Audio-Text Multimodal Speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.

Color Image Compression and Encryption Algorithm Based on 2D Compressed Sensing and Hyperchaotic System

With the advent of the information security era,it is necessary to guarantee the privacy,accuracy,and dependable transfer of pictures.This study presents a new approach to the encryption and compression of color images.It is predicated on 2D compressed sensing(CS)and the hyperchaotic system.First,an optimized Arnold scrambling algorithm is applied to the initial color images to ensure strong security.Then,the processed images are con-currently encrypted and compressed using 2D CS.Among them,chaotic sequences replace traditional random measurement matrices to increase the system’s security.Third,the processed images are re-encrypted using a combination of permutation and diffusion algorithms.In addition,the 2D projected gradient with an embedding decryption(2DPG-ED)algorithm is used to reconstruct images.Compared with the traditional reconstruction algorithm,the 2DPG-ED algorithm can improve security and reduce computational complexity.Furthermore,it has better robustness.The experimental outcome and the performance analysis indicate that this algorithm can withstand malicious attacks and prove the method is effective.

Multifractal analysis of white matter structural changes on 3D magnetic resonance imaging between normal aging and early Alzheimer's disease

Applications of multifractal analysis to white matter structure changes on magnetic resonance imaging（MRI） have recently received increasing attentions. Although some progresses have been made, there is no evident study on applying multifractal analysis to evaluate the white matter structural changes on MRI for Alzheimer＇s disease（AD） research. In this paper, to explore multifractal analysis of white matter structural changes on 3D MRI volumes between normal aging and early AD, we not only extend the traditional box-counting multifractal analysis（BCMA） into the 3D case, but also propose a modified integer ratio based BCMA（IRBCMA） algorithm to compensate for the rigid division rule in BCMA. We verify multifractal characteristics in 3D white matter MRI volumes. In addition to the previously well studied multifractal feature,△α, we also demonstrated △ f as an alternative and effective multifractal feature to distinguish NC from AD subjects.Both △α and △ f are found to have strong positive correlation with the clinical MMSE scores with statistical significance.Moreover, the proposed IRBCMA can be an alternative and more accurate algorithm for 3D volume analysis. Our findings highlight the potential usefulness of multifractal analysis, which may contribute to clarify some aspects of the etiology of AD through detection of structural changes in white matter.

Automated Performance Tuning of Data Management Systems with Materializations and Indices

Automated performance tuning of data management systems offer various benefits such as improved performance, declined administration costs, and reduced workloads to database administrators (DBAs). Currently, DBAs tune the performance of database systems with a little help from the database servers. In this paper, we propose a new technique for automated performance tuning of data management systems. Firstly, we show how to use the periods of low workload time for performance improvements in the periods of high workload time. We demonstrate that extensions of a database system with materialised views and indices when a workload is low may contribute to better performance for a successive period of high workload. The paper proposes several online algorithms for continuous processing of estimated database workloads and for the discovery of the best plan for materialised view and index database extensions and of elimination of the extensions that are no longer needed. We present the results of experiments that show how the proposed automated performance tuning technique improves the overall performance of a data management system.

On the Mechanical Analysis and Control for the Tension System of the Cylindrical Filament Winding

The constant winding tension can make the filament arranged in order. The stress distribution between the filament balance fully gives play to the enhancement of filament, and increases the intensive workload of the composite winding material. This paper conducts the mechanical analysis for the unwinding roller and tension measuring roller of the cylindrical winding machine so that gets the mechanical model, gives error compensation formula caused by the radius change of the yarn group in the unwinding side, designs the closed-loop control system and utilizes the dynamical- integral PID control strategy to achieve the tension control during the process of the cylindrical winding.

