Big Data最新文献

英文中文

Spatiotemporal Convolutions and Video Vision Transformers for Signer-Independent Sign Language Recognition 基于时空卷积和视频视觉变换的独立手语识别

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220534

Mark Marais, Dane Brown, James Connan, Alden Boby

Sign language is a vital tool of communication for individuals who are deaf or hard of hearing. Sign language recognition (SLR) technology can assist in bridging the communication gap between deaf and hearing individuals. However, existing SLR systems are typically signer-dependent, requiring training data from the specific signer for accurate recognition. This presents a significant challenge for practical use, as collecting data from every possible signer is not feasible. This research focuses on developing a signer-independent isolated SLR system to address this challenge. The system implements two model variants on the signer-independent datasets: an R(2+ I)D spatiotemporal convolutional block and a Video Vision transformer. These models learn to extract features from raw sign language videos from the LSA64 dataset and classify signs without needing handcrafted features, explicit segmentation or pose estimation. Overall, the R(2+1)D model architecture significantly outperformed the ViViT architecture for signer-independent SLR on the LSA64 dataset. The R(2+1)D model achieved a near-perfect accuracy of 99.53% on the unseen test set, with the ViViT model yielding an accuracy of 72.19 %. Proving that spatiotemporal convolutions are effective at signer-independent SLR.

手语是聋人或重听人交流的重要工具。手语识别(SLR)技术可以帮助弥合聋人与正常人之间的沟通差距。然而，现有的单反系统通常依赖于签名者，需要来自特定签名者的训练数据才能准确识别。这对实际使用提出了重大挑战，因为从每个可能的签名者那里收集数据是不可行的。本研究的重点是开发一个独立于签名者的隔离单反系统来解决这一挑战。该系统在签名无关的数据集上实现了两种模型变体:R(2+ I)D时空卷积块和视频视觉变压器。这些模型学习从LSA64数据集的原始手语视频中提取特征，并在不需要手工制作特征、显式分割或姿势估计的情况下对标志进行分类。总体而言，在LSA64数据集上，R(2+1)D模型体系结构在与签名者无关的SLR方面明显优于ViViT体系结构。R(2+1)D模型在未见的测试集上实现了近乎完美的99.53%的准确率，而ViViT模型的准确率为72.19%。证明了时空卷积在与签名无关的单反中是有效的。

{"title":"Spatiotemporal Convolutions and Video Vision Transformers for Signer-Independent Sign Language Recognition","authors":"Mark Marais, Dane Brown, James Connan, Alden Boby","doi":"10.1109/icABCD59051.2023.10220534","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220534","url":null,"abstract":"Sign language is a vital tool of communication for individuals who are deaf or hard of hearing. Sign language recognition (SLR) technology can assist in bridging the communication gap between deaf and hearing individuals. However, existing SLR systems are typically signer-dependent, requiring training data from the specific signer for accurate recognition. This presents a significant challenge for practical use, as collecting data from every possible signer is not feasible. This research focuses on developing a signer-independent isolated SLR system to address this challenge. The system implements two model variants on the signer-independent datasets: an R(2+ I)D spatiotemporal convolutional block and a Video Vision transformer. These models learn to extract features from raw sign language videos from the LSA64 dataset and classify signs without needing handcrafted features, explicit segmentation or pose estimation. Overall, the R(2+1)D model architecture significantly outperformed the ViViT architecture for signer-independent SLR on the LSA64 dataset. The R(2+1)D model achieved a near-perfect accuracy of 99.53% on the unseen test set, with the ViViT model yielding an accuracy of 72.19 %. Proving that spatiotemporal convolutions are effective at signer-independent SLR.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80853503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Deep Learning Model for Predicting Under-Five Mortality in Zimbabwe 预测津巴布韦五岁以下儿童死亡率的深度学习模型

