Improving Diversity with Multi-Loss Adversarial Training in Personalized News Recommendation

Users’interests are often diverse and multi-grained,with their underlying intents even more so.Effectively captur-ing users’interests and uncovering the relationships between diverse interests are key to news recommendation.Meanwhile,diversity is an important metric for evaluating news recommendation algorithms,as users tend to reject excessive homogeneous information in their recommendation lists.However,recommendation models themselves lack diversity awareness,making it challenging to achieve a good balance between the accuracy and diversity of news recommendations.In this paper,we propose a news recommendation algorithm that achieves good performance in both accuracy and diversity.Unlike most existing works that solely optimize accuracy or employ more features to meet diversity,the proposed algorithm leverages the diversity-aware capability of the model.First,we introduce an augmented user model to fully capture user intent and the behavioral guidance they might undergo as a result.Specifically,we focus on the relationship between the original clicked news and the augmented clicked news.Moreover,we propose an effective adversarial training method for diversity(AT4D),which is a pluggable component that can enhance both the accuracy and diversity of news recommendation results.Extensive experiments on real-world datasets confirm the efficacy of the proposed algorithm in improving both the accuracy and diversity of news recommendations.

A Unified Model Fusing Region of Interest Detection and Super Resolution for Video Compression

High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution enhancement.Our method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data transmission.To validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical applications.The proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement tasks.This unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom dataset.The implications of this research extend to optimizing low-bitrate video streaming scenarios.By selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth conditions.Empirical results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual quality.This work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited environments.The innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic diseases.Daily and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or not.Typically,smartphones and their associated sensing devices operate in distributed and unstable environments.Therefore,collecting their data and extracting useful information is a significant challenge.In this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical activities.Using the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical activities.This system is based on the calculation of calories burned by each user during physical activities.In this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical workouts.To identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional LSTM.Since human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information simultaneously.While Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal data.The results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and uncertainty.To overcome this constraint and improve performance(96%),we proposed to use the fusion mechanisms.The last combines deep learning classifiers tomodel non-accurate and ambiguous data to obtain synthetic information to aid in decision-making.The Voting and Dempster-Shafer(DS)approaches are employed.The results showed that fused classifiers based on DS theory outperformed individual classifiers(96%)with the highest accuracy level of 98%.Also,the findings disclosed that participants engaging in physical activities are healthy,showcasing a disparity in the distribution of physical activities between men and women.

A privacy-preserving method for publishing data with multiple sensitive attributes

The overgeneralisation may happen because most studies on data publishing for multiple sensitive attributes(SAs)have not considered the personalised privacy requirement.Furthermore,sensitive information disclosure may also be caused by these personalised requirements.To address the matter,this article develops a personalised data publishing method for multiple SAs.According to the requirements of individuals,the new method partitions SAs values into two categories:private values and public values,and breaks the association between them for privacy guarantees.For the private values,this paper takes the process of anonymisation,while the public values are released without this process.An algorithm is designed to achieve the privacy mode,where the selectivity is determined by the sensitive value frequency and undesirable objects.The experimental results show that the proposed method can provide more information utility when compared with previous methods.The theoretic analyses and experiments also indicate that the privacy can be guaranteed even though the public values are known to an adversary.The overgeneralisation and privacy breach caused by the personalised requirement can be avoided by the new method.

A News Media Bias and Factuality Profiling Framework Assisted by Modeling Correlation

News media profiling is helpful in preventing the spread of fake news at the source and maintaining a good media and news ecosystem.Most previous works only extract features and evaluate media from one dimension independently,ignoring the interconnections between different aspects.This paper proposes a novel news media bias and factuality profiling framework assisted by correlated features.This framework models the relationship and interaction between media bias and factuality,utilizing this relationship to assist in the prediction of profiling results.Our approach extracts features independently while aligning and fusing them through recursive convolu-tion and attention mechanisms,thus harnessing multi-scale interactive information across different dimensions and levels.This method improves the effectiveness of news media evaluation.Experimental results indicate that our proposed framework significantly outperforms existing methods,achieving the best performance in Accuracy and F1 score,improving by at least 1%compared to other methods.This paper further analyzes and discusses based on the experimental results.

