the application of deep learning classification methods in precision agriculture. [ABSTRACT FROM AUTHOR]

The essence of the Single Image Super Resolution (SISR) task revolves around learning and memorizing the mapping relationship between low-resolution and high-resolution images. Presently, prevailing SISR methods predominantly depend on simplistic long-range connections and intricate dense connections to establish long-term memory within the network. However, a notable limitation is the absence of a transitioning mechanism from short-term to long-term memory, impeding the smooth transfer of information. The intermediate-term memory mechanism assumes a critical role in the human memory system, acting as a vital bridge between short-term and long-term memory. Its ability to integrate fragmented neuronal information through specific intermediate-term connectivity patterns facilitates the formation of long-term memory. Inspired by this mechanism, we propose a deep feature extraction and fusion method based on intermediate-term connectivity, addressing the challenges associated with smooth information transfer between short-term and long-term memory. In this study, we introduce IMSR (Intermediate-term Memory Super Resolution), a lightweight model that efficiently aggregates features from different temporal and spatial levels within the network. By doing so, IMSR enhances the representation of both global and local information, contributing to improved performance. Additionally, we incorporate the Reconstructive Attention Mechanism (RAM) at the end of IMSR, allowing for precise tuning and fine-grained control of features to facilitate the integration of complementary information. Through extensive experimental evaluations, we demonstrate that IMSR surpasses other state-of-the-art lightweight models across four benchmark datasets, while maintaining a low parameter count and computational complexity. [ABSTRACT FROM AUTHOR]

The software Defect Prediction (SDP) model uses previously learned data to predict whether a future example (such as a file, class, or module) will be defective or not. Accurate forecast results can help software testers arrange testing resources more efficiently. Nonetheless, there are still difficulties in more exact and reliable defect predictions. This study presents the SDP-CMPOA framework, which stands for Software Defect Prediction Crossover with Brownian Motion-based Pelican Optimization Algorithm. The stages of the approach are pre-processing, feature extraction, feature selection, and detection. The preprocessing stage involves improved data normalization. Higher-order statistical features, enhanced statistical features, and raw features are all taken from the pre-processed data. The primary barrier to precise software defect detection and hence adhering to the ideal feature selection method will be the curse of dimensionality. This research proposes a novel Crossover with the Brownian motion-based Pelican Optimization Algorithm for selecting the best features (CMPOA). Finally, hybrid classifiers like Improved Bidirectional Long Short Term Memory (Bi-LSTM and) Deep Max out models are employed for defect prediction. The classifier analysis of KCI/SDP dataset accuracy of the projected model is 9.17%, 9.6%, 7.20%, 13.3%, and 5.7% better than the other methods such as DBN, SVM, CNN, RF, RNN, and SDP- CMPOA respectively at the 60th learning percentage. The efficiacy of the SDP-CMPOA is examined in comparison to other extant schemes with respect to certain measures. [ABSTRACT FROM AUTHOR]

Speaker recognition is extensively applied in several applications, namely identity verification, electronic voice eavesdropping, surveillance, voice recognition, etc. In an effective speaker recognition system, the extraction and selection of salient and discriminative features is an essential process for accurately identifying the speakers. Therefore, a novel hybrid framework is introduced in this research manuscript. Initially, the input data are acquired from the three-benchmark databases: THUYG-20 SRE corpus, Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), and LibriSpeech. Further, the emotional features are extracted by utilizing hybrid feature extraction techniques which are, amplitude, zero cross rate, energy, Root Mean Square (RMS), statistical moments, autocorrelation, and Mel-Frequency Cepstral Coefficients (MFCC). Then, the feature optimization is carried out using Improved Butterfly Optimization Algorithm (IBOA) that decreases the computational time and complexity of the recognition model. At last, a hybrid classifier: Convolutional Neural Network (CNN) with Long Short Term Memory (LSTM) is implemented for speaker recognition, and its performance is analyzed in terms of F1-score, specificity, accuracy, Positive Predictive Value (PPV), and sensitivity. The empirical investigation demonstrated that the IBOA-based hybrid LSTM network achieved 92.65%, 96.97% and 96.98% of recognition accuracy on the LibriSpeech, RAVDESS and THUYG-20 SRE corpus databases. These results are more impressive than the comparative models, Deep Neural Network (DNN), random forest, K-Nearest Neighbor (KNN), LSTM, Multi class Support Vector Machine (MSVM), Deep Convolutional Recurrent Neural Network (DCRNN), Golden Ratio aided Neural Network (GRaNN), deep sequential LSTM, and Probabilistic Neural Network (PNN). [ABSTRACT FROM AUTHOR]

Background: The increasing rate of intensive care unit (ICU) readmissions poses significant challenges in healthcare, impacting both costs and patient outcomes. Predicting patient readmission after discharge is crucial for improving medical quality and reducing expenses. Traditional analyses of electronic health record (EHR) data have primarily focused on numerical data, often neglecting valuable text data. Methods: This study employs a hybrid model combining BERTopic and Long Short-Term Memory (LSTM) networks to predict ICU readmissions. Leveraging the MIMIC-III database, we utilize both quantitative and text data to enhance predictive capabilities. Our approach integrates the strengths of unsupervised topic modeling with supervised deep learning, extracting potential topics from patient records and transforming discharge summaries into topic vectors for more interpretable and personalized predictions. Results: Utilizing a comprehensive dataset of 36,232 ICU patient records, our model achieved an AUROC score of 0.80, thereby surpassing the performance of traditional machine learning models. The implementation of BERTopic facilitated effective utilization of unstructured data, generating themes that effectively guide the selection of relevant predictive factors for patient readmission prognosis. This significantly enhanced the model's interpretative accuracy and predictive capability. Additionally, the integration of importance ranking methods into our machine learning framework allowed for an in-depth analysis of the significance of various variables. This approach provided crucial insights into how different input variables interact and impact predictions of patient readmission across various clinical contexts. Conclusions: The practical application of BERTopic technology in our hybrid model contributes to more efficient patient management and serves as a valuable tool for developing tailored treatment strategies and resource optimization. This study highlights the significance of integrating unstructured text data with traditional quantitative data to develop more accurate and interpretable predictive models in healthcare, emphasizing the importance of individualized care and cost-effective healthcare paradigms. [ABSTRACT FROM AUTHOR]