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220453

John Batani

The death of children before they reach five years old (under-five mortality or U5M) is a global scourge that has attracted the attention of many governments, including the World Health Organisation and the United Nations. Children under-five in Sub-Saharan Africa are disproportionately susceptible to death, with a fifteen-fold likelihood of death compared to their counterparts in developed countries. Regardless of the numerous efforts by the Zimbabwean Government to improve child health, such as free access to care, provision of nutritional supplements, immunisation programmes and prevention of mother-to-child transmission, the country still has high under-five mortality rates (U5MRs). Zimbabwe's failure to reduce U5MRs to acceptable levels suggests that the current methods must be complemented. Identifying contextual risk factors and children at risk of death could help paediatricians to make timely and targeted interventions and policymakers to review existing and craft new policies to save children's lives. Therefore, this study applied deep learning to Zimbabwe's 2019 Multiple Indicator Cluster Survey data to predict under-five mortality and identify its associated risk factors. The study used a deep neural network with four hidden layers, k-fold cross-validation and the stochastic gradient descent (SGD) optimiser. All layers used the Rectified Linear Unit activation function except the output layer, which used the sigmoid activation for binary classification. The model produced a 90.04% accuracy, 92.39% precision, 87.30% recall and 95.04% area under the curve. Though the model predicts under-five mortality, it does not prescribe the appropriate interventions to save lives, a gap that future studies could fill.

五岁以下儿童死亡(五岁以下儿童死亡或U5M)是一个全球性的灾难，已引起包括世界卫生组织和联合国在内的许多政府的关注。撒哈拉以南非洲五岁以下儿童特别容易死亡，其死亡可能性是发达国家儿童的15倍。尽管津巴布韦政府为改善儿童健康作出了许多努力，例如免费获得护理、提供营养补充、免疫方案和预防母婴传播，但该国五岁以下儿童死亡率仍然很高。津巴布韦未能将5岁以下儿童死亡率降低到可接受的水平，这表明必须补充当前的方法。确定环境风险因素和面临死亡风险的儿童可以帮助儿科医生及时采取有针对性的干预措施，也可以帮助决策者审查现有政策并制定新的政策，以挽救儿童的生命。因此，本研究将深度学习应用于津巴布韦2019年的多指标聚类调查数据，以预测五岁以下儿童死亡率并确定其相关风险因素。该研究使用了具有四个隐藏层的深度神经网络，k-fold交叉验证和随机梯度下降(SGD)优化器。除了输出层使用sigmoid激活进行二值分类外，所有层都使用了Rectified Linear Unit激活函数。该模型的准确率为90.04%，精密度为92.39%，召回率为87.30%，曲线下面积为95.04%。虽然该模型预测了五岁以下儿童的死亡率，但它并没有规定适当的干预措施来挽救生命，这是未来研究可以填补的空白。

{"title":"A Deep Learning Model for Predicting Under-Five Mortality in Zimbabwe","authors":"John Batani","doi":"10.1109/icABCD59051.2023.10220453","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220453","url":null,"abstract":"The death of children before they reach five years old (under-five mortality or U5M) is a global scourge that has attracted the attention of many governments, including the World Health Organisation and the United Nations. Children under-five in Sub-Saharan Africa are disproportionately susceptible to death, with a fifteen-fold likelihood of death compared to their counterparts in developed countries. Regardless of the numerous efforts by the Zimbabwean Government to improve child health, such as free access to care, provision of nutritional supplements, immunisation programmes and prevention of mother-to-child transmission, the country still has high under-five mortality rates (U5MRs). Zimbabwe's failure to reduce U5MRs to acceptable levels suggests that the current methods must be complemented. Identifying contextual risk factors and children at risk of death could help paediatricians to make timely and targeted interventions and policymakers to review existing and craft new policies to save children's lives. Therefore, this study applied deep learning to Zimbabwe's 2019 Multiple Indicator Cluster Survey data to predict under-five mortality and identify its associated risk factors. The study used a deep neural network with four hidden layers, k-fold cross-validation and the stochastic gradient descent (SGD) optimiser. All layers used the Rectified Linear Unit activation function except the output layer, which used the sigmoid activation for binary classification. The model produced a 90.04% accuracy, 92.39% precision, 87.30% recall and 95.04% area under the curve. Though the model predicts under-five mortality, it does not prescribe the appropriate interventions to save lives, a gap that future studies could fill.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77115425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Swimming Goggles Optical Design by Fresnel Lenses 菲涅耳透镜的泳镜光学设计

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.3390/engproc2023038090

Feng-Ming Yeh, Liang-Ying Huang, Chao-Kai Chang, Ya-Hui Hsieh, Hsuan-Fu Wang, Rong-Seng Chang, Der-Chin Chen

引用次数: 0

Design of a 45 nm Complementary Metal Oxide Semiconductor Low Noise Amplifier for a 30 GHz Millimeter-Wave Wireless Transceiver in Radar Sensor Applications 用于雷达传感器中30ghz毫米波无线收发器的45 nm互补金属氧化物半导体低噪声放大器的设计

