Intelligent User Research Articles

Artificial Intelligence in Engineering Education

Due to the growing interest in artificial intelligence in recent years, teaching this discipline to students of applied technical specialties is becoming relevant. Despite the formation of this scientific direction for almost 70 years, there is still no clear understanding of the terminology of this science, its tasks at the present stage and its application in engineering education. Moreover, the artificial intelligence terminology often misleads students. The article examines the current situation with the development of ideas related artificial intelligence, the possibility of its using in engineering education. Based on the analysis of the real possibilities of artificial intelligence, the actual content of education in the discipline of “Artificial intelligence in transport construction” is determined. The article focuses on users of artificial intelligence, not developers. The authors consider the competencies of a specialist that can be formed during the study of the above indicated discipline, as well as new relevant competencies that are necessary for a specialist in connection with the wide dissemination of artificial intelligence in the conditions of his/her professional activity. The functional model of artificial intelligence used in teaching students how to interact with it is considered. The article gives the examples of tasks solved by students today with the help of artificial intelligence technology during trial training.

Secure V2V and V2I Communication in Intelligent Transportation Using Cloudlets

Intelligent Transportation System (ITS) is a vision which offers safe, secure and smart travel experience to drivers. This futuristic plan aims to enable vehicles, roadside transportation infrastructures, pedestrian smart-phones and other devices to communicate with one another to provide safety and convenience services. Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication in ITS offers ability to exchange speed, heading angle, position and other environment related conditions amongst vehicles and with surrounding smart infrastructures. In this intelligent setup, vehicles and users communicate and exchange data with random untrusted entities (like vehicles, smart traffic lights or pedestrians) whom they don't know or have met before. The concerns of location privacy and secure communication further deter the adoption of this smarter and safe transportation. In this paper, we present a secure and trusted V2V and V2I communication approach using edge infrastructures where instead of direct peer to peer communication, we introduce trusted cloudlets to authorize, check and verify the authenticity, integrity and ensure anonymity of messages exchanged in the system. Moving vehicles or road side infrastructure are dynamically connected to nearby cloudlets, where security policies can be implemented to sanitize or stop fake messages and prevent rogue vehicles to exchange messages with other vehicles. We also present a formal attribute-based model for V2V and V2I communication, called AB-ITS, along with proof of concept implementation of the proposed solution in AWS IoT platform. This cloudlet supported architecture complements direct V2V or V2I communication, and serves important use cases such as accident or ice-threat warning and other safety applications. Performance metrics of our proposed architecture are also discussed and compared with existing ITS technologies.

Artificial intelligence and end user tools to develop a nurse duty roster scheduling system

ObjectivesA nurse duty roster is usually prepared monthly in a hospital ward. It is common for nurses to make duty shift requests prior to scheduling. A ward manager normally spends more than a working day to manually prepare and subsequently to optimally adjust the schedule upon staff requests and hospital policies. This study aimed to develop an automatic nurse roster scheduling system with the use of open-source operational research tools by taking into account the hospital standards and the constraints from nurses. MethodsArtificial intelligence and end user tools operational research tools were used to develop the code for the nurse duty roster scheduling system. To compare with previous research on various heuristics in employee scheduling, the current system was developed on open architecture and adopted with real shift duty requirements in a hospital ward. ResultsThe schedule can be generated within 1 min under both hard and soft constraint optimization. All hard constraints are fulfilled and most nurse soft constraints could be met. Compared with those schedules prepared manually, the computer-generated schedules were more optimally adjusted as real time interaction among nurses and management personnel. The generated schedules were flexible to cope with daily and hourly duty changes by redeploying ward staff in order to maintain safe staffing levels. ConclusionsAn economical but yet highly efficient and user friendly solution to nurse roster scheduling system has been developed and adopted using open-source operational research methodology. The open-source platform is found to perform satisfactorily in scheduling application. The system can be implemented to different wards in hospitals and be regularly updated with new hospital polices and nurse manpower by hospital information personnel with training in artificial intelligence.

