Adaptive Process Model Research Articles

Data Categorization and Model Weighting Approach for Language Model Adaptation in Statistical Machine Translation

Language model encapsulates semantic, syntactic and pragmatic information about specific task. Intelligent systems especially natural language processing systems can show different results in terms of performance and precision when moving among genres and domains. Therefore researchers have explored different language model adaptation strategies in order to overcome effectiveness issue. There are two main categories in language model adaptation techniques. The first category includes the techniques that based on the data selection where task-oriented corpus can be extracted and used to train and generate models for specific translations. While the second category focuses on developing a weighting criterion to assign the test data to specific model corpus. The purpose of this research is to introduce language model adaptation approach that combines both categories (data selection and weighting criterion) of language model adaptation. This approach applies data selection for specific-task translations by dividing the corpus into smaller and topic-related corpora using clustering process. We investigate the effect of different approaches for clustering the bilingual data on the language model adaptation process in terms of translation quality using the Europarl corpus WMT07 that includes bilingual data for English-Spanish, English-German and English-French. A mixture of language models should assign any given data to the right language model to be used in the translation process using a specific weighting criterion. The proposed language model adaptation has achieved better translation quality compare to the baseline model in Statistical Machine Translation (SMT).

Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks

Despite there being clear evidence for top-down (e.g., attentional) effects in biological spatial hearing, relatively few machine hearing systems exploit top-down model-based knowledge in sound localisation. This paper addresses this issue by proposing a novel framework for binaural sound localisation that combines model-based information about the spectral characteristics of sound sources and deep neural networks (DNNs). A target source model and a background source model are first estimated during a training phase using spectral features extracted from sound signals in isolation. When the identity of the background source is not available, a universal background model can be used. During testing, the source models are used jointly to explain the mixed observations and improve the localisation process by selectively weighting source azimuth posteriors output by a DNN-based localisation system. To address the possible mismatch between training and testing, a model adaptation process is further employed on-the-fly during testing, which adapts the background model parameters directly from the noisy observations in an iterative manner. The proposed system therefore combines model-based and data-driven information flow within a single computational framework. The evaluation task involved localisation of a target speech source in the presence of an interfering source and room reverberation. Our experiments show that by exploiting model-based information in this way, sound localisation performance can be improved substantially under various noisy and reverberant conditions.

A stochastic optimization model based on adaptive feedback correction process and surrogate model uncertainty for DNAPL-contaminated groundwater remediation design

A stochastic optimization model based on an adaptive feedback correction process and surrogate model uncertainty was proposed and applied for remediation strategy design at a dense non-aqueous phase liquids (DNAPL)-contaminated groundwater site. One hundred initial training samples were obtained using the Latin hypercube sampling method. A surrogate model of a multiphase flow simulation model was constructed based on these samples employing the self-adaptive particle swarm optimization kriging (SAPSOKRG) method. An optimization model was built, using the SAPSOKRG surrogate model as a constraint. Then, an adaptive feedback correction process was designed and applied to iteratively update the training samples, surrogate model, and optimization model. Results showed that the training samples, the surrogate model, and the optimization model were effectively ameliorated. However, the surrogate model is an approximation of the simulation model, and some degree of uncertainty exists even though the surrogate model was ameliorated. Therefore, residuals between the surrogate model and the simulation model were calculated, and an uncertainty analysis was conducted. Based on the uncertainty analysis results, a stochastic optimization model was constructed and solved to obtain optimal remediation strategies at different confidence levels (60, 70, 80, 90, 95%) and under different remediation objectives (average DNAPL removal rate ≥ 70, ≥ 75, ≥ 80, ≥ 85, ≥ 90%). The optimization results demonstrated that the higher the confidence level and remediation objective, the more expensive was remediation. Therefore, decision makers can weigh remediation costs, confidence levels, and remediation objectives to make an informed choice. This also allows decision makers to determine the reliability of a selected strategy and provides a new tool for DNAPL-contaminated groundwater remediation design.

