Integration Of Different Models Research Articles

Exploring the Factors of Online Social Networks (OSNs) on Individual Investors’ Capital Market Investment Decision: An Integrated Approach

Online social networks (OSNs) are a terrifically emerging platform for information dissemination around the world. Like other settings, acceptance and adoption of OSNs among the individual capital market investors are extensive. The study developed a conceptual model for behavioural finance integrating a technology acceptance model (TAM) and valence framework from the information systems and marketing disciplines, respectively. The integrated model added some persuasive constructs from social capital and diffusion innovation theory with a view to explore the key factors swaying investors’ intention to adopt and use the OSN’s services. By using an online and offline structured questionnaire, 510 data were collected from individual capital market investors in Bangladesh. Structural Equation Modelling (SEM) was used for data analysis. The study determined that the proposed integrated model with additional constructs outperformed other models. Perceived usefulness (PU), perceived enjoyment (PE), trust and personal innovativeness in IT (PIIT) had a substantial sway on the investor’s intention to use OSNs. Hedonic value is more robust predictor of intention to use OSNs than utilitarian value. Intention to use properly mediated the relationships and had strong significant impact on investor’s investment decision. But perceived ease of use (PEOU) and perceived risk had no direct significant effect on intention to use. PEOU had significant impact on intention to use through PU and PE. Gender moderated the relationships of different constructs with the intention to use OSNs for investment decisions in the capital market. It contributes knowledge by including the integration of different models in stock market perspectives and the inclusion of technological aspect in the behavioural finance literature. The findings of the study will also succor different firms and regulatory authorities to adopt OSNs as an information dissemination platform.

Unraveling the Key Factors of Successful ERP Post Implementation in the Indonesian Construction Context

Aim/Purpose: This study aims to evaluate the success of ERP post-implementation and the factors that affect the overall success of the ERP system by integrating the Task Technology Fit (TTF) model into the Information System Success Model (ISSM). Background: Not all ERP implementations provide the expected benefits, as post-implementation challenges can include inflexible ERP systems and ongoing costs. Therefore, it is necessary to evaluate the success after ERP implementation, and this research integrates the Task Technology Fit (TTF) model into the Information System Success Model (ISSM). Methodology: For data analysis and the proposed model, the authors used SmartPLS 3 by applying the PLS-SEM test and one-tailed bootstrapping. The researchers distributed questionnaires online to 115 ERP users at a construction company in Indonesia and successfully got responses from 95 ERP users. Contribution: The results obtained will be helpful and essential for future researchers and Information System practitioners – considering the high failure rate in the use of ERP in a company, as well as the inability of organizations and companies to exploit the benefits and potential that ERP can provide fully. Findings: The results show that Perceived Usefulness, User Satisfaction, and Task-Technology Fit positively affect the Organizational Impact of ERP implementation. Recommendations for Practitioners: The findings can help policymakers and CEOs of businesses in Indonesia’s construction sector create better business strategies and use limited resources more effectively and efficiently to provide a considerably higher probability of ERP deployment. The findings of this study were also beneficial for ERP vendors and consultants. The construction of the industry has specific characteristics that ERP vendors should consider. Construction is a highly fragmented sector, with specialized segments demanding specialist technologies. Several projects also influence it. They can use them to identify and establish several alternative strategies to deal with challenges and obstacles that can arise during the installation of ERP in a firm. Vendors and consultants can supply solutions, architecture, or customization support by the standard operating criteria, implement the ERP system and train critical users. The ERP system vendors and consultants can also collaborate with experts from the construction sector to develop customized alternatives for construction companies. That would be the most outstanding solution for implementing ERP in this industry. Recommendation for Researchers: Future researchers can use this combined model to study ERP post-implementation success on organizational impact with ERP systems in other company information systems fields, especially the construction sector. Future integration of different models can be used to improve the proposed model. Integration with models that assess the level of Information System acceptance, such as Technology Acceptance Model 3 (TAM3) or Unified Theory of Acceptance and Use of Technology 2 (UTAUT2), can be used in future research to deepen the exploration of factors that influence ERP post-implementation success in an organization. Impact on Society: This study can guide companies, particularly in the construction sector, to maintain ERP performance, conduct training for new users, and regularly survey user satisfaction to ensure the ERP system’s reliability, security, and performance are maintained and measurable. Future Research: It is increasing the sample size with a larger population at other loci (private and state-owned) that use ERP to see the factors influencing ERP post-implementation success and using mixed methods to produce a better understanding. With varied modes, it is possible to get better results by adding unique factors to the research, and future integration of other models can be used to improve the proposed model.