An Efficient Detection Approach of Content Aware Image Resizing

Content aware image resizing(CAIR)is an excellent technology used widely for image retarget.It can also be used to tamper with images and bring the trust crisis of image content to the public.Once an image is processed by CAIR,the correlation of local neighborhood pixels will be destructive.Although local binary patterns(LBP)can effectively describe the local texture,it however cannot describe the magnitude information of local neighborhood pixels and is also vulnerable to noise.Therefore,to deal with the detection of CAIR,a novel forensic method based on improved local ternary patterns(ILTP)feature and gradient energy feature(GEF)is proposed in this paper.Firstly,the adaptive threshold of the original local ternary patterns(LTP)operator is improved,and the ILTP operator is used to describe the change of correlation among local neighborhood pixels caused by CAIR.Secondly,the histogram features of ILTP and the gradient energy features are extracted from the candidate image for CAIR forgery detection.Then,the ILTP features and the gradient energy features are concatenated into the combined features,and the combined features are used to train classifier.Finally support vector machine(SVM)is exploited as a classifier to be trained and tested by the above features in order to distinguish whether an image is subjected to CAIR or not.The candidate images are extracted from uncompressed color image database(UCID),then the training and testing sets are created.The experimental results with many test images show that the proposed method can detect CAIR tampering effectively,and that its performance is improved compared with other methods.It can achieve a better performance than the state-of-the-art approaches.

Impacts of prior parameter distributions on Bayesian evaluation of groundwater model complexity

This study used the marginal likelihood and Bayesian posterior model probability for evaluation of model complexity in order to avoid using over-complex models for numerical simulations. It focused on investigation of the impacts of prior parameter distributions(involved in calculating the marginal likelihood) on the evaluation of model complexity. We argue that prior parameter distributions should define the parameter space in which numerical simulations are made. New perspectives on the prior parameter distribution and posterior model probability were demonstrated in an example of groundwater solute transport modeling with four models, each simulating four column experiments. The models had different levels of complexity in terms of their model structures and numbers of calibrated parameters. The posterior model probability was evaluated for four cases with different prior parameter distributions. While the distributions substantially impacted model ranking, the model ranking in each case was reasonable for the specific circumstances in which numerical simulations were made. For evaluation of model complexity, it is thus necessary to determine the parameter spaces for modeling, which can be done by conducting numerical simulation and usineg engineering judgment based on understanding of the system being studied.

Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

As the use of facial attributes continues to expand,research into facial age estimation is also developing.Because face images are easily affected by factors including illumination and occlusion,the age estimation of faces is a challenging process.This paper proposes a face age estimation algorithm based on lightweight convolutional neural network in view of the complexity of the environment and the limitations of device computing ability.Improving face age estimation based on Soft Stagewise Regression Network(SSR-Net)and facial images,this paper employs the Center Symmetric Local Binary Pattern(CSLBP)method to obtain the feature image and then combines the face image and the feature image as network input data.Adding feature images to the convolutional neural network can improve the accuracy as well as increase the network model robustness.The experimental results on IMDB-WIKI and MORPH 2 datasets show that the lightweight convolutional neural network method proposed in this paper reduces model complexity and increases the accuracy of face age estimations.

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress.However,due to the domain shift problem,applying an off-the-shelf detector to another domain leads to a significant performance drop.A large number of ground truth labels are required when using another domain to train models,demanding a large amount of human and financial resources.In order to avoid excessive resource requirements and performance drop caused by domain shift,this paper proposes a new domain adaptive approach to cross-domain vehicle detection.Our approach improves the cross-domain vehicle detection model from image space and feature space.We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space.For feature space,we align feature distributions between the source domain and the target domain to improve the detection accuracy.Experiments are carried out using the method with two different datasets,proving that this technique effectively improves the accuracy of vehicle detection in the target domain.