NKT cells are innate-like T cells, recruited to the skin during viral infection, yet their contributions to long-term immune memory to viruses are unclear. We identified granzyme K, a product made by cytotoxic cells including NKT cells, as linked to induction of Th1-associated antibodies during primary dengue virus (DENV) infection in humans. We examined the role of NKT cells in vivo using DENV-infected mice lacking CD1d-dependent (CD1ddep) NKT cells. In CD1d-KO mice, Th1-polarized immunity and infection resolution were impaired, which was dependent on intrinsic NKT cell production of IFN-γ, since it was restored by adoptive transfer of WT but not IFN-γ–KO NKT cells. Furthermore, NKT cell deficiency triggered immune bias, resulting in higher levels of Th2-associated IgG1 than Th1-associated IgG2a, which failed to protect against a homologous DENV rechallenge and promoted antibody-dependent enhanced disease during secondary heterologous infections. Similarly, Th2 immunity, typified by a higher IgG4/IgG3 ratio, was associated with worsened human disease severity during secondary infections. Thus, CD1ddep NKT cells establish Th1 polarity during the early innate response to DENV, which promotes infection resolution, memory formation, and long-term protection from secondary homologous and heterologous infections in mice, with consistent associations observed in humans. These observations illustrate how early innate immune responses during primary infections can influence secondary infection outcomes. [ABSTRACT FROM AUTHOR]

Previous research suggests that applying anodal transcranial direct-current stimulation (tDCS) to the medial-frontal cortex can improve how quickly subjects learn to make simple discriminations (i.e., red from blue). Here, we tested the idea that this enhanced task learning is attributable to superior encoding of relevant information into visual long-term memory. Thirty subjects completed an anodal stimulation session and a sham session, with order counterbalanced across subjects, before performing recognition-memory tasks using pictures of real-world objects and visually presented words or nonwords. These tasks allowed us to detect potential memory differences across types of memoranda. Contrary to the hypothesis that the medial-frontal cortex helps control encoding fidelity, we found that anodal tDCS delivered over this brain region did not significantly improve subjects’ memory for visual stimuli, regardless of stimulus type. Our findings show no evidence that targeting medial-frontal cortex with tDCS changes the fidelity of our visual long-term memories. [ABSTRACT FROM AUTHOR]

As a sport conducted in dynamically changing natural environments, orienteering places high demands on athletes' cognitive processing abilities and visual search efficiency. However, previous studies on orienteering have been primarily limited by the use of fixed stimulus materials on computer screens, which are unable to fully simulate authentic sports scenarios. To better understand the sports expertise of orienteering athletes in terms of their real scene image recognition performance and visual search characteristics, this study recruited 40 orienteering athletes, both experts and novices, as participants. By utilizing eye-tracking technology and setting observation points in real-world scenarios to conduct image recognition task tests, the ecological validity of the experiment was further enhanced. The results showed that the experts demonstrated a high level of accuracy and a short response time, with visual search characteristics including few saccade counts, low fixation frequency, concentrated fixation points, simple and clear fixation paths, and higher visual search efficiency. This study further reveals that long-term specialized training will lead to the formation of a unique cognitive structure related to the specific knowledge and long-term memory required by expert orienteering athletes, thereby promoting the development of expert advantage. [ABSTRACT FROM AUTHOR]

It is critical to identify and detect hazardous, flammable, explosive, and poisonous gases in the realms of industrial production and medical diagnostics. To detect and categorize a range of common hazardous gasses, we propose an attention-based Long Short term memory Full Convolutional network (ALSTM-FCN) in this paper. We adjust the network parameters of ALSTM-FCN using the Sparrow search algorithm (SSA) based on this, by comparison, SSA outperforms Particle Swarm Optimization (PSO) Algorithm, Genetic Algorithm (GA), Gray Wolf Optimization (GWO) Algorithm, Cuckoo Search (CS) Algorithm and other traditional optimization algorithms. We evaluate the model using University of California-Irvine (UCI) datasets and compare it with LSTM and FCN. The findings indicate that the ALSTM-FCN hybrid model has a better reliability test accuracy of 99.461% than both LSTM (89.471%) and FCN (96.083%). Furthermore, AdaBoost, logistic regression (LR), extra tree (ET), decision tree (DT), random forest (RF), K-nearest neighbor (KNN) and other models were trained. The suggested approach outperforms the conventional machine learning model in terms of gas categorization accuracy, according to experimental data. The findings indicate a potential for a broad range of polluting gas detection using the suggested ALSTM-FCN model, which is based on SSA optimization. [ABSTRACT FROM AUTHOR]

Second language (L2) grammar learning is difficult. Two frameworks—the psycholinguistic lexical bottleneck hypothesis and the neurocognitive declarative/procedural model—predict that faster L2 lexical processing should facilitate L2 incidental grammar learning. We tested these predictions in a pretest–posttest syntactic adaptation study of English relative‐clause attachment preferences. First‐language German speakers listened to relative clauses disambiguated to the English low‐attachment preference (secretaries of the professor who is/naps at home)—via either a copula (e.g., is), which should be processed rapidly (copula group; n = 48), or a lexical verb (e.g., naps), which should be processed more slowly (lexical group; n = 48). Only the copula group showed significant pretest‐to‐posttest learning. Moreover, the amount of learning was predicted by procedural learning abilities in the copula group, but by vocabulary size in the lexical group. The results, which are consistent with both frameworks, show that the L2 lexicon impacts L2 grammar learning, and reveal moderating psycholinguistic and neurocognitive variables. [ABSTRACT FROM AUTHOR]