Enhancing Deep Learning Semantics:The Diffusion Sampling and Label-Driven Co-Attention Approach

The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse domains.Nonetheless,self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency structures.In response,this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network(DSLD),which adopts a diffusion sampling method to capture more comprehensive semantic information of the data.Additionally,themodel leverages the joint correlation information of labels and data to introduce the computation of text representation,correcting semantic representationbiases in thedata,andincreasing the accuracyof semantic representation.Ultimately,the model computes the corresponding classification results by synthesizing these rich data semantic representations.Experiments on seven benchmark datasets show that our proposed model achieves competitive results compared to state-of-the-art methods.

Deep Learning Recognition for Arabic Alphabet Sign Language RGB Dataset

This paper introduces a Convolutional Neural Network (CNN) model for Arabic Sign Language (AASL) recognition, using the AASL dataset. Recognizing the fundamental importance of communication for the hearing-impaired, especially within the Arabic-speaking deaf community, the study emphasizes the critical role of sign language recognition systems. The proposed methodology achieves outstanding accuracy, with the CNN model reaching 99.9% accuracy on the training set and a validation accuracy of 97.4%. This study not only establishes a high-accuracy AASL recognition model but also provides insights into effective dropout strategies. The achieved high accuracy rates position the proposed model as a significant advancement in the field, holding promise for improved communication accessibility for the Arabic-speaking deaf community.

WIDEBAND, INTELLIGENT AND INTEGRATED HF COMMUNICATIONS

The high-frequency(HF)communication,commonly covering the frequency range between 3 and30MHz,is an effective and important long-distance communication approach.Using the ionosphere as a natural high altitude reflector,trans-horizon HF radio transmission is possible with advantages such as high mobility,convenient deployment,strong survivability and

考虑交通参与者的城市交叉口车速预测模型

为了提高车辆在城市交叉口自由行驶状态下的车速预测性能,提出一种考虑本车与其他交通参与者交互特性的车速预测新方法.首先,提出一种车辆目标细分方法来区分其他车辆相对于本车的行驶方向,并应用目标检测算法YOLOv5识别潜在的交通冲突和弱势交通参与者;然后,将识别的交通参与者信息与历史车速信息相结合,建立基于长短期记忆网络的车速预测模型,在左转、右转以及直行3种不同的驾驶场景下验证交通参与者信息对于提高车速预测性能的有效性.结果表明:与仅以历史车速为输入的基准模型相比,考虑交通参与者的车速预测模型表现出更好的性能,其在很大程度上解决了预测模型在一个预测时域内精度逐渐下降的问题,并对城市交叉口的复杂交通环境表现出更强的适应性.

An Ensemble-Based Hotel Reviews System Using Naive Bayes Classifier

The task of classifying opinions conveyed in any form of text online is referred to as sentiment analysis.The emergence of social media usage and its spread has given room for sentiment analysis in our daily lives.Social media applications and websites have become the foremost spring of data recycled for reviews for sentimentality in various fields.Various subject matter can be encountered on social media platforms,such as movie product reviews,consumer opinions,and testimonies,among others,which can be used for sentiment analysis.The rapid uncovering of these web contents contains divergence of many benefits like profit-making,which is one of the most vital of them all.According to a recent study,81%of consumers conduct online research prior to making a purchase.But the reviews available online are too huge and numerous for human brains to process and analyze.Hence,machine learning classifiers are one of the prominent tools used to classify sentiment in order to get valuable information for use in companies like hotels,game companies,and so on.Understanding the sentiments of people towards different commodities helps to improve the services for contextual promotions,referral systems,and market research.Therefore,this study proposes a sentiment-based framework detection to enable the rapid uncovering of opinionated contents of hotel reviews.A Naive Bayes classifier was used to process and analyze the dataset for the detection of the polarity of the words.The dataset from Datafiniti’s Business Database obtained from Kaggle was used for the experiments in this study.The performance evaluation of the model shows a test accuracy of 96.08%,an F1-score of 96.00%,a precision of 96.00%,and a recall of 96.00%.The results were compared with state-of-the-art classifiers and showed a promising performance andmuch better in terms of performancemetrics.