Interaction Design System for Artificial Intelligence User Interfaces Based on UML Extension Mechanisms

With the rapid development of computer network technology in recent years, more and more demands have been placed on the functionality and attributes of the user interface. In the development of many computer projects, the variability and flexibility of user interface requirements have greatly increased the complexity of program development for researchers. In addition, the poor reusability of page access control writing has created a pressing need for a highly standardized and flexible way of developing software. Thus, the development and design of user interfaces for application software systems occupy an important position and have been a hot topic of research in the field of human-computer interaction. The traditional methods of describing user interaction, such as state transitions and data flow diagrams, are not based on global and intuitive concepts. Moreover, there is little support for the design of user interface interaction behavior, resulting in user interfaces being ignored at design time and left to implementers to grasp at coding time. It is therefore an issue that needs to be addressed in order to integrate traditional methods and intuitive descriptions from the user’s perspective into a new interface development model and methodology. This research creates a user interface framework based on interaction behavior from the user’s perspective. Furthermore, UML extension mechanisms are used to enable the user interface framework to better support UML-based modelling environments. In addition, the UML is structured and extended to include structural elements that support interface generation, and a structured use case model is proposed, which drives the analysis and design of the individual submodels. The extracted abstract interface elements and their mapping to concrete interface elements are documented in a way that explores the generation of different target languages under different platforms. This study incorporates user requirements and provides a scientific reference for the development and design of user interfaces.

Research on Adoption Behavior and Influencing Factors of Intelligent Pension Services for Elderly in Shanghai.

With the rapid development of artificial intelligence and Internet-of-Things technology, the traditional pension service mode has changed, and intelligent pension services have become a new direction of development. Descriptive statistical analysis is conducted on the supply status and demand of intelligent pension services. It is believed that the current intelligent pension services are still in the initial stage of development, and the contradiction between supply and demand is prominent. The demand for intelligent pension of the elderly is high, but the user acceptance and satisfaction are not high. On this basis, variables were selected from individual characteristics, family situation, economic status, education level, living conditions, and other indicators for multivariate unconditional logistic regression analysis. It was found that the adoption behavior of intelligent pension service users was most significantly affected by age, number of children, living conditions, service cost, service docking channel, and equipment operation difficulty. Based on the conclusion, this article puts forward some suggestions such as taking the government as the center to realize the multi-governance of intelligent pension services, improving the supply of intelligent pension service-related facilities guided by demand, optimizing the service mode based on the platform to realize dynamic combination, and taking talents as the core to promote the high-quality development of intelligent pension services.

The Role of Business Intelligence in Promoting Decision-Making in Humanitarian Organizations Operating in Turkey, Orange Organization as a Sample

This study aimed to identify the relationship between business intelligence systems and the decision-making process of humanitarian organizations operating in Turkey. In this study, the non-experimental quantitative descriptive research method was preferred, which is one of the types of scientific research suitable for the aim of the current research. The number of community members surveyed as a whole was (105) and represent the number of employees in the orange organization for this, data were collected and analyzed, and hypotheses were tested using SPSS. Several tests were conducted suitable for research, including noting the correlations between the variables, in addition to looking at the averages and proving the hypotheses. After conducting the process of analyzing the study data and its hypotheses, the study reached several results, the most prominent of which are first: There is a strong correlation between business intelligence systems and the decision-making process in humanitarian organizations operating in Turkey at the level of significance α ≤ 0.05. Second: There is a positive correlation between the quality of information and the quality of systems used in business intelligence systems and both user satisfaction and perceived value and its use in humanitarian organizations operating in Turkey at the level of significance α ≤ 0.05. Third: There is a positive correlation between the satisfaction of users of business intelligence systems with regard to decision-making in humanitarian organizations operating in Turkey at the specified significance level α ≤ 0.05.

User Access Control in Open Radio Access Networks: A Federated Deep Reinforcement Learning Approach

Targeting at implementing the next generation radio access networks (RANs) with virtualized network components, the open RAN (O-RAN) has been regarded as a novel paradigm towards fully open, virtualized and interoperable RANs. Through particularly introducing RAN intelligent controllers (RICs), machine learning (ML) can be unprecedentedly installed, adapting to various vertical applications and deployment environments without sophisticated planning efforts. However, the O-RAN also suffers two critical challenges of load balancing and frequent handovers in the massive base station (BS) deployment. In this paper, an intelligent user access control scheme with deep reinforcement learning (DRL) is proposed. To optimize the performance of distributed deep Q-networks (DQNs) trained by user equipments (UEs), a federated DRL-based scheme is proposed with a global model server installed in the RIC to update the DQN parameters. To further predictively train a global DQN with acceptable signaling overheads, the upper confidence bound (UCB) algorithm to select the optimal UE set and a dueling structure to decompose the DQN parameters are developed. With the proposed scheme, each UE effectively maximizes the long-term throughput and avoids frequent handovers. The simulation results well justify the outstanding performance of the proposed scheme over the-state-of-the-arts, to serve as references for the O-RAN standardization.

Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model’s fairness—and move closer towards responsible AI.