\u201cI had to somehow still be flexible\u201d: exploring adaptations during implementation of brief cognitive behavioral therapy in primary care

BackgroundPrimary care clinics present challenges to implementing evidence-based psychotherapies (EBPs) for depression and anxiety, and frontline providers infrequently adopt these treatments. The current study explored providers’ perspectives on fidelity to a manualized brief cognitive behavioral therapy (CBT) as delivered in primary care clinics as part of a pragmatic randomized trial. Data from the primary study demonstrated the clinical effectiveness of the treatment and indicated that providers delivered brief CBT with high fidelity, as evaluated by experts using a standardized rating form. Data presented here explore challenges providers faced during implementation and how they adapted nonessential intervention components to make the protocol “fit” into their clinical practice.MethodsA multiprofessional group of providers (n = 18) completed a one-time semi-structured interview documenting their experiences using brief CBT in the primary care setting. Data were analyzed via directed content analysis, followed by inductive sorting of interview excerpts to identify key themes agreed upon by consensus. The Dynamic Adaptation Process model provided an overarching framework to allow better understanding and contextualization of emergent themes.ResultsProviders described a variety of adaptations to the brief CBT to better enable its implementation. Adaptations were driven by provider skills and abilities (i.e., using flexible content and delivery options to promote treatment engagement), patient-emergent issues (i.e., addressing patients’ broader life and clinical concerns), and system-level resources (i.e., maximizing the time available to provide treatment).ConclusionsThe therapeutic relationship, individual patient factors, and system-level factors were critical drivers guiding how providers adapted EBP delivery to improve the “fit” into their clinical practice. Adaptations were generally informed by tensions between the EBP protocol and patient and system needs and were largely not addressed in the EBP protocol itself. Adaptations were generally viewed as acceptable by study fidelity experts and helped to more clearly define delivery procedures to improve future implementation efforts. It is recommended that future EBP implementation efforts examine the concept of fidelity on a continuum rather than dichotomized as adherent/not adherent with focused efforts to understand the context of EBP delivery.Trial registrationClinicalTrials.gov, NCT01149772

RUL Prediction of Deteriorating Products Using an Adaptive Wiener Process Model

Degradation modeling plays an important role in system health diagnosis and remaining useful life (RUL) prediction. Recently, a class of Wiener process models with adaptive drift was proposed for degradation-based RUL prediction, which has been proven flexible and effective. However, the existing studies use an autoregressive model of order 1 for the adaptive drift, which can result in difficulties in both model estimation and RUL prediction. This paper proposes a new adaptive Wiener process model that utilizes a Brownian motion for the adaptive drift. The new model shares the flexibility of the existing models, but avoids the difficulties in model estimation and RUL prediction. A model estimation procedure based on maximum likelihood estimation is developed, and the RUL prediction based on the proposed model is formulated. The effectiveness of the model in RUL prediction is validated using simulation and through an application to the lithium-ion battery degradation data.

The level of performance stabilization influences motor adaptation on an isometric force control task.

This study compared the effects of two levels of performance stabilization on the adaptation to unpredictable perturbations in an isometric control force task with the goal of controlling 40% of the maximum force. The experiment consisted of pre-exposure and exposure phases. In the pre-exposure two levels of performance stabilization were manipulated: a stabilization group (SG) performed three trials in a row while maintaining 40% of the maximum force for three seconds and an absolute error less than or equal to 5% (i.e., the criteria of performance), and a superstabilization group (SSG) performed six blocks of the same criteria. During the exposure phase, the task was the same as that in the pre-exposure phase; however, it was inserted 9 trials of perturbations when the task goal changed to 60% of the maximum force. We measured the %RMSE, RMS from the biceps and triceps brachii and co-contraction. In the pre-exposure phase, both groups showed similar performance and muscle activity. When exposed to the perturbations, SSG performance more quickly returned to the previous level of accuracy, showed lower muscle activation and demonstrated a greater muscle co-contraction than did SG. The results give support to the adaptive process model on motor learning.

