Sequential Model Research Articles

Sequential model for predicting patient adherence in subcutaneous immunotherapy for allergic rhinitis.

Subcutaneous Immunotherapy (SCIT) is the long-lasting causal treatment of allergic rhinitis (AR). How to enhance the adherence of patients to maximize the benefit of allergen immunotherapy (AIT) plays a crucial role in the management of AIT. This study aims to leverage novel machine learning models to precisely predict the risk of non-adherence of AR patients and related local symptom scores in 3years SCIT. The research develops and analyzes two models, sequential latent-variable model (SLVM) of Stochastic Latent Actor-Critic (SLAC) and Long Short-Term Memory (LSTM). SLVM is a probabilistic model that captures the dynamics of patient adherence, while LSTM is a type of recurrent neural network designed to handle time-series data by maintaining long-term dependencies. These models were evaluated based on scoring and adherence prediction capabilities. Excluding the biased samples at the first time step, the predictive adherence accuracy of the SLAC models is from 60% to 72%, and for LSTM models, it is 66%-84%, varying according to the time steps. The range of Root Mean Square Error (RMSE) for SLAC models is between 0.93 and 2.22, while for LSTM models it is between 1.09 and 1.77. Notably, these RMSEs are significantly lower than the random prediction error of 4.55. We creatively apply sequential models in the long-term management of SCIT with promising accuracy in the prediction of SCIT nonadherence in AR patients. While LSTM outperforms SLAC in adherence prediction, SLAC excels in score prediction for patients undergoing SCIT for AR. The state-action-based SLAC adds flexibility, presenting a novel and effective approach for managing long-term AIT.

Eichner classification based on panoramic X-ray images using deep learning: A pilot study.

Research using panoramic X-ray images using deep learning has been progressing in recent years. There is a need to propose methods that can classify and predict from image information. In this study, Eichner classification was performed on image processing based on panoramic X-ray images. The Eichner classification was based on the remaining teeth, with the aim of making partial dentures. This classification was based on the condition that the occlusal position was supported by the remaining teeth in the upper and lower jaws. Classification models were constructed using two convolutional neural network methods: the sequential and VGG19 models. The accuracy was compared with the accuracy of Eichner classification using the sequential and VGG19 models. Both accuracies were greater than 81%, and they had sufficient functions for the Eichner classification. We were able to build a highly accurate prediction model using deep learning scratch sequential model and VGG19. This predictive model will become part of the basic considerations for future AI research in dentistry.

Torque and d-q axis current dynamics of an inverter fed induction motor drive that leverages computational intelligent techniques

<abstract> <p>Emphasizing the significance of Model Predictive Control (MPC) in modern optimization of control systems, the proposed research distinctively highlights its predictive prowess through the application of current state variables and well-structured mathematical models. We introduced a Predictive Current Control (PCC) strategy applied to a Three-Phase Inverter-fed Induction Motor (IM), with a particular focus on the Sequential Model methodology. The Sequential Model MPC algorithm employed a cost functional approach, predicated on the square of the discrepancy between reference and stator-measured currents of the IM in d-q reference frame. This method, implemented and tested in both MATLAB/Simulink and Python environments, utilized a minimization principle to guide the switching states of the inverter, thereby ensuring the accuracy of voltage signals for the induction motor. The projected study further included a comparative analysis of the electromagnetic torque, load currents, rotor speed, and angle deviations derived from the Sequential Model with those obtained through the Ant Colony Optimization (ACO) and Nelder-Mead methods. The results distinctly illustrated the robust adaptability of the Sequential Model methodology, outperforming the ACO and Nelder-Mead techniques in certain aspects such as minimum current errors, better speed regulations, and rotor angle trajectories.</p> </abstract>

Comparative Analysis of Deep Learning Algorithms for Phishing Email Detection

Using skewed sequential data, the study explores the effectiveness of numerous sequential models designed for binary classification tasks. The dataset under investigation consists of 5,595 testing samples and 13,055 training samples, a structure that presents significant difficulties because of uneven labelling. The researchers carefully go through pretreatment procedures, which include text data encoding and effective methods for handling missing information, in order to address this. The study employs and examines a wide range of algorithms, which reflects the heterogeneous sequential modelling environment. A variety of neural network architectures are included in the arsenal: CNN, CNN-RNN, RCNN. The binary classification job at hand is used to thoroughly assess each architecture, revealing both its advantages and disadvantages. The study's evaluation approach, which presents a wide range of measures indicating consistently excellent performance overall, is its key component. Among these algorithms stand out as the best with an astounding 97% accuracy rate on a variety of evaluation metrics. This strong performance highlights their ability to handle sequential data with unbalanced labels and establishes a standard for further work in related fields. Beyond its empirical results, the study is important because it provides a well-designed assessment approach that may be used as a benchmark by practitioners facing similar problems. Through the clarification of important concepts related to model selection and performance evaluation, the study provides professionals and academics with crucial resources to efficiently traverse the complex terrain of sequential modelling.