Tissue specific prediction of N^(6)-methyladenine sites based on an ensemble of multi-input hybrid neural network

N^(6)-Methyladenine is a dynamic and reversible post translational modification,which plays an essential role in various biological processes.Because of the current inability to identify m6A-containing mRNAs,computational approaches have been developed to identify m6A sites in DNA sequences.Aiming to improve prediction performance,we introduced a novel ensemble computational approach based on three hybrid deep neural networks,including a convolutional neural network,a capsule network,and a bidirectional gated recurrent unit(BiGRU)with the self-attention mechanism,to identify m6A sites in four tissues of three species.Across a total of 11 datasets,we selected different feature subsets,after optimized from 4933 dimensional features,as input for the deep hybrid neural networks.In addition,to solve the deviation caused by the relatively small number of experimentally verified samples,we constructed an ensemble model through integrating five sub-classifiers based on different training datasets.When compared through 5-fold cross-validation and independent tests,our model showed its superiority to previous methods,im6A-TS-CNN and iRNA-m6A.

基于Transformer编码器的多级表示与融合特征输入的语音情感识别方法

为了提高语音情感识别的准确度,探讨了将Transformer应用于语音情感识别的可能性.将对数梅尔尺度谱图及其一阶差分特征相融合作为输入,使用Transformer来提取分层语音表示,分析注意头个数和Transformer编码器层数的变化对识别精度的影响.结果表明,在ABC、CASIA、DES、EMODB和IEMOCAP语音情感数据库上,相比以MFCC为特征的Transformer,所提模型的精度分别提高了13.98%、8.14%、24.34%、8.16%和20.9%.该模型表现优于递归神经网络(RNN)、卷积神经网络(CNN)、Transformer等其他模型.

无双线性对的基于身份的认证密钥协商协议

鉴于目前大多数基于身份的认证密钥协商(ID-AK)协议需要复杂的双线性对运算,该文利用椭圆曲线加法群构造了一个无双线性对的ID-AK协议。协议去除了双线性对运算,效率比已有协议提高了至少33.3%;同时满足主密钥前向保密性、完善前向保密性和抗密钥泄露伪装。在随机预言机模型下,协议的安全性可规约到标准的计算性Diffie-Hellman假设。

安全高效基于身份签名方案的密码学分析

基于身份的数字签名方案最显著的特点是,只需要签名人的身份信息而无需签名人的证书来验证签名的有效性,这极大地简化了密钥管理.2006年,Paterson和Schuldt构造了标准模型下可证明安全的基于身份的数字签名方案,但计算效率不高.谷科等人提出了新型的改进方案来提高效率,并声称新方案在标准模型下可证明安全且比同类方案更高效.然而,新方案并不具备不可伪造性.给出了两种具体的攻击:敌手可以伪造用户的密钥或者敌手可以直接伪造任何消息的签名.进一步指出安全性证明中的缺陷,即,敌手的view与安全模拟成功的事件不独立.

基于时空特征点的非监督姿态建模和行为识别的算法研究

姿态建模是行为描述和识别的关键环节,提出了基于时空特征点的姿态建模方法.提取样本库中姿态的时空特征点作为底层特征,一个姿态对应一个时空特征点集合;采用非监督分类方法对姿态样本归类,获得典型姿态的聚类结果,每个典型姿态类别采用基于EM的高斯混合模型进行建模.计算各典型姿态间的转移概率,建立状态已知的描述人类多种行为的VMM模型,实现对行为的描述.针对行为识别问题,提出将汉字分词的二元语法模型应用于行为识别.实验证明该算法具有计算复杂度低、鲁棒性强等优点.

Terminal sliding mode control based on super-twisting algorithm

An improved non-singular terminal sliding mode control based on the super-twisting algorithm is proposed for a class of second-order uncertain nonlinear systems. This method can effectively avoid the singularity problem and obviously reduce the chattering phenomenon. The stability of the proposed procedure is proven to be finite-time convergence using the Lyapunov theory against uncertain unmodeled dynamic and external disturbances. An example is given to show the proposed improved non-singular terminal sliding mode control (SMC) law effectively. © 1990-2011 Beijing Institute of Aerospace Information.

