Self-adaptive Process Research Articles

SALE: Self-adaptive LSH encoding for multi-instance learning

Multi-instance learning (MIL) is commonly used to classify a set of instances, also known as a bag, where labels for the training set are only available for each bag. Many MIL methods exist, but they often suffer from high computation complexity and the key information from MIL being ignored, which deteriorates the classification performance. Recently, locality-sensitive hashing (LSH), with its high scalability, has shown the ability in enhancing MIL performance. However, for these LSH-based methods, the fixed number of bits is used to represent each projected dimension, resulting in subtle information loss and the algorithm performance reduction. In this paper, we propose a self-adaptive LSH encoding method for MIL, termed as SALE. SALE uses LSH to generate the primary batches, followed by a self-adaptive process for reconstruction. Reconstructed bags are transformed into random super histograms (RSH) using an incomplete coding method, and then weighted through a scheme that takes advantage of key instances. These weighted RSHs are used to train the learning model. SALE efficiently deals with large MIL problems, due to its low complexity and RSH’s ability to exploit key information of MIL. Experiments demonstrate SALE’s good performance compared to state-of-the-art MIL methods.

A Positive Model for Reducing and Preventing School Burnout in High School Students

School is an essential institution that provides children with opportunities for cognitive, affective, behavioral, and social development; it equips them with the necessary qualifications for them to make their place in society and at work. Although one of school's most important functions is to help children in their learning processes (Zigler, Kagan, & Muenchow, 1982), this institution can become a stress factor (Chang, Rand, & Strunk, 2000) that causes students to experience emotional, academic, behavioral, and interpersonal problems (Erdur-Baker, Ozmen, & Ozmen, 2011). Students have difficulty concentrating on activities related to school (Jacob, 2005); their lack of concentration negatively affects their level of learning while damaging the academic and social aspects of their development not just in school but also in their future (Beaman & Wheldall, 1997; Little & Hudson, 1998; Stornes & Bru, 2011). For example, negative thinking and depression, avoiding academic tasks, lack of concentration, and fear of school are the most serious problems encountered at school (Poulou & Norwich, 2000). In particular, children who are in a demanding and competitive education system can find themselves in a process where they are forced to be under greater internal and external pressures regarding outperforming their peers.In addition to high grade point averages playing an important role in moving to the next educational stage starting with elementary school, students also face difficult exams that they need to pass. While moving to the next stage of education is challenging in that it requires a new process of self-adaptation (Anderman, Maehr, & Midgley, 1999; Anderman & Midglay, 1997; Bernd & Mekos, 1995; Rice, 2001; Simmons, Carlton-Ford, & Blyth, 1987; Wigfield, Eccles, Maclver, Reuman, & Midgley, 1991), this transition period, which comes after a rather painful process, makes students' new school life even more difficult. The transition from middle school to high school is one of the most important transitions in adolescence (Salmela-Aro, Savolainen, & Holopainen, 2009). When coming to high school with an accumulation of fatigue, boredom, and stress, students are under pressure to prepare for tests that will determine their future; it gives them serious direction in terms of their profession. In this process, they also try to form a sense of identity as a result of the developmental stage they are going through while trying to fulfill developmental tasks in terms of social, professional, and sexual aspects (Steinberg, 2007). Over one's school career, the high school years have particular significance for experiencing school burnout. Students' risk of experiencing school burnout increases at this time because of the negative influences from their accumulated experiences in the education system, as well as the from the stress and sense of tiredness due to the challenging and painful process when passing from middle school to high school. These things combine with the cognitive, affective, social, and behavioral turmoil of adolescence. Bask and Salmela-Aro's (2013) findings, based on their longitudinal study, confirm this view. They found that the burnout levels of high school students between 16-18 years old show an increase, and these students are at risk of losing their self-confidence and having their self-efficacy beliefs diminish.When students encounter excessive demands with respect to school and education, they start having difficulty meeting these demands. As a result, they experience intense stress and pressure. When students cannot cope with being under stress and pressure for a long time (Friesen & Sarros, 1989; Torun, 1997; Kacmaz, 2005), they develop burnout symptoms that stem from school (McCarthy, Pretty, & Catano, 1990; Yang & Farn, 2005). School-burnout syndrome, which leads to serious consequences such as depression (Salmela-Aro et al., 2009), school absenteeism, loss of motivation for classes, dropping out of school (Bask & Salmela-Aro, 2013; McCarthy et al. …

