Information security has become an important subject in the artificial intelligence filed to handle big data. Most of the systems aim at obstacle detection on ordinary roads. In this paper, we proposed a method for detecting obstacles in a field environment based on convolutional neural network (CNN). Firstly, we propose a region of interest (ROI) extraction algorithm to deal with the suspected obstacle

The probability of occurrence, occurrence time and holding time make the estimation of the multiresource, multidimensional, transmissible and dynamic characteristics of supply-chain risk more valuable to achieving the goal of risk assessment. A dynamic Bayesian network model of supply-chain risk is constructed to describe the property of supply-chain risk; the Bayesian inference tool is then used to

Supply chains now cope with a lot of uncertainties, and their stakeholders are intensely interconnected, revealing new opportunities at a tremendous pace. In this context, companies must rethink their decision support systems to remain competitive. Particularly strategic supply chain capacity planning systems that should ensure resource availability. Unfortunately, existing systems do not satisfactorily

The aim of this paper is to describe a solution suitable for the automation of standard pollen information service (EN 16868:2019). We are describing the RealForAll integrated information system developed for automatic airborne pollen detection and real-time data delivery to end-users. This solution is based on the measurements from the Rapid-E airborne particle monitor. The system incorporates an

This paper proposes a method for knowledge-based document assembly. A document assembly system is implemented as a proof of concept with service contracts as a sample document type. In comparison to related research, the method presented in this paper uses an explicit formulation of legal norms that prescribes the content and the form of service contracts to assist in the document assembly process

ABSTRACT This research aims at investigating the critical factors that promote users in protecting the Bring Your Own Device (BYOD) information security. Perceived value serves as the core variable and integrates the Technology Threat Avoidance Theory and the Value-based Adoption Model to propose an integrated model. The questionnaire survey employed to verify the hypotheses. The results show that

In order to improve the detection rate of pedestrian, a novel technique that is based on hybrid Gaussian background modeling combined with HOG and SVM is proposed. The random video frame test sample is used to verify the performance of the model. The results show that under the condition of ensuring the detection rate and detection rate, the false detection rate of the hybrid Gauss combined with the

The paper’s goal is to propose an IoT assisted Cyber-Physical System with a fault detection technique using a fuzzy algorithm for the supply chain management (SCM). Mathematical models are important for detecting faults. Devicescan contribute to device vulnerabilities. Propertiesof the components in an embedded application can identify defective components in cyber systems of SCM. In this paper linear

Food retailer’s grading and selection is an essential process for determining the consumer priceand guaranteeing the quality before launching to the market. Such a grading process, however, often relies on human expertise for making a subjective judgement. This paper proposes a hybrid approach using fuzzy analytic hierarchy process for determining weights of evaluation criteria and TOPSIS (Technique

This paper proposes anew architecture for wide area networks. The architecture is based on the concept of independent islands connected via adynamically reconfigured core. Reconfiguration can take place at the level of the physical layer and data link layer, which forces the reconfiguration of other network protocols. During normal network operation, the currently available alternative connections

ABSTRACT Survey data were collected from 179 rural strategic decision-makers in Hunan Province, China. The results show that the emotional energy has a significant long-term impact on rural tourism enterprises. Emotional energy is based on group solidarity, and to further explore the rational realization mechanism of group unity, the Stackelberg model and the Shapley value are used to obtain the cooperative

Coupling a production scheduling process with maintenance logs can provide important advantages. For instance, this enables the adaptation of planning to the reality of the shop floor. Nevertheless, maintenance logs are often highly unstructured, as they mainly rely on free-form text comments from operators, and are imbalanced, as commonplace issues happen more often than critical problems. This hinders

ABSTRACT This study aims to investigate how Twitter has been used during an international product recall. Based on the SMCC model and the Crisis Response framework, the study proposes a new crisis communication model (SBCC) to analyse the 2016 Mars product recall tweet dataset. The study finds that the platform has mainly been used to ask questions and spread negative information from the news media

Presently, Large communication energy is required for the entire project planning system in automation industries. This paper suggests the loss of energy efficiency modeling based on the Multiple Fuzzy Aggravated Energy Scheduling Approach (MFAESA). The Multiple Fuzzy Algorithms Energy Scheduling Approach in assistance with IoT setting builds up and incorporates the fuzzy algorithm in a single objective

