Long short-term memory networks for vehicle sensor fusion

This paper presents Track-LITE, a novel target-tracking framework that synergistically integrates an Interacting Multiple Model (IMM) filter with a Long Short-Term Memory (LSTM) network, governed by a dynamic on–off trigger mechanism. The IMM filter provides a reliable baseline for gradual motion, while the LSTM is selectively activated to refine estimates following abrupt maneuvers, a key contribution enabling adaptive accuracy. Quickest Change Detection (QCD) serves as the mechanism to detect these motion changes, collecting evidence of significant shifts and triggering the powerful LSTM to enhance prediction results. A bespoke feedback loop, another significant innovation, leverages LSTM residual errors to iteratively adjust IMM model weights, ensuring continuous adaptability across diverse motion profiles. The activation threshold, a critical derived design contribution, is optimized by jointly balancing false-alarm rate and latency, enabling precise coordination between the IMM and LSTM modules. With LSTM active only 30% of the time, Track-LITE achieves an RMSE comparable to continuous LSTM, while reducing computational load by 70%, a testament to its efficiency. This performance trade-off makes Track-LITE exceptionally well-suited for real-time, resource-constrained applications such as autonomous navigation and drone tracking.

Modern decision-making in fixed income asset management benefits from intelligent systems, which involve the use of state-of-the-art machine learning models and appropriate methodologies. We conduct the first study of bond yield forecasting using long short-term memory (LSTM) networks, validating its potential and identifying its memory advantage. Specifically, we model the 10-year bond yield using univariate LSTMs with three input sequences and five forecasting horizons. We compare those with multilayer perceptrons (MLP), univariate and with the most relevant features. To demystify the notion of black box associated with LSTMs, we conduct the first internal study of the model. To this end, we calculate the LSTM signals through time, at selected locations in the memory cell, using sequence-to-sequence architectures, uni and multivariate. We then proceed to explain the states’ signals using exogenous information, for what we develop the LSTM-LagLasso methodology. The results show that the univariate LSTM model with additional memory is capable of achieving similar results as the multivariate MLP using macroeconomic and market information. Furthermore, shorter forecasting horizons require smaller input sequences and vice-versa. The most remarkable property found consistently in the LSTM signals, is the activation/deactivation of units through time, and the specialisation of units by yield range or feature. Those signals are complex but can be explained by exogenous variables. Additionally, some of the relevant features identified via LSTM-LagLasso are not commonly used in forecasting models. In conclusion, our work validates the potential of LSTMs and methodologies for bonds, providing additional tools for financial practitioners.

Flash floods occur frequently and distribute widely in mountainous areas because of complex geographic and geomorphic conditions and various climate types. Effective flash flood forecasting with useful lead times remains a challenge due to its high burstiness and short response time. Recently, machine learning has led to substantial changes across many areas of study. In hydrology, the advent of novel machine learning methods has started to encourage novel applications or substantially improve old ones. This study aims to establish a discharge forecasting model based on Long Short-Term Memory (LSTM) networks for flash flood forecasting in mountainous catchments. The proposed LSTM flood forecasting (LSTM-FF) model is composed of T multivariate single-step LSTM networks and takes spatial and temporal dynamics information of observed and forecast rainfall and early discharge as inputs. The case study in Anhe revealed that the proposed models can effectively predict flash floods, especially the qualified rates (the ratio of the number of qualified events to the total number of flood events) of large flood events are above 94.7% at 1–5 h lead time and range from 84.2% to 89.5% at 6–10 h lead-time. For the large flood simulation, the small flood events can help the LSTM-FF model to explore a better rainfall-runoff relationship. The impact analysis of weights in the LSTM network structures shows that the discharge input plays a more obvious role in the 1-h LSTM network and the effect decreases with the lead-time. Meanwhile, in the adjacent lead-time, the LSTM networks explored a similar relationship between input and output. The study provides a new approach for flash flood forecasting and the highly accurate forecast contributes to prepare for and mitigate disasters.

