Terminal Users Research Articles

Secure and Efficient k-anonymous Trajectory Privacy Protection Method based on Differential Privacy

The Location-based service scheme have already involved in every aspect of People's daily life and are increasingly used in various industries. Aiming at the problem of the security and efficiency of mobile terminal users’ trajectory privacy protection in location-based service, we propose a k-anonymous trajectory privacy protection scheme based on differential privacy. This scheme adopts differential privacy technology to add Laplace noise to the user's trajectory many times to generate 2k noise trajectory, and then according to the trajectory similarity to determine k-1 noise users whose trajectory are similar to the user trajectory, and sets them and the real user as an anonymous user group, and then uses the anonymous user group to request LBS services. Security analysis shows that the scheme satisfies the security features of anonymity, unforgeability, and anti-counterfeiting attack. The simulation results show that the scheme not only guarantees the similarity between the false trajectory and the real trajectory but also has higher execution efficiency.

Effectiveness of an Acupuncture Steam-Warming Eye Mask on Dry Eye Disease in Visual Display Terminal Users: A Prospective Randomized Controlled Trial.

We aim to evaluate the effectiveness of an acupuncture steam-warming eye mask (ASEM) on dry eye disease (DED) in visual display terminal (VDT) users. This prospective randomized clinical trial included VDT users with DED-related features who were randomly assigned to the ASEM group (ASEM for 2 weeks, 20 participants) or the steam-warming eye mask (SEM) group (SEM for 2 weeks, 20 participants). The tear film break-up time (TBUT), Schirmer test, tear meniscus height, ocular surface staining scores, eyelid and meibomian gland exam, subjective symptoms, and quality of life (QoL) scores before and after treatment were collected. A generalized linear mixed model was applied to compare the improvement of symptoms and signs between the two groups. After the 2-week treatment, all the subjective symptoms and questionnaire scores in the ASEM group improved significantly (all p < 0.05), whereas the feelings of relaxation, comfortable, and refreshment did not change in the SEM group (both p > 0.05). The TBUT, tear meniscus height, and meibum quality in the lower eyelid were significantly better in the ASEM group than the SEM group (all p < 0.05), whereas no significant changes were observed in the Schirmer test and ocular surface staining scores. Compared with the SEM group, the ASEM group experienced a stronger feeling of refreshment (p = 0.013), lower sensation of ocular discharge (p = 0.031), higher TBUT (p = 0.045), better meibomian gland expressibility of both eyelids (both p < 0.05), and better meibum quality of both eyelids (both p < 0.05), even after adjustments for age and sex. In conclusion, comparing with SEM, ASEM can improve some subjective DED symptoms, tear film stability, and meibum status in VDT users.

USERS’ SATISFACTION WITH INTERCITY BUS TERMINAL QUALITY IN LAGOS STATE, NIGERIA

Globally, efficient intercity public transport relies on well-designed and high-quality terminal facilities and services to enhance accessibility, mobility, and safety for passengers and freight. Despite governmental efforts, bus terminals in Nigerian urban areas are becoming hotspots for unregulated activities and traffic chaos. In response, this study investigates users’ satisfaction with Lagos State's intercity bus terminal quality, analysing socio-economic profiles, satisfaction levels with quality of terminal facilities (QoTF) and services (QoTS), and challenges impacting terminal operations. Using a cross-sectional survey, 200 questionnaires were distributed to terminal users, employing a multistage sampling technique. Descriptive (weighted mean analysis) and inferential (multiple linear regression [MLR] analysis) statistics were employed for data analysis. Results indicate that the majority of respondents are male, aged below 40, and permanent terminal users. Satisfaction is noted with 13 out of 24 parameters of QoTF, with top-ranking parameters including parking space, restaurant facilities, and waste disposal facilities. However, dissatisfaction is expressed with 8 out of 14 parameters of QoTS. Least-satisfied QoTS parameters include staff attitudes, passenger safety, and bus service reliability. Top-rated challenges affecting terminal operations are security concerns, sanitation facility deficiencies and insufficient passenger amenities. MLR analysis indicates a significant influence of terminal facilities on overall service satisfaction (F= 2.899, p= 0.000 &lt;0.05). In conclusion, enhancing both terminal facilities and services is crucial for efficient operations in Lagos State's bus terminals. Recommendations include improving security measures, sanitary infrastructure and staff training to address user concerns and enhance satisfaction.

