Categories Of Features Research Articles

Robustness of radiomic features in healthy abdominal parenchyma of patients with repeated examinations on dual-layer dual-energy CT

ObjectivesRobustness of radiomic features in physiological tissue is an important prerequisite for quantitative analysis of tumor biology and response assessment. In contrast to previous studies which focused on different tumors with mostly short scan-re-scan intervals, this study aimed to evaluate the robustness of radiomic features in cancer-free patients and over a clinically encountered inter-scan interval. Materials and methodsPatients without visible tumor burden who underwent at least two portal-venous phase dual energy CT examinations of the abdomen between May 2016 and January 2020 were included, while macroscopic tumor burden was excluded based upon follow-up imaging for all patients (≥3 months). Further, patients were excluded if no follow-up imaging was available, or if the CT protocol showed deviations between repeated examinations. Circular regions of interest were placed and proofread by two board-certified radiologists (4 years and 5 years experience) within the liver (segments 3 and 6), the psoas muscle (left and right), the pancreatic head, and the spleen to obtain radiomic features from normal-appearing organ parenchyma using PyRadiomics. Radiomic feature robustness was tested using the concordance correlation coefficient with a threshold of 0.75 considered indicative for deeming a feature robust. ResultsIn total, 160 patients with 480 repeated abdominal CT examinations (range: 2–4 per patient) were retrospectively included in this single-center, IRB-approved study. Considering all organs and feature categories, only 4.58 % (25/546) of all features were robust with the highest rate being found in the first order feature category (20.37 %, 22/108). Other feature categories (grey level co-occurrence matrix, grey level dependence matrix, grey level run length matrix, grey level size zone matrix, and neighborhood gray-tone difference matrix) yielded an overall low percentage of robust features (range: 0.00 %-1.19 %). A subgroup analysis revealed the reconstructed field of view and the X-ray tube current as determinants of feature robustness (significant differences in subgroups for all organs, p < 0.001) as well as the size of the region of interest (no significant difference for the pancreatic head with p = 0.135, significant difference with p < 0.001 for all other organs). ConclusionRadiomic feature robustness obtained from cancer-free subjects with repeated examinations using a consistent protocol and CT scanner was limited, with first order features yielding the highest proportion of robust features.

TabTranSELU: A transformer adaptation for solving tabular data

Tabular data are most prevalent datasets in real world, yet the integration of deep learning algorithms in tabular data often garners less attention despite their widespread utilization in other field. This phenomenon could be attributed to the dominance of the classical algorithms in their simplicity and interpretability, and the superior performance of the gradient boosting tree models in tabular data. In this paper, a simple yet affective adaptation of the Transformer architecture tailored specifically for tabular data is presented, not only achieving good performance but also retains a high degree of explain ability. The model encodes both continuous and categorical features, alongside their respective names, and feed them into an enhanced Transformer structure enriched with Scaled Exponential Linear Unit activation. Through rigorous experimentation, our model not only outperforms classical algorithms and similar Transformer-based counterparts, but also are comparable to the performance of gradient boosting tree models.

Triple Feature Disentanglement for One-Stage Adaptive Object Detection

In recent advancements concerning Domain Adaptive Object Detection (DAOD), unsupervised domain adaptation techniques have proven instrumental. These methods enable enhanced detection capabilities within unlabeled target domains by mitigating distribution differences between source and target domains. A subset of DAOD methods employs disentangled learning to segregate Domain-Specific Representations (DSR) and Domain-Invariant Representations (DIR), with ultimate predictions relying on the latter. Current practices in disentanglement, however, often lead to DIR containing residual domain-specific information. To address this, we introduce the Multi-level Disentanglement Module (MDM) that progressively disentangles DIR, enhancing comprehensive disentanglement. Additionally, our proposed Cyclic Disentanglement Module (CDM) facilitates DSR separation. To refine the process further, we employ the Categorical Features Disentanglement Module (CFDM) to isolate DIR and DSR, coupled with category alignment across scales for improved source-target domain alignment. Given its practical suitability, our model is constructed upon the foundational framework of the Single Shot MultiBox Detector (SSD), which is a one-stage object detection approach. Experimental validation highlights the effectiveness of our method, demonstrating its state-of-the-art performance across three benchmark datasets.

TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation

Next Point-of-Interest (POI) recommendation has been proven effective at utilizing sparse, intricate spatial-temporal trajectory data to recommend subsequent POIs to users. While existing methods commonly alleviate the problem of data sparsity by integrating spatial-temporal context information, POI category features, and social relationships, they largely overlook the fact that the trajectory sequences collected in the datasets are often incomplete. This oversight limits the model’s potential to fully leverage historical context. In light of this background, we propose Trajectory Data Augmentation with Uncertainty (TAU) for Next POI Recommendation. TAU is a general graph-based trajectory data augmentation method designed to complete user mobility patterns by marrying uncertainty estimation into the next POI recommendation task. More precisely, TAU taps into the global transition pattern graph to identify sets of intermediate nodes located between every pair of locations, effectively leveraging edge weights as transition probabilities. During trajectory sequence construction, TAU selectively prompts intermediate nodes, chosen based on their likelihood of occurrence as pseudo-labels, to establish comprehensive trajectory sequences. Furthermore, to gauge the certainty and impact of pseudo-labels on the target location, we introduce a novel confidence-aware calibration strategy using evidence deep learning (EDL) for improved performance and reliability. The experimental results clearly indicate that our TAU method achieves consistent performance improvements over existing techniques across two real-world datasets, verifying its effectiveness as the state-of-the-art approach to the task.

Wavelet Dynamic Selection Network for Inertial Sensor Signal Enhancement

As attitude and motion sensing components, inertial sensors are widely used in various portable devices, covering consumer electronics, sports health, aerospace, etc. But the severe intrinsic errors of inertial sensors heavily restrain their function implementation, especially the advanced functionality, including motion trajectory recovery and motion semantic recognition, which attracts considerable attention. As a mainstream signal processing method, wavelet is hailed as the mathematical microscope of signal due to the plentiful and diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet dynamic selection network (WDSNet), which intelligently selects the appropriate wavelet basis for variable inertial signals. In addition, existing deep learning architectures excel at extracting features from input data but neglect to learn the characteristics of target categories, which is essential to enhance the category awareness capability, thereby improving the selection of wavelet basis. Therefore, we propose a category representation mechanism (CRM), which enables the network to extract and represent category features without increasing trainable parameters. Furthermore, CRM transforms the common fully connected network into category representations, which provide closer supervision to the feature extractor than the far and trivial one-hot classification labels. We call this process of imposing interpretability on a network and using it to supervise the feature extractor the feature supervision mechanism, and its effectiveness is demonstrated experimentally and theoretically in this paper. The enhanced inertial signal can perform impracticable tasks with regard to the original signal, such as trajectory reconstruction. Both quantitative and visual results show that WDSNet outperforms the existing methods. Remarkably, WDSNet, as a weakly-supervised method, achieves the state-of-the-art performance of all the compared fully-supervised methods.

Features of translation policies on the Chinese mainland (1979–2021)

Abstract This research presents a new classification of translation policy by referring to Baldauf’s (2006) framework of language planning. It constructs a policy database containing 363 policy documents issued on the Chinese mainland from 1979 to 2021, and analyzes the features of each policy category by integrating corpus analysis with text analysis. It is revealed that policy documents on translation education aim to train professional translators with standard national tests and postgraduate programs; policy documents on translation profession are committed to improving the professional title system for translators and interpreters; policy documents on translation standardization are supported by national standards and cover various stakeholders and fields; and policy documents on official translation projects aim to disseminate Chinese culture, provide language services for international events, and organize minority language translation. With these findings, this study contributes to research on translation policy with new knowledge about China and a novel perspective, classification, and approach.

Abstract 2318: Multimodal machine learning for the automatic classification of recurrent cancers