Methods: We conducted a double-blind, randomised, placebo-controlled crossover trial with healthy older adults (65-79 years, n = 35). Participants first learned a word list and were then administered long-acting L-DOPA (or placebo) before a full night of sleep. Before sleeping, a proportion of the words were re-exposed using a recognition test to strengthen memory. L-DOPA was active during sleep and the practice-recognition test, but not during initial learning. Results: The single dose of L-DOPA increased total slow-wave sleep duration by approximately 11% compared to placebo, while also increasing spindle amplitudes around slow oscillation peaks and around 1-4 Hz NREM spectral power. However, behaviourally, L-DOPA worsened memory of words presented only once compared to re-exposed words. The coupling of spindles to slow oscillation peaks correlated with these differential effects on weaker and stronger memories. To gauge whether L-DOPA affects encoding or retrieval of information in addition to consolidation, we conducted a second experiment targeting L-DOPA only to initial encoding or retrieval and found no behavioural effects. Discussion: Our results demonstrate that L-DOPA augments slow wave sleep in elderly, perhaps tuning coordinated network activity and impacting the selection of information for long-term storage. The pharmaceutical modification of slowwave sleep and long-term memory may have clinical implications. [ABSTRACT FROM AUTHOR]

Pneumonia is a serious inflammatory disease that causes lung ulcers, and it is one of the leading reasons for pediatric death in the world. Chest X-rays are perhaps the most commonly utilized modalities to recognize pneumonia. Generally, the illness could be analyzed by a specialist radiologist. But for some reason, the diagnosis may be subjective. Thus, the physicians must be guided by computer-aided diagnosis frameworks in this challenging task. In this study, we propose a combined deep learning architecture to identify pneumonia in chest radiography images. We first, use Adaptive Median Filter for images enhancement, then we employ a regularized Convolutional Neural Network for features extraction, and then we use Long Short Term Memory as a classifier. Finally, the attention mechanism is used to direct the network attention to relevant features. The suggested approach was tested on two publicly available pneumonia X-ray datasets provided by Kermany and the Radiological Society of North America. On the Kermany and RSNA datasets, the suggested technique attained accuracy rates of 99.91% and 88.86%, respectively. In the last stage of our experiments, we employed a Grad-CAM-based color visualization technique to precisely interpret the detection of pneumonia in radiological images. The results outperformed those of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

EEG-based classification from human states is still challenging in human-computer interaction (HCI). Since it reflects brain activity directly, electroencephalography (EEG) has significant advantages in emotion classification research. This study recorded EEG signals from 12 participants while they perceived emotional audio-visual stimulation movie clips for four minutes. The six emotions studied were anger, excitement, fear, happiness, sadness, and a neutral state. We also perform raw data preprocessing to obtain clean data, extracting the power spectrum using Fast Fourier Transform (FFT) to generate feature vectors. In addition, we conduct extensive experiments to validate the classification of human states using subject-independent machine-learning techniques. As a result, the LSTM network achieved the highest classification accuracy of 81.46% for six emotional states, while the SVM network achieved only 68.64%. In addition, we achieved 82.89% accuracy in the Bi-LSTM network with two layers when applying the deep learning methods to different layers. In conclusion, extensive experiments were conducted on our collected dataset. Experimental results indicate that the LSTM network, a time-sequence-related model, has superior classification results of 82.89% than other methods. It also shows that the long duration of EEG signals is crucial for detecting the emotional state changes of various subject types, including individual subjects and cross-subjects. In future research, we will investigate multiple evaluation experiments utilizing deep learning models or propose novel EEG-based emotion classification features to improve the accuracy of emotion classification. [ABSTRACT FROM AUTHOR]

Goal-directed memory reactivation involves retrieving the most relevant information for the current behavioral goal. Previous research has linked this process to activations in the fronto-parietal network, but the underlying neurocognitive mechanism remains poorly understood. The current electroencephalogram (EEG) study explores attentional selection as a possible mechanism supporting goal-directed retrieval. We designed a long-term memory experiment containing three phases. First, participants learned associations between objects and two screen locations. In a following phase, we changed the relevance of some locations (selective cue condition) to simulate goal-directed retrieval. We also introduced a control condition, in which the original associations remained unchanged (neutral cue condition). Behavior performance measured during the final retrieval phase revealed faster and more confident responses in the selective vs. neutral condition. At the EEG level, we found significant differences in decoding accuracy, with above-chance effects in the selective cue condition but not in the neutral cue condition. Additionally, we observed a stronger posterior contralateral negativity and lateralized alpha power in the selective cue condition. Overall, these results suggest that attentional selection enhances task-relevant information accessibility, emphasizing its role in goal-directed memory retrieval. [ABSTRACT FROM AUTHOR]