Diffusion tensor imaging in the courtroom:Distinction between scientific specificity and legally admissible evidence

Interest and uptake of science and medicine peer-reviewed literature by readers outside of a paper’s topical subject,field or even discipline is ever-expanding.While the application of knowledge from one field or discipline to others can stimulate innovative solutions to problems facing modern society,it is also fraught with danger for misuse.In the practice of law in the United States,academic papers are submitted to the courts as evidence in personal injury litigation from both the plaintiff(complainant)and defendant.Such transcendence of an academic publication over disciplinary boundaries is immediately met with the challenge of application by a group that inherently lacks in-depth knowledge on the scientific method,the practice of evidence-based medicine,or the publication process as a structured and internationally synthesized process involving peer review and guided by ethical standards and norms.A modern-day example of this is the ongoing conflict between the sensitivity of diffusion tensor imaging(DTI)and the legal standards for admissibility of evidence in litigation cases of mild traumatic brain injury(mTBI).In this review,we amalgamate the peer-reviewed research on DTI in mTBI with the court’s rationale underlying decisions to admit or exclude evidence of DTI abnormalities to support claims of brain injury.We found that the papers which are critical of the use of DTI in the courtroom reflect a primary misunderstanding about how diagnostic biomarkers differ legally from relevant and admissible evidence.The clinical use of DTI to identify white matter abnormalities in the brain at the chronic stage is a valid methodology both clinically as well as forensically,contributes data that may or may not corroborate the existence of white matter damage,and should be admitted into evidence in personal injury trials if supported by a clinician.We also delve into an aspect of science publication and peer review that can be manipulated by scientists and clinicians to publish an opinion piece and misrepresent it as an unbiased,evidencebased,systematic research article in court cases,the decisions of which establish precedence for future cases and have implications on future legislation that will impact the lives of every citizen and erode the integrity of science and medicine practitioners.

Predicting the Popularity of Online News Based on the Dynamic Fusion of Multiple Features

Predicting the popularity of online news is essential for news providers and recommendation systems.Time series,content and meta-feature are important features in news popularity prediction.However,there is a lack of exploration of how to integrate them effectively into a deep learning model and how effective and valuable they are to the model’s performance.This work proposes a novel deep learning model named Multiple Features Dynamic Fusion(MFDF)for news popularity prediction.For modeling time series,long short-term memory networks and attention-based convolution neural networks are used to capture long-term trends and short-term fluctuations of online news popularity.The typical convolution neural network gets headline semantic representation for modeling news headlines.In addition,a hierarchical attention network is exploited to extract news content semantic representation while using the latent Dirichlet allocation model to get the subject distribution of news as a semantic supplement.A factorization machine is employed to model the interaction relationship between metafeatures.Considering the role of these features at different stages,the proposed model exploits a time-based attention fusion layer to fuse multiple features dynamically.During the training phase,thiswork designs a loss function based on Newton’s cooling law to train the model better.Extensive experiments on the real-world dataset from Toutiao confirm the effectiveness of the dynamic fusion of multiple features and demonstrate significant performance improvements over state-of-the-art news prediction techniques.

An Edge Computing Algorithm Based on Multi-Level Star Sensor Cloud

Star sensors are an important means of autonomous navigation and access to space information for satellites.They have been widely deployed in the aerospace field.To satisfy the requirements for high resolution,timeliness,and confidentiality of star images,we propose an edge computing algorithm based on the star sensor cloud.Multiple sensors cooperate with each other to forma sensor cloud,which in turn extends the performance of a single sensor.The research on the data obtained by the star sensor has very important research and application values.First,a star point extraction model is proposed based on the fuzzy set model by analyzing the star image composition,which can reduce the amount of data computation.Then,a mappingmodel between content and space is constructed to achieve low-rank image representation and efficient computation.Finally,the data collected by the wireless sensor is delivered to the edge server,and a differentmethod is used to achieve privacy protection.Only a small amount of core data is stored in edge servers and local servers,and other data is transmitted to the cloud.Experiments show that the proposed algorithm can effectively reduce the cost of communication and storage,and has strong privacy.