ABSTRACT A symbiotic simulation system (S3) enables interactions between a physical system and its computational model representation. To support operational decisions, an S3 uses real-time data from the physical system, which is gathered via sensors and saved in an enterprise data storage system (EDSS). Both real-time and historical data are then used as inputs to the different components of an S3

Based on the analysis of the internal control theory of Listed Companies in China and the United States, it is found that there are some differences in the definition, objectives and elements of internal control between China and the United States. The analysis shows that the internal control of Listed Companies in China is generally effective from 2013 to 2017, but it is decreasing year by year. Comparing

To improve human action recognition performance of visual data, we proposed Hybrid Sampling Ensemble Learning method. 1)define the curvature distance distribution to fit discrete images into continuous expandable surfaces. 2)obtain density-weighted curvature distance of the images through class imbalance adjustment. 3)use auto-regressive classification tree strategy by utilizing the hierarchical regress

This paper sets supply chain buyback contract model with retailer's complete rationality and fairness concern respectively under stochastic demand, and uses Bayesian theorem to solve retailer's two-stage order decision under demand updating, so as to analyze the influence of retailer's fairness concern on the optimal order decision and the coordination of the buyback contract. The results show that

This study provides empirical rationale and guidance for incorporating investor sentiment into mutual fund enterprise information systems. It investigates the effect of fund-specific investor sentiment on fund risk taking and performance. Working on a sample of equity funds in China, our panel regressions reveal that fund risk-taking is negatively related to lagged fund-specific investor sentiment

Sharing bicycles, as boosted by the advanced mobile technologies, is expected to mitigate the traffic congestion and air pollution issues in China. A survey study was conducted with 335 valid samples to identify the key factors that influence the customers' intention of use for bike-sharing system and quantify the corresponding importance. Five machine learning techniques for classification are applied

Recent works in image perception and multimedia technology have paved the way for automated analysis of visual arts. Intelligent painting based on image perception, processing and identification in multimedia enterprise is the trend. In this paper, we use a Cross- Contrast Neural Network (CCNN) model to automatic art identification in oil painting. To achieve this point, we first retrained a tailored

From last decade, machine learning (ML) techniques have been used for Urdu text processing. Due to lack of language resources, potential of deep learning (DL) models have not been exploited yet for Urdu text document classification. A text document has more noise, redundant information, and large vocabulary than short text like tweets. This study is the systematic comparison of four well-known DL models

Objective: To reduce the effects of light changes, scale changes, local occlusion and other factors during target tracking, a kernel-correlation filtering (KCF) target tracking algorithm is introduced, which introduces the target block model. Results: Comparative experiments of multiple mainstream algorithms on multiple data sets. Experimental results show that the algorithm has the highest accuracy

ABSTRACT A platform offering web technologies and interoperable components is proposed, allowing integration of different technologies into a robust system. Key modules are provided in home, to support integration of IoT devices, and in the cloud, offering centralised services and storage. Communication between the two is performed using the open FIWARE-Orion protocol. Data are not tied to methods

The selection and evaluation of solid rocket multi-stage combined schemes with multiple attributes are main issues needed to be resolve. This paper innovatively applied the power generalised compensative weighted averaging (PGCWA) aggregation operator to help multi-stage combined solid rocket select optimal compositional scheme among multiple schemes under multi-attribute environment. The attribute

We consider a service-oriented supply chain consisting of a manufacturer and an operator both with fairness concerns. The manufacturer provides equipment maintenance by choosing an optimal maintenance service level to maximise its profit, which may reduce the profit of the operator and the efficiency of the supply chain. We initially establish optimisation models with fairness concerns, and then a

We present the architecture and the usability testing of a novel cloud-based platform, which integrates cyber-physical systems and interoperability standards enabling a clinical decision support system for risk stratification, diagnosis, prognosis and treatment of CAD. In this work multi-disciplinary human data were used for the development of machine learning and computational biomechanics based predictive

ABSTRACT Process mining can be used to discover different variants of a business process. To optimise the performance of the process, the best variant needs to be identified. However, process performance is multi-dimensional and how these dimensions weigh out against each other to find the best performing process is often unclear. This paper proposes to use conjoint analysis and regression analysis

Recently, many financial institutions have found their way to communicate with customers with Social Network Services (SNS) applications. Previous studies shown that active SNS activities of companies have positive effects on customer relationship. Yet little is known of which factors affect customer satisfaction and retention on SNS usage. In this study, we conducted a survey with 169 individuals