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220474

Shingirirai M. Chakoma, K. Ogudo

The millimeter-wave (mmWave) frequency band is rapidly becoming utilized in wireless technologies due to its large bandwidth and high data throughput. Wireless technology is increasingly becoming the backbone of the Internet of Things (IoT). This has resulted in increased applications of the radio frequency (RF) spectrum and congestion of the microwave band. This can be solved by utilizing more bandwidth at higher frequency bands. One notable application of IoT pertains to radar sensing, which has experienced increased popularity across various domains such as autonomous vehicles, gesture recognition, drones, and health monitoring. Radar sensors have been employed in these applications to perform tasks including proximity sensing, direction detection, speed measurement, target localization, and capturing physiological indicators such as heartbeat and breathing. Several factors have an impact on the performance of radar sensors, encompassing the maximum range for target detection, measurement precision, capability to differentiate between multiple targets, and ability to operate effectively in environments with high levels of noise. This paper presents the design of a 45 nm complementary metal-oxide-semiconductor (CMOS) low noise amplifier (LNA) for a mmWave Ka-band wireless transceiver for radar sensors. The LNA was designed to operate at 0.6V and 700 μA for low power consumption. The LNA consists of an inductive degenerated common source (CS) and a common gate (CG) diode-connected load. The LNA achieves a power gain of 31.19 dB and a noise figure (NF) of 0.133 dB at 30 GHz consuming 0.42 mW of power.

毫米波(mmWave)频段由于其大带宽和高数据吞吐量而迅速应用于无线技术。无线技术正日益成为物联网(IoT)的支柱。这导致了射频(RF)频谱的应用增加和微波频段的拥塞。这可以通过在更高的频带上利用更多的带宽来解决。物联网的一个值得注意的应用是雷达传感，它在自动驾驶汽车、手势识别、无人机和健康监测等各个领域越来越受欢迎。雷达传感器已在这些应用中用于执行任务，包括接近感测、方向检测、速度测量、目标定位以及捕获心跳和呼吸等生理指标。有几个因素会影响雷达传感器的性能，包括目标探测的最大距离、测量精度、区分多个目标的能力，以及在高噪声环境中有效操作的能力。本文设计了一种45 nm互补金属氧化物半导体(CMOS)低噪声放大器(LNA)，用于雷达传感器的毫米波ka波段无线收发器。LNA的工作电压为0.6V，电压为700 μA，功耗低。LNA由一个电感退化共源(CS)和一个共门(CG)二极管连接负载组成。该LNA在30 GHz时的功率增益为31.19 dB，噪声系数(NF)为0.133 dB，功耗为0.42 mW。

{"title":"Design of a 45 nm Complementary Metal Oxide Semiconductor Low Noise Amplifier for a 30 GHz Millimeter-Wave Wireless Transceiver in Radar Sensor Applications","authors":"Shingirirai M. Chakoma, K. Ogudo","doi":"10.1109/icABCD59051.2023.10220474","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220474","url":null,"abstract":"The millimeter-wave (mmWave) frequency band is rapidly becoming utilized in wireless technologies due to its large bandwidth and high data throughput. Wireless technology is increasingly becoming the backbone of the Internet of Things (IoT). This has resulted in increased applications of the radio frequency (RF) spectrum and congestion of the microwave band. This can be solved by utilizing more bandwidth at higher frequency bands. One notable application of IoT pertains to radar sensing, which has experienced increased popularity across various domains such as autonomous vehicles, gesture recognition, drones, and health monitoring. Radar sensors have been employed in these applications to perform tasks including proximity sensing, direction detection, speed measurement, target localization, and capturing physiological indicators such as heartbeat and breathing. Several factors have an impact on the performance of radar sensors, encompassing the maximum range for target detection, measurement precision, capability to differentiate between multiple targets, and ability to operate effectively in environments with high levels of noise. This paper presents the design of a 45 nm complementary metal-oxide-semiconductor (CMOS) low noise amplifier (LNA) for a mmWave Ka-band wireless transceiver for radar sensors. The LNA was designed to operate at 0.6V and 700 μA for low power consumption. The LNA consists of an inductive degenerated common source (CS) and a common gate (CG) diode-connected load. The LNA achieves a power gain of 31.19 dB and a noise figure (NF) of 0.133 dB at 30 GHz consuming 0.42 mW of power.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79166773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and Construction of a Web-Based Communication Interface for Home Automation 基于web的家庭自动化通信接口的设计与实现