Cross-cultural differences in information processing of chatbot journalism: chatbot news service as a cultural artifact

PurposeHow does algorithmic information processing affect the thoughts and behavior of artificial intelligence (AI) users? In this study, the authors address this question by focusing on algorithm-based chatbots and examine the influence of culture on algorithms as a form of digital intermediation.Design/methodology/approachThe authors conducted a study comparing the United States (US) and Japan to examine how users in the two countries perceive the features of chatbot services and how the perceived features affect user trust and emotion.FindingsClear differences emerged after comparing algorithmic information processes involved in using and interacting with chatbots. Major attitudes toward chatbots are similar between the two cultures, although the weights placed on qualities differ. Japanese users put more weight on the functional qualities of chatbots, and US users place greater emphasis on non-functional qualities of algorithms in chatbots. US users appear more likely to anthropomorphize and accept explanations of algorithmic features than Japanese users.Research limitations/implicationsDifferent patterns of chatbot news adoption reveal that the acceptance of chatbots involves a cultural dimension as the algorithms reflect the values and interests of their constituencies. How users perceive chatbots and how they consume and interact with the chatbots depends on the cultural context in which the experience is situated.Originality/valueA comparative juxtaposition of cultural-algorithmic interactions offers a useful way to examine how cultural values influence user behaviors and identify factors that influence attitude and user acceptance. Results imply that chatbots can be a cultural artifact, and chatbot journalism (CJ) can be a socially contextualized practice that is driven by the user's input and behavior, which are reflections of cultural values and practices.

Ethical Regulation of Artificial Intelligence as a Factor of Information Security: the Experience of Thailand

The object of the study is the relations in the field of ethical regulation of the use of artificial intelligence technologies. The subject of the study is represented by the regulatory documents of Thailand, which establish prescriptions for the design, development, research, training, deployment and application of artificial intelligence technologies. The features of the Thai approach to the regulation of relations in this area are highlighted. The subjects involved in the regulatory mechanism of artificial intelligence are determined. The ethical requirements for the use of artificial intelligence technologies in relation to certain categories of subjects are investigated. The interrelation of ethical regulation of artificial intelligence technologies and security in the information space is traced. The national model of ethical regulation of artificial intelligence is characterized. Thailand implements a state-centrist model of ethical regulation of artificial intelligence, in which the state defines the basic ethical principles of artificial intelligence and regulates in detail the activities of public and private sector entities on each of these principles. A feature of the Thai model is the emphasis on the importance of training and advanced training of civil servants who are able to use digital technologies in management processes and effectively implement ethical principles in the course of performing their functions. Thailand has included artificial intelligence users in the circle of subjects responsible for the implementation of ethical requirements, as active participants in regulatory processes that can quickly influence the content of algorithms by providing the necessary information to artificial intelligence operators. The Thai model is designed to educate not a passive, but an active user of digital technologies, who is encouraged to raise awareness and improve skills in their use, which leads to strengthening the legal status of users with the help of "soft law" tools. Thailand's implementation of its model of ethical regulation of artificial intelligence will have a positive impact on ensuring information security.

An Intelligent Vehicle Alarm User Terminal System Based on Emotional Identification Technology

Negative emotions could increase the risks of traffic accidents. However, the driver’s emotional identification is rarely considered in the current design of intelligent vehicle alarm user terminals (IVAUTs). To solve the problem, this paper tries to design an IVAUT system based on emotional identification technology. Firstly, the transformer network was combined with a convolutional neural network (CNN) into a voice emotional identification system for intelligent vehicle alarm, and an emotional labeling approach was provided. Next, a bimodal fusion model was developed based on decompose-CNNs, which includes an appearance module, an optical flow module, and a bimodal fusion module. The proposed emotional identification approach was proved effective through experiments.

Learning-Based Multi Attribute Network Selection in Heterogeneous Wireless Access

The rise of heterogeneous networks including macro, micro, pico, femto, and WLAN presents new challenges in optimizing user’s access to the networks. To fully utilize the capacity of such rich field of heterogeneous wireless connectivity, mobile devices should be able to select Radio Access Network (RAN) for their connection depending on their need. The proposed algorithm here is based on an autonomous agent at the mobile node and assisted by integration of distributed cloud services, e.g. the edge cloud. The selection of RAN is based on a Multi Attribute Decision Making process combined with the Reinforcement Learning that reinforces historical data collected from the edge cloud. Mobile agent is responsible for collecting data, executing the selection algorithm, possibly offloading the parts of the execution to the edge cloud, and providing feedback to the edge cloud after termination of the connection. The ultimate aim is to the design of RAN selection algorithm owned by autonomous and intelligent user agents that can significantly improve the user’s experience in terms of network coverage, data rate, latency, and battery lifetime. Through extensive simulation scenarios, we demonstrate the stability and precision of our proposed algorithm.