Review of Crop Yield Estimation using Machine Learning and Deep Learning Techniques


 
 
 The agriculture sector is subjected to constant challenge of yield deficit due to rising population, improper resource management and shrinking agricultural land. Advance yield estimates help in systematic planning to reduce such losses. However, prediction of accurate estimates is still an open challenge due to geographical diversity, crop diversity and crop area. Recently non-destructive approach has gained attention due to its robustness and provides easy availability of data from heterogeneous resources compared to its counterpart; destructive approach which is computational, resource intensive and hence less utilized. This paper conducts a detailed study on utilization of non-destructive approach to estimate yield taking into account, input feature, and methodology. We consider five major observations namely, data acquisition, pre-processing techniques, features, methodology, and result. Moreover, we summarize analysis of each observation, extract most prominent technique, the adopted methods, and finally recommends integration of different models that can be explored to improve accuracy.
 
 

Large-Scale Landslide Susceptibility Mapping Using an Integrated Machine Learning Model: A Case Study in the Lvliang Mountains of China

Integration of different models may improve the performance of landslide susceptibility assessment, but few studies have tested it. The present study aims at exploring the way to integrating different models and comparing the results among integrated and individual models. Our objective is to answer this question: Will the integrated model have higher accuracy compared with individual model? The Lvliang mountains area, a landslide-prone area in China, was taken as the study area, and ten factors were considered in the influencing factors system. Three basic machine learning models (the back propagation (BP), support vector machine (SVM), and random forest (RF) models) were integrated by an objective function where the weight coefficients among different models were computed by the gray wolf optimization (GWO) algorithm. 80 and 20% of the landslide data were randomly selected as the training and testing samples, respectively, and different landslide susceptibility maps were generated based on the GIS platform. The results illustrated that the accuracy expressed by the area under the receiver operating characteristic curve (AUC) of the BP-SVM-RF integrated model was the highest (0.7898), which was better than that of the BP (0.6929), SVM (0.6582), RF (0.7258), BP-SVM (0.7360), BP-RF (0.7569), and SVM-RF models (0.7298). The experimental results authenticated the effectiveness of the BP-SVM-RF method, which can be a reliable model for the regional landslide susceptibility assessment of the study area. Moreover, the proposed procedure can be a good option to integrate different models to seek an “optimal” result.

Continuous low-frequency EEG decoding of arm movement for closed-loop, natural control of a robotic arm

Objective. Continuous decoding of voluntary movement is desirable for closed-loop, natural control of neuroprostheses. Recent studies showed the possibility to reconstruct the hand trajectories from low-frequency (LF) electroencephalographic (EEG) signals. So far this has only been performed offline. Here, we attempt for the first time continuous online control of a robotic arm with LF-EEG-based decoded movements. Approach. The study involved ten healthy participants, asked to track a moving target by controlling a robotic arm. At the beginning of the experiment, the robot was fully controlled by the participant’s hand trajectories. After calibrating the decoding model, that control was gradually replaced by LF-EEG-based decoded trajectories, first with 33%, 66% and finally 100% EEG control. Likewise with other offline studies, we regressed the movement parameters (two-dimensional positions, velocities, and accelerations) from the EEG with partial least squares (PLS) regression. To integrate the information from the different movement parameters, we introduced a combined PLS and Kalman filtering approach (named PLSKF). Main results. We obtained moderate yet overall significant (α = 0.05) online correlations between hand kinematics and PLSKF-decoded trajectories of 0.32 on average. With respect to PLS regression alone, the PLSKF had a stable correlation increase of Δr = 0.049 on average, demonstrating the successful integration of different models. Parieto-occipital activations were highlighted for the velocity and acceleration decoder patterns. The level of robot control was above chance in all conditions. Participants finally reported to feel enough control to be able to improve with training, even in the 100% EEG condition. Significance. Continuous LF-EEG-based movement decoding for the online control of a robotic arm was achieved for the first time. The potential bottlenecks arising when switching from offline to online decoding, and possible solutions, were described. The effect of the PLSKF and its extensibility to different experimental designs were discussed.