Application of empirical mode decomposition and Euclidean distance technique for feature selection and fault diagnosis of planetary gearbox

Planetary gearbox plays an important role in large and complex mechanical equipment due to the advantage that it can provide larger transmission ratio in a compact space than fixed shaft gearbox. However, its fault diagnosis is a dilemma due to the special structure and harsh working conditions. This paper applies Empirical Mode Decomposition (EMD) and Euclidean Distance Technique (EDT) for planetary gearbox feature selection and fault diagnosis. EMD is a self-adaptive signal processing method that can be applied to non-linear and non-stationary signal and it can also get the aim of de-noising. EDT can give out the quantitative fault diagnosis result. And its theoretical knowledge is easy to understand. An intrinsic mode function (IMF) selection method based on energy ratio is proposed to select IMFs which include sensitive fault information. A two-stage feature selection and weighting method based on EDT is applied to get a new combinative feature and 36 feature parameters are extracted before this process. Then, the feature vector matrix of each raw signal can be computed out by extracting the new combinative feature from every IMF. Finally, the diagnosis result can be obtained through calculating the Euclidean Distance value between two feature vector matrixes. Namely, the health state of the tested signal is as same as the trained signal which the Euclidean Distance between them is the minimum. The performance of the proposed method is validated by experimental data and industrial data.

A dynamic systems theory approach to development of listening strategy use and listening performance

This study investigated the developmental trajectories of an EFL learner's listening strategy use and listening performance and explored the dynamic correlation between the two variables from a dynamic systems perspective. A Chinese EFL learner's listening strategy use and listening performance were traced and examined every two weeks over a forty-week span. The data were analyzed using dynamic systems techniques including the moving min-max graph, Loess smoothing, variability, Monte Carlo technique, spline interpolation, moving window correlation and linear regression. It was found that the learner's listening strategy use and listening performance showed non-linear developmental patterns; regression in listening performance could predict progress to some extent; and the proximity of a new phase was characterized by great fluctuations and variability; there was a downward trend in the relationship between listening strategy use and listening performance over the study period. The analysis of the dynamic complex developmental path of individual listening strategies suggests a simplification, self-organization and self-adaptation process. The developmental patterns and dynamic correlations can provide insights into the interaction between listening strategies and listening performance in a dynamic system. The findings have valuable implications for theory construction and pedagogical practice relating to the development of listening strategies and performance.

A piecewise partitioning Scaled Boundary Finite Element algorithm to solve viscoelastic problems with cyclic symmetry

Scaled Boundary Finite Element Method (SBFEM) and a temporally adaptive algorithm are combined to solve viscoelastic problems. By expanding variables at a discretized time interval, a spatially and temporally coupled viscoelastic problem is decoupled into a series of recursive spatial problems, which are solved by SBFEM, the computing accuracy in the time domain is controlled via a self-adaptive process. For the cyclic symmetric structures, the cyclic symmetry is exploited to reduce the computational expense of SBFEM, both the eigenvalue and system equations of SBFEM are partitioned into a number of smaller independent problems, which are solved by a partitioning algorithm. Two numerical examples are given to verify and illustrate the proposed approach.

Self-adaptive image processing using blind image quality assessment technique

Image processing technique for filtering noise is a major challenge for DSP engineers. When the images are corrupted by noise whose characteristics cannot be evaluated a priori, processing systems need to be flexible and adaptable. General-purpose filters based on assumptions about image noise models fail to meet the quality and performance criteria in dealing with unmodelled noise. At the same time, evolutionary algorithms based adaptable filter architecture is proved to be successful in this regard. While existing evolutionary techniques based designs use uncorrupted reference image and compute mean absolute error for evolving a noise filter, the paper proposes a novel noise quality index based technique. The proposed entropy based scheme estimates noise content without any reference image and such a system is vital in situations where uncorrupted image reference is unavailable. Based on experimental results, the paper compares no-reference image noise assessment techniques with reference based technique and concludes that the proposed blind noise assessment method is accurate as referenced based techniques. From implementation point of view, the no-reference scheme is computationally intensive.