Cultural Adaptation of a Dyadic Intervention for Korean Couples Coping with Alzheimer’s Disease

ABSTRACTObjectives: The Couples Life Story Approach (CLSA) was recently developed in the U.S. for older couples dealing with dementia to improve their quality of life. The purpose of this article is to describe how the CLSA was adapted to be culturally appropriate for older Korean couples and to discuss cultural themes that emerged during the implementation process.Methods: The intervention was adapted using the Cultural Adaptation Process Model. The revised materials were implemented on 56 Korean couples. A multiple case study method was used to analyze the clinical data.Results: Four cultural themes were identified: (1) dealing with negative memories in early years of marriage; (2) communication styles and patterns; (3) ways to incorporate difficult life events into the Life Story Book; and (4) complex dynamics of heirarchy in the relationship between older couples and the interventionist. With each theme, case examples are described that illustrate relevant issues.Conclusions: Cultural adaptation can be conducted systematically to improve the delivery of the CLSA for different populations.Clinical Implications: Cliniocians working with older Korean couples affected by dementia should consider cultural uniqueness in a life-story approach.

Business Model Adaptation to Institutional Voids: The Case of Jumia, the Amazon of Africa

Business model adaptation to institutional voids in developing countries is critical for the survival of firms seeking to explore the opportunities in these markets. However, extant literature has not articulated the central issues relating to how firms adapt business model to developing countries. We tackle this issue by taking the perspective of a developing country-based firm adapting a business model designed for developed economies to its local context. Based on a longitudinal case study of Jumia - an online retailing company in Africa, we show that a developing country- based firm attempting to exploit the success of established business models proposed by developed country-based firms in its local context cannot simply replicate the model proposed by developed country-based firms, but has to adapt it with the aim of filling the various infrastructural voids, regulatory voids and cultural voids of its home country. We find that the business model adaptation to these various types of institutional voids in developing countries involves three phases consisting of legitimacy phase, localization phase and consolidation phase. Throughout these phases, significant adjustments are made to various components of the business model, with the value creation and delivery component witnessing the major adjustment and modification at the localization phase of the business model adaptation process.

Advanced Economic Control of Electricity-Based Space Heating Systems in Domestic Coalitions with Shared Intermittent Energy Resources

Over the past few years, Domestic Heating Automation Systems (DHASs) that optimize the domestic space heating control process with minimum user input, utilizing appropriate occupancy prediction technology, have emerged as commercial products (e.g., the smart thermostats from Nest and Honeywell). At the same time, many houses are being equipped with, potentially grid-connected, Intermittent Energy Resources (IERs), such as rooftop photovoltaic systems and/or small wind turbine generators. Now, in many regions of the world, such houses can sell energy to the grid but at a lower price than the price of buying it. In this context, and given the anticipated increase in electrification of heating, the next generation DHASs need to incorporate Advanced Economic Control (AEC). Such AEC can exploit the energy buffer that heating loads provide, in order to shift the consumption of electricity-based heating systems to follow the intermittent energy generation of the house. By so doing, the energy imported from the grid can be minimized and considerable monetary gains for the household can be achieved, without affecting the occupants’ schedule. These benefits can be amplified still further in domestic coalitions, where a number of houses come together and share their IER generation to minimize their cumulative grid energy import. Given the above, in this work we extend a state-of-the-art DHAS, to propose AdaHeat+, a practical DHAS, that, for the first time, incorporates AEC. Our work is applicable to both individual houses and domestic coalitions and comes complete with an allocation mechanism to share the coalition gains. Importantly, we propose an effective heuristic heating schedule planning approach for collective AEC that (i) has a complexity that scales in a linear and parallelizable manner with the coalition size, and (ii) enables AdaHeat+ to handle the distinct preferences, in balancing heating cost and thermal discomfort, of the households. Our approach relies on stochastic IER power output predictions. In this context, we propose a simple and effective formulation for the site-specific calibration of such predictions based on adaptive Gaussian process modeling. Finally, we demonstrate the effectiveness of AdaHeat+ through real data evaluation, to show that collective AEC can improve heating cost-efficiency by up to 60%, compared to independent AEC (and even more when compared to no-AEC).