The challenges of air quality modelling when crossing multiple spatial scales

Multiscale air quality assessment implies understanding the interaction among atmospheric processes and scales. In this perspective, the use of air quality models has a fundamental role and the way they address these interactions is very important for the quality of results. However, in multiscale air quality modelling, the relationship between models, simulation domains and resolutions remains a challenging research issue. This paper presents a state-of-the-art review on multiscale air quality modelling applications from the regional to the street level, identifying which models are used, the methodological principles and the required input datasets. Based on the findings, an analysis of the current limitations associated with the integration of different models and multiple spatial scales in a single modelling system is presented and discussed. Lastly, taking as support the reviewed contents, a set of guidelines for strengthening the synergy among scales and harmonizing different types of models within a system is proposed. Unsuitable or non-existent urban canopy parametrizations (UCP), limited grid resolutions, discarded microscale impacts on upper domains, inadequate input data and simplified chemistry are some important aspects contributing to large uncertainties when analyzing multiscale air quality results. To overcome these shortcomings in current multiscale modelling systems, more research aimed at improving the modelling performance is required, focusing on (i) UCP coupled to mesoscale models, (ii) developing modelling systems with two-way nesting capability to boost feedbacks among domains and (iii) promoting the use, improvement and development of multiscale online modelling systems, in order to have a comprehensive multiscale understanding of all atmospheric processes that govern the transport, dispersion, transformation and deposition of air pollutants.

Integrated Modeling of Structural Genes Using MCuNovo.

Correct modeling of protein-coding genes based on genome and cDNA data is a prerequisite for functional studies. Various programs such as MAKER, Cufflinks, Oases, and Trinity have been developed, each with advantages and drawbacks. Manual integration of different models for a single gene is cumbersome and becomes a daunting task for 14,000-18,000 genes in a typical holometabolous insect. We developed methods to evaluate the output of MAKER, Cufflinks, Oases and Trinity and select the best models to constitute the MCOT1.0 set for Manduca sexta, a biochemical model insect. To apply these methods in other organisms, we improved the algorithm (designated MCuNovo Gene Selector) and automated the data processing. In this chapter, we describe background information of algorithm development and how to prepare and run this program.

Evaluation of Freight Measures by Integrating Simulation Tools: The Case of Volos Port, Greece

Abstract Simulation modelling tools have been widely adopted for the evaluation of alternatives in transport planning, management and logistics. The complexity that underlies in transport systems and logistics necessitate the integration of different models that are capable of overcoming limitations that may exist individually to each model. Towards this direction, this paper aims to integrate two simulation software and use the integrated model for the evaluation of traffic and logistics measures in the wider area of Volos Port, Greece. The built model is able to simulate the traffic conditions on a transport network along with port’s intra-logistics processes and is used to evaluate a set of measures in the year 2030, by comparing it with the situation in the year 2030 without having implemented any new measure. For the evaluation, a set of indicators is used to gauge the environmental and transport impacts. The analysis is completed by using a multi-criteria decision making tool to generate the Logistics Sustainability Index (LSI) to summarize the information that is provided by the indicators. The results show that the use of integrated simulation models can provide a holistic impact evaluation of complex decisions with a high level of accuracy.