Exploring users' adoption intentions in the evolution of artificial intelligence mobile banking applications: the intelligent and anthropomorphic perspectives

PurposeThe development of mobile technology has changed the traditional financial industry and banking sector. While traditional banks have adopted artificial intelligence (AI) techniques to deepen the development of mobile banking applications (apps), the current literature lacks research on the use of AI-based constructs to explore users' mobile banking app adoption intentions. To fill this gap, based on stimulus-organism-response (SOR) theory, two AI feature constructs as stimuli are considered, namely, perceived intelligence and anthropomorphism. This study then develops a research model to investigate how intelligence and anthropomorphism affect task-technology fit (TTF), perceived cost, perceived risk and trust (organism), which in turn influence users' AI mobile banking app adoption (response).Design/methodology/approachThis study used a convenience nonprobability sampling approach; a total of 451 responses were collected to examine the model. The partial least squares technique was utilized for data analysis.FindingsThe results show that intelligence and anthropomorphism increase users' willingness to adopt mobile banking apps through TTF and trust. However, higher levels of anthropomorphism enhance users' perceived cost. In addition, both intelligence and anthropomorphism have insignificant effects on perceived risk. The results provide theoretical contributions for AI-based mobile banking app adoption and offer practical guidance for bank planning to use AI to retain users.Originality/valueBased on SOR theory, this study reveals that as features, AI-enabled intelligence and anthropomorphism help us further understand users' perceptions regarding cost, risk, TTF and trust in the context of AI-enabled app adoption intentions.

REQIBA: Regression and Deep Q-Learning for Intelligent UAV Cellular User to Base Station Association

Unmanned Aerial Vehicles (UAVs) are emerging as important users of next-generation cellular networks. By operating in the sky, UAV users experience very different radio conditions than terrestrial users, due to factors such as strong Line-of-Sight (LoS) channels (and interference) and Base Station (BS) antenna misalignment. As a consequence, the UAVs may experience significant degradation to their received quality of service, particularly when they are moving and are subject to frequent handovers. The solution is to allow the UAV to be aware of its surrounding environment, and intelligently connect into the cellular network taking advantage of this awareness. In this paper we present REgression and deep Q-learning for Intelligent UAV cellular user to Base station Association (REQIBA), a solution that allows a UAV flying over an urban area to intelligently connect to underlying BSs, using information about the received signal powers, the BS locations, and the surrounding building topology. We demonstrate how REQIBA can as much as double the total UAV throughput, when compared to heuristic association schemes similar to those commonly used by terrestrial users. We also evaluate how environmental factors such as UAV height, building density, and throughput loss due to handovers impact the performance of our solution.

User experience evaluation of intelligent sports bracelet based on multi-factor fusion

In order to overcome the problems of the traditional methods, such as the low accuracy of calculating the weight of evaluation factors, the high error rate of evaluation and the long output time of evaluation results, a user experience evaluation method based on multi-factor fusion was proposed. Building intelligent motion bracelet user experience evaluation system, determine various evaluation factors relative to the membership degree of evaluation factor set, to construct judgment matrix, get the weights of preliminary results, the weighting results are consistency check, get the final weight calculation results, and the multi-factor fusion method was used to construct intelligent motion bracelet user experience evaluation model, get the final user experience evaluation result. Experimental results show that the calculation accuracy of the weight of evaluation factors is more than 94%, the error rate of evaluation varies from 0 to 2%, and the average output time of evaluation results is 0.62 s.

Intelligent Recommendation-Based User Plane Handover With Enhanced TCP Throughput in Ultra-Dense Cellular Networks

In ultra-dense cellular networks (UDNs) with user/control plane(U/C) splitting, frequent handovers in user planes are unavoidable, which seriously degrades the transmission control protocol (TCP) throughput of mobile station (MS). To enhance the TCP throughput in UDNs, this paper proposes an intelligent recommendation-based user plane handover scheme. Firstly, based on intelligent recommendation algorithms, a mobility prediction algorithm called content-based collaborative hybrid filters (CCHF) is proposed to predict the target small base station (SBS). When the MS moves into the cell-edge of the source SBS, it can pre-access the predicted target SBS and set up connections to the predicted target SBS and the source SBS simultaneously. This is the proposed CCHF-dual-handover scheme. With an accurate prediction and a simultaneous connection, CCHF-dual-handover can present enhanced signal to interference and noise ratio (SINR) at cell-edge, reduced handover interruption ratio (HIR), and improved MS’s TCP throughput. Moreover, TCP throughput of CCHF-dual-handover is analyzed to show the impact of various key parameters (such as MS’s velocity and pre-access threshold). Finally, simulations are carried out to evaluate the performance of the proposed CCHF-dual-handover. Given random trajectory, the prediction accuracy using CCHF is increased by more than 100% compared with existing prediction algorithms. Given accurate prediction, the CCHF-dual-handover can improve the TCP throughput by up to 150% compared with that of existing handover schemes.

