Centroid-Based Routing protocol with moving sink node for uniform and non-uniform distribution of wireless sensor nodes

The Journal of Supercomputing - A routing protocol called ‘Centroid-Based Routing (CBR)’ is proposed to optimize the total system energy for a given wireless sensor network. We have...     

A three-layer back-propagation neural network for spam detection using artificial immune concentration

In this paper, a three-layer back-propagation neural network (BPNN) is employed for spam detection by using a concentration based feature construction (CFC) approach. In the CFC approach, ‘self’ and ‘non-self’ concentrations are constructed through ‘self’ and ‘non-self’ gene libraries, respectively, to form a two-element concentration vector for expressing the e-mail efficiently. A three-layer BPNN with two-element input is then employed to classify e-mails automatically. Comprehensive experiments are conducted on two public benchmark corpora PU1 and Ling to demonstrate that the proposed CFC approach based BPNN classifier not only has a very much fast speed but also achieves 97 and 99% of classification accuracy on corpora PU1 and Ling by just using a two-element concentration feature vector.     

分类技术在心电图自动诊断模型中的应用比较

提高心电图诊断的有效性和准确性的关键在于心电图分类的质量。文中针对这一情况，详细论述了利用各种分类技术对提取的心电图特征数据进行分类的方法，并在比较各种分类算法的基础上，提出了一种基于CBR的心电图自动诊断系统的结构模型。     

Combining case-based reasoning with Bee Colony Optimization for dose planning in well differentiated thyroid cancer treatment

Thyroid cancers are the most common endocrine carcinomas. Case-based reasoning (CBR) is used in this paper to describe a physician’s expertise, intuition and experience when treating patients with well differentiated thyroid cancer. Various clinical parameters (the patient’s diagnosis, the patient’s age, the tumor size, the existence of metastases in the lymph nodes and the existence of distant metastases) influence a physician’s decision-making in dose planning. The weights (importance) of these parameters are determined here with the Bee Colony Optimization (BCO) meta-heuristic. The proposed CBR–BCO model suggests the I-131 iodine dose in radioactive iodine therapy. This approach is tested on real data from patients treated in the Department of Nuclear Medicine, Clinical Center Kragujevac, Serbia. By comparing the results that are obtained through the developed CBR–BCO model with those resulting from the physician’s decision, it has been found that the developed model is highly reflective of reality.     

一种改进的案例推理分类方法研究

特征属性的权重分配和案例检索策略对案例推理（Case-based reasoning,CBR）分类的准确率有显著影响. 本文提出一种结合遗传算法、内省学习和群决策思想改进的CBR分类方法. 首先,利用遗传算法得到多组属性权重,再根据内省学习原理对每组权重进行迭代调整;然后,通过案例群检索策略得到满足大多数原则的群决策分类结果;最后,以典型分类数据集的对比实验证明了本文方法能进一步提高CBR分类的准确率. 这表明内省学习可以保证权重分配的合理性,案例群检索策略能充分利用案例库的潜在信息,对提升CBR的学习能力有显著作用.     

Mapping coral reefs at reef to reef-system scales, 10s–1000s km2, using object-based image analysis