Biomimetic cytotoxicity control of select nitrogenous disinfection byproducts in water

Nitrogenous disinfection byproducts (N-DBPs) in water are carcinogenic, teratogenic, and mutagenic. In this work, we developed a biomimetic reduction approach based on the cysteine thiol that destructed the highly toxic, select nitrogenous haloacetamides (HAMs) and haloacetonitriles (HANs) while effectively controlling the cytotoxicity of the degradation products to serve as a basis for further technological applications (e.g. immobilized contact bed for terminal users). Mechanisms on toxicity control were elucidated. Results showed the degradation and cytotoxicity control of HAMs as more efficient than that of the HANs. The cytotoxicity of the chlorinated, brominated, and iodinated HAMs and HANs was reduced to 25 %− 0.25 % of the original after biomimetic reduction using a reasonable concentration ratio. Through a combination of thiol-specific reactivity, dehalogenation, and quantitative structure-activity relationship analyses, the major toxicity control mechanisms were found to be the reductive dehalogenation of the N-DBPs. The halogenated functional groups on the N-DBPs had a more pronounced effect than the amide and nitrile groups on the cytotoxicity and detoxification effect. Patterns of toxicity interaction variations with DBPs concentrations were identified to detect possible synergistic cytotoxicity interactions under various combinations of HAMs and HANs in the presence of the cysteine thiol. Results could benefit future N-DBPs control efforts.

A Two-Stage Framework for Exploiting the Multi-Elasticity of Multi-Energy Demands in Integrated Electricity and Gas Markets

With the development of integrated electricity and gas markets (IEGM), the participation of multi-energy demands (MEDs) is an effective measure to achieve a win-win goal of market efficiency improvement and demand cost reduction. The MEDs, composed of terminal users and energy conversion equipment (ECE), can adjust purchased electricity and gas with the variation in energy prices. Such adjustment behaviors of purchased energy in response to energy prices are defined as the multi-elasticity of MEDs. Considering that, this paper aims to analyze and quantify the multi-elasticity of MEDs and exploit it using a market-based approach. Firstly, the volume-price bidding curves are proposed to describe the multi-elasticity of MEDs considering the price-response features of terminal loads and multi-energy substitution features of ECE. Based on the proposed bidding curves, the energy consumption behaviors of MEDs with the change in prices can be effectively quantified. Moreover, a decentralized two-stage market framework is proposed to exploit the multi-elasticity in the IEGM clearing based on the multi-elasticity bidding curves of MEDs. In the proposed framework, the electricity market and gas market are cleared separately with the information exchange of the MEDs' clearing results of purchased gas and electricity. Furthermore, the consensus ADMM-based algorithm is applied to coordinately solve the IEGM clearing problem integrated with the multi-elasticity of MEDs. Numerical simulations are carried out for different test systems to validate the effectiveness of the proposed models.

Electromagnetic Accessibility of Starlink User Terminals

The results of assessing the electromagnetic accessibility of radio emission sources of the Starlink satellite communication system are presented. The features of the organizational and technical structure of the system are considered. Its main technical capabilities for organizing the provision of telecommunications services to users of subscriber terminals are analyzed. The technical features of the infrastructure of the Starlink satellite communication system, which are essential for the electromagnetic accessibility of its sources, have been studied. The possibility of radio links for transmitting information content in the upstream and downstream channels of the Starlink satellite communication system was assessed. The main stages of the developed methodology for assessing the electromagnetic accessibility of sources are presented. Analytical expressions are given for calculating the probability of detection and attenuation of signals. The requirements for the sensitivity of the receiving equipment of monitoring equipment are substantiated. Dependences of the level of signal attenuation on the distance of control equipment were obtained.

Dry Eyes among Visual Display Terminal Users Visiting the Outpatient Department of Ophthalmology of a Tertiary Care Centre.

Visual display terminal usage has increased substantially in recent years across all age groups and is considered one of the major risk factors for dry eye disease. Early assesment of dry eyes and prevention is important. The aim of this study is to find the prevalence of dry eyes among visual display terminal users visiting the Outpatient Department of Ophthalmology of a tertiary care centre. A descriptive cross-sectional study was conducted among patients visiting the Department of Ophthalmology in a tertiary care centre after receiving ethical approval from the Institutional Review Committee. Data was collected from 1 October 2021 to 31 March 2022. Convenience sampling method was used. The point estimate was calculated at a 90% Confidence Interval. Among 94 visual display terminal users, the prevalence of dry eyes was 55 (58.51%) (50.18-66.84, 90% Confidence Interval). The prevalence of dry eyes among visual display terminal users visiting the Outpatient Department of Ophthalmology was similar to other studies done in similar settings. dry eyes; health; prevalence.

