User Demands Research Articles

Incentivized BiLSTM with Triplet Attention for Predecting Congestion in Network Traffic

In the world of online live video streaming, network traffic congestion poses a serious risk to user experience and service quality. Several factors contributing to the congestion include insufficient bandwidth, an increase in user demand, as well as ineffective data routing. The incapacity of the prediction algorithms to Adjust to modifications in network circumstances and challenges in detecting long-range relationships may restrict their ability to effectively estimate congestion in dynamic contexts when it comes to online streaming video. In order to overcome these constraints, this study created an Incentivized-RF-Triplet ASTM (“Incentivized learning-based triplet attention enabled rat fierce hunting optimized Bidirectional Long Short-Term Memory) for network traffic congestion prediction in online streaming video. A reward” scheme built into the Incentivized learning mechanism pushes the algorithm to prioritize online live video streaming congestion prediction. The sequential structure of network traffic data is handled by the BiLSTM architecture, that is well-known for capturing temporal dependencies. By utilizing the triplet Attention method, the model is better able to identify relevant regions within the input data as well as identify congestion patterns more successfully. The RFSO method incorporates social behavior with selection and searching qualities to further improve the classifier's parameters. Therefore, the characteristics of the model can be tuned more effectively and robustly, improving its effectiveness in congestion detection. The outcomes of the experiment show how well the Incentivized-RF-Triplet ASTM technique works to precisely estimate traffic congestion for the Darpa99week1 dataset. 95.97% accuracy, 96.08% specificity, and 0.22 mean square error are reported.

SDN-controlled multi-user NOMA-OFDM VLC system based on a resource allocation algorithm.

We propose a novel, to our knowledge, resource allocation algorithm (RAA) for a multi-user non-orthogonal multiple access orthogonal frequency division multiplexing (NOMA-OFDM) visible light communication (VLC) system. The proposed algorithm considers both the interference between users and their channel diversity. Bit allocation to users in each iteration is based on the ratio between the already allocated number of bits and the demanded number of bits of users, rather than their channel gains. In this way, the inherent issue of prioritizing strong users in a conventional RAA is avoided. We implement a software-defined-network (SDN)-controlled VLC system with real-time signal generation to validate the proposed RAA. The allocation results in the SDN platform are used to configure a FPGA-based transmitter. Experiments of a two-user NOMA-OFDM system with 115-191 Mbit/s throughput show that the system can dynamically react to the change of data demand and channel responses of users. We further demonstrate that the proposed algorithm outperforms conventional RAAs regardless of the data demand, receiving angles, and distances of users.

Hybrid Machine Learning Approaches for 5G Traffic Prediction

ABSTRACT Accurate traffic prediction poses great difficulties because of the continuously increasing scale and diversity of 5G network traffic, which is driven by user demands. Moreover, certain characteristics of 5G traffic are constantly changing; thus, simulations using traditional models often lead to incorrect estimations or inefficient utilization of available resources. Consequently, we propose a hybrid machine learning model that integrates support vector machine (SVM) and decision tree algorithms to enhance efficiency of 5G traffic prediction. The structure of the hybrid model dynamically adjusts by adding or removing hidden layers and units within the network to improve prediction performance. The efficacy of the proposed model is evaluated using metrics like mean squared error, mean absolute error, and root mean squared error (RMSE). Findings show that the hybrid model consistently achieves lower error rates than SVM alone. Further performance enhancement of the hybrid model in predicting 5G traffic is also supported by comparisons of R-squared values against signal-to-noise ratios. These outcomes show the potential of the proposed method to improve traffic prediction accuracy in 5G networks, serving as a powerful tool for network control.

Gaussian Mixture Model Based Voronoi Partitioning Scheme in Multi-Beam Satellites

With advances in technology and growing user needs, satellite communication is changing over time. Efficiently managing resources across diverse satellite coverage areas can be significantly enhanced through the application of Artificial Intelligence (AI) and Machine Learning (ML). The intended project seeks to employ fundamental machine learning algorithms, including Weighted k-means and Gaussian Mixture Model (GMM), to cluster user demands within a designated geographical region. This approach aims to optimize the utilization of satellite bandwidth in a multi-beam satellite system. A comparison of the results obtained using two techniques indicates improved performance of the GMM in terms of allocating the user demands. To ensure effective coverage, the clusters are transformed into shapes that match the coverage areas of the satellite. A technique called Voronoi Tessellation is used to create irregular polygons, and then these polygons are approximated as ellipses to cover the clusters more effectively.

