Corrigendum for the paper: A Multi-Layered Image Format for the Web with an Adaptive Layer Selection Algorithm

The main target of this article is to propose a simple Received Signal Strength Indicator‐ (RSSI‐) based adaptive Physical Layer (PHY) selection approach for Bluetooth Low Energy 5.0 (BLE 5) and compare the performance of adaptive PHY selection with the performance of individual PHY. This article also validates the simulation results acquired from the in‐house developed Ray Tracing (RT) tool with the BLE 5 measurements conducted in a corridor of the TUAS building, Aalto University. The performance metrics considered for the analysis are RSSI, throughput, and outage ratio. The impact of different transmission power on BLE 5 is also analyzed. The obtained simulation results indicate a Root Mean Square Error (RMSE) of about 4.6 dB between the measured and the simulated RSSI at 2.4 GHz frequency. By investigating these results, an adaptive PHY selection algorithm is proposed in this article. The adaptive PHY selection approach enhances the mean throughput of the system and improves the outage ratio as well. In the light of acquired results, the adaptive PHY selection scheme shows significant performance gain and is found more beneficial in the case of an environment with mixed RSSI samples, i.e., a mix of low and high RSSI values.

In Quorum based cross datacenter distributed storage systems, data replication is a widely used technology. Such systems usually choose weak consistency, means they prone to select less number of replicas in read request in order to improve the performance, which lead to the possibility of getting stale data. In this paper, we propose an adaptive replica selection algorithm to make sure the system does not exceed specific stale read ratio while achieving good performance. Firstly, we choose a suitable distribution model from many candidates to estimate the time interval between current read request and nearest write request before it. Then we use Monte-Carlo method to simulate the processing order of read request and write request in different replicas. At last we use those estimated values to determine minimal number of replicas each read request needs to select in order to achieve a specific consistency level. We conduct a comprehensive experiments and the result shows our algorithm is effective.

Texture compression is an important technique to reduce memory storage and increase rendering speed in graphic processing units (GPUs). To ensure fast decoding and retain random memory access characteristics, the industry standard DXTC compression finds an approximate line segment in color space for each 4×4 block. The idea has been extended to multiline solutions by segmenting the 4×4 block into several partitions and adopted by the new format BPTC. BPTC can provide the highest quality than other texture compression standards. However, the limited partition combinations used in BPTC would smooth the texture detail in some cases. This work introduces an adaptive color grouping and selection algorithm to relax the texture smoothing issue. Simulation results show that the proposed algorithm can improve the average PSNR by 0.78 dB for those blocks.

In this paper, we present a scheme to improve immune cloning selection algorithm. The improved algorithm, which is referred to as adaptive cloning selection algorithm (ACSA), is proposed and then applied to function optimization. At first, we present adaptive gene mutation which decides mutation probability of each code point (locus) based on the quality of antibodies and the number of evolution iterations. Secondly, we present an iteratively increasing method from one locus to the all ones, which can be used in function optimization. Then, the cloning selection process of evolution is divided into two-stages. The first step is to increase locus of antibodies. In the other one, the Baldwin effect learning operator is employed. And finally, an experiment is carried out to verify the theoretical analyses on several testing functions.

Cognitive radar is a new framework of radar system proposed by Simon Haykin recently. Adaptive waveform selection is an important problem of intelligent transmitter in cognit i ve radar. In this paper, the problem of adaptive waveform selection is modeled as stochastic dynamic programming model. Then backward dynamic programming, temporal difference learning and Q-learning are used to solve this problem. Optimal waveform selection algorithm and approximate solutions are proposed respectively. The simulation results demonstrate that the two approximate methods approach the optimal waveform selection scheme and have lower uncertainty of state estimation compared to fixed waveform. The performance of temporal difference learning is better than Q-learning, but Q-learning is more suitable to use in radar scene. Finally, the whole paper is summarized.

Extracting frequent itemsets from datasets is an important problem in data mining, for which several mining methods including FP‐Growth have been proposed. FP‐Growth is a classical frequent itemset mining method, which generates pattern databases without candidates. Many improvements have been made in the literature due to the high time complexity and memory usage of FP‐Growth. However, most of them still suffer from performance issues on large datasets. In this paper, we design an auxiliary structure, Array Prefix‐Tree (AP‐Tree), and propose a new algorithm, Array Prefix‐Tree Growth (APT‐Growth), which is further parallelized as a Spark workflow, referred to as PAPT‐Growth. Based on a density threshold, we incorporate an adaptive algorithm selection process into PAPT‐Growth to ensure its running time performance. We conduct extensive experiments on different thresholds and multiple datasets, and experimental results show the performance superiority of PAPT‐Growth in comparison with several state‐of‐the‐art methods such as PFP, YAFIM, and DFPS. The analysis on density reveals a changing point, which justifies the necessity and validity of adaptive algorithm selection.

The performance of underwater acoustic target classification decreases and is unstable when the training set contains noisy, redundant or irrelevant samples. In this paper, a new adaptive immune clonal sample selection algorithm (AICISA) is proposed to address this problem. AICISA is aimed at directing generation evolution. An experiment about the application of AICISA using the multi-field features extracted from 4 kinds of underwater acoustic targets was conducted. Experimental results show that AICISA can select effective subsets of samples. Reducing the sample size by 90%, the classification accuracy of SVM is improved by 10%. AICISA also shows good convergence and stability. The optimal subset of samples obtained by AICISA has good generalization ability and can remarkably reduce the classification time.