This paper aims to predict the occurrence of pests and diseases for cotton based on long short term memory (LSTM) network. First, the problem of occurrence of pests and diseases was formulated as time series prediction. Then LSTM was adopted to solve the problem. LSTM is a special kind of recurrent neutral network (RNN), which introduces gate mechanism to prevent the vanished or exploding gradient problem. It has been shown good performance in solving time series problem and can handle the long-term dependency problem, as mentioned in many literatures. The experimental results showed that LSTM performed good on the prediction of occurrence of pests and diseases in cotton fields, and yielded an Area Under the Curve (AUC) of 0.97. The paper further verified that the weather factors indeed have strong impact on the occurrence of pests and diseases, and the LSTM network has great advantage on solving the long-term dependency problem.

Utilization of the Long Short-Term Memory network for predicting streamflow in ungauged basins in Korea

In order to enhance the accuracy of thermal response estimation, this study proposes the utilization of a deep learning-driven method, specifically the Long Short-Term Memory (LSTM) network, for predicting temperature-induced strains and deflections in the Queensferry Crossing, UK. Initially, an examination of the temperature fields of the bridge is conducted based on monitored temperature data. Subsequently, the LSTM network is introduced as a tool to estimate thermal response utilizing temperature field information. The study proceeds to discuss the results of temperature-induced response estimation, including strains and deflections, obtained through the LSTM network, with a comparative analysis against a linear regression model. It is observed that the temperature discrepancies among steel components within the bridge are lesser in comparison to those of concrete components. The LSTM network exhibits higher estimation accuracy than the linear model, manifesting in an improvement of mean square error from 4.45 to 0.89 for strain estimation. In addition, the LSTM network can partially address time-lag effects. However, the estimation performance of the LSTM network is influenced by the structural response type and the resolution of employed sensors. Specifically, the correlation coefficient (R) associated with strain estimation is measured at 0.980 using the LSTM network, whereas R for deflection estimation stands at 0.825. Generally, local structural responses, such as strains, outperform global responses like deflections. Furthermore, sensors with higher resolutions yield enhanced estimation accuracy.

<p dir="ltr">Recurrent Neural Networks (RNNs) are a major class of Artificial Neural Networks (ANNs). Suitable network architecture is vital for RNNs to achieve high performance. However, designing the architecture of deep RNNs (DRNNs) is a complicated and time-consuming process. Each layer of a DRNN contains numerous hyper-parameters. It is challenging to optimize the hyper-parameters of all layers jointly to achieve the best possible learning performance. Trial-and-error methods for designing DRNNs have been proven to be laborious and highly costly in practice. Therefore, an efficient automatic architecture search technique is needed to design DRNNs.</p><p dir="ltr">Genetic Algorithm (GA) is a popular evolutionary computation based approach. Existing research works already explored the use of GAs in designing ANNs. But, most of the existing approaches focus on the design of fixed-depth ANNs. However, it is not easy to fix the depth of DRNNs in advance, since different problems need DRNNs of different depths. Hence, the potential of GA has to be further explored to evolve the architecture of DRNNs of varying depths.</p><p dir="ltr">The primary goal of this thesis is to develop advanced GA approaches for designing Long Short Term Memory (LSTM) based DRNN architectures of varying depths effectively and efficiently.</p><p dir="ltr">Firstly, this thesis proposes a GA-based algorithm called Two-Stage Surrogate-Assisted GA (TS-SA-GA) with a progressive incremental strategy to design the architecture of LSTM networks of varying depths. The progressive approach can effectively extend well-designed shallow networks to high performing deep networks. Moreover, the new GA-based algorithm adopts newly designed knowledge-driven crossover and mutation operators to identify and repair LSTM network designs affected by inappropriate use of activation functions, thereby significantly reducing the chances for GA to evolve hard-to-train LSTM network architectures. Furthermore, this thesis proposes a two-stage surrogate method to predict the trainability and fitness of LSTM networks. This improves the efficiency and effectiveness of the GA-based algorithm to evolve LSTM networks.</p><p dir="ltr">Secondly, this thesis proposes a new algorithm called Evolutionary Design of LSTM Ensembles (ED-LSTM-Ensemble) based on multi-objective optimization techniques to evolve LSTM networks and ensembles simultaneously to directly utilize the ensemble performance to drive the evolution of base LSTM networks. Additionally, this thesis proposes a connection weight inheritance strategy to evolve LSTM networks and ensembles efficiently and effectively.</p><p dir="ltr">Thirdly, this thesis proposes a new algorithm called Skip Connections through Evolutionary and Differential Architecture search (SCEDA) to design LSTM networks together with appropriate skip connections automatically. Designing LSTM networks together with skip connections is highly challenging. This thesis hybridize gradient-based DAS and evolutionary architecture search to optimize the architecture of LSTM networks with suitable skip connections in a single evolutionary process to improve the efficiency and effectiveness of the search process.</p><p dir="ltr">Finally, this thesis conducts an in-depth empirical analysis of the impact of activation functions on the trainability of LSTM networks based on the concept of Edge Of Chaos. The analysis reveals the strong interrelation between the activation functions across multiple layers of an LSTM network and the trainability of the network. The analysis also highlights the importance of controlling activation functions to avoid generating untrainable LSTM networks. On the basis of the analysis, this thesis proposes a machine learning model to guide the use of activation functions in LSTM networks.</p>