Self-adaptive processing graph with operator fission for elastic stream processing

Self adaptive mechanism for scaling stream processing systems.Automatic scaling by increasing/decreasing the number of processing operators.Model that changes graph topology based on a reactive and predictive algorithms.Results show that both algorithms enable online self-adaptation of the graph. Nowadays, information generated by the Internet interactions is growing exponentially, creating massive and continuous flows of events from the most diverse sources. These interactions contain valuable information for domains such as government, commerce, and banks, among others. Extracting information in near real-time from such data requires powerful processing tools to cope with the high-velocity and the high-volume stream of events. Specially designed distributed processing engines build a graph-based topology of a static number of processing operators creating bottlenecks and load balance problems when processing dynamic flows of events. In this work we propose a self-adaptive processing graph that provides elasticity and scalability by automatically increasing or decreasing the number of processing operators to improve performance and resource utilization of the system. Our solution uses a model that monitors, analyzes and changes the graph topology with a control algorithm that is both reactive and proactive to the flow of events. We have evaluated our solution with three stream processing applications and results show that our model can adapt the graph topology when receiving events at high rate with sudden peaks, producing very low costs of memory and CPU usage.

Self-adaptive statistical process control for anomaly detection in time series

Anomaly detection in time series has become a widespread problem in the areas such as intrusion detection and industrial process monitoring. Major challenges in anomaly detection systems include unknown data distribution, control limit determination, multiple parameters, training data and fuzziness of ‘anomaly’. Motivated by these considerations, a novel model is developed, whose salient feature is a synergistic combination of statistical and fuzzy set-based techniques. We view anomaly detection problem as a certain statistical hypothesis testing. Meanwhile, ‘anomaly’ itself includes fuzziness, therefore, can be described with fuzzy sets, which bring a facet of robustness to the overall scheme. Intensive fuzzification is engaged and plays an important role in the successive step of hypothesis testing. Because of intensive fuzzification, the proposed algorithm is distribution-free and self-adaptive, which solves the limitation of control limit and multiple parameters. The framework is realized in an unsupervised mode, leading to great portability and scalability. The performance is assessed in terms of ROC curve on university of California Riverside repository. A series of experiments show that the proposed approach can significantly increase the AUC, while the false alarm rate is improved. In particular, it is capable of detecting anomalies at the earliest possible time.

World-Class Dispatching Management Practices Featured by KPIs Centered Self-Adaptive Management Process

World-Class Dispatching Management Practices Featured by KPIs Centered Self-Adaptive Management Process

서비스 지향 컴퓨팅 환경에서 서비스 안정성 케이스 기반 자가 적응 방법

서비스 지향 시스템 환경에서는 하나의 독립된 시스템이 다른 시스템에서 제공하는 서비스를 사용함으로써 시스템의 목표를 달성한다. 이러한 시스템 환경에서는 사용중인 서비스의 품질 저하가 실시간으로 시스템 장애를 유발할 수 있다. 기존 자가 적응 방법들은 서비스의 품질 저하 발생 후 대처하는 fault tolerance 방식을 따르고 있기 때문에 서비스 품질 저하로 인한 피해 발생을 예방하지 못한다. 따라서, 자가적응 시스템의 신뢰도를 보존하기 위해서는 사용 중인 서비스를 fault tolerance 방식의 품질 기반 적응이 아닌 서비스 안정성 케이스를 기반으로 자가 적응해야 한다. 본 논문에서는 기존의 보증 속성 표현 방법인 Goal Structuring Notation 모델링을 활용하여 서비스 안정성 케이스를 표현 및 분석하기 위한 방법과, 서비스 안정성 케이스 분석 결과에 따른 적응 조치 방법, 서비스 생명주기에 따른 서비스 안정성 케이스 기반 자가 적응 메커니즘 적용 방법, 서비스 안정성 케이스 기반 자가 적응을 위한 프레임워크 아키텍처를 제안한다.

A Nanocurrent Power Management IC for Multiple Heterogeneous Energy Harvesting Sources

This paper presents a fully autonomous power converter IC for energy harvesting from multiple and multitype sources, such as piezoelectric, photovoltaic, thermoelectric, and RF transducers. The converter performs an independent self-adapting input power tracking process for each source. The peak power conversion efficiency measured during single-source operation is 89.6%. With all sources enabled, the intrinsic current consumption is as low as 47.9 nA/source. A self-starting battery-less architecture has been implemented in a 0.32-μm STMicroelectronics BCD technology with a 2142 μm × 2142 μm die area. The IC only requires a single-shared inductor and an external storage capacitor for the basic working configuration. With respect to other multisource energy harvesters, this design specifically introduces a series of nanopower design techniques for extreme minimization of the intrinsic consumption during operation. The small chip size combined with the limited number of required external component, the high conversion efficiency, and the state-of-the-art intrinsic nanocurrent consumption make the IC suitable for many critical applications with very limited available power, such as wearable devices or unobtrusive wireless sensor networks.