Rationale: Central neuropathic pain resulting from spinal cord injury is notoriously debilitating and difficult to treat with few currently available treatments. A novel molecule with intrathecal administration: Ziconotide has been approved for treatment of refractory neuropathic pain in general. It acts as a presynaptic calcium channel blocker. A pilot study has shown its potential in SCI neuropathic pain patients. Objective: The aim of this study is to determine the long-term (6 months) efficacy of chronic intrathecal ziconotide for the treatment of neuropathic SCI pain. Study design: Multicenter, Randomized, Comparative, Placebo controlled, Double blind clinical trial, with a crossover of random alternated periods of 6 months (placebo or ITZ) for a total of 15 months including a total of 44 patients. Study population: • Patients with SCI of various etiologies exhibiting neuropathic pain refractory to non-invasive treatments. • > 18 years. Intervention: Intrathecal administration of ziconotide via an implanted pump. Study outcomes: Primary study outcome Difference in pain intensity for all patients between effective treatment and placebo periods. Secondary study outcomes 1. Continuous evaluation of pain intensity. 2. Percentage of patients with at least 30% of pain reduction. 3. Satisfaction level of the patient pain relief. 4. Declarations of serious adverse events. 5. Duration and intensity of spontaneous and provoked pain. 6. Quality of life. 7. Patient global impression of change. 8. Quantification of daily dosages of analgesic drug intake. 9. Long term memory and neurocognitive effects. 10. Assessment of the patient's physical and emotional distress. Nature and extent of the burden and risks associated with participation, benefit, and group relatedness: Participation in this study is in accordance with current treatment protocols for SCI neuropathic pain in France therefore it proposes a treatment that would currently be considered regular practice even though no RCT evidence is yet available. The study gives patients the advantage of directly testing versus placebo a treatment that otherwise entails significant constraints. A Data Safety Monitoring board (DSMB) will be created for continuous safety analysis. Furthermore, patients will be followed in specialized pain centers offering the possibility of continuing their treatment after the study period. [ABSTRACT FROM AUTHOR]

While the influence of context on long-term memory (LTM) is well documented, its effects on the interaction between working memory (WM) and LTM remain less understood. In this study, we explored these interactions using a delayed match-to-sample task, where participants (6 males, 16 females) encountered the same target object across six consecutive trials, facilitating the transition from WM to LTM. During half of these target repetitions, the background color changed. We measured the WM storage of the target using the contralateral delay activity in electroencephalography. Our results reveal that task-irrelevant context changes trigger the reactivation of long-term memories in WM. This reactivation may be attributed to content–context binding in WM and hippocampal pattern separation. [ABSTRACT FROM AUTHOR]

Acetylation of histone proteins by histone acetyltransferases (HATs), and the resultant change in gene expression, is a well-established mechanism necessary for long-term memory (LTM) consolidation, which is not required for short-term memory (STM). However, we previously demonstrated that the HAT p300/CBP-associated factor (PCAF) also influences hippocampus (HPC)-dependent STM in male rats. In addition to their epigenetic activity, HATs acetylate nonhistone proteins involved in nongenomic cellular processes, such as estrogen receptors (ERs). Given that ERs have rapid, nongenomic effects on HPC-dependent STM, we investigated the potential interaction between ERs and PCAF for STM mediated by the dorsal hippocampus (dHPC). Using a series of pharmacological agents administered directly into the dHPC, we reveal a functional interaction between PCAF and ERα in the facilitation of short-term object-in-place memory in male but not female rats. This interaction was specific to ERα, while ERβ agonism did not enhance STM. It was further specific to dHPC STM, as the effect was not present in the dHPC for LTM or in the perirhinal cortex. Further, while STM required local (i.e., dHPC) estrogen synthesis, the facilitatory interaction effect appeared independent of estrogens. Finally, western blot analyses demonstrated that PCAF activation in the dHPC rapidly (5 min) activated downstream estrogen-related cell signaling kinases (c-Jun N-terminal kinase and extracellular signal-related kinase). Collectively, these findings indicate that PCAF, which is typically implicated in LTM through epigenetic processes, also influences STM in the dHPC, possibly via nongenomic ER activity. Critically, this novel PCAF–ER interaction might exist as a male-specific mechanism supporting STM. [ABSTRACT FROM AUTHOR]

Glioblastoma (GBM) is the most common and most malignant primary brain tumor, presenting significant treatment challenges due to its heterogeneity, invasiveness, and resistance to conventional therapies. Despite aggressive treatment protocols, the prognosis remains poor, with a median survival time of approximately 15 months. Recent advancements in mRNA vaccine technology, particularly the development of lipid nanoparticles (LNPs), have revitalized interest in mRNA-based therapies. These vaccines offer unique advantages, including rapid production, personalization based on tumor-specific mutations, and a strong induction of both humoral and cellular immune responses. mRNA vaccines have demonstrated potential in preclinical models, showing significant tumor regression and improved survival rates. Early-phase clinical trials have indicated that mRNA vaccines are safe and can induce robust immune responses in GBM patients. Combining mRNA vaccines with other immunotherapeutic approaches, such as checkpoint inhibitors, has shown synergistic effects, further enhancing their efficacy. However, challenges such as optimizing delivery systems and overcoming the immunosuppressive tumor microenvironment remain. Future research should focus on addressing these challenges and exploring combination therapies to maximize therapeutic benefits. Large-scale, randomized clinical trials are essential to validate the efficacy and safety of mRNA vaccines in GBM therapy. The potential to reshape the tumor microenvironment and establish long-term immunological memory underscores the transformative potential of mRNA vaccines in cancer immunotherapy. [ABSTRACT FROM AUTHOR]

Background: Idiopathic intracranial hypertension (IIH) is typically characterized by headaches and vision loss. However, neurocognitive deficits are also described. Our study aimed to test the influence of therapeutic lumbar puncture on the latter. Methods: A total of 15 patients with IIH were tested with a battery of neurocognitive tests at baseline and after therapeutic lumbar drainage. Hereby, Logical Memory of the Wechsler Memory Scale—Revised Edition (WMS-R), the California Verbal Learning Test Short Version (CVLT), alertness, selective attention, and word fluency were used. Changes in cognitive functioning in the course of CSF pressure lowering were analysed and compared with age, sex, and education-matched healthy controls. Results: Before intervention, scores of Logical Memory, the RWT, and the HADS-D were significantly lower in IIH patients compared to matched controls. After short-term normalization of CSF pressure, the RWT improved significantly. Additionally, significant positive correlations were found between headache intensity and subjective impairment, as well as between BMI and CSF opening pressure. Conclusions: Our findings confirm lower performance in terms of long-term verbal memory and word fluency compared to controls, as well as depressive symptoms in IIH patients. Significant improvement after short-term normalization of intracranial pressure by means of CSF drainage was seen only for word fluency. This indicates that short-term normalization of CSF pressure is not sufficient to normalize observed neurocognitive deficits. [ABSTRACT FROM AUTHOR]