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220488

Lesetja S. Mabunda, T. S. Hlalele

A web-based communication interface for home automation enables users to remotely control and monitor their home appliances and devices using a web browser. This technology has the potential to improve energy efficiency and convenience of homes, but also raises security and privacy concerns. This paper focus on the development of a web-based home automation communication interface employing the ThingSpeak platform as the cloud interfacing service, an Arduino board as the microcontroller, and the ESP8266 as the internet module. The subsystem components were tested using hardware testing circuits and a software code written using Arduino IDE to determine the standard operating procedure and results show that they all conform to the operating standards. When the PIR sensor was tested a voltage of 0 V was measured on the digital pin 2 of the Arduino when no motion is detected and a voltage of 3.25 V when motion is detected. The MQ7 sensor gave a reading of 1.73 V on the analog data pin when not exposed to CO (carbon monoxide) and a reading of 3.25 V when exposed to CO.

基于网络的家庭自动化通信接口使用户可以使用网络浏览器远程控制和监控他们的家用电器和设备。这项技术有可能提高能源效率和家庭的便利性，但也引起了安全和隐私方面的担忧。本文以ThingSpeak平台为云接口服务，以Arduino板为微控制器，以ESP8266为互联网模块，重点开发基于web的家庭自动化通信接口。采用硬件测试电路和Arduino IDE编写的软件代码对子系统组件进行了测试，确定了标准的操作程序，结果表明它们都符合操作标准。在测试PIR传感器时，Arduino的数字引脚2在没有检测到运动时测量到0 V电压，在检测到运动时测量到3.25 V电压。当不暴露于CO(一氧化碳)时，MQ7传感器在模拟数据引脚上的读数为1.73 V，暴露于CO时的读数为3.25 V。

引用次数: 0

Perception and Expectations of Vote Counting and Validation Systems: A Survey of Electoral Stakeholders 选票计数和确认系统的感知和期望:选举利益相关者的调查

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220571

Patrick Mwansa, Boniface Kabaso

Inconsistencies, unclear processes, and procedures in most democratic countries' election management, particularly vote-counting, cause mistrust and dispute in election results. This study explores the perceptions and expectations of electoral stakeholders on vote counting and validation processes in different African countries. Employing thematic analysis and using the Activity Theory as a lens, the research identifies key themes, such as technical aspects, accuracy, speed, efficiency, transparency, security, challenges, improvements, and the roles of observers and Election Management Bodies (EMBs). The findings highlight various challenges, such as poor network coverage, insufficient staff training, and corruption, informing the formation of a requirement specification for vote counting and validation systems. Despite potential drawbacks and challenges associated with technology solutions, the study proposes a set of ideal requirements specifications for an accurate, efficient, transparent, and secure election vote counting and validation process. The study contributes to ongoing discussions on transparency, accessibility, and the use of electronic voting systems to enhance electoral accuracy and integrity. It suggests avenues for future research, including evaluating legal and regulatory frameworks, voter education, technical challenges, and alternative technological approaches to vote counting and validation.

在大多数民主国家的选举管理中，特别是在计票过程中，不一致、不明确的过程和程序导致了对选举结果的不信任和争议。本研究探讨了不同非洲国家选举利益相关者对计票和确认过程的看法和期望。本研究采用专题分析并以活动理论为视角，确定了关键主题，如技术方面、准确性、速度、效率、透明度、安全性、挑战、改进以及观察员和选举管理机构(EMBs)的作用。调查结果突出了各种挑战，如网络覆盖不足、工作人员培训不足以及腐败，为选票计数和验证系统的需求规范的形成提供了信息。尽管与技术解决方案相关的潜在缺陷和挑战，该研究提出了一套理想的要求规范，以实现准确、高效、透明和安全的选举计票和验证过程。这项研究有助于正在进行的关于透明度、可及性和使用电子投票系统以提高选举准确性和完整性的讨论。它提出了未来研究的途径，包括评估法律和监管框架、选民教育、技术挑战以及计票和验证的替代技术方法。

