Data-driven intelligent monitoring system for key variables in wastewater treatment process

In wastewater treatment process(WWTP), the accurate and real-time monitoring values of key variables are crucial for the operational strategies. However, most of the existing methods have difficulty in obtaining the real-time values of some key variables in the process. In order to handle this issue, a data-driven intelligent monitoring system, using the soft sensor technique and data distribution service, is developed to monitor the concentrations of effluent total phosphorous(TP) and ammonia nitrogen(NH_4-N). In this intelligent monitoring system, a fuzzy neural network(FNN) is applied for designing the soft sensor model, and a principal component analysis(PCA) method is used to select the input variables of the soft sensor model. Moreover, data transfer software is exploited to insert the soft sensor technique to the supervisory control and data acquisition(SCADA) system. Finally, this proposed intelligent monitoring system is tested in several real plants to demonstrate the reliability and effectiveness of the monitoring performance.

An Intelligent Graph Edit Distance-Based Approach for Finding Business Process Similarities

There are numerous application areas of computing similarity between process models.It includes finding similar models from a repository,controlling redundancy of process models,and finding corresponding activities between a pair of process models.The similarity between two process models is computed based on their similarity between labels,structures,and execution behaviors.Several attempts have been made to develop similarity techniques between activity labels,as well as their execution behavior.However,a notable problem with the process model similarity is that two process models can also be similar if there is a structural variation between them.However,neither a benchmark dataset exists for the structural similarity between process models nor there exist an effective technique to compute structural similarity.To that end,we have developed a large collection of process models in which structural changes are handcrafted while preserving the semantics of the models.Furthermore,we have used a machine learning-based approach to compute the similarity between a pair of process models having structural and label differences.Finally,we have evaluated the proposed approach using our generated collection of process models.

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

One of the biggest dangers to society today is terrorism, where attacks have become one of the most significantrisks to international peace and national security. Big data, information analysis, and artificial intelligence (AI) havebecome the basis for making strategic decisions in many sensitive areas, such as fraud detection, risk management,medical diagnosis, and counter-terrorism. However, there is still a need to assess how terrorist attacks are related,initiated, and detected. For this purpose, we propose a novel framework for classifying and predicting terroristattacks. The proposed framework posits that neglected text attributes included in the Global Terrorism Database(GTD) can influence the accuracy of the model’s classification of terrorist attacks, where each part of the datacan provide vital information to enrich the ability of classifier learning. Each data point in a multiclass taxonomyhas one or more tags attached to it, referred as “related tags.” We applied machine learning classifiers to classifyterrorist attack incidents obtained from the GTD. A transformer-based technique called DistilBERT extracts andlearns contextual features from text attributes to acquiremore information from text data. The extracted contextualfeatures are combined with the “key features” of the dataset and used to perform the final classification. Thestudy explored different experimental setups with various classifiers to evaluate the model’s performance. Theexperimental results show that the proposed framework outperforms the latest techniques for classifying terroristattacks with an accuracy of 98.7% using a combined feature set and extreme gradient boosting classifier.

Leveraging Robust Artificial Intelligence for Mechatronic Product Development—A Literature Review

Mechatronic product development is a complex and multidisciplinary field that encompasses various domains, including, among others, mechanical engineering, electrical engineering, control theory and software engineering. The integration of artificial intelligence technologies is revolutionizing this domain, offering opportunities to enhance design processes, optimize performance, and leverage vast amounts of knowledge. However, human expertise remains essential in contextualizing information, considering trade-offs, and ensuring ethical and societal implications are taken into account. This paper therefore explores the existing literature regarding the application of artificial intelligence as a comprehensive database, decision support system, and modeling tool in mechatronic product development. It analyzes the benefits of artificial intelligence in enabling domain linking, replacing human expert knowledge, improving prediction quality, and enhancing intelligent control systems. For this purpose, a consideration of the V-cycle takes place, a standard in mechatronic product development. Along this, an initial assessment of the AI potential is shown and important categories of AI support are formed. This is followed by an examination of the literature with regard to these aspects. As a result, the integration of artificial intelligence in mechatronic product development opens new possibilities and transforms the way innovative mechatronic systems are conceived, designed, and deployed. However, the approaches are only taking place selectively, and a holistic view of the development processes and the potential for robust and context-sensitive artificial intelligence along them is still needed.