This study examines the feasibility of using event-related potentials (ERPs) obtained from electroencephalographic (EEG) recordings as biomarkers for long-term memory item classification. Previous studies have identified old/new effects in memory paradigms associated with explicit long-term memory and familiarity. Recent advancements in convolutional neural networks (CNNs) have enabled the classification of ERP trials under different conditions and the identification of features related to neural processes at the single-trial level. We employed this approach to compare three CNN models with distinct architectures using experimental data. Participants (N = 25) performed an association memory task while recording ERPs that were used for training and validation of the CNN models. The EEGNET-based model achieved the most reliable performance in terms of precision, recall, and specificity compared with the shallow and deep convolutional approaches. The classification accuracy of this model reached 62% for known items and 66% for unknown items. Good overall accuracy requires a trade-off between recall and specificity and depends on the architecture of the model and the dataset size. These results suggest the possibility of integrating ERP and CNN into online learning tools and identifying the underlying processes related to long-term memorization. [ABSTRACT FROM AUTHOR]

Background: Spina bifida (SB) is a rare congenital disease characterized by not only physical but also neuropsychological disturbances. Among these neuropsychological impairments, memory deficits are a significant concern, as they substantially hinder aspects of crucial importance in the lives of individuals with SB such as medical needs or daily life activities. The main objective is to conduct a systematic review of the current evidence on the memory deficits in the SB population, including children, adolescents, and adults. Methods: Four databases (PubMed, SCOPUS, Web of Science, and ProQuest) were systematically screened for eligible studies. Results: The present review reveals cognitive difficulties in different memory types among individuals with SB. These deficits, identified in childhood, seem to persist into adulthood. Specifically, impairments are evident in short-term memory, working memory, and long-term memory. The neuropsychological instruments applied in the studies that were included in this systematic review vary, however, most reach the same conclusions. Conclusions: The present findings underscore the importance of incorporating cognitive assessments, particularly those focused on the memory domain, into routine childhood evaluations for individuals with SB. Early identification of these cognitive difficulties allows for the timely implementation of cognitive interventions that could leverage the inherent plasticity of the developing brain, and prevent or delay the onset of these deficits in later adulthood for people with SB, ultimately improving their functionality and quality of life. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is a challenging research problem and has a tremendous impact on electricity generation, transmission, and distribution. A robust forecasting algorithm can help power system operators to better tackle the ever-changing electric power demand. This paper presents a novel deep neural network for short-term electric load forecasting for the St. John's campus of Memorial University of Newfoundland (MUN). The electric load data are obtained from the Memorial University of Newfoundland and combined with metrological data from St. John's. This dataset is used to formulate a multivariate time-series forecasting problem. A novel deep learning algorithm is presented, consisting of a 1D Convolutional Neural Network, which is followed by an encoder–decoder-based network with attention. The input used for this model is the electric load consumption and metrological data, while the output is the hourly prediction of the next day. The model is compared with Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM)-based Recurrent Neural Network. A CNN-based encoder–decoder model without attention is also tested. The proposed model shows a lower mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), and higher R2 score. These evaluation metrics show an improved performance compared to GRU and LSTM-based RNNs as well as the CNN encoder–decoder model without attention. [ABSTRACT FROM AUTHOR]

Purpose: Videos and images are becoming an educational tool in every domain. The objective was to assess the contribution of short educational endoscopic videos in learning the complex anatomy of the tympanic cavity. Methods: We conducted a prospective study amongst all the otolaryngology residents in 2021 in the greater Paris area (n = 74), from the first year to fifth year. We divided the residents into two groups who had the same 30-min anatomy class based on anatomical drawings. The second group had a 4-min endoscopic educational video at the end, whereas the first group did not. A video test of 10 surgical situations with each time 5 anatomic structures to identify was created. All the residents took the test just after the class, and 1 month later to assess long-term memory. The MERSQI score (design to assess the quality of educational studies) applied to our study was calculated. Results: The two groups were comparable in terms of training. The "video" group had significantly better results in the first test, mean score 24.40/50 (± 11.7) versus 16.74/50 (± 11.1) (p = 0.005) and also at 1 month, mean score 23.25/50 (± 12.3) versus 18.01/50 (± 11.3) (p = 0.035). The score in each group, and the difference between both groups, increased with resident seniority. The MERSQI score of our study was 14.5/18. Conclusion: This study highlights the educational value of videos to help memorise complex 3D anatomy such as in the tympanic cavity. [ABSTRACT FROM AUTHOR]