Abstract The National Cancer Institute’s (NCI) Surveillance, Epidemiology, and End Results (SEER) registries maintain and organize cancer incidence information allowing researchers to derive valuable insights into cancer epidemiology. While significant attention has been devoted to identifying cancers either from clinical text or through tabular data collected by SEER registries, there has been less emphasis on integrating these distinct modes of data. In our multimodal deep learning approach, we use longitudinal tabular data from the Consolidated Tumor Case (CTC) database that encompass a patient’s past diagnoses. This tabular information can augment clinical text to aid in the classification of pathology reports indicative of recurrent cancers. Four NCI SEER registries (Louisiana, New Jersey, Seattle and Utah) have manually labeled 61,150 pathology reports with one of six categories, which we refine into a four-class classification problem. Each pathology report is identified as either positive for recurrence, negative for recurrence/not disease free, new tumor, or an “other” (no malignancy/uncertain) class. Natural Language Processing techniques can extract meaningful information from clinical pathology reports, aiding in the identification of subtle indicators of recurrence by using relevant context. We use a hierarchical self-attention model (HiSAN) to construct document embeddings and classify the pathology report. To further enhance the predictive accuracy of our modeling approach we fuse the textual information from a pathology report with categorical data about patient’s cancer history. For each report, we create a patient context vector that encapsulates tumor-level information from patient’s previous cancer(s). The selected CTC records are associated with cancers diagnosed more than 120 days before the date of biospecimen collection stated in the pathology report. The patient context vector is crafted based on diverse categorical features; including cancer staging, patient age, treatment and sites of metastasis at the time of diagnosis. Features are represented using a combination of one-hot encoding and binning. Additionally, we employ patient and feature-level normalization to maintain proportional significance of features for individuals with multiple past diagnoses. We present preliminary results corresponding to different approaches for classifying cancer recurrence; first, we observe that using only the pathology reports as input yields an accuracy of 68%. Secondly, when using only CTC features with an XGBoost model, we achieve an accuracy of 49%. Finally we show that leveraging multiple data modalities, i.e. HiSAN generated pathology report embeddings and CTC data, significantly improves the model’s predictive accuracy to 76%. This research demonstrates a promising path forward in enhancing classification of clinical text by incorporating longitudinal patient history data. Citation Format: Patrycja Krawczuk, Zachary Fox, Dakota Murdock, Jennifer Doherty, Antoinette Stroupe, Stephen M. Schwartz, Lynne Penberthy, Elizabeth Hsu, Serban Negoita, Valentina Petkov, Heidi Hanson. Multimodal machine learning for the automatic classification of recurrent cancers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2318.

Applying green learning to regional wind power prediction and fluctuation risk assessment

Deep Learning (DL) models, such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), have been widely used to predict the intermittency of wind power; however, the non-linear activation functions and backpropagation mechanisms in DL models increase computational complexity and energy consumption. This paper proposes a prediction model based on Green Learning (GL) to reduce energy consumption. The proposed GL model replaces the feature extraction of activation functions with a hybrid feature extraction approach combining categorical and numerical features. We also employ cluster centroids and quantile regression forest for classification/regression to eliminate the need for backpropagation in optimizing hyperparameters. Using Taiwan as a case study, this paper evaluates the risk of fluctuations in regional wind power generation in 2030. In simulations, the proposed GL model achieved excellent accuracy with energy consumption significantly lower than that of DL models. Our analysis also revealed that by 2030, fluctuations in wind power generation during the winter will exceed 40% of the peak supply capacity in the central region, indicating the need to enhance the resilience of regional power systems.

Prediction of bitcoin stock price using feature subset optimization

In light of recent cryptocurrency value fluctuations, Bitcoin is gradually gaining recognition as an investment vehicle. Given the market's inherent volatility, accurate forecasting becomes crucial for making informed investment decisions. Notably, previous research has utilized machine learning methods to enhance the accuracy of Bitcoin price predictions. However, few studies have explored the potential of employing diverse modeling methods for sampling with varying data formats and dimensional characteristics. This study aims to identify the internal feature subset that yields the highest returns in forecasting Bitcoin's price. Specifically, Bitcoin's internal features were categorized into four groups: currency data, block details, mining information, and network difficulty. Subsequently, a long short-term memory (LSTM) artificial neural network was employed to predict the next day's Bitcoin closing price, utilizing various categorizations of feature subsets. The model underwent training using two and a half years of historical data for each feature. The findings revealed a mean absolute error rate of 6.38% when modeling with the block details category features. This enhanced performance primarily stemmed from the positive relationship between Bitcoin price and this data subset's low ambiguity. Experimental results underscored that, compared to other investigated feature subsets, the categorization of block detail features provided the most accurate Bitcoin price predictions, laying the foundation for future research in this domain.