{"title":"Perception and Expectations of Vote Counting and Validation Systems: A Survey of Electoral Stakeholders","authors":"Patrick Mwansa, Boniface Kabaso","doi":"10.1109/icABCD59051.2023.10220571","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220571","url":null,"abstract":"Inconsistencies, unclear processes, and procedures in most democratic countries' election management, particularly vote-counting, cause mistrust and dispute in election results. This study explores the perceptions and expectations of electoral stakeholders on vote counting and validation processes in different African countries. Employing thematic analysis and using the Activity Theory as a lens, the research identifies key themes, such as technical aspects, accuracy, speed, efficiency, transparency, security, challenges, improvements, and the roles of observers and Election Management Bodies (EMBs). The findings highlight various challenges, such as poor network coverage, insufficient staff training, and corruption, informing the formation of a requirement specification for vote counting and validation systems. Despite potential drawbacks and challenges associated with technology solutions, the study proposes a set of ideal requirements specifications for an accurate, efficient, transparent, and secure election vote counting and validation process. The study contributes to ongoing discussions on transparency, accessibility, and the use of electronic voting systems to enhance electoral accuracy and integrity. It suggests avenues for future research, including evaluating legal and regulatory frameworks, voter education, technical challenges, and alternative technological approaches to vote counting and validation.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89214510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Constraints of The Adoption of Gamification for Education and Training in Higher Education Institutions: A Systematic Literature Review 高等院校教育培训采用游戏化的制约因素:系统文献综述

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icABCD59051.2023.10220568

S. Oguta, Akindele Akinyinka, S. Ojo, B. Maake

Gamification, a concept that describes the use of game design elements in non-game scenarios, inan attempt to induce fun and motivation in non-game scenarios, has found application in a variety of contexts. In education, popular gamification elements that have been introduced to make learning fun includes the use of points, levels, missions, leaderboards, badges, and avatars. New gamification such as the use of social robots is now in vogue. Despite the enormous potential of these gaming concepts, researchers have unearthed some challenges that face the adoption of gamification in educational systems of Higher Education Institutions. In this study's systematic literature review, the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework was used to explore the difficulties encountered when using gamification in training and education at colleges and universities and tosuggest potential solutions. Several researches that employed gamification were elicited from databases such as google scholar, Scopus and research gate. The shortcomings encountered during the deployment of gamification in these studies were summarized. The study's findings reveal that he difficulties encountered when adopting gamification in education and training in higher education institutions can be divided into three categories: design concerns, issues with short-term engagement, and problems with user adaptability. Likewise, potential fixes for the issues were mapped out for future designers of educational gamified systems to follow.

游戏化是一个描述在非游戏场景中使用游戏设计元素的概念，它试图在非游戏场景中引入乐趣和动机，并在各种情境中得到应用。在教育领域，为使学习变得有趣而引入的流行游戏化元素包括使用点数、关卡、任务、排行榜、徽章和化身。新的游戏化，如社交机器人的使用，现在很流行。尽管这些游戏概念具有巨大的潜力，但研究人员发现了在高等教育机构的教育系统中采用游戏化所面临的一些挑战。在本研究的系统文献综述中，使用PRISMA(系统评价和荟萃分析的首选报告项目)框架来探索在高校培训和教育中使用游戏化时遇到的困难，并提出潜在的解决方案。一些使用游戏化的研究是从google scholar、Scopus和research gate等数据库中提取出来的。总结了在这些研究中部署游戏化过程中遇到的缺点。研究结果显示，高等教育机构在教育和培训中采用游戏化时遇到的困难可以分为三类:设计问题、短期参与问题和用户适应性问题。同样，我们也为未来的教育游戏化系统设计师列出了潜在的修复方法。

{"title":"The Constraints of The Adoption of Gamification for Education and Training in Higher Education Institutions: A Systematic Literature Review","authors":"S. Oguta, Akindele Akinyinka, S. Ojo, B. Maake","doi":"10.1109/icABCD59051.2023.10220568","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220568","url":null,"abstract":"Gamification, a concept that describes the use of game design elements in non-game scenarios, inan attempt to induce fun and motivation in non-game scenarios, has found application in a variety of contexts. In education, popular gamification elements that have been introduced to make learning fun includes the use of points, levels, missions, leaderboards, badges, and avatars. New gamification such as the use of social robots is now in vogue. Despite the enormous potential of these gaming concepts, researchers have unearthed some challenges that face the adoption of gamification in educational systems of Higher Education Institutions. In this study's systematic literature review, the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework was used to explore the difficulties encountered when using gamification in training and education at colleges and universities and tosuggest potential solutions. Several researches that employed gamification were elicited from databases such as google scholar, Scopus and research gate. The shortcomings encountered during the deployment of gamification in these studies were summarized. The study's findings reveal that he difficulties encountered when adopting gamification in education and training in higher education institutions can be divided into three categories: design concerns, issues with short-term engagement, and problems with user adaptability. Likewise, potential fixes for the issues were mapped out for future designers of educational gamified systems to follow.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89522631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-03 DOI: 10.1109/icabcd59051.2023.10220548