Frequent occurrence of diseases has posed a serious threat to the healthy development of the laying hens industry. Previous studies have focused mainly on the application of artificial intelligence technologies to the intelligent diagnosis of laying hens diseases at present. However, the low accuracy with single data or knowledge cannot fully meet the diagnosis of complex laying hens diseases, particularly for the small number of diagnosable diseases. Graph structure and knowledge graphs can be expected to easily acquire a large amount of data. Furthermore, diagnosing diseases has been limited in the incomplete analysis of correlation information and incomplete knowledge of laying hens using a single text description. This study aims to propose a Bidirectional Encoder Representation from Transformers (BERT) that integrates the knowledge graph and text of typical laying hens diseases using a Transformer based Bidirectional Long Short Term Memory Network (BiLSTM), in order to construct BERT-LHDKG (BERT Laying Hens Disease Knowledge). The diagnostic model was used for intelligent diagnosis of 38 typical diseases in the laying hens, such as Mycoplasma Synoviae, Newcastle Disease, and Infectious Rhinitis. The disease text and knowledge graph data were more comprehensively combined to conduct a comprehensive analysis of the incidence of laying hens. The triple vectors were introduced to represent the knowledge graph. The text feature vector and the triple vector were added inside the BERT model to form a fusion vector. More useful features were extracted for the disease analysis and diagnosis. The performance comparison test showed that the macro precision of the BERT-LHDKG diagnostic model was 94.27%, the macrorecall was 94.12%, and the macro-F1 was 94.01%. The macro precision was improved by 10.02, 2.64, 2.18 percentage points, the macrorecall was improved by 10.28, 2.29, 2.29 percentage points, and macro-F1 was improved by 10.66, 2.51, 2.19 percentage points, respectively, compared with deep learning models, such as TextCNN, the BERT model combined with CNN (convolutional neural networks), and the ERNIE model combined with BiLSTM. Better performance was also achieved in the five viral, bacterial, toxic, and metabolic diseases that were prone to occur in laying hens farming. The macroF1 values of the BERT-LHDKG diagnostic model were 96.43%, 95.57%, 96.72%, and 98.24%, respectively. The ablation experiments showed that the removal of each layer from the BERT-LHDKG structure reduced the diagnostic accuracy of the improved model. Meanwhile, the macro precision, macrorecall, and macro-F1 of the improved model decreased by 5.14, 4.98, and 5.46 percentage points, respectively, after the removal of the laying hens disease knowledge graph. Therefore, the knowledge graph was integrated to link the entities and relationships in the epidemic texts to the corresponding entities in the knowledge graph. The semantic information of the text was enriched to fully understand the content of the text. Thereby, the accuracy and robustness of the improved model was improved for epidemic diagnosis. In addition, the laying hen disease diagnosis web system was developed on the basis of the BERT-LHDKG diagnostic model, indicating the flexibility of remote diagnosis for laying hen diseases through human-machine dialogue. [ABSTRACT FROM AUTHOR]

Radiotherapy widely applied for local tumor therapy in clinic has been recently reinvigorated by the discovery that radiotherapy could activate systematic antitumor immune response. Nonetheless, the endogenous radio-immune effect is still incapable of radical tumor elimination due to the prevention of immune cell infiltration by the physical barrier in tumor microenvironment (TME). Herein, an engineered Salmonella secreting nattokinase (VNPNKase) is developed to synergistically modulate the physical and immune characteristics of TME to enhance radio-immunotherapy of colon tumors. The facultative anaerobic VNPNKase enriches at the tumor site after systemic administration, continuously secreting abundant NKase to degrade fibronectin, dredge the extracellular matrix (ECM), and inactivate cancer-associated fibroblasts (CAFs). The VNPNKase- dredged TME facilitates the infiltration of CD103+ dendritic cells (DCs) and thus the presentation of tumor-associated antigens (TAAs) after radiotherapy, recruiting sufficient CD8+ T lymphocytes to specifically eradicate localized tumors. Moreover, the pre-treatment of VNPNKase before radiotherapy amplifies the abscopal effect and achieves a long-term immune memory effect, preventing the metastasis and recurrence of tumors. Our research suggests that this strategy using engineered bacteria to breach tumor physical barrier for promoting immune cell infiltration possesses great promise as a translational strategy to enhance the effectiveness of radio-immunotherapy in treating solid tumors. Herein, VNP20009 is engineered to secrete NKase (VNPNKase), which modulates the physical and immune characteristics of solid tumors by degrading ECM and inactivating CAFs. VNPNKase-remodeled TME facilitates the tumoral infiltration of immune cells after radiotherapy, achieving complete elimination of primary tumors, a potent abscopal effect, and a long-term immune memory response, which is promising for promoting clinical radio-immunotherapy of solid tumors. [Display omitted] • VNP20009 is engineered to secret nattokinase (VNPNKase). • VNPNKase dredges the extracellular matrix and inactivates cancer-associated fibroblasts. • Tumor physical barrier breached by VNPNKase facilitates the tumoral infiltration of immune cells after radiotherapy. • VNPNKase-remodeled tumor microenvironment potentiates radio-immunotherapy of solid colon tumors. [ABSTRACT FROM AUTHOR]

Working memory capacity (WMC) has received a great deal of attention in cognitive psychology partly because WMC correlates broadly with other abilities (e.g., reading comprehension, second-language proficiency, fluid intelligence) and thus seems to be a critical aspect of cognitive ability. However, it is still rigorously debated why such correlations occur. Some theories posit a single ability (e.g., attention control, short-term memory capacity, controlled memory search) as the primary reason behind WMC's predictiveness, whereas others argue that WMC is predictive because it taps into multiple abilities. Here, we tested these single- and multifaceted accounts of WMC with a large-scale (N = 974) individual-differences investigation of WMC and three hypothesized mediators: attention control, primary memory, and secondary memory. We found evidence for a multifaceted account, such that no single ability could fully mediate the relation between WMC and higher order cognition (i.e., reading comprehension and fluid intelligence). Further, such an effect held regardless of whether WMC was measured via complex span or n-back. Public Significance Statement: Individual differences in working memory capacity predict a host of important outcomes such as intelligence, academic performance, emotion regulation, and second-language acquisition. This study indicates that these relationships are likely multifaceted. Complex cognitive processes require the instantiation of task goals, the maintenance of goal-relevant information in short-term memory, and the controlled retrieval of information from long-term memory. We find that these three abilities can explain why working memory capacity is such a diverse predictor of critical outcomes. [ABSTRACT FROM AUTHOR]