Adapting Meaning-Centered Psychotherapy in Advanced Cancer for the Chinese Immigrant Population.

The Chinese immigrant community faces multiple barriers to quality cancer care and cancer survivorship. Meaning-centered psychotherapy (MCP) is an empirically-based treatment shown to significantly reduce psychological distress while increasing spiritual well-being and a sense of meaning and purpose in life in advanced cancer patients. However, it has not yet been adapted for racial and ethnic minority populations for whom the concept of "meaning" may likely differ from that of westernized White populations. In this study, we conducted a community needs assessment to inform the cultural adaptation of MCP for Chinese patients with advanced cancer, in accordance with Bernal et al. ecological validity model and the cultural adaptation process model of Domenech-Rodriquez and Weiling. We conducted interviews until saturation with 11 key Chinese-serving community leaders and health professionals with a range of areas of expertise (i.e. oncology, psychology, palliative care, cancer support services), to examine community needs, priorities, and preferences within the context of the MCP intervention. Sessions were audio recorded and transcribed. The research team analyzed the transcripts using Atlas.ti. Six frequently occurring themes were identified. Interviewees described the role of the family, traditional Chinese values, cancer stigma, and social norms (e.g. saving face) in adapting MCP. Researchers and clinicians should consider the role of the family in treatment, as well as specific social and cultural values and beliefs in adapting and delivering MCP for Chinese patients with advanced cancer.

Deep Learning Backend for Single and Multisession i-Vector Speaker Recognition

The promising performance of Deep Learning (DL) in speech recognition has motivated the use of DL in other speech technology applications such as speaker recognition. Given i-vectors as inputs, the authors proposed an impostor selection algorithm and a universal model adaptation process in a hybrid system based on Deep Belief Networks (DBN) and Deep Neural Networks (DNN) to discriminatively model each target speaker. In order to have more insight into the behavior of DL techniques in both single and multi-session speaker enrollment tasks, some experiments have been carried out in this paper in both scenarios. Additionally, the parameters of the global model, referred to as universal DBN (UDBN), are normalized before adaptation. UDBN normalization facilitates training DNNs specifically with more than one hidden layer. Experiments are performed on the NIST SRE 2006 corpus. It is shown that the proposed impostor selection algorithm and UDBN adaptation process enhance the performance of conventional DNNs 8-20 % and 16-20 % in terms of EER for the single and multi-session tasks, respectively. In both scenarios, the proposed architectures outperform the baseline systems obtaining up to 17 % reduction in EER.

Cognitive state recognition using wavelet singular entropy and ARMA entropy with AFPA optimized GP classification

Cognitive state, which is the inner mental state of a person while interacting with an artificial system through man-machine interface, can be affected by various factors, such as fatigue, stress, mental workload, attention deficit, and executive function, among others, which can lead to errors, accidents, or even disasters. One practical solution to this problem is to monitor and recognize the cognitive state of subjects via physiological signals. In this study, a hybrid adaptive flower pollination algorithm-Gaussian process model is proposed to recognize the cognitive state of in-flight pilots. Instead of using the traditional conjugate gradient technique to find optimal hyperparameters, an improved flower pollination algorithm is proposed. The adaptive Lévy strategy is then used to increase the robustness of this algorithm, as well as to enhance the global optimization and generalization capability of the Gaussian process model. In addition to conventional features in the time-frequency domain, a novel set of features involving wavelet singular entropy and autoregressive-moving average entropy is proposed to improve classification accuracy. Experiments are performed through flight simulations in a full flight simulator with six degrees of freedom. Comparable experimental results validate the feasibility of the proposed method for recognizing cognitive state and provide a wide range of conclusions on the feature selection and feature patterns of cognitive state.