Edge Collaborative Online Task Offloading Method Based on Reinforcement Learning

With the vigorous development of industries such as self-driving, edge intelligence, and the industrial Internet of Things (IoT), the amount and type of data generated are unprecedentedly large, and users’ demand for high-quality services continues to increase. Edge computing has emerged as a new paradigm, providing storage, computing, and networking resources between traditional cloud data centers and end devices with solid timeliness. Therefore, the resource allocation problem in the online task offloading process is the main area of research. It is aimed at the task offloading problem of delay-sensitive customers under capacity constraints in the online task scenario. In this paper, a new edge collaborative online task offloading management algorithm based on the deep reinforcement learning method OTO-DRL is designed. Based on that, a large number of simulations are carried out on synthetic and real data sets, taking obstacle recognition and detection in unmanned driving as a specific task and experiment. Compared with other advanced methods, OTO-DRL can well realize the increase in the number of tasks requested by mobile terminal users in the field of edge collaboration while guaranteeing the service quality of task requests with higher priority.

Tear film changes in symptomatic versus asymptomatic video display terminal users following computer challenge test

PurposeTo assess the real-time changes in the tear film and ocular surface of symptomatic video display terminal (VDT) versus asymptomatic users. MethodsA total of 35 symptomatic (29 ± 5.6 years; Group 1, mild dry eye disease) and 35 asymptomatic (24.1 ± 4.6 years; Group 2) VDT users with a mean OSDI of 28 ± 11 and 0.86 ± 2.1, respectively, had tear film examination (Oculus Keratograph 5 M and Tearlab Osmolarity System) at baseline and after 1 h of watching a movie on the laptop inside a controlled environment chamber along with blink rate calculation. ResultsThe mean VDT use was 11.4 ± 3.2 h/day in Group 1 and 2.3 ± 2.3 h/day in Group 2. In Group 1, the mean pre- and post-VDT task values for NIBUT and bulbar congestion were 10.7 ± 3.7s and 6.7 ± 3.1s (P = 0.007), and 0.8 ± 0.4 and 1.1 ± 0.5 (P = 0.01), respectively. There were no significant changes in tear meniscus height (P = 0.77), Schirmer I (P =0.14), corneal staining score (P = 1.0), and tear osmolarity (P > 0.05). Group 2 showed insignificant change in all parameters. Only 16.2% individuals in Group 1 met modified TFOS-DEWS II diagnostic criteria at baseline that increased to 67.6% following VDT task. The blink rate reduced significantly during the last 15 min (6.8 ± 3.4 vs. 9.3 ± 4.5; P = 0.006) compared to the first 15 min of the task in Group 1, whereas no significant change occurred in Group 2. ConclusionTear film instability and increased bulbar congestion are observed in symptomatic VDT users after computer work despite baseline stable tear film. The changes are significantly altered in symptomatic VDT users compared to asymptomatic users.

Blockchain-based fake news traceability and verification mechanism

The rapid development of the Internet and Internet of Things has rapidly introduced human society into the information age, and the way of fake news production has been updated, which has greatly affected the normal life of human beings. In order to identify worthless fake news and trace massive fake news data from unknown sources, and share valuable news data to fully disseminate effective real news, news owners usually store news data in cloud. Users of IoT terminals can access news data on demand without storing it locally. However, the authenticity of the fictive newspaper numbers source, which is easy to destroy, and the social media platform. Besides, when massive news data is saved on cloud server, the news owners have to at the risk of lose physical control over news data and it will face the risk of fake news being disseminated and real news being falsified. Thus, this paper proposes a novel mechanism for secure storage of news data using blockchain technology. Firstly, traceability and verification of fake news data is improved by the cooperative storage model on and off the chain. Secondly due to the inability of past polynomial commitment to update the commitment, we will be a hindrance to use polynomial commitment to build a secure authentication protocol. Therefore, in this paper, we design the update algorithm for polynomial commitment in order to be able to guarantee the consistency of on-chain and blockchain database news data.