Evolving unipolar memristor spiking neural networks

Neuromorphic computing – brain-like computing in hardware – typically requires myriad complimentary metal oxide semiconductor spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper, we consider the unipolar memristor synapse – a device capable of non-Hebbian switching between only two states (conductive and resistive) through application of a suitable input voltage – and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant non-plastic connections whilst performing at least comparably.

A novel on-chip step-dimmer for low cost AC-powered HV-LED driver

This letter proposes a novel on-chip step-dimmer using an analog dimming method for a high PF AC-powered LED driver. The full AC LED driver can achieve a very high PF and a low THD by using a self-adaptive power processing circuit while delivering a best-in-class dimming performance with the proposed step-dimmer. Under the control of the dimming signal, the dimming voltage is step-adjusted from 1.0V to 2.5V, the average LED current can be changed from 40% to 100% of the nominal LED current value. To verify the feasibility of the proposed scheme, an 8-string 4.4WAC-powered LED driver with the proposed step-dimmer was designed and simulated using a 0.35 um-700V BCD Magnachip process. The gained results verify that the proposed step-dimmer can maintain a high performance of the AC LED driver under different dimming modes with a PF and a THD around 0.998 and 6%, respectively.

Towards a self-adaptive service-oriented methodology based on extended SOMA

We propose a self-adaptive process (SAP) that maintains the software architecture quality using the MAPE-K standard model. The proposed process can be plugged into various software development processes and service-oriented methodologies due to its explicitly defined inputs and outputs. To this aim, the proposed SAP is integrated with the service-oriented modeling and application (SOMA) methodology in a two-layered structure to create a novel methodology, named self-adaptive service-oriented architecture methodology (SASOAM), which provides a semi-automatic self-aware method by the composition of architectural tactics. Moreover, the maintenance activity of SOMA is improved using architectural and adaptive patterns, which results in controlling the software architecture quality. The improvement in the maintainability of SOMA is demonstrated by an analytic hierarchy process (AHP) based evaluation method. Furthermore, the proposed method is applied to a case study to represent the feasibility and practicality of SASOAM.

Evolving output-context fuzzy system for effective rule base

This study develops an evolving output-context fuzzy system (EOCFS) that initiates the evolving process with a single fuzzy rule in which consequent and antecedent parts cover the whole output and input domains respectively. The EOCFS further evolves the output domain and adds more fuzzy rules to achieve an effective rule base. The proposed model is a self-organizing method that can automatically identify prominent distinct data in the output domain for a new fuzzy rule. Thus, the EOCFS constantly evolves by reducing the model error. In addition, the evolving process is realized on the output domain while the self-adaptive process is achieved on the output domain and its associated input domain. The evolving termination index and uncertainty controller of the self-adaptive process are dynamically attained from past and current knowledge. Therefore, effective rule base is the balanced fuzzy model of the approximated system. To illustrate the effectiveness of the proposed algorithm, synthetic and real-world data are considered with low to high dimension inputs. Results show that the proposed EOCFS achieves better performance than the existing models with regard to accuracy and number of rules.

Approach of self-adaptive illumination for optical imaging systems.

An optical imaging signal is vulnerable to undesired features such as ambient light illumination and partial specular reflection from the target; the success of extracting target features from images depends largely on appropriate design of illumination. This paper presents an approach for self-adaptive illumination for optical imaging systems. The proposed illumination system projects a reference image to a target surface as an initial structured illumination, and then adjusts the projected image automatically to compensate the negative influences of undesired features. After this self-adaptive control process, undesired features would appear mostly invisible in the captured images. The signal-to-noise ratio would be improved dramatically well before subsequent image processing. In the validation experiments, several images with uniform brightness were offered as reference images; the captured images could achieve high brightness uniformity, even when the target surface was uneven or was illuminated by ambient light. In a further experiment of selective vessel illumination on a human palm, simulated vessel regions were selectively illuminated. Undesired features, like palm prints, almost disappeared in the images captured.