Business model adaptation for emerging markets: a case study of a German automobile manufacturer in India

Emerging markets offer a wide range of opportunities for firms from developed markets, especially in terms of high growth potential. However, business models that enable firms to achieve competitive advantage in their home markets are often challenged by the different nature of emerging markets. Firms, therefore, have to innovate and adapt their business models to better fit the specific context of these international markets. Based on a longitudinal case study of a German luxury automobile manufacturer's internationalization to India, we develop a phase model of the business model adaptation process to emerging markets. We find that firms adapt their business models in four phases: international extension, local emergence, local expansion, and local consolidation. Firms step‐wise adjust business model components along this process to develop a local emerging market business model. In each phase of the business model adaptation process, firms emphasize different components of the business model, before they enter into continuous adjustments of all business model components. Furthermore, we find that firms overall adjust some components of their business model more significantly than others. Our findings are of particular relevance to the literature on business model internationalization and the literature that points out the evolutionary, step‐wise nature of business model innovation.

CASE STUDY OF CRITICAL SUCCESS FACTORS IN THE NEW PRODUCT DEVELOPMENT IN A SMALL ELECTROMEDICAL PRODUCT BUSINESS

In a society that consumes a growing amount of technology, Technology-Based Firms (TBF) are highlighted as creators and suppliers of this technology, and are used to good models of New Product Development (NPD) aimed at effectiveness and greater efficiency on its processes. The Electromedical Devices industry is considered to be medium-high technological intensity, and companies in this sector play an important role in the Brazil, both economically, offering products with local solutions at a lower cost, as supporting the supply of solutions then increasing the population's access to health services. Current literature indicates several NPD models, but is lacking in jobs that point models tailored for specific activities branches, and the consequent application of these models in business. This work consists of an exploratory research with a qualitative approach, based on a single case study of a small company of Electromedical Products whose data sources were documents, observations and interviews in order to investigate and explain how the model adaptation process was conducted in the studied company, why certain decisions were made, and how the company conducted a strategy to deal with the Critical Success Factors (CSF) in the development of its new product line. As a result it became clear that the company encountered many obstacles, some inherent to Small Business, others common to TBF, and also regulatory, specific barriers of companies operating in the Electromedical Devices sector, but even with these obstacles, the studied company was able to develop and implement a solid strategy to deal with the CSF in the development of its products, resulting in a complete portfolio of products that meets the local regulations, which were accepted by the market, with domestic and international sales.

The Discovery of the Implemented Software Engineering Process Using Process Mining Techniques

Process model guidance is an important feature by which the software process is orchestrated. Without complying with this guidance, the production lifecycle deviates from producing a reliable software with high-quality standards. Usually, teams break the process deliberately or impulsively. Application Lifecycle Management (ALM) tools log what teams do even if they break the process. The log file could be a key to discover the behavior of the undertaken process against the targeted process model. Since the date of its introduction, Process Mining techniques have been used in business process domains with no focus on the software engineering processes. This research brings the Process Mining techniques to the software engineering domain. The research shows a conclusive effort that used a Scrum adapted process model as an example of Agile adoption. This research has applied Process Mining discovery techniques to capture the actually implemented process by the Scrum team. This application clarifies the gap between the standard process guidance and the actually implemented one. The research’s results showed that Process Mining techniques have the ability to discover and verify the deviation on both levels; the process itself as well as the work items state-machine workflows.

Developing a computational solution of mobile robot self-localisation problem

This paper presents a computational solution for the mobile robot self-localization problem using a new adaptive data fusion structure. Input sensors are employed for feeding the fusion structure, and consequently more precise perception from a highly noisy environment can be obtained. This adaptation process relies on two main steps; firstly, to choose the sensors and secondly, employing a model adaptation process. Using this process, the more incorrect data are eliminated, the more accurate localization results are obtained. Also, implementing more accurate sensor models, the values of error obtained in the final iterations will be less. By implanting the proposed process, simulation results indicate that the proposed structure is very useful and effective, especially when compared to the conventional techniques of localization problems solutions which rely mainly on the information theory.