A sustainable city is a smart city with a minimal impact on the environment, by incorporating technologies to reduce pollution. Traffic congestion which is a major concern contributes to global warming and climate change. Traffic forecasting projects future traffic patterns, using historical and current data to enhance traffic flow management. We propose a whole novel approach for predicting traffic congestion rate based on air quality data. We developed a new ensemble voting model based on Long Short Term Memory (LSTM) and Polynomial Regression (PolReg) models that use a new voting thresholded algorithm instead of the existing voting ones. The hyperparameters were optimized with the Genetic Agorithm, to overcome the non-stationarity of time series. A comparative study with the literature confirmed that our framework outperforms existing researches by keeping an absolute effectiveness according to learning curves, with Mean Absolute Error of 0.04, R-Squared of 0.93, and Root Mean Square Error (RMSE) of 0.05. [ABSTRACT FROM AUTHOR]

Sentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day‐to‐day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi‐LSTM RAO) to classify sentiment of tweets. Initially, data is obtained from Twitter API, Sentiment 140 and Stanford Sentiment Treebank‐2 (SST‐2). The raw data is pre‐processed and it is subjected to feature extraction which is performed using Bag of Words (BoW) and Term Frequency‐Inverse Document Frequency (TF‐IDF). The feature selection is performed using Gazelle Optimization Algorithm (GOA) which removes the irrelevant or redundant features that maximized model performance and classification is performed using Bi LSTM–RAO. The RAO optimizes the loss function of Bi‐LSTM model that maximized accuracy. The classification accuracy of proposed method for Twitter API, Sentiment 140 and SST 2 dataset is obtained as 909.44%, 99.71% and 99.86%, respectively. These obtained results are comparably higher than ensemble framework, Robustly Optimized BERT and Gated Recurrent Unit (RoBERTa‐GRU), Logistic Regression‐Long Short Term Memory (LR‐LSTM), Convolutional Bi‐LSTM, Sentiment and Context Aware Attention‐based Hybrid Deep Neural Network (SCA‐HDNN) and Stochastic Gradient Descent optimization based Stochastic Gate Neural Network (SGD‐SGNN). [ABSTRACT FROM AUTHOR]

The primary aim of this article is to propose an effective dengue disease monitoring system by integrating deep learning models with Internet of Things (IoT) and fog computing. In this context, the disease related parameters are collected using IoT devices and further, the reports are securely transmitted to the healthcare facilities utilizing fog computing. In this article, the misdiagnosis error is reduced utilizing attention based long short term memory (ALSTM) network with coati optimization algorithm (COA). The Attention model allocates higher weight to significant parameters and pay additional consideration while training the model. Therefore, the conventional LSTM network is combined with a self‐attention mechanism for enabling this model to focus on relevant parts of the input sequences for precise dengue disease prediction. The Attention Model differs from the conventional model since it delivers higher amount of data into the decoder and improves additional stages to the attention decoder before making its output. Furthermore, the COA is integrated with the ALSTM network for optimal hyper‐parameter selection. The ALSTM‐COA model evaluates the dengue related parameters like nausea, vomiting, skin rash, joint pain, muscle pain, soft bleeding, temperature of water‐sites, humidity of water‐sites, and so forth, for timely dengue disease diagnosis and clinical decision‐making. The experiments performed on a real time dataset state that the ALSTM‐COA model achieves significant prediction results by utilizing different performance measures like recall, accuracy, fall‐out, miss rate, training time, and testing time. The ALSTM‐COA model obtains an accuracy of 99.27%, latency of 0.03 s, and time complexity of 8 s for 500 health records, which are superior to the comparative deep learning models. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by the accumulation of amyloid-β, leading to N-methyl-D-aspartate (NMDA) receptor-dependent synaptic depression, spine elimination, and memory deficits. Glycine transporter type 1 (GlyT1) modulates glutamatergic neurotransmission via NMDA receptors (NMDAR), presenting a potential alternative therapeutic approach for AD. This study investigates the neuroprotective potential of GlyT1 inhibition in an amyloid-β-induced AD mouse model. C57BL/6 mice were treated with N-[3-([1,1-Biphenyl]-4-yloxy)-3-(4-fluorophenyl)propyl]-N-methylglycine (NFPS), a GlyT1 inhibitor, 24 h prior to intrahippocampal injection of amyloid-β. NFPS pretreatment prevented amyloid-β-induced cognitive deficits in short-term and long-term memory, evidenced by novel object recognition and spatial memory tasks. Moreover, NFPS pretreatment curbed microglial activation, astrocytic reactivity, and subsequent neuronal damage from amyloid-β injection. An extensive label-free quantitative UPLC-MSE proteomic analysis was performed on the hippocampi of mice treated with NFPS. In proteomics, KEGG enrichment analysis revealed increased in dopaminergic synapse, purine-containing compound biosynthetic process and long-term potentiation, and a reduction in Glucose catabolic process and glycolytic process pathways. The western blot analysis confirmed that NFPS treatment elevated BDNF levels, correlating with enhanced TRKB phosphorylation and mTOR activation. Moreover, NFPS treatment reduced the GluN2B expression after 6 h, which was associated with an increase on CaMKIV and CREB phosphorylation. Collectively, these findings demonstrate that GlyT1 inhibition by NFPS activates diverse neuroprotective pathways, enhancing long-term potentiation signaling and countering amyloid-β-induced hippocampal damage. [ABSTRACT FROM AUTHOR]

Conventional approaches to forecasting the risk of athlete injuries are constrained by their narrow scope in feature extraction, often failing to adequately account for temporal dependencies and the effects of long-term memory. This paper enhances the Long Short-Term Memory (LSTM) network, specifically tailoring it to harness temporal data pertaining to athletes. This advancement significantly boosts the accuracy and effectiveness of predicting the risk of injuries among athletes. The network structure of the LSTM model was improved, and the collected data was converted into the temporal data form of the LSTM input. Finally, historical data labeled with injury labels were used to train the improved LSTM model, and gradient descent iterative optimization was used to adjust the parameters of the improved LSTM model. The improved LSTM network model was compared with the traditional athlete injury risk prediction model in terms of performance. The incorporation of enhanced LSTM networks for the analysis of temporal athlete data holds significant research significance. This approach has the potential to substantially enhance the accuracy and effectiveness of athlete injury risk prediction, contributing to a deeper understanding of the temporal dynamics influencing injuries in sports. [ABSTRACT FROM AUTHOR]