引用次数: 0

An Improved Dual-Channel Deep Q-Network Model for Tourism Recommendation. 一种改进的双通道深度Q网络旅游推荐模型。

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-01 Epub Date: 2023-03-17 DOI: 10.1089/big.2021.0353

Shengbin Liang, Jiangyong Jin, Jia Ren, Wencai Du, Shenming Qu

Tourism recommendation results are affected by many factors. Traditional recommendation methods have problems such as low recommendation accuracy and lack of personalization due to sparse data. This article uses implicit features such as contextual information, time-series travel trajectories, and comment data to address these issues. First, the Long Short-Term Memory (LSTM) network is introduced as the model basis, and deals with the input data of the model such as contextual information, scenic spot information, and tourist comments and so on for feature extraction. Then, the online behavior and long-term interest preference of users are analyzed, using positive feedback and negative feedback mechanism, the Deep Q-Network (DQN) value function of dual-channel mechanism is constructed. Finally, we propose a recommendation strategy, in which, a value evaluation network and a target network are proposed for each agent to learn the optimal strategy. The model is trained on the Yelp, DP, and Tourism datasets covering multiple scenarios to provide users with tourism recommendation services. Compared with baseline models such as Ultra Simplification of Graph Convolutional Networks, DQN, Actor-Critic, and Latent Factor Model, this model has an average increase of 76.61% in accuracy compared with the comparison model, and an average increase of 43.48% in the normalized discounted cumulative gain compared with the baseline model.

旅游推荐结果受多种因素影响。传统的推荐方法由于数据稀疏，存在推荐精度低、缺乏个性化等问题。本文使用了隐含的特征，如上下文信息、时间序列旅行轨迹和评论数据来解决这些问题。首先，引入长短期记忆（LSTM）网络作为模型基础，处理模型的输入数据，如上下文信息、景点信息和游客评论等，进行特征提取。然后，分析了用户的在线行为和长期兴趣偏好，利用正反馈和负反馈机制，构建了双通道机制的深度Q网络（DQN）值函数。最后，我们提出了一种推荐策略，其中，为每个代理提出了一个价值评估网络和一个目标网络来学习最优策略。该模型在Yelp、DP和Tourism数据集上进行训练，涵盖多个场景，为用户提供旅游推荐服务。与图卷积网络的超简化、DQN、Actor-Critic和潜在因素模型等基线模型相比，该模型的准确率比比较模型平均提高了76.61%，归一化贴现累积增益比基线模型平均提高43.48%。

{"title":"An Improved Dual-Channel Deep Q-Network Model for Tourism Recommendation.","authors":"Shengbin Liang, Jiangyong Jin, Jia Ren, Wencai Du, Shenming Qu","doi":"10.1089/big.2021.0353","DOIUrl":"10.1089/big.2021.0353","url":null,"abstract":"Tourism recommendation results are affected by many factors. Traditional recommendation methods have problems such as low recommendation accuracy and lack of personalization due to sparse data. This article uses implicit features such as contextual information, time-series travel trajectories, and comment data to address these issues. First, the Long Short-Term Memory (LSTM) network is introduced as the model basis, and deals with the input data of the model such as contextual information, scenic spot information, and tourist comments and so on for feature extraction. Then, the online behavior and long-term interest preference of users are analyzed, using positive feedback and negative feedback mechanism, the Deep Q-Network (DQN) value function of dual-channel mechanism is constructed. Finally, we propose a recommendation strategy, in which, a value evaluation network and a target network are proposed for each agent to learn the optimal strategy. The model is trained on the Yelp, DP, and Tourism datasets covering multiple scenarios to provide users with tourism recommendation services. Compared with baseline models such as Ultra Simplification of Graph Convolutional Networks, DQN, Actor-Critic, and Latent Factor Model, this model has an average increase of 76.61% in accuracy compared with the comparison model, and an average increase of 43.48% in the normalized discounted cumulative gain compared with the baseline model.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9880099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of Driving Fatigue Characteristics in Cold and Hypoxia Environment of High-Altitude Areas. 高海拔地区寒冷缺氧环境下驾驶疲劳特性分析。