Ascendancy of coworking space: user perceptions toward workspace features

Purpose This research paper aims to provide recommendations for enhancing the service quality of coworking spaces in Malaysia through effective workplace management. This study emphasizes the importance of avoiding over-promising and under-delivering, prioritizing cleanliness, functionality and customer satisfaction over profit to prevent user attrition. Design/methodology/approach Questionnaire surveys were administered to users of selected coworking spaces in Kuala Lumpur, Malaysia. Respondents were asked to assess both their expectations and perceived performance of various coworking space features. The resulting gap scores were then analyzed to develop recommendations for enhancing the overall performance of these coworking spaces. Findings The analysis of the responses indicated that users had higher expectations for “location” and “facilities services,” while the actual service performance in these areas was less satisfactory. Among the nine sub-attributes under “facilities and services,” three (opening hours, coffee and tea corner, café or restaurant) received negative gap scores, significantly affecting overall user satisfaction. Therefore, it is strongly recommended that coworking space managers prioritize the consistent provision and maintenance of these key features to better meet user demands and enhance satisfaction levels. Originality/value This study is innovative in applying a gap analysis approach to coworking spaces, identifying discrepancies between user expectations and actual service performance. This method provides a deeper understanding of the areas that require improvement, contributing to more user-centered coworking space management.

Forecast Errors and Welfare Conclusions Based on the Flyvbjerg Database

Abstract The so-called Flyvbjerg database is the largest source of data on the performance of major investment projects. It has generated influential analyses of the magnitude of and reasons for cost overruns and demand shortfalls in major projects. Those analyses have demonstrated, among other things, the systematic presence of large forecast errors in both construction costs and in user demand in the first year of operation. They have also linked those results to the social welfare consequences of the underlying projects, suggesting that the large and systematic forecast errors are indicative of welfare destruction. Given how influential those analyses have been, this paper examines the link between the database, empirical analyses thereof, and social benefit–cost analysis (BCA). To that end, both the measurement of variables in the database and the estimation of forecast errors are contrasted against BCA. The conditions for the estimated forecast errors to approximate those obtained from a BCA are spelled out, and the scope for drawing welfare conclusions based on those estimates is discussed. Furthermore, numerical simulations are presented to explore whether the estimated forecast errors do indeed imply likely welfare destruction. The simulations suggest that as large as the forecast errors are, welfare destruction is no foregone conclusion.

A Heterogeneous Multi-Satellite Dynamic Mission Planning Method Based on Metaheuristic Algorithms

The increasing demand for satellite communication necessitates efficient resource management, especially as next-generation high-throughput satellites (HTSs) face challenges in optimizing user connections. This paper presents a novel method that integrates a discretely improved Particle Swarm Optimization (PSO) algorithm with a dynamic task management framework to enhance satellite resource allocation efficiency. The PSO algorithm is adapted for discrete selection problems to maximize a fitness function based on user priority, user preference, and capacity satisfaction, thus ensuring accurate user–satellite matching. A main loop function iteratively updates user data and connection statuses, thus achieving continuous optimization of satellite connections. Through simulation studies, we validated the effectiveness of this method under dynamically changing user demands, demonstrating that the Discrete PSO algorithm significantly outperforms Simulated Annealing (SA) and the Genetic Algorithm (GA) in user satisfaction, maintaining levels above 0.996 even under high demand. Additionally, it effectively prioritizes high-demand users, ensuring their satisfaction remains above 0.95. Overall, our method enhances the management of daily communication tasks, significantly improving service quality and user satisfaction.

Optimal design of neural network-based fuzzy predictive control model for recommending educational resources in the context of information technology

Abstract As the information technology develops, educational resource recommendation system has become an indispensable part of the education field. At the same time, people’s demand for personalised educational resources is also growing; therefore, how to accurately predict user demand and provide personalised recommendations has become an important issue. In this study, a fuzzy predictive control model on the grounds of neural network is proposed to optimise the design of educational resource recommendation in the context of information technology. After experimental testing, the model recommendation fit reached 95.16 and 92.91% on the two test datasets, which are significantly higher than the control model. The average F1 values of the proposed model also reached 95.21 and 88.77%, which are higher than the control model. In other control experiments, the proposed model of this study also has a better performance. The relevant outcomes showcase that the predictive performance and recommendation effect of the model can be further enhanced by improving the structure of the neural network and the parameter optimisation method. Meanwhile, the proposed model has high performance in information overload and personalised demand, which offers a useful reference for the optimal design of educational resource recommendation system.