Coral reef maps at various spatial scales and extents are needed for mapping, monitoring, modelling, and management of these environments. High spatial resolution satellite imagery, pixel <10 m, integrated with field survey data and processed with various mapping approaches, can provide these maps. These approaches have been accurately applied to single reefs (10–100 km²), covering one high spatial resolution scene from which a single thematic layer (e.g. benthic community) is mapped. This article demonstrates how a hierarchical mapping approach can be applied to coral reefs from individual reef to reef-system scales (10–1000 km²) using object-based image classification of high spatial resolution images guided by ecological and geomorphological principles. The approach is demonstrated for three individual reefs (10–35 km²) in Australia, Fiji, and Palau; and for three complex reef systems (300–600 km²) one in the Solomon Islands and two in Fiji. Archived high spatial resolution images were pre-processed and mosaics were created for the reef systems. Georeferenced benthic photo transect surveys were used to acquire cover information. Field and image data were integrated using an object-based image analysis approach that resulted in a hierarchically structured classification. Objects were assigned class labels based on the dominant benthic cover type, or location-relevant ecological and geomorphological principles, or a combination thereof. This generated a hierarchical sequence of reef maps with an increasing complexity in benthic thematic information that included: ‘reef’, ‘reef type’, ‘geomorphic zone’, and ‘benthic community’. The overall accuracy of the ‘geomorphic zone’ classification for each of the six study sites was 76–82% using 6–10 mapping categories. For ‘benthic community’ classification, the overall accuracy was 52–75% with individual reefs having 14–17 categories and reef systems 20–30 categories. We show that an object-based classification of high spatial resolution imagery, guided by field data and ecological and geomorphological principles, can produce consistent, accurate benthic maps at four hierarchical spatial scales for coral reefs of various sizes and complexities.     

A case-based classifier for hypertension detection

The exploration of three-dimensional (3D) anthropometry scanning data along with other existing subject medical profiles using data mining techniques becomes an important research issue for medical decision support. This research attempts to construct a classification approach based on the hybrid use of case-based reasoning (CBR) and genetic algorithms (GAs) for hypertension detection using anthropometric body surface scanning data. The obtained result reveals the relationship between a subject’s 3D scanning data and hypertension disease. The GA is adopted to determine the appropriate feature weights for CBR. The proposed approaches were experimented and compared with a regular CBR and other widely used approaches including neural nets and decision trees. The experiment showed that applying GA to determine the suitable weights in CBR is a feasible approach to improving the effectiveness of case matching of hypertension disease. It also demonstrated that different weighted CBR approach presents better classification accuracy over the results obtained from other approaches.     

Performance enhancement of extreme learning machine for multi-category sparse data classification problems

This paper presents a performance enhancement scheme for the recently developed extreme learning machine (ELM) for multi-category sparse data classification problems. ELM is a single hidden layer neural network with good generalization capabilities and extremely fast learning capacity. In ELM, the input weights are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for sparse data classification problem depends critically on three free parameters. They are, the number of hidden neurons, the input weights and the bias values which need to be optimally chosen. Selection of these parameters for the best performance of ELM involves a complex optimization problem.In this paper, we present a new, real-coded genetic algorithm approach called ‘RCGA-ELM’ to select the optimal number of hidden neurons, input weights and bias values which results in better performance. Two new genetic operators called ‘network based operator’ and ‘weight based operator’ are proposed to find a compact network with higher generalization performance. We also present an alternate and less computationally intensive approach called ‘sparse-ELM’. Sparse-ELM searches for the best parameters of ELM using K-fold validation. A multi-class human cancer classification problem using micro-array gene expression data (which is sparse), is used for evaluating the performance of the two schemes. Results indicate that the proposed RCGA-ELM and sparse-ELM significantly improve ELM performance for sparse multi-category classification problems.     

Classification of rural landscapes from low-density lidar data: is it theoretically possible?

Lidar technology has become an important data source in 3D terrain modelling. In Spain, the National Plan for Aerial Orthophotography will soon release public low-density lidar data (0.5–1 pulses/m²) for most of the country territory. Taking advantage of this fact, this article experimentally assesses the possibility of classifying a rural landscape into eight classes using multitemporal and multidensity lidar data and analyses the effect of point density on classification accuracy. Two statistical methods (transformed divergence and the Jeffries–Matusita distance) were used to assess the possibility of discriminating the eight classes and to determine which data layers were best suited for classification purposes. The results showed that ‘dirt road’ cannot be discriminated from ‘bare earth’ and that the possibility of discriminating ‘bare earth’, ‘pavement’, and ‘low vegetation’ decreases when using densities below 4 pulses/m². Two non-parametric tests, the Kruskal–Wallis test and the Friedman test, were used to strengthen the results by assessing their statistical significance. According to the results of the Kruskal–Wallis test, lidar point density does not significantly affect the classification, whereas the results of the Friedman test show that bands could be considered as the only parameter affecting the possibility of discriminating some of the classes, such as ‘high vegetation’. Finally, the J48 algorithm was used to perform cross-validation in order to obtain the most familiar quantitative values in the international literature (e.g. overall accuracy). Mean overall accuracy was around 85% when the eight classes were considered and increased up to 95% when ‘dirt road’ was disregarded.     