Green integrated cooperative spectrum sensing for cognitive satellite terrestrial networks

AbstractIn this paper, a two‐way relay‐aided cognitive satellite terrestrial network (TR‐CSTN) model is proposed, where primary users are located at the edge of the base station. In the TR‐CSTN, one of satellite terminal users (STUs) is selected by the fusion center as the TR to forward information between two edge primary users with power of the TR. Meanwhile, these edge primary users share the licensed frequency band with the selected TR to send information to the satellite. Then, given the limited spectrum utilization and energy efficiency (EE) of the communication system, the cooperative spectrum sensing is employed to realize green communication. Specifically, the fusion center threshold, energy detection threshold, sensing duration and number of STUs are jointly optimized to enhance EE. Furthermore, considering that the node's energy shortage results in a short network lifetime, absolute EE gets improved. In detail, a power allocation scheme named normalized power aided Lévy flight trajectory‐based whale optimization algorithm (NP‐LWOA) is provided, which fulfills effective energy compensation among STUs to prolong the network lifetime notably. Finally, numerical results confirm the theoretical analysis and show the effectiveness of the TR‐CSTN and the NP‐LWOA in efficiently achieving the concept of green communication compared with other methods.

An Active Service Recommendation Model for Multi-Source Remote Sensing Information Using Fusion of Attention and Multi-Perspective

With the development and popularization of remote sensing earth observation technology and the remote sensing satellite system, the problems of insufficient proactiveness, relevance and timeliness of large-scale remote sensing supporting services are increasingly prominent, which seriously restricts the application of remote sensing resources in multi-domain and cross-disciplinary. It is urgent to help terminal users make appropriate decisions according to real-time network environment and domain requirements, and obtain the optimal resources efficiently from the massive remote sensing resources. In this paper, we propose a recommendation algorithm using fusion of attention and multi-perspective (MRS_AMRA). Based on MRS_AMRA, we further implement an active service recommendation model (MRS_ASRM) for massive multi-source remote sensing resources by combining streaming pushing technology. Firstly, we construct value evaluation functions from multi-perspective in terms of remote sensing users, data and services to enable the adaptive provision of remote sensing resources. Then, we define multi-perspective heuristic policies to support resource discovery, and fusion these policies through the attention network, to achieve the accurate pushing of remote sensing resources. Finally, we implement comparative experiments to simulate accurate recommendation scenarios, compared with state-of-the-art algorithms, such as DIN and Geoportal. Furthermore, MRS_AMRA achieves an average improvement of 10.5% in the recommendation accuracy NDCG@K, and in addition, we developed a prototype system to verify the effectiveness and timeliness of MRS_ASRM.

Comparison of mucin levels at the ocular surface of visual display terminal users with and without dry eye disease

BackgroundThe long-term use of visual display terminals (VDT) is linked to an increased risk of dry eye disease (DED). Numerous studies have indicated that ocular mucins play a vital role in the pathogenesis of DED. Therefore, we aimed to evaluate (1) whether mRNA levels of membrane-associated mucins (MAMs), including MUC1, MUC4, MUC16, and MUC20, as well as MUC5AC are altered in conjunctival cells of VDT users with and without DED and (2) the relationship between mucin levels and subjective and objective tests of DED in VDT users.MethodsSeventy-nine VDT users were enrolled and divided into DED (n = 53) and control (n = 26) groups. All participants were evaluated for parameters of DED using the Ocular Surface Disease Index (OSDI) questionnaire, tear breakup time (TBUT), corneal fluorescein staining (CFS), lissamine green (LG) staining, and tear meniscus height (TMH). Based on the conjunctival impression cytology (CIC) method, differences in MUC1, MUC4, MUC16, MUC20, and MUC5AC mRNA expression levels were observed between the DED and control groups, and between symptomatic and asymptomatic participants.ResultsThe DED group showed significantly decreased MUC1, MUC16, and MUC20 expressions (all P < 0.05) compared to the control group. In addition, these mucin levels were lower in subjects with frequent ocular symptoms (foreign body sensation, blurred vision and painful or sore eyes) than in asymptomatic participants (all P < 0.05). Correlation analysis revealed that MUC1, MUC16, and MUC20 levels in VDT users were positively correlated with TBUT or TMH, or both. However, no significant relationship was found between MUC4 and MUC5AC levels and the DED parameters.ConclusionVDT users with an increased frequency of ocular discomfort or a diagnosis of DED had a decreased MUC1, MUC16 and MUC20 mRNA expression in their conjunctival cells. MAMs deficiency in the conjunctival epithelium may be one of the mechanisms leading to tear film instability and DED in VDT users.