Deep Learning Model for News Quality Evaluation Based on Explicit and Implicit Information

Recommending high-quality news to users is vital in improving user stickiness and news platforms’reputation.However,existing news quality evaluation methods,such as clickbait detection and popularity prediction,are challenging to reflect news quality comprehensively and concisely.This paper defines news quality as the ability of news articles to elicit clicks and comments from users,which represents whether the news article can attract widespread attention and discussion.Based on the above definition,this paper first presents a straightforward method to measure news quality based on the comments and clicks of news and defines four news quality indicators.Then,the dataset can be labeled automatically by the method.Next,this paper proposes a deep learning model that integrates explicit and implicit news information for news quality evaluation(EINQ).The explicit information includes the headline,source,and publishing time of the news,which attracts users to click.The implicit information refers to the news article’s content which attracts users to comment.The implicit and explicit information affect users’click and comment behavior differently.For modeling explicit information,the typical convolution neural network(CNN)is used to get news headline semantic representation.For modeling implicit information,a hierarchical attention network(HAN)is exploited to extract news content semantic representation while using the latent Dirichlet allocation(LDA)model to get the subject distribution of news as a semantic supplement.Considering the different roles of explicit and implicit information for quality evaluation,the EINQ exploits an attention layer to fuse them dynamically.The proposed model yields the Accuracy of 82.31%and the F-Score of 80.51%on the real-world dataset from Toutiao,which shows the effectiveness of explicit and implicit information dynamic fusion and demonstrates performance improvements over a variety of baseline models in news quality evaluation.This work provides empirical evidence for explicit and implicit factors in news quality evaluation and a new idea for news quality evaluation.

A multiple sensitive attributes data publishing method with guaranteed information utility

Data publishing methods can provide available information for analysis while preserving privacy.The multiple sensitive attributes data publishing,which preserves the relationship between sensitive attributes,may keep many records from being grouped and bring in a high record suppression ratio.Another category of multiple sensitive attributes data publishing,which reduces the possibility of record suppression by breaking the relationship between sensitive attributes,cannot provide the sensitive attributes association for analysis.Hence,the existing multiple sensitive attributes data publishing fails to fully account for the comprehensive information utility.To acquire a guaranteed information utility,this article defines comprehensive information loss that considers both the suppression of records and the relationship between sensitive attributes.A heuristic method is leveraged to discover the optimal anonymity scheme that has the lowest comprehensive information loss.The experimental results verify the practice of the proposed data publishing method with multiple sensitive attributes.The proposed method can guarantee information utility when compared with previous ones.

A Bandwidth-Link Resources Cooperative Allocation Strategy of Data Communication in Intelligent Transportation Systems

The bandwidth resources allocation strategies of the existing Internet of Vehicles(IoV) are mainly base on the communication architecture of the traditional 802.11 x in the wireless local area network(WLAN). The traditional communication architecture of IoV will easily cause significant delay and low Packet Delivery Ratio(PDR) for disseminating critical security beacons under the condition of high-speed movement, distance-varying communication, and mixed traffic. This paper proposes a novel bandwidth-link resources cooperative allocation strategy to achieve better communication performance under the road conditions of intelligent transportation systems(ITS). Firstly, in traffic scenarios, based on the characteristic to predict the relative position of the mobile transceivers, a strategy is developed to cooperate on the mobile cellular network and the Dedicated Short-Range Communications(DSRC). Secondly, by adopting the general network simulator NS3, the dedicated mobile channel models that are suitable for the data interaction of ITS, is applied to confirm the feasibility and reliability of the strategy. Finally, by the simulation, comparison, and analysis of some critical performance parame-ters, we conclude that the novel strategy does not only reduce the system delay but also improve the other communication performance indicators, such as the PDR and communication capacity.