This paper presents a qualitative study in which we evaluate the core parts of an adaptive algorithm for next-exercise selection in an e-learning system. The algorithm was previously constructed from a series of studies where participants played the role of a teacher and chose the difficulty of a subsequent exercise for a learner based on their performance, mental effort and self esteem. In this paper, we present these findings to real teachers to gain insights into whether the algorithm is effective and appropriate for future inclusion in an intelligent tutoring system. Overall, we found that teachers believed that the recommendations from the algorithm were appropriate.

Adaptive model selection for time series prediction in wireless sensor networks

Analyzing user behavior characteristics in a complex power grid environment is essential for user behavior planning and resource coordination optimization. Traditional user behavior analysis methods based on model-driven and causal analysis have the disadvantages of strong subjectivity and physical models that are difficult to deal with the randomness and uncertainty of user behavior in complex grid environments. In this paper, we use unsupervised learning methods to analyze user behavior in complex power grid environments, and propose user behavior analysis methods based on stacked autoencoder and clustering. We first reduce the complexity of user behavior data by proposing adaptive feature selection algorithm of user behavior based on stacked autoencoder and unsupervised learning (AFS-SAEUL). Finally, we build a user behavior analysis model based on adaptive feature selection and improved clustering (UBA-AFSIC). The model improved the performance of unsupervised classification of user behavior by fusing the adaptive generation strategy of the initial cluster centers. The simulation experiment results on two real electricity datasets and one public electric vehicle charging dataset show that compared with the existing feature selection algorithm and clustering algorithm, the algorithms proposed in this paper have higher feature selection rate and better clustering performance.

Adaptive operator scheduling algorithms for continuous query processing are usually designed to serve a single performance objective, such as minimizing memory usage or maximizing query throughput. We observe that different performance objectives may sometimes conflict with each other. Also due to the dynamic nature of streaming environments, the performance objective may need to change dynamically. Furthermore, the performance specification defined by users may itself be multi-dimensional. Therefore, utilizing a single scheduling algorithm optimized for a single objective is no longer sufficient. In this paper, we propose a novel adaptive scheduling algorithm selection framework named AMoS. It is able to leverage the strengths of existing scheduling algorithms to meet multiple performance objectives. AMoS employs a lightweight learning mechanism to assess the effectiveness of each algorithm. The learned knowledge can be used to select the algorithm that probabilistically has the best chance of improving the performance. In addition, AMoS has the flexibility to add and adapt to new scheduling algorithms, query plans and data sets during execution. Our experimental results show that AMoS significantly outperforms the existing scheduling algorithms with regard to satisfying both uni-objective and multi-objective performance requirements. 1

This thesis addresses a problem with job scheduling in a computational grid. It investigates the performance impact when some sites in the grid apply a priority policy in favor of local jobs and proposes an adaptive site selection algorithm for grid scheduler to reduce the severity of this impact. It is demonstrated that when some sites apply a priority policy in favor of local jobs, other sites will suffer from much longer completion times. The proposed grid scheduling algorithm takes into account local scheduling policies and adjusts the global scheduling accordingly. The results show that the new algorithm can reduce the performance impact due to different local priority policies and perform effectively under various levels of workload and fractions of sites with different policies.

The use of low Earth orbit (LEO) satellites for world-wide surveillance services is currently actively discussed and developed because the constellation of satellites is one major approach which can provide global seamless network services. Because synthetic aperture radar (SAR), which is used for satellite image acquisition and its related signal processing, is dealing with large volumes of image data, corresponding on-demand adaptive methods for SAR image processing are essentially required for stabilized surveillance services under the consideration of data burst situations. Thus, an adaptive vision algorithm for ship detection which is one of major tasks in SAR image processing researches is proposed based on Lyapunov optimization framework, which maximizes the detection performance while satisfying stability conditions. The high-performance filters are utilized for precisely recognizing the targets whereas they introduce relatively larger delays (i.e., tradeoff exists between performances and delays). Therefore, the proposed Lyapunov optimization-based adaptive filter selection algorithm is designed based on the characteristics. Our data-intensive performance evaluation results prove that the proposed algorithm achieves desired performance improvements.

This paper aims to study the brain-computer interface (BCI) training system for motor imagery (MI) based on virtual reality. In this paper, the MI-BCI software was designed and implemented by using C# and MATLAB mixed programming method, besides, three types of EEG signal pre-processing algorithms, five feature extraction algorithms, and two classification recognition algorithms were integrated to provide off-line analysis, on-line analysis, and adaptive algorithm selection. The results show that by automatically selecting the optimal combination of algorithms for the subjects, the integration degree between the BCI system and the subjects, and the universality of the BCI system are improved. The test objects can all complete the roaming test by constantly adjusting their state of mind under the feedback of virtual reality. The designed training system in this paper can improve the MI ability of subjects.

This contribution presents a machine vision system capable of revealing, detecting and characterizing defects on non-plane transparent surfaces. Because in this kind of surface, transparent and opaque defects can be found, special lighting conditions are required. Therefore, the cornerstone of this machine vision is the innovative lighting system developed. Thanks to this, the defect segmentation is straightforward and with a very low computational burden, allowing real-time inspection. To aid in the conception of the imaging conditions, the lighting system is completely described and also compared with other commercial lighting systems. In addition, for the defect segmentation, a new adaptive threshold selection algorithm is proposed. Finally, the system performance is assessed by conducting a series of tests using a commercial model of headlamp lens.