On relevant features for the recurrence prediction of urothelial carcinoma of the bladder

BackgroundUrothelial bladder cancer (UBC) is characterized by a high recurrence rate, which is predicted by scoring systems. However, recent studies show the superiority of Machine Learning (ML) models. Nevertheless, these ML approaches are rarely used in medical practice because most of them are black-box models, that cannot adequately explain how a prediction is made. ObjectiveWe investigate the global feature importance of different ML models. By providing information on the most relevant features, we can facilitate the use of ML in everyday medical practice. Design, setting, and participantsThe data is provided by the cancer registry Rhineland-Palatinate gGmbH, Germany. It consists of numerical and categorical features of 1,944 patients with UBC. We retrospectively predict 2-year recurrence through ML models using Support Vector Machine, Gradient Boosting, and Artificial Neural Network. We then determine the global feature importance using performance-based Permutation Feature Importance (PFI) and variance-based Feature Importance Ranking Measure (FIRM). ResultsWe show reliable recurrence prediction of UBC with 82.02% to 83.89% F1-Score, 83.95% to 84.49% Precision, and an overall performance of 69.20% to 70.82% AUC on testing data, depending on the model. Gradient Boosting performs best among all black-box models with an average F1-Score (83.89%), AUC (70.82%), and Precision (83.95%). Furthermore, we show consistency across PFI and FIRM by identifying the same features as relevant across the different models. These features are exclusively therapeutic measures and are consistent with findings from both medical research and clinical trials. ConclusionsWe confirm the superiority of ML black-box models in predicting UBC recurrence compared to more traditional logistic regression. In addition, we present an approach that increases the explanatory power of black-box models by identifying the underlying influence of input features, thus facilitating the use of ML in clinical practice and therefore providing improved recurrence prediction through the application of black-box models.

Spatial-temporal constraints for surface soil moisture mapping using Sentinel-1 and Sentinel-2 data over agricultural regions

Surface soil moisture (SSM) information could have important applications in agricultural and regional water management. Remote sensing, particularly synthetic aperture radar (SAR), is an important technology for the estimation of spatial–temporal SSM over larger areas. Using Sentinel-1 and Sentinel-2 data, this research developed a general spatial–temporal constrained machine-learning-based method for surface soil moisture mapping over agricultural regions. Central to this method is the construction of spatial and temporal constraints and their implementation in machine-learning models. We first defined the spatial and temporal constraints for SSM estimation by investigating the spatial division of cultivated crop types and the temporal division of cumulative precipitation. Second, under the presumption that the SSM and associated variables are smoothly changing, we extracted the temporal difference variables from the multi-temporal remote sensing data. Finally, we incorporated two constraints as categorical features and temporal differences into a CatBoost-based model to improve surface soil moisture mapping. We verified the proposed model in a Spain study area with multi-temporal remote sensing observations. The experimental results after incorporating the spatial–temporal constraints demonstrate the efficacy of the proposed model for mapping surface soil moisture over agricultural regions, with significantly improved R2 = 0.7328, RMSE = 0.0451 vol, and MAE = 0.0351 vol This study also concluded that using multiple polarization in the machine-learning-based method could reliably and accurately estimate surface soil moisture.

End-to-end Point Supervised Object Detection with low-level instance features

The use of point-level annotations in Point Supervision Object Detection (PSOD) has gained popularity due to its low labeling cost and the provision of specific location information. Previous studies have often relied on Multiple Instance Learning (MIL) to select and refine a low-quality pseudo box, which heavily relies on category information. This method concentrates on identifying the most distinctive objects in each category within an image. However, without the boundary constraints provided by Ground-Truth (GT), the detector may suffer from instance ambiguity problems, which can significantly deteriorate the model’s performance. To tackle these concerns, we propose an end-to-end object detection model called low-level instance features object detector (LIFOD) to mime low-level instance features information to refine the pseudo box. LIFOD utilizes a Low-level Feature Extractor (LFE) module to exploit low-level instance feature information to combine low-level feature information and category information, thus solving the challenge of instance ambiguity. To further alleviate the problem of local minima, we introduce bounding box regression in LIFOD and implement an end-to-end training strategy for point-supervised models to mitigate local minima. We evaluate our proposed LIFOD method on the public datasets COCO 2014 and 2017 and show that it outperforms the existing image-level and point-level supervised detection methods, and significantly reduces the gap in performance between PSOD and box-level object detection.