Feasibility of central loop TEM method for prospecting multilayer water-fi lled goaf

With deep mining of coal mines, prospecting multilayer water-filled goaf has become a new content that results from geophysical exploration in coalfields. The central loop transient electromagnetic （TEM） method is favorable for prospecting conductive layers because of the coupling relationship between its field structure and formation. However, the shielding effect of conductive overburden would not only require a longer observation time when prospecting the same depth but also weaken the anomalous response of underlying layers. Through direct time domain numerical simulation and horizontal layered earth forward modeling, this paper estimates the length of observation time required to prospect the target, and the distinguishable criterion of multilayer water-filled goal is presented with observation error according to the effect of noise on observation data. The observed emf curves from Dazigou Coal Mine, Shanxi Province can distinguish multilayer water-filled goaf. In quantitative inversion interpretation of observed curves, using electric logging data as initial parameters restrains the equivalence caused by coal formation thin layers. The deduced three-layer and two-layer water-filled goals are confirmed by the drilling hole. The result suggests that when observation time is long enough and with the anomalous situation of underlying layers being greater than the observation error, the use of the central loop TEM method to orosoect a multilaver water-filled goaf is feasible.

Hybrid and Full-Digital Beamforming in mmWave Massive MIMO Systems: A Comparison Considering Low-Resolution ADCs

In a millimeter-wave(mmWave)Massive multiple-input multiple-output(MIMO)systems,full-digital beamforming(i.e.,connecting each antenna with a specific radio-frequency(RF)chain)becomes inefficient due to the hardware cost and power consumption.Therefore,hybrid analog and digital transceiver where the number of RF chains are much smaller than that of the antennas has drawn great research interest.In this work,we investigate the use of low-resolution analog-to-digital converters(ADCs)in the uplink of multi-user hybrid and full-digital mmWave Massive MIMO systems.To be specific,we compare the performance of full-digital minimum mean square error(MMSE)and hybrid MMSE beamforming in both sum rates and energy efficiency.Accurate approximations of sum rates and energy efficiency are provided for both schemes,which captures the dominant factors.The analytical results show that full-digital beamforming outperforms hybrid beamforming in terms of sum rates and requires only a small portion(γ)of antennas used by hybrid beamforming to achieve the same sum rates.We given sufficient condition for full-digital beamforming to outperform hybrid beamforming in terms of energy efficiency.Moreover,an algorithm is proposed to search for the optimal ADC resolution bits.Numerical results demonstrate the correctness of the analysis.

Medical data publishing based on average distribution and clustering

Most of the data publishing methods have not considered sensitivity protection,and hence the adversary can disclose privacy by sensitivity attack.Faced with this problem,this paper presents a medical data publishing method based on sensitivity determination.To protect the sensitivity,the sensitivity of disease information is determined by semantics.To seek the trade-off between information utility and privacy security,the new method focusses on the protection of sensitive values with high sensitivity and assigns the highly sensitive disease information to groups as evenly as possible.The experiments are conducted on two real-world datasets,of which the records include various attributes of patients.To measure sensitivity protection,the authors define a metric,which can evaluate the degree of sensitivity disclosure.Besides,additional information loss and discernability metrics are used to measure the availability of released tables.The experimental results indicate that the new method can provide better privacy than the traditional one while the information utility is guaranteed.Besides value protection,the proposed method can provide sensitivity protection and available releasing for medical data.

LED Adaptive Deployment Optimization in Indoor VLC Networks

Driven by the continuous penetration of high data rate services and applications,a large amount of unregulated visible light spectrum is used for communication to fully meet the needs of 6th generation(6G)mobile technologies.Visible light communication(VLC)faces many challenges as a solution that complements existing radio frequency(RF)networks.This paper studies the optimal configuration of LEDs in indoor environments under the constraints of illumination and quality of experience(QoE).Based on the Voronoi tessellation(VT)and centroidal Voronoi tessellation(CVT)theory,combined with the Lloyd’s algorithm,we propose two approaches for optimizing LED deployments to meet the illumination and QoE requirements of all users.Focusing on(i)the minimization of the number of LEDs to be installed in order to meet illumination and average QoE constraints,and(ii)the maximization of the average QoE of users to be served with a fixed number of LEDs.Monte Carlo simulations are carried out for different user distribution compared with hexagonal,square and VT deployment.The simulation results illustrate that under the same conditions,the proposed deployment approach can provide less LEDs and achieve better QoE performance.