False Vision Graphics in Logo Design Based on Artificial Intelligence in the Visual Paradox Environment.

There are numerous fresh ways of thinking and creativity as a result of the ongoing development of art design. How do you create a fantastic logo that has extraordinary artistic effects? The incorrect interpretation of artistic graphics can cause a special visual phenomenon known as the contradiction between visual images and objective reality, which causes people's visual systems to produce points of interest. Wrong vision graphics, or visual paradox, can give people a wonderful experience that transcends time and space and reveals the enigmatic beauty that is concealed in the natural order, which is in line with the design goals of sign art. The integration of design and artificial intelligence has drawn a lot of attention as science and technology have advanced. Designing an intelligent and comfortable user experience is more important than ever, especially given the world's growing digital demand. The technical limitations of algorithm black boxes exacerbate the power disparity between humans and algorithms, which is inherent in artificial algorithms. According to its research, artificial intelligence's algorithm is responsible for roughly 60% of its calculations. Random forest technology's current benefits and drawbacks are contrasted with those of popular algorithms, and a clear vision of its potential applications in the future is presented. The artificial algorithm's recommended operation mechanism chooses the algorithm's nontechnical neutrality and value orientation.

Intelligent Marketing and Targeting Users in Advertisement Online Using Data Mining

Intelligent Marketing and Targeting Users in Advertisement Online Using Data Mining

Effects of Font Style and Font Color in News Text on User Cognitive Load in Intelligent User Interfaces

The advances on the Internet and news media technologies suggest intelligent and personalised media interfaces in order to improve reading efficiency of news readers and enhance news disseminations. Cognitive load is one of factors that affect the understanding ability of news readers and therefore news dissemination. It is expected that the display elements in an intelligent user interface of news media could be automatically adjusted to modulate the audience’s perceived cognitive load level in order to improve the news reading efficiency. While the font style and font colour of news text are the main display elements in the user interface of news media, it is not clear how these elements affect perceived cognitive load of news readers. This paper investigates perceived cognitive load of news readers under different font style and font colour conditions. Experiments with the news text in Chinese as a case study found that the change of text font style of keywords resulted in the increase of the reader’s perceived cognitive load during reading news text under the low introduced cognitive load and blue colour displayed keywords. While under the high introduced cognitive load, the italic font and red colour of keywords text resulted in the decrease of the reader’s perceived cognitive load significantly during reading news text, which therefore improves the news reading efficiency. This paper is limited to the effects of two aspects of news text (font styles and colours) on user’s perceived cognitive load. The future work will focus on the investigation of effects of other factors such as news pictures and their colours, numbers, and locations on user’s perceived cognitive load.

Research on the method of travel area clustering of urban public transport based on Sage-Husa adaptive filter and improved DBSCAN algorithm.

The travel trajectory data of mobile intelligent terminal users are characterized by clutter, incompleteness, noise, fuzzy randomness. The accuracy of original data is an essential prerequisite for better results of trajectory data mining. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is one of the most effective trajectory data mining methods, but the selection of input parameters often limits it. The Sage-Husa adaptive filtering algorithm effectively controls the error range of mobile phone GPS data, which can meet the positioning accuracy requirements for DBSCAN spatial clustering having the advantages of low cost and convenient use. Then, a novel cluster validity index was proposed based on the internal and external duty cycle to balance the influence of the distance within-cluster, the distance between clusters, and the number of coordinate points in the process of clustering. The index can automatically choose input parameters of density clustering, and the effective clustering can be formed on different data sets. The optimized clustering method can be applied to the in-depth analysis and mining of traveler behavior trajectories. Experiments show that the Sage -Husa adaptive filtering algorithm proposed further improves the positioning accuracy of GPS, which is 17.34% and 15.24% higher eastward and northward, 14.25%, and 18.17% higher in 2D and 3D dimensions, respectively. The number of noise points is significantly reduced. At the same time, compared with the traditional validity index, the evaluation index based on the duty cycle proposed can optimize the input parameters and obtain better clustering results of traveler location information.