Conditional Community Search Based on Weight Information

Community search aims to identify cohesive subgraphs containing user-given query nodes in social networks. As information technology develops, user demands for community search have become increasingly sophisticated. The searched communities must not only meet the structural cohesiveness requirements but also adhere to some complex search conditions based on Boolean expressions. For example, certain desired nodes should be contained in the communities, while certain undesired nodes cannot exist in the communities, which is called conditional community search. However, existing solutions for conditional community search often introduce some undesired nodes into the identified communities and exhibit relatively low search efficiency. To overcome these drawbacks, therefore, this paper investigates the problem of conditional community search based on weight information. First, we refine the original problem definition of conditional community search and outline the need for an improved algorithm for calculating the weights of the nodes. Then, we explore two novel algorithms for searching conditional communities based on calculated weight information. Finally, we conduct extensive experiments on several real-world datasets to verify the accuracy and efficiency of our proposed searching algorithms.

Robust deadline-aware network function parallelization framework under demand uncertainty

The orchestration of Service Function Chains (SFCs) in Mobile Edge Computing (MEC) becomes crucial for ensuring efficient service provision, especially under dynamic and uncertain demand. Meanwhile, the parallelization of Virtual Network Functions (VNFs) within an SFC can further optimize resource usage and reduce the risk of deadline violations. However, most existing works formulate the SFC orchestration problem in MEC with deterministic demands and costly runtime resource reprovisioning to handle dynamic demands. This paper introduces a Robust Deadline-aware network function Parallelization framework under Demand Uncertainty (RDPDU) designed to address the challenges posed by unpredictable fluctuations in user demand and resource availability within MEC networks. RDPDU to consider end-to-end latency for SFC assembly by modeling load-dependent processing latency and load-independent propagation latency. Also, RDPDU formulates the problem assuming uncertain demand by Quadratic Integer Programming (QIP) to be resistant to dynamic service demand fluctuations. By discovering dependencies between VNFs, the RDPDU effectively assembles multiple sub-SFCs instead of the original SFC. Finally, our framework uses Deep Reinforcement Learning (DRL) to assemble sub-SFCs with guaranteed latency and deadline. By integrating DRL into the SFC orchestration problem, the framework adapts to changing network conditions and demand patterns, improving the overall system's flexibility and robustness. Experimental evaluations show that the proposed framework can effectively deal with demand fluctuations, latency, deadline, and scalability and improve performance against recent algorithms.

Exploring the Influence of Software Evolution on Mobile App Accessibility: Insights from User Reviews

Software systems constantly evolve to accommodate stakeholders' and environments' requirements that change over time. In this process, the frequent modifications can increase software complexity and negatively impact its global quality when conducted in an unstructured way. The evolutive nature of mobile environments led researchers to investigate how mobile app evolution impacts complexity, security, resource consumption, maintainability, usability, and accessibility. In particular, there has been limited research on the impact of app updates on mobile accessibility: most studies focused on tracking the number of accessibility violations found by automated tools across successive versions of a small set of applications. In a previous work, we made a contribution to this field by identifying accessibility reviews associated with app updates and prompting ChatGPT-4 to provide an overview of the main accessibility issues and enhancements perceived by users in the new releases of a mobile app. In this manuscript, we extend our previous work by adopting manual content analysis to delve deeper into our research questions and by adding new research questions associated with the identification of reviews linked to app updates, user characteristics, WCAG principles and guidelines, and user demands reported in accessibility reviews. Our results show that the accessibility barriers reported by users are mostly linked to the WCAG 2.2 Perceivable principle, and the Distinguishable and Adaptable guidelines, which includes poor color scheme, small font size, unlabeled elements, and lack of customization options. Accordingly, the consequences of the lack of accessibility is mainly connected to the difficult users experience to perceive elements of the interface (e.g. difficult to read and distinguish content, watch videos) and to use screen readers, in addition to feel discriminated against. The most common demand developers and organizations receive is to bring back some accessible feature or to fix accessibility bugs.

Effect of different heat treatment on thermal and electrical conductivity, and microhardness of Erbium-reinforced in-situ processed (ZrB2/Al2O3) 7085 AA nanocomposites for high temperature applications