Getting Workers to Engage in Organizational Citizenship Behaviors and Decrease Their Intention to Quit: A Sequential Mediation Process Model: A Sequential Mediation Process Model

Getting Workers to Engage in Organizational Citizenship Behaviors and Decrease Their Intention to Quit: A Sequential Mediation Process Model: A Sequential Mediation Process Model

HASHTAG-BASED TWEET EXPANSION FOR IMPROVED TOPIC MODELLING

In this paper author employing BILSTM, BERT and GRAPHCNN algorithms to predict topics from heterogeneous and homogenous tweets where heterogeneous refers to unrelated tweets and homogenous refers to related tweets. To predict topics from text many existing algorithms are available such as tweet aggregation, where related tweets are combined into a single document or 2) tweet expansion with related text from external sources. The first approach faces the problem of losing the topic distribution in individual tweets. While finding a relevant text from the external source for a random tweet in the second approach is challenging for various reasons like differences in writing styles, multilingual content, and informal text. In contrast to adding context from external resources or combining related tweets into a pool, this study uses the internal vocabulary (hashtags) to counter under-specificity and sparsity in tweets. Earlier studies have indicated hashtags to be an important feature for representing the underlying context present in the tweet. Sequential models like Bidirectional Long Short Term Memory (BiLSTM) and Convolution Neural Network (CNN) over distributed representation of words have shown promising results in capturing semantic relationships between words of a tweet in the past. Motivated by the above, this article proposes a unified framework of hashtag-based tweet expansion exploiting text-based and network-based representation learning methods such as BiLSTM, BERT, and Graph Convolution Network (GCN). The hashtag-based expanded tweets using the proposed framework have significantly improved topic modelling performance compared to un-expanded (raw) tweets and hashtag-poolingbased approaches over two real-world tweet datasets of different nature.Propose paper will expand or identify TWEETS from given Hashtags and then identify topics from expanded HashtagsBILSTM, GRAPHCNN and BERT are based on Text processing which can be used to efficiently process and predict topics from the tweets. It’s difficult to train all 3 algorithms so we are training BERT and BILSTM. To train above algorithms author is using tweets from various HASHTAGS and not publish those tweets on internet so we have collected some tweets from various hashtags and below are the dataset details.

A sequential lumped kinetic modelling approach for the co-pyrolysis of plastic mixtures with a heavy refinery intermediate product in a tubular reactor

A novel sequential approach for the lumped kinetic modelling of a plastic pyrolysis process in a tubular reactor.

Predicting Student Engagement Using Sequential Ensemble Model

Predicting Student Engagement Using Sequential Ensemble Model

Real-Time Predicting the Low-Temperature Performance of WLTC-Based Lithium-Ion Battery Using an LSTM-PF Sequential Ensemble Model

Real-Time Predicting the Low-Temperature Performance of WLTC-Based Lithium-Ion Battery Using an LSTM-PF Sequential Ensemble Model

FSASA: Sequential recommendation based on fusing session-aware models and self-attention networks

The recommendation system can alleviate the problem of ?information overload?, tap the potential value of data, push personalized information to users in need, and improve information utilization. Sequence recommendation has become a hot research direction because of its practicality and high precision. Deep Neural Networks (DNN) have the natural advantage of capturing comprehensive relations among different entities, thus almost occupying a dominant position in sequence recommendation in the past few years. However, as Deep Learning (DL)-based methods are widely used to model local preferences under user behavior sequences, the global preference modeling of users is often underestimated, and usually, only some simple and crude user latent representations are introduced. Therefore, this paper proposes a sequential recommendation based on Fusing Session-Aware models and Self-Attention networks (FSASA). Specifically, we use the Self-Attentive Sequential Recommendation (SASRec) model as a global representation learning module to capture long-term preferences under user behavior sequences and further propose an improved session-aware sequential recommendation model as a local learning representation module from user model the user?s dynamic preferences in the historical behavior, and finally use the Gated Recurrent Unit (GRU) module to calculate their weights. Experiments on three widely used recommendation datasets show that FSASA outperforms state-of-the-art baselines on two commonly used metrics.

Toward a causal model of curiosity and creativity.