Robust Drug Use Detection on X: Ensemble Method with a Transformer Approach

There is a growing trend for groups associated with drug use to exploit social media platforms to propagate content that poses a risk to the population, especially those susceptible to drug use and addiction. Detecting drug-related social media content has become important for governments, technology companies, and those responsible for enforcing laws against proscribed drugs. Their efforts have led to the development of various techniques for identifying and efficiently removing drug-related content, as well as for blocking network access for those who create it. This study introduces a manually annotated Twitter dataset consisting of 112,057 tweets from 2008 to 2022, compiled for use in detecting associations connected with drug use. Working in groups, expert annotators classified tweets as either related or unrelated to drug use. The dataset was subjected to exploratory data analysis to identify its defining features. Several classification algorithms, including support vector machines, XGBoost, random forest, Naive Bayes, LSTM, and BERT, were used in experiments with this dataset. Among the baseline models, BERT with textual features achieved the highest F1-score, at 0.9044. However, this performance was surpassed when the BERT base model and its textual features were concatenated with a deep neural network model, incorporating numerical and categorical features in the ensemble method, achieving an F1-score of 0.9112. The Twitter dataset used in this study was made publicly available to promote further research and enhance the accuracy of the online classification of English-language drug-related content.

StackDPP: a stacking ensemble based DNA-binding protein prediction model.

DNA-binding proteins (DNA-BPs) are the proteins that bind and interact with DNA. DNA-BPs regulate and affect numerous biological processes, such as, transcription and DNA replication, repair, and organization of the chromosomal DNA. Very few proteins, however, are DNA-binding in nature. Therefore, it is necessary to develop an efficient predictor for identifying DNA-BPs. In this work, we have proposed new benchmark datasets for the DNA-binding protein prediction problem. We discovered several quality concerns with the widely used benchmark datasets, PDB1075 (for training) and PDB186 (for independent testing), which necessitated the preparation of new benchmark datasets. Our proposed datasets UNIPROT1424 and UNIPROT356 can be used for model training and independent testing respectively. We have retrained selected state-of-the-art DNA-BP predictors in the new dataset and reported their performance results. We also trained a novel predictor using the new benchmark dataset. We extracted features from various feature categories, then used a Random Forest classifier and Recursive Feature Elimination with Cross-validation (RFECV) to select the optimal set of 452 features. We then proposed a stacking ensemble architecture as our final prediction model. Named Stacking Ensemble Model for DNA-binding Protein Prediction, or StackDPP in short, our model achieved 0.92, 0.92 and 0.93 accuracy in 10-fold cross-validation, jackknife and independent testing respectively. StackDPP has performed very well in cross-validation testing and has outperformed all the state-of-the-art prediction models in independent testing. Its performance scores in cross-validation testing generalized very well in the independent test set. The source code of the model is publicly available at https://github.com/HasibAhmed1624/StackDPP . Therefore, we expect this generalized model can be adopted by researchers and practitioners to identify novel DNA-binding proteins.

Personalized Federated Learning with Adaptive Feature Extraction and Category Prediction in Non-IID Datasets

Federated learning trains a neural network model using the client’s data to maintain the benefits of centralized model training while maintaining their privacy. However, if the client data are not independently and identically distributed (non-IID) because of different environments, the accuracy of the model may suffer from client drift during training owing to discrepancies in each client’s data. This study proposes a personalized federated learning algorithm based on the concept of multitask learning to divide each client model into two layers: a feature extraction layer and a category prediction layer. The feature extraction layer maps the input data to a low-dimensional feature vector space. Furthermore, the parameters of the neural network are aggregated with those of other clients using an adaptive method. The category prediction layer maps low-dimensional feature vectors to the label sample space, with its parameters remaining unaffected by other clients to maintain client uniqueness. The proposed personalized federated learning method produces faster learning model convergence rates and higher accuracy rates for the non-IID datasets in our experiments.

Semantic segmentation of remote sensing images based on multiscale features and global information modeling

The main difficulties in semantic segmentation of remote sensing images include the effect of shadows, the blurring of feature differences between categories, and loss of small-scale category features during processing. To deal with these challenges, we propose a semantic segmentation network for RSI based on multi-scale features and global information modeling. A skillfully designed two-branch fusion attention based on an adaptive fusion converter is added to the multilevel cascaded HRNet structure to better combine multiscale features and global modeling information. Prior to this, “Coordinate attention” was combined with “Spatial attention” designed in this paper to form a Feed-forward Attention Layer (FAL) to encode finer feature information cues. Meanwhile, a more refined multilayer decoder is designed to obtain better image category recovery. Various experiments were conducted on four different scenarios and types of datasets including WHDLD, Potsdam, Vaihingen, and LoveDa, and in terms of the significant evaluation metric MIOU, with dividing the training, validation, and test sets in the ratio of 6:2:2, the performance of our model on the above four datasets was obtained with 61.79%, 70.79%, 81.15%, and 52.55%.In addition, a comparison with other excellent works is made and the results show that our designed model has better performance.