Unsupervised classification of multispectral Landsat images with multidimensional particle swarm optimization

This article proposes a novel unsupervised classification approach for automatic analysis of multispectral Landsat images. The automatic classification of the information in multidimensional (MD) Landsat data space by dynamic clustering is addressed as an optimization problem and two recently proposed heuristic techniques based on Particle Swarm Optimization (PSO) are applied to determine the optimal (number of) clusters in a given input data space: distance metric and a proper validity index function. The first technique, the so-called MD-PSO, re-forms the native structure of swarm particles (agents) in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Fractional global best formation (FGBF) basically collects all promising dimensional components and fractionally creates an artificial global best (aGB) agent that has the potential to be a better ‘guide’ than the swarm’s native global best position (gbest) agent. In this study, the proposed dynamic clustering approach based on MD-PSO and FGBF techniques is applied to automatically classify the colour-coded representations of the multispectral (MD) Landsat data. The approach has been applied to real-world multispectral data and it provided quite encouraging results compared to the traditional K-means and ISODATA (iterative self-organizing data analysis) clustering methods. The proposed unsupervised technique determines the true number of classes within Landsat data for optimal classification performance while preserving spatial resolution and textural information in the classification map.     

A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees

We developed a multiscale object-based classification method for detecting diseased trees (Japanese Oak Wilt and Japanese Pine Wilt) in high-resolution multispectral satellite imagery. The proposed method involved (1) a hybrid intensity–hue–saturation smoothing filter-based intensity modulation (IHS-SFIM) pansharpening approach to obtain more spatially and spectrally accurate image segments; (2) synthetically oversampling the training data of the ‘Diseased tree’ class using the Synthetic Minority Over-sampling Technique (SMOTE); and (3) using a multiscale object-based image classification approach. Using the proposed method, we were able to map diseased trees in the study area with a user's accuracy of 96.6% and a producer's accuracy of 92.5%. For comparison, the diseased trees were mapped at a user's accuracy of 84.0% and a producer's accuracy of 70.1% when IHS pansharpening was used alone and a single-scale classification approach was implemented without oversampling the ‘Diseased tree’ class.     

基于遥感案例推理的海岸带养殖信息提取

目前基于目视解释或光谱分类的养殖信息提取效率低,难以克服由于地物混杂带来的“椒盐”噪声现象且难以融合地学知识。针对养殖信息提取中存在的问题,首先在分析现有养殖信息提取方法和案例推理CBR(Case\|Based Reasoning)用于遥感图像处理的基础上,提出基于遥感案例推理的海岸带养殖信息提取的研究思路;其次,结合养殖区域的空间特征和属性特征,构建案例的表达模型以及CBR相似性推理模型;最后,对不属于案例构建区的粤西沙田镇进行养殖信息提取的CBR实验,精度达到84.56%。对比CBR方法和传统监督分类方法可知,CBR方法是实现海岸带养殖信息快速准确提取的一种有效手段。     