A Conceptual Design and Modeling Framework for Integrated Additive Manufacturing

Modeling and simulation for additive manufacturing (AM) is commonly used in industry. Nevertheless, a central issue remaining is the integration of different models focusing on different objectives and targeting different levels of details. The objective of this work is to increase the prediction capability of characteristics and performances of additively manufactured parts and to co-design parts and processes. The paper contributes to this field of research by integrating part's performance model and additive technology process model into a single early integrated model. The paper uses the dimensional analysis conceptual modeling (DACM) framework in an AM perspective to generate causal graphs integrating the AM equipment and the part to be printed. DACM offers the possibility of integrating existing knowledge in the model. The framework supported by a computer tool produces a set of governing equations representing the relationships among the influencing variables of the integrated model. The systematic identification of the weaknesses and contradictions in the system and qualitative simulation of the system are some of the potential uses of the model. Ultimately, it is a way to create better designs of machines and parts, to control and qualify the manufacturing process, and to control three-dimensional (3D) printing processes. The DACM framework is tested on two cases of a 3D printer using the fused filament fabrication (FFF) powder bed fusion. The analysis, applied to the global system formed of the 3D printer and the part, illustrates the existence of contradictions. The analysis supports the early redesign of both parts and AM process (equipment) and later optimization of the control parameters.

Expanding scope and computational challenges in process scheduling

In this paper, we present a brief overview of enterprise-wide optimization and challenges in multiscale temporal modeling and integration of different models for the levels of planning, scheduling and control. Next, we review Generalized Disjunctive Programming (GDP), as a new modeling paradigm for scheduling problems that are illustrated with the STN and RTN models. We then address scheduling problems that expand the scope of the area: simultaneous scheduling and heat integration, pipeline scheduling, crude oil and refined products blending, and demand side management. We illustrate the advantage of the GDP modeling framework, describe effective strategies for global optimization, and describe multistage affinely adjustable robust optimization for uncertain interruptible load. We address integration of planning and scheduling, for which several approaches are reviewed, including use of traveling salesman constraints for multiperiod refinery planning, and multisite planning and scheduling of multiproduct batch plants. We report computational results to highlight the challenges.

Integration of Tuyere, Raceway and Shaft Models for Predicting Blast Furnace Process

A novel modeling strategy is presented for simulating the blast furnace iron making process. Such physical and chemical phenomena are taking place across a wide range of length and time scales, and three models are developed to simulate different regions of the blast furnace, i.e., the tuyere model, the raceway model and the shaft model. This paper focuses on the integration of the three models to predict the entire blast furnace process. Mapping output and input between models and an iterative scheme are developed to establish communications between models. The effects of tuyere operation and burden distribution on blast furnace fuel efficiency are investigated numerically. The integration of different models provides a way to realistically simulate the blast furnace by improving the modeling resolution on local phenomena and minimizing the model assumptions.

Reinforcing the applicability of multi-model environments for software process improvement using knowledge management

Nowadays software development organizations look for tools and methods that help them maintain their competitiveness. A key approach for organizations in order to achieve this competitiveness is a successful implementation of software process improvement (SPI). Unfortunately, most of the times, software process improvement involves a path full of obstacles due to the lack of knowledge for choosing the right implementation. The most common and critical problem consists of the selection and application of the right reference model for guiding this implementation. As an effort for helping organizations in the selection of the right implementation of improvements, multi-model environments arised enabling the use of best practices from different reference models. Multi-model approach facilitates the improvement task in order to achieve the organization's business goals. In this context, effective integration of models and standards can play a crucial role in the implementation of multi-model environments as reference support tool. Nevertheless the use of multi-model approaches presents difficulties related to the lack of knowledge of how to manage the amount of information and the correct integration of different models and standards. In this sense, knowledge management technologies have proven to be highly promising support for knowledge sharing and system integration. This work presents an ontological framework based on a multi-model approach, which facilitates and supports the SPI for small and medium companies for a life cycle process improvement. Life cycle process improvement pursues the necessary actions in a deliberate, structured and methodical manner, required in each stage of the life cycle of software development, capable for improving process to current organization needs. Finally, a case study is presented in order to show the performance of the framework.