Artificial intelligence is increasingly used in advanced manufacturing systems to realise intelligent manufacturing. However, there is still a lack of empirical research on the impact of intelligent manufacturing on enterprise performances, especially for China. The author adopts the enterprise panel data of intelligent manufacturing implemented by China’s manufacturing industry in 2014 to 2019, and

Production environments are becoming more complex and dynamics. This is influenced by external factors related with products’ characteristics and costumers’ requirements and internal factors related with processing times variability, machine failures, setup times, between others. To face this increasing complexity and dynamics, it is crucial to have effective production control methods, considering

ABSTRACT Understanding the developmental trajectories of big data analytics in the corporate context is highly relevant for information systems research and practice. This study presents a comprehensive bibliometric analysis of applications of big data analytics in enterprises. The sample for this study contained a total of 1727 articles from the Scopus database. The sample was analyzed with techniques

To better forecast the security in supply-demand management of Chinese forestry enterprises and close the supply-demand gap due to short timber supply, the linear weighted method and artificial neural network (ANN) are jointly applied to forecast the security in supply-demand of the forestry industry. The theories of supply-demand management and early-warning systems are clarified. Indexes in the

Cloud computing has attracted many enterprises to migrate or deploy their applications into the cloud platform so as to reduce their operational costs. In this paper, we investigate the reasonable resource allocation for migrating enterprise applications to the cloud. We first formulate a generalisation form of utility maximisation model for resource allocation of enterprise applications migration

The purpose of this study is to examine the effect of technological boundary-spanning search and crowdfunding interaction on crowdfunding innovation performance. The study investigated technology-oriented innovative crowdfunding projects on three major Chinese crowdfunding platforms. A hierarchical regression analysis is applied to explore the model’s hypotheses. The results show that crowdfunding

Enterprises are increasingly using big data analytics and intelligence to solve business processes between original equipment manufacturers (OEMs) and original design manufacturers (ODMs) to increase the competitiveness and improve the efficiency of solutions. This research applies a cloud computing-based enterprise resource planning (ERP) system and OEM/ODM system to business to business (B2B) e-commerce

The purpose of this study is to explore the intelligent oil well identification and model construction, so as to make the identification of oil well more intelligent. The convolutional neural network (CNN) algorithm in the deep learning algorithm is used to construct the recognition model of oil well function diagram, the collected original data are gradually converted into standardised binary images

This paper addresses the pricing policies of substitutable fresh food products under different market structures. By considering the quality changes of fresh products over time, these paper models a situation wherein substitutable fresh products are sold and the seller makes decisions regarding the times to markdown prices and offer discount rates. Furthermore, the standard and two-level evolution

Recently, solution of discretisation operator technique with circular (DOTWC) approach, and runge-kutta implicit are presented for the Eigen efficient analysis, in this paper based on the various surveys it has been analysed that the efficiency is considered as low and computational burden terms to be high. Henceforth, the implicitly of the restarted Arnoldi (IRA) with intelligent physical system (IPS)

To effectively protect sensitive information, this paper proposes a method of text Emotional modulation steganography based on machine learning. Firstly, we explore an intelligent dynamic expansion method for text emotional lexicon based on deep learning in detail. Secondly, the cosine similarity algorithm is used to combine the two most similar emotional words into emotional word pairs, which is the

To establish a business model of intelligent manufacturing, the sequence Generative Adversarial Network (SeqGAN) was used to optimise the Back Propagation (BP) neural network algorithm improved by multi-objective Genetic Algorithm to propose the sequence Generative Adversarial Network-Genetic Algorithm Back Propagation Algorithm (SeqGAN-GABP). Meanwhile, the Elman algorithm was optimised by the SeqGAN

This article studies the application of fuzzy logic to the risk analysis of a new software product development and marketing in specific case of a small size IT company. Identification and analysis of external and internal risk factors show that this type of business activity could be evaluated as high-risk enterprise. So, the purpose of the paper is to develop robust method to evaluate probability

In next-generation high-speed networks, Elastic Optical Networks (EONs) play a promising role due to its more flexibility and optimal spectrum management. Some of the key facts of EON that have to be addressed are Routing and Spectrum allocation. In this paper, an efficient routing algorithm is proposed along with optimization of spectrum allocation for EON. Improved Bellman Floyd Warshall (IBFW) shortest

Precision agriculture involves manipulation of variations in field productivity, maximization of income, scale backing of wastes, and minimizing of the impact on surroundings using automated machine-controlled information assortment and documentation. This work focuses on the efficient control of farm irrigation by exploiting the capabilities of Internet of Things (IoT) and Big Data-based Decision