Analysis of core protein clusters identifies candidate variable sites conferring metronidazole resistance in Helicobacter pylori

Background:Metronidazole is one of the first-line drugs of choice in the standard triple therapy used to eradicate Helicobacter pylori infection.Hence,the global emergence of metronidazole resistance in Hp poses a major challenge to health professionals.Inactivation of RdxA is known to be a major mechanism of conferring metronidazole resistance in H.pylori.However,metronidazole resistance can also arise in H.pylori strains expressing functional RdxA protein,suggesting that there are other mechanisms that may confer resistance to this drug.Methods:We performed whole-genome sequencing on 121 H.pylori clinical strains,among which 73 were metronidazoleresistant.Sequence-alignment analysis of core protein clusters derived from clinical strains containing full-length RdxA was performed.Variable sites in each alignment were statistically compared between the resistant and susceptible groups to determine candidate genes along with their respective amino-acid changes that may account for the development of metronidazole resistance in H.pylori.Results:Resistance due to RdxA truncation was identified in 34%of metronidazole-resistant strains.Analysis of core protein clusters derived from the remaining 48 metronidazole-resistant strains and 48 metronidazole-susceptible identified four variable sites significantly associated with metronidazole resistance.These sites included R16H/C in RdxA,D85N in the inner-membrane protein RclC(HP0565),V265I in a biotin carboxylase protein(HP0370)and A51V/T in a putative threonylcarbamoyl–AMP synthase(HP0918).Conclusions:Our approach identified new potential mechanisms for metronidazole resistance in H.pylori that merit further investigation.

CYBERSPACE SECURITY

With rapid development and wide application of information technology,mankind is entering into an information age.The world where people live and work has been changed to a brand new triple-dimensional space that consists of the physical world,the human society and the cyberspace.It is well known that the cyberspace is an essential environment of human existence and development and it

Delay optimization scheduling algorithm in cognitive radio networks

In cognitive radio networks,delay scheduling optimization has attracted an increasing attention in recent years. Numerous researches have been performed on it with different scenarios. However,these approaches have either high computational complexity or relatively poor performance. Delay scheduling is a constraint optimization problem with non-deterministic polynomial（ NP） hard feathers. In this paper,we proposed an immune algorithm-based suboptimal method to solve the problem. Suitable immune operators have been designed such as encoding,clone,mutation and selection. The simulation results show that the proposed algorithm yields near-optimal performance and operates with much lower computational complexity.

Survey and Tutorial on Hybrid Human-Artificial Intelligence

The growing computing power,easy acquisition of large-scale data,and constantly improved algorithms have led to a new wave of artificial intelligence(AI)applications,which change the ways we live,manufacture,and do business.Along with this development,a rising concern is the relationship between AI and human intelligence,namely,whether AI systems may one day overtake,manipulate,or replace humans.In this paper,we introduce a novel concept named hybrid human-artificial intelligence(H-AI),which fuses human abilities and AI capabilities into a unified entity.It presents a challenging yet promising research direction that prompts secure and trusted AI innovations while keeping humans in the loop for effective control.We scientifically define the concept of H-AI and propose an evolution road map for the development of AI toward H-AI.We then examine the key underpinning techniques of H-AI,such as user profile modeling,cognitive computing,and human-in-the-loop machine learning.Afterward,we discuss H-AI’s potential applications in the area of smart homes,intelligent medicine,smart transportation,and smart manufacturing.Finally,we conduct a critical analysis of current challenges and open gaps in H-AI,upon which we elaborate on future research issues and directions.

A Provable Secure ID-Based Explicit Authenticated Key Agreement Protocol Without Random Oracles

In this paper, we present an identity-based explicit authenticated key agreement protocol that is provably secure without random oracles. The protocol employs a new method to isolate a session key from key confirmation keys so that there is no direct usage of hash functions in the protocol. The protocol is proved secure without random oracles in a variant of Bellare and Rogaway style model, an exception to current proof method in this style model in the ID-based setting. We believe that this key isolation method is novel and can be further studied for constructing more efficient protocols.