A fuzzy control scheme for video transmission in Bluetooth wireless

This paper is concerned with transmission of Moving Picture Expert Group (MPEG) video over a Bluetooth wireless network using a fuzzy approach. MPEG Variable Bit Rate (VBR) video sources suffer from long delay and excessive loss due to the sudden bursts in bit rate. Constant Bit Rate (CBR) encoding scheme may work well for a network with a guaranteed bandwidth. However, a Bluetooth channel is subject to wireless interference and can never guarantee a constant bandwidth. Subsequently, it is impossible to transmit a CBR video over Bluetooth wireless without data loss or image quality degradation. To resolve this problem, a fuzzy control system is introduced at the Host Controller Interface (HCI). The system consists of a traffic-shaping buffer whose role is to prevent excessive back-to-back cells being generated during the peak transmissions of MPEG video sources. The output bit rate of the traffic-shaping buffer is controlled by a fuzzy controller to ensure that the video stream from the host conforms to the traffic condition of the Bluetooth channel. Another fuzzy controller regulates the average arrival bit rate to the traffic-shaper to guarantee that the buffer is neither full nor empty. Computer simulation results demonstrate that the use of the fuzzy controllers reduces excessive data loss at the HCI as compared with an open loop VBR/CBR video transmission in Bluetooth.     

A New Nonlocal H 1 Model for Image Denoising

Following ideas of Kindermann et al. (Multiscale Model. Simul. 4(4):1091–1115, 2005) and Gilboa and Osher (Multiscale Model. Simul. 7:1005–1028, 2008) we introduce new nonlocal operators to interpret the nonlocal means filter (NLM) as a regularization of the corresponding Dirichlet functional. Then we use these nonlocal operators to propose a new nonlocal H ¹ model, which is (slightly) different from the nonlocal H ¹ model of Gilboa and Osher (Multiscale Model. Simul. 6(2):595–630, 2007; Proc. SPIE 6498:64980U, 2007). The key point is that both the fidelity and the smoothing term are derived from the same geometric principle. We compare this model with the nonlocal H ¹ model of Gilboa and Osher and the nonlocal means filter, both theoretically and in computer experiments. The experiments show that this new nonlocal H ¹ model also provides good results in image denoising and closer to the nonlocal means filter than the H ¹ model of Gilboa and Osher. This means that the new nonlocal operators yield a better interpretation of the nonlocal means filter than the nonlocal operators given in Gilboa and Osher (Multiscale Model. Simul. 7:1005–1028, 2008).     

Information fusion to detect and classify pedestrians using invariant features

A novel approach to detect pedestrians and to classify them according to their moving direction and relative speed is presented in this paper. This work focuses on the recognition of pedestrian lateral movements, namely: walking and running in both directions, as well as no movement. The perception of the environment is performed through a lidar sensor and an infrared camera. Both sensor signals are fused to determine regions of interest in the video data. The classification of these regions is based on the extraction of 2D translation invariant features, which are constructed by integrating over the transformation group. Special polynomial kernel functions are defined in order to obtain a good separability between the classes. Support vector machine classifiers are used in different configurations to classify the invariants. The proposed approach was evaluated offline considering fixed sensors. Results obtained based on real traffic scenes demonstrate very good detection and classification rates.     

Constructing a hybrid hierarchical value map to understand young people’s perceptions of social networking sites

ABSTRACT

Based on the means–end chains (MECs) and push–pull–mooring (PPM) model, this study aims to reveal the functional attributes of Facebook (FB) and Instagram (IG), classify them into the PPM model (i.e. push, pull, and mooring effect) and integrate the nature of MECs (i.e. attribute–consequence–value linkages) to examine young people’s perceptions of FB and IG and their switching intentions. Mixed methods, including qualitative and quantitative approaches are employed to gather data in Taiwan. Sixty-two one-on-one in-depth interviews were content-analysed to design the survey questionnaire. A total of 457 valid samples were collected to establish a hybrid hierarchical value map (HVM) for MEC and PPM analyses. The hybrid HVM shows that ‘privacy protection’ and ‘information collection’ are push effects, which are the unfavourable factors of FB that push users to migrate to IG. By contrast, ‘visual interaction’, ‘relationship maintenance’, and ‘expanding friendship ties’ are pull effects favourable to IG that encourage FB users to migrate. Moreover, ‘self-expression’ and ‘message seeding’ belonging to mooring effects are factors that discourage FB users from migrating. Valuable insights may be provided for the design and improvement of social networking sites by understanding the hybrid HVM.     