The new hybrid rule-based tool to evaluate processes in manufacturing

The aim of our study was to verify if rule-based reasoning systems could be successfully applied for integration of different models and tools which are used for solving complex decision problems in technological design. Engineering problems are unique and differ from typical problems in the domain of management. To solve those problems, an iterative search of the most suitable solutions must be carried out. This puts a pressure on researchers to utilize optimization techniques in connection with simulation methods. Our research is focused on the usage of rule-based reasoning systems for solving simple decision problems, and their integration with highly-specialized tools. This research has been conducted at one of metal foundries, within the scope of supporting technological decisions. A dedicated platform was used in the research, which is tailored for such applications, i.e., Business and Technological Rules Management System REBIT. REBIT system has been developed at the Faculty of Management at the AGH University of Science and Technology in Cracow. In this paper, we prove that the rule-based approach could provide means to integrate all stages of technological design. This kind of approach has been successfully applied in the Business Rules Management Systems.

A new logit‐artificial neural network ensemble for mode choice modeling: a case study for border transport

SummaryLogit model is one of the statistical techniques commonly used for mode choice modeling, while artificial neural network (ANN) is a very popular type of artificial intelligence technique used for mode choice modeling. Ensemble learning has evolved to be very effective approach to enhance the performance for many applications through integration of different models. In spite of this advantage, the use of ANN‐based ensembles in mode choice modeling is under explored. The focus of this study is to investigate the use of aforementioned techniques for different number of transportation modes and predictor variables. This study proposes a logit‐ANN ensemble for mode choice modeling and investigates its efficiency in different situations. Travel between Khobar‐Dammam metropolitan area of Saudi Arabia and Kingdom of Bahrain is selected for mode choice modeling. The travel on this route can be performed mainly by air travel or private vehicle through King Fahd causeway. The results show that the proposed ensemble gives consistently better accuracies than single models for multinomial choice problems irrespective of number of input variables. Copyright © 2015 John Wiley & Sons, Ltd.

Integration of complex language models in ASR and LU systems

Throughout this work, we explore different methods to integrate a complex Language Model (a hierarchical Language Model based on classes of phrases) into an automatic speech recognition (ASR) system. First of all, an integrated architecture is considered, where the integration is carried out via the composition of the different Stochastic Finite-State Automata associated with the specific Language Model (LM). On the other hand, a decoupled architecture with a two-pass decoder is employed, where the complex LM is used to reorder the N-best list. The formal definition of both methods is provided in this work, thus enabling the theoretical comparison between them. Additionally, different experiments were carried out to compare empirically the proposed approaches. The results show that although the hierarchical LMs outperform a baseline word-based LM in both cases, the integrated architecture can provide better ASR system performance. However, the decoupled architecture could be more versatile due to the two-pass strategy, allowing the integration of different models using a standard decoder. Additionally, the use of this kind of complex LMs can also be extended to other NLP applications, such as language understanding, by employing the proposed architectures.

An integrated, multi-scale modelling approach for the simulation of multiphase dispersion from accidental CO2 pipeline releases in realistic terrain

The deployment of a complete carbon capture and storage chain requires a focus upon the hazards posed by the operation of pipelines transporting carbon dioxide (CO2) at high pressure in a dense-phase (supercritical or liquid state). The consequences of an intentional or accidental release from such pipelines must be considered as an integral part of the design process. There are a number of unique challenges to modelling these releases due to the unusual phase-transition behaviour of CO2. Additionally, few experimental observations of large-scale CO2 releases have been made, and the physics and thermochemistry involved are not fully understood. This work provides an overview of elements of the EC FP7 CO2PipeHaz project, whose overall aim is to address these important and pressing issues, and to develop and validate mathematical models for multiphase discharge and dispersion from CO2 pipelines. These are demonstrated here upon a full-scale pipeline release scenario, in which dense-phase CO2 is released from a full-bore 36-in. pipeline rupture into a crater, and the resulting multiphase CO2 plume disperses over complex terrain, featuring hills and valleys. This demonstration case is specifically designed to illustrate the integration of different models for the pipeline outflow, near-field and far-field dispersion.