High structurally stable 7085 aluminium alloy (7085 AA) is increasingly gaining more attention in industries such as automotive, electrical and high-temperature applications due to its demand for prolonged usage. The performance potential of conventional 7085 AA properties can be enhanced by reinforcing it with appropriate ceramic nanoparticles (AZ), namely, Aluminium oxide (Al2O3), Zirconium diboride (ZrB2), and rare earth metals, i.e. Erbium (Er), which makes it to be utilized for high-temperature industrial applications. Thus, the primary objective of the present study is to develop 7085 AA/AZ-Er composites having enhanced thermal, electrical and mechanical properties. The composites was synthesized through an In-situ process, followed by homogenization, solution treatment and artificial ageing (T6 and T74 heat treatment). The results obtained through T6 and T74 heat treatment were compared. The concentration of AZ was maintained at 1.0 wt.%, whereas Er was varied by 0.1. 0.3 and 0.5 wt.% in the 7085 AA/AZ composites. The superior properties of 7085 AA/AZ- Er composites achieved in this study are as follows: Thermal conductivity- 153.5 ± 0.7 W/m·K, Electrical conductivity- 21.99 ± 0.08 MS/m, and Hardness- 217.12 ± 3.2 Hv. The hardness and thermal conductivity of T6 heat-treated Er-based composites are found to be superior, while T74 heat-treated composites exhibited significant improvements in electrical conductivity. It is concluded that the appropriate addition of Er concentration plays a vital role in enhancing mechanical, electrical and thermal properties irrespective of the heat treatment process.

Enhancing flexibility and system performance in 6G and beyond: A user-based numerology and waveform approach

A Mixed Numerology OFDM (MN-OFDM) system is essential in 6G and beyond. However, it encounters challenges due to Inter-Numerology Interference (INI). The upcoming 6G technology aims to support innovative applications with high data rates, low latency, and reliability. Therefore, effective handling of INI is crucial to meet the diverse requirements of these applications. To address INI in MN-OFDM systems, this paper proposes a User-Based Numerology and Waveform (UBNW) approach that uses various OFDM-based waveforms and their parameters to mitigate INI. By assigning a specific waveform and numerology to each user, UBNW mitigates INI, optimizes service characteristics, and addresses user demands efficiently. Guard Band (GB) requirements, expressed as a ratio of user bandwidth, vary significantly across different waveforms at an SIR of 25 dB. For instance, OFDM-FOFDM needs only 2.5%, while OFDM-UFMC, OFDM-WOLA, and conventional OFDM require 7.5%, 24%, and 40%, respectively. The time-frequency efficiency also varies between the waveforms. FOFDM achieves 85.6%, UFMC achieves 81.6%, WOLA achieves 70.7%, and conventional OFDM achieves 66.8%. The simulation results demonstrate that the UBNW approach not only effectively mitigates INI but also enhances system flexibility and time-frequency efficiency, while simultaneously reducing the required GB.

Research Driven by User Demand for the Design of a Cross-Border Travel Credential Bag

Cross-border travel often presents challenges in document storage, which can burden travelers. This study addresses the issue by designing a credential bag that enhances safety, convenience, and environmental sustainability. Utilizing design research, we applied the KANO model to categorize user needs, employed analytic hierarchy process to prioritize these needs, and used quality functional deployment to translate them into specific design elements. The KANO model has identified a total of 18 demand indicators, including “must-be”, one-dimensional, and attractive. An analytic hierarchy process analysis of the secondary indicators found that demands for the security of anti-theft, partition storage of documents, a variety of carrying methods and green sustainability have relatively high weight. The innovative solutions derived from the KANO-AHP-QFD model improve design practices and user experience in document storage. This approach offers a scientific and practical reference for the sustainable development of travel supplies and the luggage industry.

Research on the Operation Status and Development Strategy of Wechat Public Account

With the continuous development and progress of global science and technology, the demand of users is increasing, and Wechat, as an important information exchange platform, plays an indispensable role in daily communication and communication. The Wechat public account, one of its main functions, plays a major advantage in disseminating information and providing facilitation services. However, how to create a fair public account environment so that each content production subject achieves satisfactory communication effects needs to be further studied. This paper studies the operation status and development strategy of Wechat public accounts. By searching and reading relevant materials and literature, it comprehensively analyzes the content production characteristics of different types of Wechat public accounts and finds that the development of science and technology and the needs of users are the main factors that promote the rapid development of Wechat public accounts. It is characterized by diversity of content and subject, fragmentation of content production, low publicity cost and high communication efficiency, accurate positioning of users, and secondary transmission. However, there are still many problems in the operation of Wechat public accounts, such as insufficient attention from content producers, homogeneity and vulgar content, irregular time of content release, fan conversion rate, and insufficient user loyalty. Content producers can win better communication effects by releasing high-quality content, enhancing user loyalty, expanding the dissemination scope by secondary communication, and using Wechat public accounts for product marketing in multiple ways.

Evaluation method and design of greenhouse pear pollination drones based on grounded theory and integrated theory.