We extend Ivancovsky et al.'s finding on the association between curiosity and creativity by proposing a sequential causal model assuming that (a) curiosity determines the motivation to seek information and that (b) creativity constitutes a capacity to act on that motivation. This framework assumes that both high levels of curiosity and creativity are necessary for information-seeking behavior.

MMSleepGNet: Mixed Multibranch Sequential Fusion Model Based on Graph Convolutional Network for Automatic Sleep Staging

MMSleepGNet: Mixed Multibranch Sequential Fusion Model Based on Graph Convolutional Network for Automatic Sleep Staging

Mobile detection of cataracts with an optimised lightweight deep Edge Intelligent technique

AbstractTesting the visual field is a valuable diagnostic tool for identifying eye conditions such as cataract, glaucoma, and retinal disease. Its quick and straightforward testing process has become an essential component in our efforts to prevent blindness. Still, the device must be accessible to the general masses. This research has developed a machine learning model that can work with Edge devices like smartphones. As a result, it is opening the opportunity to integrate the disease‐detecting model into multiple Edge devices to automate their operation. The authors intend to use convolutional neural network (CNN) and deep learning to deduce which optimisers have the best results when detecting cataracts from live photos of eyes. This is done by comparing different models and optimisers. Using these methods, a reliable model can be obtained that detects cataracts. The proposed TensorFlow Lite model constructed by combining CNN layers and Adam in this study is called Optimised Light Weight Sequential Deep Learning Model (SDLM). SDLM is trained using a smaller number of CNN layers and parameters, which gives SDLM its compatibility, fast execution time, and low memory requirements. The proposed Android app, I‐Scan, uses SDLM in the form of TensorFlow Lite for demonstration of the model in Edge devices.

Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation.

Deep learning-based image compression has made great progresses recently. However, some leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the complexities of the encoding and decoding networks are quite high and not suitable for many practical applications. In this paper, we propose four techniques to balance the trade-off between the complexity and performance. We first introduce the deformable residual module to remove more redundancies in the input image, thereby enhancing compression performance. Second, we design an improved checkerboard context model with two separate distribution parameter estimation networks and different probability models, which enables parallel decoding without sacrificing the performance compared to the sequential context-adaptive model. Third, we develop a three-pass knowledge distillation scheme to retrain the decoder and entropy coding, and reduce the complexity of the core decoder network, which transfers both the final and intermediate results of the teacher network to the student network to improve its performance. Fourth, we introduce L1 regularization to make the numerical values of the latent representation more sparse, and we only encode non-zero channels in the encoding and decoding process to reduce the bit rate. This also reduces the encoding and decoding time. Experiments show that compared to the state-of-the-art learned image coding scheme, our method can be about 20 times faster in encoding and 70-90 times faster in decoding, and our R-D performance is also 2.3% higher. Our method achieves better rate-distortion performance than classical image codecs including H.266/VVC-intra (4:4:4) and some recent learned methods, as measured by both PSNR and MS-SSIM metrics on the Kodak and Tecnick-40 datasets.

Diagnosis of glaucoma from retinal fundus images using disc localization and sequential DNN model

AbstractDeep learning is an emerging trend with enormous applications over the past few years. Ophthalmology is one such area in medical applications where early disease detection is required to avoid loss of vision. Glaucoma is a rapidly growing disorder related to human eye, which arises due to the increase in pressure inside the eye. The medical diagnosis methods available for glaucoma have some limitations; hence, computer‐aided design (CAD) approach is preferred using images. In the context of image processing, convolution neural networks (CNNs) are preferred for classification because of their ability to grasp highly discriminate features from raw pixel intensities. In our approach, diagnosis of glaucoma is implemented by extracting the region of interest (ROI) by splitting the coefficients into recurrence decays and will improve the possibility of identifying even poorly differentiated exudates and upgrading the normal recurrence ranges. Later, a sequential deep neural network (DNN) model with a rectified linear unit (ReLU) and sigmoid function is designed to train the data with effective features matching from training and testing samples. The proposed model is implemented on two publicly available datasets (Drishti‐GS1 and ACRIMA) using 10‐fold cross validation (CV), 60:40 and 70:30 split ratio approaches, and performance is assessed using the metrics and plotted the region of convergence curves. The model is also tested on two more datasets (ORIGA and Refuge) to validate the robustness of the proposed model. The obtained simulation results and the evaluated performance metrics prove that our proposed model diagnose glaucoma from retinal fundus images effectively compared with other existing models.

Temporal trends in peripartum hysterectomy among individuals with a previous cesarean delivery by race/ethnicity in the United States: A population-based cohort study.