Integration of different models in the design of chemical processes: Application to the design of a power plant

With advances in the synthesis and design of chemical processes there is an increasing need for more complex mathematical models with which to screen the alternatives that constitute accurate and reliable process models. Despite the wide availability of sophisticated tools for simulation, optimization and synthesis of chemical processes, the user is frequently interested in using the ‘best available model’. However, in practice, these models are usually little more than a black box with a rigid input–output structure. In this paper we propose to tackle all these models using generalized disjunctive programming to capture the numerical characteristics of each model (in equation form, modular, noisy, etc.) and to deal with each of them according to their individual characteristics. The result is a hybrid modular–equation based approach that allows synthesizing complex processes using different models in a robust and reliable way. The capabilities of the proposed approach are discussed with a case study: the design of a utility system power plant that has been decomposed into its constitutive elements, each treated differently numerically. And finally, numerical results and conclusions are presented.

The Impact of Life Events on Emotional Reactions and Behavior Options: Theory Comparison and Research Implications

Regarding the impact of life events on individual's emotional reactions and behavior options, all the studies have tried to explain the mechanism of life events impacting on individuals from the perspective of relation between different life events and behavior decision-making, while different theories have different interpretations. Behavior/Economic Model regard people as "absolutely rational", while Averaging/Summation Model, Peak-End Rule and Mental Accounting Model regard people as "bounded rational". By detailed comparison of the latter three theories, we find that they are different from the exploring perspectives, the definition of life events and the choice of research methods. Future research should expand on the following aspects, such as discrimination and integration of different models, the interaction between different attributions of life events and individuals' as well as the diversification of research methods, etc.

Fuzzy artificial neural network (p, d, q) model for incomplete financial time series forecasting

Improving forecasting especially time series forecasting accuracy is an important yet often difficult task facing forecasters. Both theoretical and empirical findings have indicated that integration of different models can be an effective way of improving upon their predictive performance, especially when the models in the hybridization are quite different. In the literature, several hybrid techniques have been proposed by combining linear and nonlinear models, in order to overcome the deficiencies of single models and yield results that are more accurate. However, recent research activities in hybrid linear and nonlinear models indicate that these models have two basic limitations that have decreased their popularity for time series forecasting. These two basic limitations are: a the hybrid linear and nonlinear models have some assumptions that will degenerate their performance if the opposite situations occur, and b the hybrid linear and nonlinear models require a large amount of historical data in order to produce accurate results. In this paper, a novel hybrid model is proposed for time series forecasting by combining linear autoregressive integrated moving average ARIMA, nonlinear artificial neural networks ANNs, and fuzzy models. In the proposed model, no prior assumption of traditional hybrid linear and nonlinear models is considered for the relationship between the linear and nonlinear components. In the proposed model the data limitation of traditional hybrid linear and nonlinear models is also lifted through investing on the advantages of the fuzzy models. Empirical results of financial markets, especially exchange rate market, forecasting indicate that proposed model performs significantly better than its components used separately, traditional hybrid linear and nonlinear, and other fuzzy and nonfuzzy models in incomplete data situations.

Water Flow Forecasting and River Simulation for Flood Risk Analysis

The paper presents the state-of-the-art in flood forecasting and simulation applied to a river flood analysis and risk prediction. Different water flow forecasting and river simulation models are analysed. An advanced river flood forecasting and modelling approach developed within the ongoing project INFROM is described. It provides an integrated procedure for river flow forecasting and simulation advanced by integration of different models for improving predictions of the river flood risk outputs. A case study on river flow modelling and simulation for river flood risk analysis is given