IF 4.6 4区计算机科学 Q1 Computer Science

Big Data

Pub Date : 2023-08-01 Epub Date: 2023-05-18 DOI: 10.1089/big.2021.0464

Lin Tian, Jueshuai Li, Yanfei Li

The cold and hypoxic environment at high altitudes can easily lead to driving fatigue. For improving highway safety in high-altitude areas, a driver fatigue test is conducted using the Kangtai PM-60A car heart rate and oxygen tester to collect drivers' heart rate oximetry in National Highway 214 in Qinghai Province. Standard deviation (SDNN), mean (M), coefficient of RR (two R heart rate waves), RR interval coefficient of variation (RRVC), and cumulative rate of driving fatigue based on the driver's heart rate RR interval are calculated using SPSS. This study aims to derive degree of driving fatigue (DFD) in high-altitude areas when driving from lower to higher altitude. The analysis shows that the DFD growth trend of different altitude ranges presents an S-shaped curve. The driving fatigue thresholds in the altitude range of 3000-3500, 3500-4000, 4000-4500, and 4500-5000 m are 2.86, 3.82, 4.54, and 10.2, which are significantly higher than that of ordinary roads in plain areas. The start times of severe fatigue in the four altitude ranges are 35, 34, 32, and 25 minutes. The start time of driving fatigue continued to advance with the increase of age, and the DFD continued to increase with the increase of age. Results provide an empirical basis for the design of the horizontal alignment index system and antifatigue strategies to improve highway safety in high-altitude areas.

高海拔地区寒冷缺氧的环境很容易导致驾驶疲劳。为了提高高海拔地区的公路安全，在青海省214国道上，采用康泰PM-60A汽车心率血氧计对驾驶员进行了疲劳试验，采集了驾驶员的心率血氧测定值。使用SPSS计算基于驾驶员心率RR间期的标准差（SDNN）、平均值（M）、RR系数（两个R心率波）、RR间期变异系数（RRVC）和累积驾驶疲劳率。本研究旨在推导高海拔地区从低海拔向高海拔行驶时的驾驶疲劳程度。分析表明，不同海拔范围的DFD增长趋势呈S型曲线。3000-3500、3500-4000、4000-4500和4500-5000海拔范围内的驾驶疲劳阈值 m分别为2.86、3.82、4.54和10.2，显著高于平原地区的普通道路。在四个海拔范围内，严重疲劳的开始时间分别为35、34、32和25分钟。驾驶疲劳的开始时间随着年龄的增加而继续提前，DFD随着年龄的增长而继续增加。研究结果为设计水平线形指标体系和提高高海拔地区公路安全的抗疲劳策略提供了经验依据。

{"title":"Analysis of Driving Fatigue Characteristics in Cold and Hypoxia Environment of High-Altitude Areas.","authors":"Lin Tian, Jueshuai Li, Yanfei Li","doi":"10.1089/big.2021.0464","DOIUrl":"10.1089/big.2021.0464","url":null,"abstract":"The cold and hypoxic environment at high altitudes can easily lead to driving fatigue. For improving highway safety in high-altitude areas, a driver fatigue test is conducted using the Kangtai PM-60A car heart rate and oxygen tester to collect drivers' heart rate oximetry in National Highway 214 in Qinghai Province. Standard deviation (SDNN), mean (M), coefficient of RR (two R heart rate waves), RR interval coefficient of variation (RRVC), and cumulative rate of driving fatigue based on the driver's heart rate RR interval are calculated using SPSS. This study aims to derive degree of driving fatigue (DFD) in high-altitude areas when driving from lower to higher altitude. The analysis shows that the DFD growth trend of different altitude ranges presents an S-shaped curve. The driving fatigue thresholds in the altitude range of 3000-3500, 3500-4000, 4000-4500, and 4500-5000 m are 2.86, 3.82, 4.54, and 10.2, which are significantly higher than that of ordinary roads in plain areas. The start times of severe fatigue in the four altitude ranges are 35, 34, 32, and 25 minutes. The start time of driving fatigue continued to advance with the increase of age, and the DFD continued to increase with the increase of age. Results provide an empirical basis for the design of the horizontal alignment index system and antifatigue strategies to improve highway safety in high-altitude areas.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":null,"pages":null},"PeriodicalIF":4.6,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9880954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Big Data

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