Automated text classification of near-misses from safety reports: An improved deep learning approach

Examining past near-miss reports can provide us with information that can be used to learn about how we can mitigate and control hazards that materialise on construction sites. Yet, the process of analysing near-miss reports can be a time-consuming and labour-intensive process. However, automatic text classification using machine learning and ontology-based approaches can be used to mine reports of this nature. Such approaches tend to suffer from the problem of weak generalisation, which can adversely affect the classification performance. To address this limitation and improve classification accuracy, we develop an improved deep learning-based approach to automatically classify near-miss information contained within safety reports using Bidirectional Transformers for Language Understanding (BERT). Our proposed approach is designed to pre-train deep bi-directional representations by jointly extracting context features in all layers. We validate the effectiveness and feasibility of our approach using a database of near-miss reports derived from actual construction projects that were used to train and test our model. The results demonstrate that our approach can accurately classify ‘near misses’, and outperform prevailing state-of-the-art automatic text classification approaches. Understanding the nature of near-misses can provide site managers with the ability to identify work-areas and instances where the likelihood of an accident may occur.     

A comparison of machine-learning algorithms for dynamic scheduling of flexible manufacturing systems

Dispatching rules are frequently used to schedule jobs in flexible manufacturing systems (FMSs) dynamically. A drawback, however, to using dispatching rules is that their performance is dependent on the state of the system, but no single rule exists that is superior to all the others for all the possible states the system might be in. This drawback would be eliminated if the best rule for each particular situation could be used. To do this, this paper presents a scheduling approach that employs machine learning. Using this latter technique, and by analysing the earlier performance of the system, ‘scheduling knowledge’ is obtained whereby the right dispatching rule at each particular moment can be determined. Three different types of machine-learning algorithms will be used and compared in the paper to obtain ‘scheduling knowledge’: inductive learning, backpropagation neural networks, and case-based reasoning (CBR). A module that generates new control attributes allowing better identification of the manufacturing system's state at any particular moment in time is also designed in order to improve the ‘scheduling knowledge’ that is obtained. Simulation results indicate that the proposed approach produces significant performance improvements over existing dispatching rules.     

Reusing training data with generative/discriminative hybrid model for practical acceleration-based activity recognition

This paper proposes a new daily activity recognition method that can learn an activity classification model with small quantities of training data by sharing training data among different activity classes. Many existing activity recognition studies employ a supervised machine learning approach and thus require an end user’s labeled training data, this approach places a large burden on the user. In this study, we assume that a user wears sensors (accelerometers) on several parts of the body such as the hands, waist, and thigh, and we attempt to share sensor data obtained from only selected accelerometers (e.g., only waist and thigh sensors) among two different activity classes based on a sensor data similarity measure. This approach permits us to correctly learn parameters of an activity classification model by using sufficient quantities of shared sensor data without adding new training data. We confirmed the effectiveness of our method by using 48 h of sensor data obtained from 20 participants, and achieved a good recognition accuracy.     

Real-time construction worker posture analysis for ergonomics training

Construction activities performed by workers are usually repetitive and physically demanding. Execution of such tasks in awkward postures can strain their body parts and can result in fatigue, injuries or in severe cases permanent disabilities. In view of this, it is essential to train workers, before the commencement of any construction activity. Furthermore, traditional worker monitoring methods are tedious, inefficient and are carried out manually whereas, an automated approach, apart from monitoring, can yield valuable information concerning work-related behavior of worker that can be beneficial for worker training in a virtual reality world. Our research work focuses on developing an automated approach for posture estimation and classification using a range camera for posture analysis and categorizing it as ergonomic or non-ergonomic. Using a range camera, first we classify worker’s pose to determine whether a worker is ‘standing’, ‘bending’, ‘sitting’, or ‘crawling’ and then estimate the posture of the worker using OpenNI middleware to get the body joint angles and spatial locations. A predefined set of rules is then formulated to use this body posture information to categorize tasks as ergonomic or non-ergonomic.