With the rapid increase in bridge spans, the mitigation of risk to flutter (aeroelastic instability) is of critical importance in the design of long-span bridges, especially considering the more frequent intense hurricanes under climate change. Although the strong nonlinearities of the aeroelastic (self-excited) forces in wind–bridge interactions can be well captured through either numerical simulations or experimental tests, both are expensive and time consuming. Hence, it is important to develop an efficient reduced-order model for the simulations of nonlinear aeroelastic forces on the bridge decks. This study proposes a reduced-order model based on the long short-term memory (LSTM) network to simulate the nonlinear aeroelastic forces on bridge decks with various leading edges, and thus rapidly predict the corresponding post-flutter behaviors of long-span bridges. To generate the training datasets, computational fluid dynamics (CFD) was employed to simulate the nonlinear aeroelasticities of bridge decks with a wide range of leading-edge configurations and wind speeds. Trained on the high-fidelity CFD datasets, the LSTM network takes the motion of a bridge deck, leading-edge angles and wind speeds as inputs and outputs the nonlinear aeroelastic forces on the bridge decks. A hybrid loss function utilizing the prediction errors of both aeroelastic forces simulated by the LSTM network and the bridge deck responses calculated by the Newmark-β algorithm was introduced into the training process to improve the network performance. The prediction results of the trained LSTM model were compared with the CFD simulations, which demonstrated that the nonlinear aeroelastic forces of the bridge deck with various leading edges can be accurately and efficiently acquired by the proposed LSTM model.

To address the issues of slow convergence speed, poor dynamic adaptability, and path redundancy in the Double Deep Q Network (DDQN) within complex obstacle environments, this paper proposes an enhanced algorithm within the deep reinforcement learning framework. This algorithm, termed LPDDQN, integrates Prioritized Experience Replay (PER) and the Long Short Term Memory (LSTM) network to improve upon the DDQN algorithm. First, Prioritized Experience Replay (PER) is utilized to prioritize experience data and optimize storage and sampling operations through the SumTree structure, rather than the conventional experience queue. Second, the LSTM network is introduced to enhance the dynamic adaptability of the DDQN algorithm. Owing to the introduction of the LSTM model, the experience samples must be sliced and populated. The performance of the proposed LPDDQN algorithm is compared with five other path planning algorithms in both static and dynamic environments. Simulation analysis shows that in a static environment, LPDDQN demonstrates significant improvements over traditional DDQN in terms of convergence, number of moving steps, success rate, and number of turns, with respective improvements of 24.07%, 17.49%, 37.73%, and 61.54%. In dynamic and complex environments, the success rates of all algorithms, except TLD3 and the LPDDQN, decreased significantly. Further analysis reveals that the LPDDQN outperforms the TLD3 by 18.87%, 2.41%, and 39.02% in terms of moving steps, success rate, and number of turns, respectively.