Robotic Process Automation with New Future Trends

The invention concept of Robotic Process Automation (RPA) has emerged as a transformative technology that has revolved the local business processes by programming repetitive task and efficiency adjusting the operations. This research had focused on developing the RPA environment and its future features in order to elaborate on the projected policies based on its comprehensive experiences. The current and previous situations of industry are looking for IT solutions to fully scale their company Improve business flexibility, improve customer satisfaction, improve productivity, accuracy and reduce costs, quick scalability in RPA has currently appeared as an advance technology with exceptional performance. It emphasizes future trends and foresees the evolution of RPA by integrating artificial intelligence, learning of machine and cognitive automation into RPA frameworks. Moreover, it has analyzed the technical constraints, including the scalability, security issues and interoperability, while investigating regulatory and ethical considerations that are so important to the ethical utilization of RPA. By providing a comprehensive analysis of RPA with new future trends in this study, researcher’s ambitions to provide valuable insights the benefits of it on industrial performances from the gap observed so as to guide the strategic decision and future implementation of the RPA.

Advanced Data Collection and Analysis in Data‑Driven Manufacturing Process

The rapidly increasing demand and complexity of manufacturing process potentiates the usage of manufacturing data with the highest priority to achieve precise analyze and control,rather than using simplified physical models and human expertise.In the era of data-driven manufacturing,the explosion of data amount revolutionized how data is collected and analyzed.This paper overviews the advance of technologies developed for in-process manufacturing data collection and analysis.It can be concluded that groundbreaking sensoring technology to facilitate direct measurement is one important leading trend for advanced data collection,due to the complexity and uncertainty during indirect measurement.On the other hand,physical model-based data analysis contains inevitable simplifications and sometimes ill-posed solutions due to the limited capacity of describing complex manufacturing process.Machine learning,especially deep learning approach has great potential for making better decisions to automate the process when fed with abundant data,while trending data-driven manufacturing approaches succeeded by using limited data to achieve similar or even better decisions.And these trends can demonstrated be by analyzing some typical applications of manufacturing process.

Research of intelligence data mining based on commanding decision-making

In order to rapidly and effectively meet the informative demand from commanding decision-making, it is important to build, maintain and mine the intelligence database. The type, structure and maintenance of military intelligence database are discussed. On this condition, a new data-mining arithmetic based on relation intelligence database is presented according to the preference information and the requirement of time limit given by the commander. Furthermore, a simple calculative example is presented to prove the arithmetic with better maneuverability. Lastly, the problem of how to process the intelligence data mined from the intelligence database is discussed.

Competency Driven Resource Evaluation Method for Business Process Intelligence

Enterprises are continuously aiming at improving the execution of processes to achieve a competitive edge.One of the established ways of improving process performance is to assign the most appropriate resources to each task of the process.However,evaluations of business process improvement approaches have established that a method that can guide decision-makers to identify the most appropriate resources for a task of process improvement in a structured way,is missing.It is because the relationship between resources and tasks is less understood and advancement in business process intelligence is also ignored.To address this problem an integrated resource classification framework is presenting that identifies competence,suitability,and preference as the relationship of task with resources.But,only the competence relationship of human resources with a task is presented in this research as a resource competence model.Furthermore,the competency calculation method is presented as a user guider layer for business process intelligencebased resource competence evaluation.The computed capabilities serve as a basic input for choosing the most appropriate resources for each task of the process.Applicability of method is illustrated through a heathcare case study.

Design of an Intelligent Usage Parameter Control in ATM Networks

This paper presents the principle of the fuzzy associate memory controlled leaky bucket (FAMLB) and several concepts for Usage Parameter Control (UPC) in ATM networks. The multiplex weight and random fuzzy rules adjustment method in the system architecture are introdued. The conclusions show that the FAMLB is a better dynamic method of UPC than the traditional ones.

Transforming Data into Actionable Insights with Cognitive Computing and AI

How organizations analyze and use data for decision-making has been changed by cognitive computing and artificial intelligence (AI). Cognitive computing solutions can translate enormous amounts of data into valuable insights by utilizing the power of cutting-edge algorithms and machine learning, empowering enterprises to make deft decisions quickly and efficiently. This article explores the idea of cognitive computing and AI in decision-making, emphasizing its function in converting unvalued data into valuable knowledge. It details the advantages of utilizing these technologies, such as greater productivity, accuracy, and efficiency. Businesses may use cognitive computing and AI to their advantage to obtain a competitive edge in today’s data-driven world by knowing their capabilities and possibilities [1].