Greenhouse cultivation promotes an efficient and environmentally friendly agricultural production model, significantly enhancing resource sustainability and advancing sustainable agriculture. Traditional greenhouse pollination methods are inefficient and labor-intensive, limiting the economic benefits of greenhouse pear cultivation. To improve pollination efficiency and achieve fully automated mechanized operations, an innovative design method for greenhouse pear pollination drones has been developed. First, design criteria were extracted using Grounded Theory (GT), and the Analytic Hierarchy Process (AHP) was employed to determine the weight of user demand evaluation indicators. Next, the Quality Function Deployment (QFD) method translated user needs into technical requirements, resulting in the final ranking of design element weights. The drone was then designed based on these weighted rankings, yielding an optimal solution. This method quantifies the functional requirements of the product, effectively identifying key needs for the greenhouse pear pollination drones and proposing targeted solutions. Additionally, it provides a design reference for other highly functional agricultural machinery products.

Towards ML Models’ Recommendations

AbstractArtificial Intelligence encompasses a range of technologies that replicate human-like cognitive abilities through computer systems, enabling the execution of tasks associated with intelligent beings. A prominent way to achieve this is machine learning (ML), which optimizes system performance by employing learning algorithms to create models based on data and its inherent patterns. Today, a multitude of ML models exist having diverse characteristics, including the algorithm type, training dataset, and resultant performance. Such diversity complicates the selection of an appropriate model for a specific use case, answering user demands. This paper presents an approach for ML models retrieval based on the matching between user inputs and ML models criteria, all described in a semantic ML ontology named SML model (Semantic Machine Learning model), which facilitates the process of ML models selection. Our approach is based on similarities measures that we tested and experimented to score the ML models and retrieve the ones matching, at best, user inputs.

Implementation of PWA in Scholarship Application Using Microservices Architecture for Enhancing User Engagement

The shortage of traditional web development makes researchers turn to web development using Progressive Web App (PWA) in developing a web, which has been increasingly done. PWA has the ability to function even with a low internet connection, maintain interactive user and access speeds, and provide real-time notifications. In modern web development, where the demand for data, features, and users can increase rapidly, an architecture is required to handle this problem. Microservices architecture can answer this. This research will develop a scholarship application using PWA and microservices architecture. The scholarship application was developed using Veu.js for the front end of the client application, MySQL for the application database, and the SLIM framework for microservices implementation. Furthermore, we utilized RAbbitMQ to develop a message broker and Docker for microservices contaner. The scholarship application developed using PWA technology and microservices in this research has been tested by conducting a User Acceptance Test. The results are the implementation of PWA in the scholarship application using microservice architecture has worked well, and the application performance has been able to overcome problems in terms of scalability, speed, and reliability.

Design of Routing Algorithm for Communication of Power Wireless Sensor Networks Based on Improved Harmony Search

In this paper, a routing algorithm for the communication of power wireless sensor networks based on improved harmony search is proposed to reduce the communication routing delay and energy consumption of power wireless sensor networks. Firstly, according to the composition of communication routing delay and energy consumption of power wireless sensor networks, the delay model and energy consumption model are constructed respectively, and the objective function is constructed by assigning different weights. Then, artificial bee colony algorithm and Levy flight mechanism improved harmony search algorithm are adopted for solving the objective function. Experiment results reveal that the algorithm can meet different users’ different demands on delay and energy consumption. If the user needs low delay, set the low delay weight to 1 and the power consumption weight to 0, then the average delay is 7s, and the average power consumption is 3203J. When user demand is low energy consumption, set the delay weight to 0 and the energy consumption weight to 1, so that the average energy consumption is 2667J and the average delay is 15s, which can meet the needs of users.

An Intelligent Scheduling Approach on Mobile OS for Optimizing UI Smoothness and Power

Mobile devices need to respond quickly to diverse user inputs. The existing approaches often heuristically raise the CPU/GPU frequency according to the empirical rules when facing burst inputs and various changes. Although doing so can be effective sometimes, the existing approaches still need improvements. For instance, raising processors’ frequency can lead to high power consumption when the frequency is over-provisioned or fails to meet user demands when the frequency is under-provisioned. To this end, we propose MobiRL, a reinforcement learning-based scheduler for intelligent adjusting CPU/GPU frequency to satisfy user demands accurately on mobile systems. MobiRL monitors the mobile system status and autonomously learns to optimize UI smoothness and power consumption by conducting CPU/GPU frequency-adjusting actions. The experimental results on the latest delivered smartphones show that MobiRL outperforms the widely used commercial scheduler on real devices – reducing the frame drop rate by 4.1% and reducing power consumption by 42.8%, respectively. Moreover, compared with a study using Q-Learning for CPU frequency scheduling, MobiRL achieves up to 2.5% lower frame drop rate and reduces power consumption by 32.6%, respectively. Our approach has been deployed in mobile phone products.