Novel E2E-QoE metric for PHY optimization: A cross-layered framework

Existing systems use key performance indicators (KPIs) as metrics for physical layer (PHY) optimization, which suffers from the problem of over-optimization, because some unnecessary PHY enhancements are imperceptible to terminal users and thus induce additional cost and energy waste. Therefore, it is necessary to utilize directly the quality of experience (QoE) of user as a metric of optimization, which can achieve the global optimum of QoE under cost and energy constraints. However, QoE is still a metric of application layer that cannot be easily used to design and optimize the PHY. To address this problem, we in this paper propose a novel end-to-end QoE (E2E-QoE) based optimization architecture at the user-side for the first time. Specifically, a cross-layer parameterized model is proposed to establish the relationship between PHY and E2E-QoE. Based on this, an E2E-QoE oriented PHY anomaly diagnosis method is further designed to locate the time and root cause of anomalies. Finally, we investigate to optimize the PHY algorithm directly based on the E2E-QoE. The proposed frameworks and algorithms are all validated using the data from real fifth-generation (5G) mobile system, which show that using E2E-QoE as the metric of PHY optimization is feasible and can outperform existing schemes.

NGHIÊN CỨU, ỨNG DỤNG MÔ-ĐUN NS-3 MMWAVE ĐÁNH GIÁ HIỆU NĂNG SÓNG MILIMET TRONG MẠNG THẾ HỆ MỚI 5G

The new generation mobile network 5G has become the main technology foundation in the architecture of the Internet of Things (IoT). In particular, millimeter wave communication technology in 5G is the core technology of the new generation network. Research on 5G networks faces many challenges in deploying real-life models to evaluate effectiveness. To resolve those issues, the article introduced the mmWave module integrated in the NS-3 network simulation toolkit to simulate and evaluate 5G network performance. The mmWave module is applied to simulate 5G network scenarios with the signal-to-noise ratio parameter SINR (Signal Interference + Noise Ration), thereby evaluating the wave quality from the base station to the terminal users to determine the most optimal location to build the base station.

Privacy-preserving data aggregation scheme against deletion and tampering attacks from aggregators

Because privacy-preserving data aggregation protocols provide data privacy and data compression, they have been extensively studied in smart grids. However, most of the existing data aggregation protocols are based on honest-but-curious aggregators, or adopt computationally intensive asymmetric homomorphic encryption, making these protocols only provably secure in weak security models, or resulting in high computational complexity for terminal users. To address the aforementioned issues, in this work, we propose a novel lightweight privacy-preserving data aggregation scheme against malicious aggregators based on our symmetric homomorphic encryption. The proposed scheme can reduce the computational cost of smart meters while also resisting tampering and deletion attacks from malicious aggregators. One of the highlights of the proposed scheme is its ability to withstand deletion attacks from malicious aggregators, which makes it unnecessary for the malicious aggregator to aggregate the readings of all smart meters instead of only a part of them. Therefore, our scheme is more secure than other schemes. It is the first privacy-preserving data aggregation scheme based on a stronger security model without multiple rounds of interaction. Finally, the detailed security analysis shows that the proposed scheme satisfies desirable security properties. Moreover, experimental results demonstrate that the proposed scheme is superior to the other four schemes in terms of computational complexity and communication overhead.

Dampak Relokasi Terminal Terboyo Semarang Bagi Pengguna Terminal

Terboyo Semarang Terminal is getting worse day by day due to tidal water that always inundates the terminal Terboyo Semarang. The existence of the terminal is needed by the community, so the government as a public servant continues to do various ways to make the terminal users feel comfortable. With the condition of the Terboyo terminal which is already less suitable for use as a passenger terminal, the Semarang City Government moved the Main Terminal located west of Semarang City, namely on Jl. Mangkang Raya Semarang in early 2016 with more complete facilities. With the passage of time, the Mangkang Terminal that has been provided by the government is not maximally used by traders, bus crews and passengers. In this study, the data from the research results were analyzed with qualitative methods by conducting direct observation or observation, interviews and documentation. from the results of interviews conducted by researchers, namely the bus crew and traders with the move of the terminal, the income received has decreased, which for the bus crew costs higher for diesel fuel and less time to rest. The use of this qualitative research aims to be more in-depth in understanding how much influence the terminal move has on traders, bus crews and passengers. The results of this research show an adverse impact, namely reduced income for bus crews, traders or sellers at the Terboyo terminal, while the impact on passengers is different, some feel benefited and some feel disadvantaged.