智能物探技术的过去、现在与未来

通过梳理国内外人工智能技术在地球物理勘探(物探)领域中的发展历程、主要研究进展以及发展方向,总结了智能物探的优势和面临的难题,并提出了解决方案。研究结果表明:(1)物探技术在人工智能发展的第2次浪潮中开始与人工智能技术相结合,得益于物探领域数据量的指数级增长、硬件算力的高速发展以及不断出现的新深度学习框架,智能物探技术从早期的机器学习发展为目前的深度学习,在地震资料处理、解释等方面的应用中取得了大量研究成果。(2)目前智能物探技术被广泛应用于标签集的构建、去噪、断裂检测、层位与层序解释、地震相分类和异常体检测、岩性识别与油气藏开发、地震反演成像等方面,大幅提高了工作效率,降低了工作成本,克服了人工交互操作和人工经验的主观性和不可靠性,助力打破传统物探技术瓶颈。(3)智能物探技术的发展面临着缺少公开的标签数据集、缺少解决地球物理领域问题的智能化框架及尚未形成适用于地球物理领域共享的智能化开发平台等难题,可以从解决数据基础、构建智能平台、开展网络架构基础性研究及与应用场景结合等方面着手解决;此外,智能物探技术的发展方向还包含智能地震成像方法研究,储层成像方法研究,油气大数据挖掘、智能风险评估与智能决策以及超算软件装备研发等方面。

“人工智能+大数据”在医院服务流程管理中的应用与实践

智慧医疗和数字化转型是医疗领域发展的方向。以吉林大学中日联谊医院实践为例,探讨了“人工智能+大数据”在医院精细化服务流程管理中的应用,着重分析其在提升医疗服务水平和满足患者需求方面的潜在优势。通过智慧医疗路径设计和构建精细化智慧管理服务流程的框架,为医院数字化转型提供思路和方法。

基于赛教融合的智能交通课程实践教学研究

结合全国大学生智能汽车竞赛百度智慧交通创意组竞赛项目,设计智能交通课程实践教学内容,从竞赛内容凝练与课程知识点结合的教学案例和实验项目,实现赛教资源融合和赛教一体化实践平台共享。设计的实验教学项目融合了图像处理、数据分析、人工智能、智能车硬件平台等内容,包括数据采集、数据分析、数据集构建,深度学习模型建立与智能车平台部署等实践环节。学生从编写简单程序开始,不断提高,到构建复杂的深度学习模型实现智能车自动巡航控制实验。将竞赛任务具有挑战性和对抗性的特点融入课程教学,吸引学生兴趣,增强学生求知欲,提升学生创新能力和工程实践能力。

基于AIGC协同工业设计流程的气道廓清辅具设计研究与实践

目的设计领域引入蓬勃发展的AIGC技术以期提高效率,在此基础上结合大数据技术和双钻模型,以提高AIGC应用于复杂产品工业设计的质量。方法提出了一种AIGC协同的“1+2”钻工业设计流程模型,通过三次发散、三次收敛来提高AIGC协同工业设计的流程效率与方案质量。首先,在ChatGPT和Python大数据爬取辅助下发散需求问题,在Python高频词分析、竞品分析、专家评审下收敛设计目标;其次,运用Midjourney的Stop参数模糊生图进行创意发散,通过对项目人员问卷调查收敛设计方向;最后,联合使用DALL·E、StableDiffusion和Midjourney发散设计细节,通过焦点小组收敛以确定最终方案并建模渲染。结果实现全面、专业、准确的长期卧床老人气道廓清的需求分析,且辅具设计方案的在用户友好程度、造型美观度、技术可行性和功能可用性方面获得了设计与工程双方专业人员的认可。结论AIGC、大数据与传统工业设计方法相结合的“1+2”钻设计流程,能够通过人工控制AIGC的参考内容、处理AIGC的生成内容,以及阶段性专家评估有效地提升AIGC协同的工业设计方案质量,为规范化的AIGC协同工业设计流程提供思路。

数字孪生在轨道交通电力牵引系统应用的探讨与展望

随着我国轨道交通电力牵引系统的快速发展与技术成熟,其可靠性评估与智能化监控技术逐渐引起关注,数字孪生是基于数据与机器学习对实际物理系统的虚拟刻画技术,可以实现对实际物理系统的行为特征模拟与参数监测,因此将数字孪生技术引入轨道交通电力牵引系统领域,可为其数字化、智能化监控与运维提供发展思路与技术手段。文章首先对数字孪生技术目前在电力牵引系统中的应用现状进行了综述,进而列举了电力牵引系统数字孪生构建过程中所需的关键技术及其发展情况——在电力牵引系统领域,数字孪生及其相关技术仍在理论研究阶段,只有针对部分子系统的探索性研究,尚未形成完善的系统建模与智能监控体系;最后,文章展望了数字孪生技术在电力牵引系统领域的工程化实现前景,探讨了其投入工程应用可能会面临的内部技术问题与外部客观挑战,旨在为后续技术研究与实践提供参考。