Context-Aware Mobile Proactive Recommendation

Mobile recommender systems aim to recommending the right product or information to the right users at anytime and anywhere. It is well known that the contextual information is often the key for the performances of mobile recommendations. Therefore, in this paper, we firstly identify which types of contextual information could affect users' personal preferences, which is called users' adaptive options preferences, and qualitatively construct an adaptive options analytical hierarchy process model for users' personal preferences , and quantitatively analyze impact weights of contextual information on users' personal preferences. Then we propose a novel contextaware learning algorithm for mobile users' adaptive options preferences. Secondly we divide all users into two groups according to their frequency in using of all services in history logs, and propose two different proactive recommendation methods for the two classes of users. Finally experiments are conducted to demonstrate the performance of the preference learning algorithm, the impact of contexts and the proportion of the training dataset on the algorithm, and recommendation precision of the two methods.

Motion silencing of flicker distortions on naturalistic videos

We study the influence of motion on the visibility of flicker distortions in naturalistic videos. A series of human subjective studies were executed to understand how motion silences the visibility of flicker distortions as a function of object motion, flicker frequency, and video quality. We found that flicker visibility is strongly reduced when the speed of coherent motion is large, and the effect is pronounced when video quality is poor. Based on this finding, we propose a model of flicker visibility on naturalistic videos. The target-related activation levels in the excitatory layer of neurons were estimated for a displayed video using a spatiotemporal backward masking model, and then the flicker visibility is predicted based on a learned model of neural flicker adaptation processes. Experimental results show that the prediction of flicker visibility using the proposed model correlates well with human perception of flicker distortions. We believe that sufficiently fast and coherent motion silences the perception of flicker distortions on naturalistic videos in agreement with a recently observed “motion silencing” effect on synthetic stimuli. We envision that the proposed model could be applied to develop perceptual video quality assessment algorithms that can predict “silenced” temporal distortions and account for them when computing quality judgments.

Stable recursive canonical variate state space modeling for time-varying processes

An adaptive recursive process modeling approach is developed to improve the accuracy of modeling time-varying processes. We adopt the exponential weighted moving average approach to update the covariance and cross-covariance of past and future observation vectors. Forgetting factors are adjusted in the recursive modeling process based on the residual of model outputs. To ensure the stability of the identified model, we introduce a constrained nonlinear optimization approach and propose a stable recursive canonical variate state space modeling (SRCVSS) method. The performance of the proposed method is illustrated with an open-loop numerical example and simulation with the closed-loop data from a continuous stirred tank heater (CSTH) system. The results indicate that the accuracy of proposed SRCVSS modeling method is higher than that of state space modeling with traditional canonical variate analysis.

An Overview of Noise-Robust Automatic Speech Recognition

New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To this end, it is critical to establish a solid, consistent, and common mathematical foundation for noise-robust ASR, which is lacking at present. This article is intended to fill this gap and to provide a thorough overview of modern noise-robust techniques for ASR developed over the past 30 years. We emphasize methods that are proven to be successful and that are likely to sustain or expand their future applicability. We distill key insights from our comprehensive overview in this field and take a fresh look at a few old problems, which nevertheless are still highly relevant today. Specifically, we have analyzed and categorized a wide range of noise-robust techniques using five different criteria: 1) feature-domain vs. model-domain processing, 2) the use of prior knowledge about the acoustic environment distortion, 3) the use of explicit environment-distortion models, 4) deterministic vs. uncertainty processing, and 5) the use of acoustic models trained jointly with the same feature enhancement or model adaptation process used in the testing stage. With this taxonomy-oriented review, we equip the reader with the insight to choose among techniques and with the awareness of the performance-complexity tradeoffs. The pros and cons of using different noise-robust ASR techniques in practical application scenarios are provided as a guide to interested practitioners. The current challenges and future research directions in this field is also carefully analyzed.