Rates of severe maternal morbidity have highlighted persistent and growing racial disparities in the United States (US). We aimed to contrast temporal trends in peripartum hysterectomy by race/ethnicity and quantify the contribution of changes in maternal and obstetric factors to temporal variations in hysterectomy rates. We conducted a population-based, retrospective study of 5,739,569 US residents with a previous cesarean delivery, using National Vital Statistics System's Natality Files (2011-2021). Individuals were stratified by self-identified race/ethnicity and classified into four periods based on year of delivery. Temporal changes in hysterectomy rates were estimated using odds ratios (ORs) and 95% confidence intervals (CIs). We used sequential logistic regression models to quantify the contribution of maternal and obstetric factors to temporal variations in hysterectomy rates. Over the study period, the peripartum hysterectomy rate increased from 1.23 (2011-2013) to 1.44 (2019-2021) per 1,000 deliveries (OR 2019-2021 vs. 2011-2013 = 1.17, 95% CI 1.10 to 1.25). Hysterectomy rates varied by race/ethnicity with the highest rates among Native Hawaiian and Other Pacific Islander (NHOPI; 2.73 per 1,000 deliveries) and American Indian or Alaskan Native (AIAN; 2.67 per 1,000 deliveries) populations in 2019-2021. Unadjusted models showed a temporal increase in hysterectomy rates among AIAN (2011-2013 rate = 1.43 per 1,000 deliveries; OR 2019-2021 vs. 2011-2013 = 1.87, 95% CI 1.02 to 3.45) and White (2011-2013 rate = 1.13 per 1,000 deliveries; OR 2019-2021 vs. 2011-2013 = 1.21, 95% CI 1.11 to 1.33) populations. Adjustment ranged from having no effect among NHOPI individuals to explaining 14.0% of the observed 21.0% increase in hysterectomy rates among White individuals. Nationally, racial disparities in peripartum hysterectomy are evident. Between 2011-2021, the rate of hysterectomy increased; however, this increase was confined to AIAN and White individuals.

A novel hardware-efficient ergodic sequential logic neuron model and virtual prosthetic trial for the cricket auditory neural network

A novel hardware-efficient ergodic sequential logic neuron model and virtual prosthetic trial for the cricket auditory neural network

Attribute Reduction Method Based on Sequential Three-Branch Decision Model

Attribute Reduction Method Based on Sequential Three-Branch Decision Model

An Intention-Aware Markov Chain Based Method for Top-K Recommendation

Recommender systems play significant roles in business, especially in e-commerce. Nevertheless, users’ behaviors are usually mixing and drifting, which is hard to tackle. Current sequential methods of item-wise interest extracting suffer from the intricacy and sparsity of data. Inspired by that category-wise interests may be intrinsic drivers of user behaviors and heterogeneous actions may reveal certain behavior patterns, we introduce intention as a tuple of category and action to address the data issues. In this paper, an intention-aware Markov chain based sequential recommendation model (IMRec) is proposed. We model the overall preferences of users as the integration of long-term preferences and short-term intents. In particular, the matrix factorization method is adopted to extract the long-term user-item preference. For the modeling of the short-term intents transition, we adopt high-order Markov chain based methods. A factorized mixture transition distribution model for high-order Markov chain approximation is leveraged in this paper to reduce the algorithm complexity. An auxiliary loss on intention representation is utilized, which brings considerable performance improvements. Experiments on real-world datasets demonstrate that our model outperforms state-of-the-art baseline models in terms of three common metrics, and shows superior stability, scalability, and training efficiency. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In e-commerce, sequential recommenders are essential to facilitate decision-making and promote business. A big challenge is to capture the sequential patterns from the mixing and drifting user-item interaction sequences. Customer behaviors are often driven by their inherent intentions, which may present more stable and reliable patterns. Motivated by that, we propose a novel intention-aware next-item recommendation algorithm with high performance. Our method models the user-item preferences as the integration of long-term preferences and short-term intents. More specifically, long-term preferences show the general tastes of users, which are modeled by latent factors of users and items. Additionally, the intention is defined as a tuple of category and action. We model the short-term intents as the intention transition from the past intentions by a high-order Markov chain. We further leverage a factorization-based mixture transition distribution model for high-order Markov chain approximation and reduce the algorithm complexity. The proposed model is validated in 4 real-world datasets and shows good recommendation performance, performance stability, model scalability, and training efficiency. Our model provides an effective recommendation method at low computational costs for e-commerce companies.

Symmetric Regularized Sequential Latent Variable Models With Adversarial Neural Networks

Symmetric Regularized Sequential Latent Variable Models With Adversarial Neural Networks