Traditional music emotion recognition (MER) faces problems such as lack of contextual information, inaccurate recognition of music emotions, and difficulty in handling nonlinear relationships. This article first used long short-term memory (LSTM) networks to capture global information and contextual relationships of music. Subsequently, the DCNN was chosen to process sequence data and capture global dependencies to improve the accuracy of MER. Finally, a MER model was constructed based on DCNN to recognize and classify music emotions. This article obtained the impact of different parameter values on model training iterations by adjusting hyperparameters related to training. The optimal values for learning rate μ , momentum coefficient α , weight attenuation coefficient γ , and Dropout coefficient were 0.01, 0.7, 0.0003, and 0.5, respectively. The DCNN used in this article was iteratively trained with recurrent neural networks, convolutional recurrent neural networks, and transform domain neural networks for audio spectrograms, and the results were compared. The experimental findings indicated that the spectral recognition accuracy of DCNN was stable at 95.68%, far higher than the other three different networks. The results showed that the DCNN method used in this article could more accurately distinguish different negative emotions and positive emotions. [ABSTRACT FROM AUTHOR]

With the rapid development of music digitization and online streaming services, automatic analysis and classification of music content has become an urgent need. This research focuses on music sentiment analysis, which is the identification and classification of emotions expressed by music through algorithms. The study defines and classifies possible emotions in music. Then, advanced artificial intelligence techniques, including traditional machine learning and deep learning methods, were employed to perform sentiment analysis on music fragments. In the process of creating and validating the model, the combination of convolutional neural network and long term memory network shows excellent performance in various performance indicators. However, for some complex or culturally ambiguous music fragments, the model may also suffer from misclassification problems. This provides the direction for further optimization of future research aimed at achieving more accurate music emotion analysis. [ABSTRACT FROM AUTHOR]

The statistical properties of energy and waiting time carry essential information about the source of repeating fast radio bursts (FRBs). In this paper, we investigate the randomness of energy and waiting time using four data samples from three extremely active repeating FRBs observed by the Five-hundred-meter Aperture Spherical radio Telescope (FAST). We report the deviation from complete randomness of the burst activity using three statistics, i.e. Hurst exponent, Pincus index, and non-Gaussian probability density distribution of fluctuations. First, the Hurst exponent greater than 0.5 reveals that there is long-term memory in the time series of energy and waiting time. Second, the deviation of the Pincus index from 1.0 manifests that the time series is not completely random. Finally, the fluctuations of energy and waiting time follow the scale-invariant q -Gaussian distribution. All these statistical properties imply that, although the time series of repeating FRBs seems to be irregular, they are not completely random, similar to the features of self-organized criticality. [ABSTRACT FROM AUTHOR]

• Deep auto-encoder model is used to handle the non-linear and redundant information in dam key parameters. • A hybrid system based on intelligent optimization algorithms and deep learning for predicting tailings dam parameters. • The uncertainty analysis provides more comprehensive and precise interval predictions. • The prediction accuracy of monitoring parameters of tailings dam is significantly improved. Tailings dams, as critical infrastructure, play a vital role in ensuring the safety and reliability of tailings pond systems. Predicting the trend of tailings dam monitoring parameters helps monitor its operational status and support safety management and decision-making. The traditional time series prediction model focuses on point prediction while neglecting the nonlinear feature of data and the uncertainty of prediction results, which is far from meeting the requirements for risk monitoring and safety management of tailings dam systems. To address this, Deep Auto-Encoder is used to extract and optimize features of multi-dimensional time series; Whale Optimization Algorithm, Long Short Term Memory, and Kernel Density Estimation are used to build a monitoring parameters trend interval prediction model. It can effectively predict and analyze the uncertainty of tailings dam monitoring parameters. Time series data of monitoring parameters are collected from a tailings dam in Anhui, China and modeled to verify the effectiveness of the model. The results show that the hybrid prediction model performs the best in monitoring parameter prediction accuracy and trend. The Root Mean Square Error values of the Whale Optimization Algorithm and Long Short Term Memory prediction for reservoir water level, surface displacement, internal displacement, phreatic line, and beach width are 0.0160, 1.0405, 0.0389, 0.0176, and 0.7525, with errors reduced by 0.37 % to 17.92 % compared to other models. The uncertainty analysis confirms the high reliability of the model. The Kernel Density Estimation effectively forecasts the fluctuation range of predicted values, significantly improving the prediction effectiveness of the monitoring parameters. [ABSTRACT FROM AUTHOR]

This article explores a novel data-driven approach based on recent developments in Koopman operator theory and dynamic mode decomposition (DMD) for modeling signalized intersections. On signalized intersections, vehicular flow and queue formation have complex nonlinear dynamics, making system identification, modeling, and controller design challenging. We employ a DMD-type approach to transform the original nonlinear dynamics into locally linear infinite-dimensional dynamics. The data-driven approach relies entirely on spatio-temporal snapshots of the traffic data. We investigate several key aspects of the approach and provide insights into the usage of DMD-type algorithms for application in adaptive signalized intersections. To validate the obtained linearized dynamics, we perform prediction of the queue lengths at the intersection and compare the results with the benchmark methods such as ARIMA and long short term memory (LSTM). The case study involves intersection pressure and queue lengths at two Orlando area signalized intersections during the morning and evening peaks. It is observed that DMD-type algorithms are able to capture complex dynamics with a linear approximation to a reasonable extent. The merits include faster computation times and significantly less requirement for a "lookback" (training) window. [ABSTRACT FROM AUTHOR]