视频侦查技术关键及其发展展望

视频侦查技术的核心是通过视频图像的提取、查看、分析和研判来获取侦查线索、固定涉案证据。多年来经过在实战应用中不断地发展创新,视频侦查技术形成了自己独特的关键技术体系:视频信息分析解读技术是侦查应用和证据固定的基础和核心;视频证据固定保全技术的规范是审判中心主义的客观要求,可以获取视频侦查记录报告、视频检验鉴定报告或视频数据关联报告;低质量视频图像的增强恢复技术专业性强,应用范围窄,技术成熟度高,然而它不断面临新的挑战。目前,视频数据的智能应用在大数据背景下变得越来越重要,仍需进一步突破视频自动识别技术的应用范畴,建立完善多层次的视频数据综合应用体系,打造适应不同业务需要的视频数据实战应用模型。

人工智能赋能教育和心理学研究中的数据处理

开展日益复杂的教育和心理学研究亟须创新数据收集和处理手段。人工智能可以帮助研究者收集具有高生态效度、动态、精准的数据,还有助于分析处理海量、多模态的数据,从而弥补传统研究手段的诸多不足。因此,教育和心理学研究与人工智能的结合是未来发展的一大方向。然而在智能化进程中也不能过度依赖数据驱动的研究方法,融合自上而下的理论驱动和自下而上的数据驱动手段至关重要。

人工智能数据采集在慢性乙型肝炎患者真实世界研究中的应用

目的:开发一套慢性乙型肝炎(乙肝)的人工智能(AI)数据采集工具,以解决传统的多中心数据采集效率低下的问题。方法:基于国际通用的数据标准,将AI的文字识别和自然语言处理应用于慢性乙肝真实世界队列研究数据采集,实现多种格式数据(包括图片格式的原始数据)的电子化采集、结构化处理,随后自动将数据填入研究电子数据采集(REDCap)系统中的电子病历报告表(eCRF)。结果:AI工具辅助数据采集与纯人工数据采集具有相同的平均准确率,均达到98.66%(P=0.23),但前者所需时间减少75.49%(P<0.05)。结论:本研究开发的AI数据采集工具可显著提高研究数据采集效率,为真实世界研究数据采集提供了新的模式。

“情景—结构—要素”视角下复杂灾害治理的情报协同体重构

[目的/意义]灾害复杂化给应急治理提出了新的要求,加强多主体情报协同是必然趋势。针对复杂灾害情景构建不足、情报协同网络结构相对松散固化、情报协同要素缺乏一体化布局的问题,文章提出复杂灾害治理情报协同体的概念,围绕情景、结构、要素进行重构。[方法/过程]首先,在情景认知的基础上采用本体构建复杂灾害情景,并描述了其实例化过程。其次,从情报协同主体的挖掘识别与主体关联的凝聚增强两方面阐述了情报协同网络的结构优化方法。最后,探讨了情报协同要素即数据、决策、流程的强化路径,将情报协同体划分为数据共享体、决策集成体、流程弹性体三个关键构成。[结果/结论]文章为复杂灾害治理的情报协同提供了一个顶层设计框架,有助于政府依托数字化转型提升应急情报能力。

矿井智能通风与关键技术研究

为使智能通风系统建设更加有序、可控,提出了矿井智能通风流程环节,将矿井智能通风流程按照生产环节划分为6个板块,即感知监测、分析诊断、智能决策、方案审批、远程集控联控、执行反馈,共包含24个具体环节,建立了各个环节输入输出要素和环节之间的功能逻辑关系。按照“矿井通风系统整体规划+采掘用风区域重点细化”思路,提出了矿井全系统智能通风应用场景实现方案和采煤工作面与掘进工作面2个细化的智能通风应用场景实现方案,将矿井智能通风各个具体环节融入具体的应用场景中。为实现智能通风应用场景,基于逻辑分层思想优化了矿井智能通风系统整体架构,规划了由硬件驱动层、功能模块层、计算处理层、数据存储层、数据采集层构成的矿井智能通风管控平台。针对通风感知监测、分析诊断、智能决策、远程集控联控4个矿井智能通风关键板块中涉及的风量风速监测感知、通风阻力在线监测、全风网风量风压解算、灾源判识和灾变定位、矿井动态需风量计算、通风系统故障诊断、风量按需调控方案决策、应急控风方案决策、无人化远程控风、无人化应急控风10个关键环节,总结分析了目前各个关键环节关键技术现状,提出了各个关键环节关键技术实现路径,通过关键技术迭代升级,最终实现矿井通风系统全生命周期内时刻处于稳定可靠、安全可控、高效节能、应急降灾的运行状态。