Numerical simulation of direct shear tests on mechanical properties of talus deposits based on self-adaptive PCNN digital image processing

The macro mechanical properties of materials with characteristics of large scale and complicated structural composition can be analyzed through its reconstructed meso-structures. In this work, the meso-structures of talus deposits that widely exist in the hydro-power engineering in the southwest of China were first reconstructed by small particles according to the in-situ photographs based on the self-adaptive PCNN digital image processing, and then numerical direct shear tests were carried out for studying the mechanical properties of talus deposits. Results indicate that the reconstructed meso-structures of talus deposits are more consistent with the actual situation because the self-adaptive PCNN digital image processing has a higher discrimination in the details of soil-rock segmentation. The existence and random distribution of rock blocks make the initial shear stiffness, the peak strength and the residual strength higher than those of the “pure soil” with particle size less than 1.25 cm apparently, but reduce the displacements required for the talus deposits reaching its peak shear strength. The increase of rock proportion causes a significant improvement in the internal friction angle of talus deposit, which to a certain degree leads to the characteristics of shear stress-displacement curves having a changing trend from the plastic strain softening deformation to the nonlinear strain hardening deformation, while an unconspicuous increase in cohesion. The uncertainty and heterogeneity of rock distributions cause the differences of rock proportion within shear zone, leading to a relatively strong fluctuation in peak strengths during the shear process, while movement features of rock blocks, such as translation, rotation and crossing, expand the scope of shear zone, increase the required shear force, and also directly lead to the misjudgment that the lower shear strength is obtained from the samples with high rock proportion. That, however, just explains the reason why the shear strength gained from a small amount of indoor test data is not consistent with engineering practice.

Bacterially inspired evolution of intelligent systems under constantly changing environments

This paper explores the capabilities of open-ended bio-inspired evolutionary construction of intelligent systems under changing environments. We present and analyze extensive results of the bacterial evolutionary system. This system creates 3D environments that simulate real constantly changing environments. Populations of artificial bacteria constantly evolve their inner biological processes in these environments as they perform every action programmed in their life cycle. This results in a decentralized, asynchronous, parallel and self-adapting general-purpose evolutionary process whose only goal is the survival of the bacterial population under successive, continuously changing environmental conditions. Results show the problem independence and general-purpose capabilities of the system by making it evolve fuzzy rule-based systems under different environments. Robustness and fault tolerance capabilities are also tested by subjecting the bacterial evolutionary system to sudden changes in the environment. Evolution is open-ended as there is no need to restart the system when changes take place. Artificial bacteria self-adapt themselves in real time in order to guarantee their survival.

A self-adaptive intelligent single-particle optimizer compression algorithm

This paper presents a self-adaptive intelligent single-particle optimizer (AdpISPO) for DNA sequence data compression codebook design. Featured with the crucial self-adaptive optimization process, AdpISPO is capable of attaining better fitness value than most existing particle swarm optimization variants with no specific parameters required. A novel DNA sequence data compression algorithm, namely BioSqueezer, is proposed in this paper. Introducing all the unique data features in constructing the compression codebook, BioSqueezer compresses DNA sequences by replacing similar fragments with the index of its corresponding code vector. For attaining higher compression ratio, the AdpISPO is employed in BioSqueezer for the codebook design. Experimental results on benchmark DNA sequences demonstrate that BioSqueezer attains better performance than other state-of-the-art DNA compression algorithms.

Manual and Automatic assigned thresholds in multi‐layer data fusion intrusion detection system for 802.11 attacks

Abuse attacks on wireless networks are becoming increasingly sophisticated. Most of the recent research on intrusion detection systems for wireless attacks either focuses on just one layer of observation or uses a limited number of metrics without proper data fusion techniques. However, the true status of a network is rarely accurately detectable by examining only one network layer. The goal of this study is to detect injection types of attacks in wireless networks by fusing multi-metrics using the Dempster–Shafer (D–S) belief theory. When combining beliefs, an important step to consider is the automatic and self-adaptive process of basic probability assignment (BPA). This study presents a comparison between manual and automatic BPA methods using the D–S technique. Custom tailoring BPAs in an optimum manner under specific network conditions could be extremely time consuming and difficult. In contrast, automatic methods have the advantage of not requiring any prior training or calibration from an administrator. The results show that multi-layer techniques perform more efficiently when compared with conventional methods. In addition, the automatic assignment of beliefs makes the use of such a system easier to deploy while providing a similar performance to that of a manual system.