Acceleration model of online educational games based on improved ensemble ML algorithm

Online educational games are easy to be affected by hardware and network status and have delay problems, which will affect students' learning interest and enthusiasm. Therefore, in this study, Bayesian optimization method is used to optimize the parameters of the “gradient boosting + category features” algorithm, and an improved “gradient boosting + categorical features” ensemble algorithm is designed using the integration framework of RF. And based on this, an online education game acceleration model is designed. The experimental results showed that the improved “gradient boosting + categorical features” algorithm, which combines Bayesian optimization and RF integration framework, was superior to the partially improved and traditional “gradient boosting + categorical features” algorithm in online education game recognition. The former's Accuracy mean and Precision mean in various online education games were 98.9 % and 99.3 %, respectively. Compared with other common ensemble algorithms and deep learning algorithms, the research outcomes expressed that the Accuracy of the algorithm designed in this study in the training phase and the F1 value in the testing phase were 98.6 % and 99.0 %. respectively, which were significantly higher than other intelligent algorithms. The test results of the game acceleration model constructed based on this algorithm and other comparative algorithms indicated that the online education game acceleration model constructed based on the improved “gradient boosting + categorical features” algorithm could minimize the delay phenomenon generated during game operation to the greatest extent. The model designed in this study has the potential to solve the problems of running lag and delay in online education games, which is beneficial for improving students' user experience and learning absorption effect in such game applications.

Genetic alterations in myeloproliferative and myelodysplastic/myeloproliferative neoplasms- a practical guide to WHO-HAEM5.

Within the World Health Organization (WHO) classification of haematopoietic neoplasms, particularly its fifth version from 2022 (WHO-HAEM5), myeloid neoplasms are not only grouped into myeloproliferative (MPN) and myelodysplastic neoplasms (MDS). There is also a group of haematological disorders that share features of both categories termed myelodysplastic /myeloproliferative neoplasms (MDS/MPN). In this article, we aim to provide a comprehensive and practical guide to WHO-HAEM5 highlighting the genetic alterations that underlie MPN and MDS/MPN. This guide provides an overview of the overlapping commonalities among these entities, as well as their unique characteristics.

A Neural Network model for Indian Supreme Court legal judgment prediction

Industry experts are motivated to collect, collate, and analyse historical data in the legal sector in attempt to predict court case outcomes as the amount of historical data available in this field has increased over time. But using judicial data to predict and defend court judgements is no simple undertaking. Using Machine Learning (ML) models and traditional approaches for categorical feature encoding, previous research on predicting court outcomes using limited experimental datasets produced a number of unexpected predictions. The paper proposes an ensemble model combining Convolutional Neural Network (CNN), attention mechanism and eXtreme Gradient Boosting (XGB) algorithm. This model is primarily based on a self-attention network, which could simultaneously capture linguistic relationships over lengthy sequences like RNN (Recurrent Neural Network) and is nevertheless speedy to train like CNN. C-XGB can obtain accuracy that surpasses the state-of-art model on numerous classification/prediction tasks simultaneously as being twice as speedy to train. The proposed C-XGB model is designed to process the documents hierarchically and calculates the attention weights. Two convolutional layers are used to calculate the attention weights, one at the word level and another at the sentence level. And finally, at the last layer, the XGB algorithm predicts the input case file’s outcome. The experimental results shows that the proposed model outperforms the existing model with 4.67% improvement in accuracy value.

Acoustic feature analysis of directional sound from parametric array speakers with application to mitigate attacks on voice-activated systems

A number of studies have identified the vulnerabilities of voice-activated devices to attacks from amplitude-demodulated sound from directional speakers. In this research, a controlled set of speech data, both live and played back from directional speakers, is analyzed to identify the acoustic features integral to speaker recognition in smart devices. A category of features, including Mel-frequency cepstral coefficients derived from Mel filter banks, are examined for potential to differentiate and classify speech sources. Potential vulnerabilities in voice-activated systems are systematically identified by examining the acoustic characteristics of diverse voice samples. This analytical approach aims to unveil potential weaknesses that could be exploited, triggering responses from these systems. The findings of this study contribute to the comprehension of the security landscape surrounding voice-activated technologies, paving the way for enhanced cybersecurity measures within this domain.