<p>Flooding is one of the most financially devastating natural hazards in the world. Studying storage-discharge relations can have the potential to improve existing flood forecasting systems, which are based on rainfall-runoff models. This presentation will assess the non-linear relation between daily water storage (ΔS) and discharge (Q) simulated by physical-based hydrological models at the Rum River Watershed, a HUC8 watershed in Minnesota, between 1995-2015, by training Long Short-Term Memory (LSTM) networks and other machine learning (ML) algorithms. Currently, linear regression models do not adequately represent the relationship between the simulated total ΔS and total Q at the HUC-8 watershed (R<sup>2</sup> = 0.3667). Since ML algorithms have been used for predicting the outputs that represent arbitrary non-linear functions between predictors and predictands, they will be used for improving the accuracy of the non-linear relation of the storage-discharge dynamics. This research will mainly use LSTM networks, the time-series deep learning neural network that has already been used for predicting rainfall-runoff relations. The LSTM network will be trained to evaluate the storage-discharge relationship by comparing two sets of non-linear hydrological variables simulated by the semi-distributed Hydrological Simulated Program-Fortran (HSPF): the relationship between the simulated discharges and input hydrological variables at selected HUC-8 watersheds, including air temperatures, cloud covers, dew points, potential evapotranspiration, precipitations, solar radiations, wind speeds, and total water storage, and the dynamics between simulated discharge and input variables that do not include the total water storage. The result of this research will lay the foundation for assessing the accuracy of downscaled storage-discharge dynamics by applying similar methods to evaluate the storage-discharge dynamics at small-scaled, HUC-12 watersheds. Furthermore, its results have the potentials for us to evaluate whether downscaling of storage-discharge dynamics at the HUC-12 watershed can improve the accuracy of predicting discharge by comparing the result from the HUC-8 and the HUC-12 watersheds.</p>

As a kind of continuous time series, plantar pressure data contains rich contact of time information which has not been fully utilized in existing gait recognition methods. In this paper, we proposed a new gait recognition method based on plantar pressure data with a Long Short-Term Memory (LSTM) network. By normalization and dimensionality reduction, the raw pressure data was converted to feature tensor. Then we feed the LSTM network with the feature tensors and implement classification recognition. We collected data from 93 subjects of different age groups, and each subjects was collected 10 sets of pressure data. The experiment results turn out that our LSTM network can get high classification accuracy and performs better than CNN model and many traditional methods.

Seismic response prediction of RC bridge piers through stacked long short-term memory network

This project focuses on improving the detection of network attacks by using a machine learning technique known as Long Short-Term Memory (LSTM) networks. LSTM networks are a type of neural network that excels at analyzing sequences of data, making them well-suited for identifying patterns associated with network intrusions. To enhance the LSTM model's effectiveness, we introduce new probability features that help the model better distinguish between normal and malicious activities. Our approach includes collecting network data, preprocessing it to make it suitable for training, and then using this data to train the LSTM model. We evaluate the model's performance using a range of metrics to ensure its accuracy and reliability. The results indicate that our method significantly improves the detection rate of network attacks while also reducing the number of false alarms. This means that our LSTM-based model not only catches more real threats but also makes fewer mistakes in identifying normal activities as attacks. Overall, this project showcases the potential of advanced machine learning techniques, like LSTM networks, to enhance cyber security measures and protect against network threats more effectively.

Scene text recognition (STR) technology has a rapid development with the rise of deep learning. Recently, the encoder-decoder framework based on attention mechanism is widely used in STR for better recognition. However, the commonly used Long Short Term Memory (LSTM) network in the framework tends to ignore certain position or visual information. To address this problem, we propose a Position Information Enhanced Encoder-Decoder (PIEED) framework for scene text recognition, in which an addition position information enhancement (PIE) module is proposed to compensate the shortage of the LSTM network. Our module tends to retain more position information in the feature sequence, as well as the context information extracted by the LSTM network, which is helpful to improve the recognition accuracy of the text without context. Besides that, our fusion decoder can make full use of the output of the proposed module and the LSTM network, so as to independently learn and preserve useful features, which is helpful to improve the recognition accuracy while not increase the number of arguments. Our overall framework can be trained end-to-end only using images and ground truth. Extensive experiments on several benchmark datasets demonstrate that our proposed framework surpass state-of-the-art ones on both regular and irregular text recognition.

Accurate and timely short-term traffic flow forecasting plays a key role in intelligent transportation systems, especially for prospective traffic control. For the past decade, a series of methods have been developed for short-term traffic flow forecasting. However, due to the intrinsic stochastic and evolutionary trend, accurate forecasting remains challenging. In this paper, we propose a noise-immune long short-term memory (NiLSTM) network for short-term traffic flow forecasting, which embeds a noise-immune loss function deduced by maximum correntropy into the long short-term memory (LSTM) network. Different from the conventional LSTM network equipped with the mean square error loss, the maximum correntropy induced loss is a local similar metric, which is immunized to non-Gaussian noises. Extensive experiments on four benchmark datasets demonstrate the superior performance of our NiLSTM network by comparing it with the frequently used models and state-of-the-art models.