Comparison of changes in visual fatigue and ocular surface after 3D and 2D viewing with augmented reality glasses

The extensive use of electronic devices commonly results in visual discomfort, particularly in stereoscopic display. Augmented Reality (AR) is a mixed technology that superimposes three-dimensional (3D) digital data onto an image of reality. Even though the visual health evaluation of 3D contents has been widely concerned, the difference between 3D and two-dimensional (2D) viewing using AR display was rarely studied. We aimed to compare the changes in visual fatigue and ocular surface parameters after 3D and 2D viewing with optical waveguide AR glasses for one hour (1hr). In the experiment, thirty young healthy participants watched the same film in 2D and 3D mode separately using AR glasses with one week interval. Subjective visual fatigue questionnaire and ocular examinations were evaluated at 3 time points: pre-watching, post-2D and post-3D visual task for 1hr. Lipid layer thickness (LLT) and total blink (TB) were evaluated with the LipiView interferometer. Tear meniscus height (TMH) and noninvasive tear breakup time (NIBUT) were measured using Keratograph 5M. The effect of viewing 2D and 3D videos for 1hr with AR glasses suggested slight visual discomfort except the symptom of pain and dullness. The lipid layer thickness and total blink showed increasing trends in both post-visual task but more obvious after 2D viewing. Blinking patterns and tear film stability are meaningful for video display terminal users in visual health education. Ocular parameters are needed to be considered in the design and usage of future AR applications.

Online Edge Learning Offloading and Resource Management for UAV-Assisted MEC Secure Communications

The mobile and flexible unmanned aerial vehicle (UAV) with mobile edge computing (MEC) can effectively relieve the computing pressure of the massive data traffic in 5G Internet of Things. In this paper, we propose a novel online edge learning offloading (OELO) scheme for UAV-assisted MEC secure communications, which can improve the secure computation performance. Moreover, the problem of information security is further considered since the offloading information of terminal users (TUs) may be eavesdropped due to the light-of-sight characteristic of UAV transmission. In the OELO scheme, we maximize the secure computation efficiency by optimizing TUs' binary offloading decision and resource management while guaranteeing dynamic task data queue stability and minimum secure computing requirement. Since the optimization problem is fractionally structured, binary constrained and multi-variable coupled, we first utilize the Dinkelbach method to transform the fractionally structured problem into a tractable form. Then, OELO generates the offloading decision based on deep reinforcement learning (DRL) and optimizes the resource management in an iterative manner through successive convex approximation (SCA). Simulation results show that the proposed scheme achieves better computing performance and enhances the stability and security compared with benchmarks.

ARPCNN: Auxiliary Review-Based Personalized Attentional CNN for Trustworthy Recommendation

Convolutional neural network (CNN)-based recommender systems are playing an increasingly significant role in the vigorous development of Industrial Internet of Things, and have made great contributions to analyzing and mining a large amount of data to provide various services for terminal users. However, as the lack of explainability in deep learning, users often have low trust in the system due to their incomprehension of recommendation results. In addition, recommender systems have been facing a serious sparsity problem, and relying only on sparse rating data to learn user preferences and similarities may face malicious recommendation attacks. The abovementioned problems have been hindering the further improvement of recommendation performance. Therefore, in order to effectively alleviate the sparsity problem and meanwhile enhance the trustworthiness, an auxiliary review-based personalized attentional CNN (ARPCNN) is proposed in this article. By applying the proposed personalized word-level attention mechanism and personalized review-level attention mechanism in parallel CNNs, critical words and informative reviews are given high attention weights. Moreover, a user auxiliary network is proposed, which regards the reviews written by kindred spirits who have a trust relationship with the user as auxiliary reviews, and effectively extracts the user’s auxiliary review features, thereby achieving more accurate user modeling to improve the recommendation performance. Extensive experiments are conducted on four real-world datasets, and the results show that the performance of the proposed model is better than that of baselines, which verifies the effectiveness of ARPCNN.