Fog computing architecture is used in various environments such as smart manufacturing, vehicular ad hoc networks. However, as an extension of cloud computing, inheriting security challenges of cloud computing is inevitable. Recently, Jia et al. proposed an authenticated key exchange scheme for fog-driven IoT health care systems. Unfortunately, we discovered their scheme is vulnerable to an ephemeral

This paper analyses how to improve the production efficiency and organisational management level of Chinese family intelligent manufacturing enterprises under the environment of big data and information integration, and ultimately enhance the economic benefits of enterprises. By reforming the organisational structure of intelligent manufacturing enterprises, in the environment of intelligent manufacturing

The issuance and implementation of intellectual property policies have promoted the rapid development of intellectual property intermediary services in China, bringing new opportunities and challenges for public sectors of the government. With their continuous development, Internet of Things (IoT) technology and big data have become the analytical tools widely applied in many technical fields. Through

A hybrid model based on latent factor model (LFM) and deep forest algorithm, namely multi-Grained Cascade forest (gcForest) was established to optimise and integrate the key recruitment links in the human resource system of intelligent manufacturing industry. The LFM mainly analysed the browsing, application, collection and other aspects of data of job users, and the gcForest mainly analysed the matching

In this paper, ant colony optimization algorithm is used, and then the records in the supply and demand documents in the material requirement planning (MRP) are used to simulate the city points that the salesperson moves, so that the artificial ants can move between cities. To find the shortest path through all cities, that is, to find the shortest path of MRP in the main file of supply and demand

This paper proposed an integrated architecture and case study highlighting practices for developing cloud computing system in smart manufacture. It developed an electronic purchase order web-based system with four business units. The research method is based on applying Rational Unified Process and ICAM DEFinition Model (IDEF). It uses scenario and IDEF model to represent the user requirements, and

This study aims to evaluate the performance of the machine tool industry in Taiwan between 2010 and 2014 by using a dynamic network data envelopment analysis (DN-DEA) model. Taiwanese machine tool industry had an improvement in productivity from 2010 to 2014. Under the two-stage DEA model, we find that productivity in the production and market stage represent a rapid growth, and the productivity growth

An important part of a rapid response to spacecraft faults is obtaining information efficiently and accurately determining the cause of the faults. The cause may originate from any stage in the life cycle. This study aims to integrate spacecraft information using fusion technologies to construct a whole life cycle knowledge graph. A human-computer interface for spacecraft rolling bearing fault diagnosis

In recent years the range of channels for customers to acquire products has generally expanded. The Smart-X system plays an essential role in pricing strategies, as fairness concerns could impact the price significantly. When customers in the BM store have concerns, the firm is induced to lower product price in the store, resulting in total profit reduction. When customers do not have fairness concerns

ABSTRACT By adopting the Decision-Usefulness theory, this study investigates separately and jointly the impact of utilising Enterprise Resources Planning system (ERPs) and the information disclosure of Segmental Reporting (SR), following the implementation of IFRS-8, on Corporate Performance (CP) in the UK context. The research was drawn on the Financial-Times-Stock-Exchange (FTSE)-100 over the period

In recent years, the model of improved GAN has been widely applied in the field of machine vision. It not only covers the traditional image processing, but also includes image conversion, image synthesis and so on.. Firstly, this paper describes the basic principles and existing problems of GAN, then introduces several improved GAN models, including Info-GAN, DC-GAN, f-GAN, Cat-GAN and others. Secondly

The optimisation process and results are classified and stored to guide the future workshop scheduling and improve the retrieval efficiency. The results show that the random inertia weight strategy is added to the standard particle swarm optimisation (PSO) algorithm. The idea of crossover and mutation in genetic algorithm (GA) is introduced to increase the diversity of population and prevent it from

An effective crisis response requires up-to-date information. The crisis cell must reach for new, external, data sources. However, new data lead to new issues: their volume, veracity, variety or velocity cannot be managed by humans only, especially under high stress and time pressure. This paper proposes (i) a framework to enhance situation awareness while managing the 5Vs of Big Data, (ii) general

Process-oriented organisations need to manage the different types of responsibilities their employees may have w.r.t. the activities involved in their business processes. Despite several approaches provide support for responsibility modelling, in current Business Process Management Systems (BPMS) the only responsibility considered at runtime is the one related to performing the work required for activity