Hybrid self-inertia weight adaptive particle swarm optimisation with local search using C4.5 decision tree classifier for feature selection problems

ABSTRACT

Feature selection is an important task to improve the classifier’s accuracy and to decrease the problem size. A number of methodologies have been presented for feature selection problems using metaheuristic algorithms. In this paper, an improved self-adaptive inertia weight particle swarm optimisation with local search and combined with C4.5 classifiers for feature selection algorithm is proposed. In this proposed algorithm, the gradient base local search with its capacity of helping to explore the feature space and an improved self-adaptive inertia weight particle swarm optimisation with its ability to converge a best global solution in the search space. Experimental results have verified that the SIW-APSO-LS performed well compared with other state of art feature selection techniques on a suit of 16 standard data sets.     

Harnessing adaptive capacity to close the pandora’s box of open innovation

ABSTRACT

This paper focuses on how companies deploy structural properties of adaptive capacity (multiplexity, redundancy and loose coupling) to cope with the phenomenon of internal challenges of Open Innovation (OI) implementation, i.e. organisational and cultural changes. We developed a single case study, which offered significant findings. First, the multiplexity of relationships in OI settings helps to face the challenges of organisational and cultural changes by triggering trust formation and interaction. Second, redundancy has twofold elements: institutional logics redundancy triggers cultural change challenges which can be overcome through management practices and communications; task redundancy facilitates knowledge sharing and collaboration, thus helping to deal with organisational change challenges. Finally, loose coupling in OI settings facilitates social interconnectedness among members through management practices, helping to face organisational and cultural change challenges. We provide managerial and theoretical implication to deal with the challenges of OI in relation to both organisational and cultural changes.     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

辉县部分景区地质灾害危险性评估及防治措施研究

为了给辉县景区减灾防灾提供地质依据,根据实际工程概况,研究了辉县部分景区地质灾害危险性预测评估及防治措施,预测评估了工程建设中、建设后可能引发或加剧地质灾害危险性,建设工程自身可能遭受已存在地质灾害危险性;评估了地质灾害危险性综合分区以及根据地质灾害危险性、防治难度和防治效益,对评估区适宜性作出评价,提出了防治地质灾害的措施和建议。     

基于机器视觉的手机电池表面缺陷检测

针对手机电池表面质量人工检测情况,开发了电池表面缺陷无损检测系统软件。首先电池表面经过倾斜矫正、感兴趣区域提取和字符灰度值修改等预处理操作,通过基于灰度密度分布和灰度差的自适应阈值亮度法对感兴趣区域进行子图像遍历,融合有重合区域的缺陷子图像并滤除没有明显缺陷的区域;然后采用支持向量机多种类分类法,提取二值图像像素分布规律作为训练特征,识别电池表面缺陷种类;最后设计了人机交互界面,确定最佳的可变参数,实验测试缺陷识别率达95%以上。     

Evaluation of fumonisin exposure by determination of fumonisin B1 in human hair and in Brazilian corn products

The aim of this study was to evaluate the dietary exposure to fumonisin B₁ (FB₁) through determination of residual FB₁ in hair and corn products consumed by 56 volunteers from Pirassununga and Erval Velho, Brazil. Data from FB₁ analyses in corn products and a Food Frequency Questionnaire (FFQ) were used for estimating the mean probable daily intake (PDI_M) for FB₁. FB₁ was detected in 4 human hair samples (7.2%), at a mean level of 21.3 ± 12.1 ng g⁻¹. The mean FB₁ level found in corn products was 360.4 ± 555.1 μg kg⁻¹. The PDI_M value of FB₁ in volunteers was 159 ± 47 ng kg⁻¹ body weight day⁻¹ which represents 7.9% of the provisional maximum tolerable daily intake (PMTDI) recommended for fumonisins. The FB₁ levels found in human hair samples from each volunteer were associated with their individual PDI of FB₁, indicating that exposure to FB₁ in the sample studied do not represent a health concern. This is the first report on the incidence of FB₁ in individual human hair in Brazil.     

Sustainability impact assessment for local energy supplies' development – The case of the alpine area of Lake Como,Italy

The development of distributed energy systems has important environmental, social and economic implications. Local decision-making processes must be guided by a careful evaluation of the sustainability of production chains and alternative choices. The aim of this study is to explore if and how an integrated assessment can quantify the extent to which bioenergy supply chain development contributes to rural development and energy policy objectives. We applied a Sustainability Impact Assessment (SIA) for local bioenergy development in the alpine area of Lake Como (Italy). We modeled the local bioenergy chain in 2008 and eleven scenarios considering different biomass utilizations, mechanization levels, combustion technologies, and subsidies schemes at 2020. We calculated economic, social and environmental indicators. We interpret and discuss the scenario analysis in order to support the bioenergy planning under the light of its implications for the different policy aims and concerns.     

A methodology to assess suitability of a site for small scale wet and dry CSP systems

This study presents a methodology to assess suitability of a site for small scale concentrated solar power (CSP) systems for its energy conversion efficiency and make‐up water requirement. Energy conversion efficiency of CSPs relies not only on the level of direct solar radiation but also on the performance of the cooling system. Regions with high solar potential have to deal with heat rejection at elevated temperatures which causes reduced energy conversion efficiencies due to high condenser temperatures. It is desirable to utilize wet cooling systems as they can achieve temperatures lower than the dry bulb temperature by evaporative cooling. On the other hand, such regions usually lack water resources which deteriorate the sustainable nature of CSP applications. This study combines various available models for both solar resource estimation and cooling systems' performance considering (i) the influence of ambient temperatures, and (ii) the influence of humidity levels. These models are integrated together to analyze the use of dry or wet cooling systems in terms of overall energy output and water consumption at a selected site in northern Cyprus. The model inputs consist of only annual hourly surface weather data and the location of the site of interest. The results show that dry cooling unit at northern Cyprus is capable of saving water about 18.7 ton/MWh while it produces 27% less energy compared to the wet cooling alternative for the representative annual weather data. Copyright © 2015 John Wiley & Sons, Ltd.     

A terrain risk assessment method for military surveillance applications for mobile assets

This study proposes an analytical and flexible terrain risk assessment method for military surveillance applications for mobile assets. Considering the risk as the degree of possibility of insurgent presence, the assessment method offers an efficient evaluation of risk in the surrounding terrain for military combat operating posts or observation posts. The method is designed for unmanned aerial vehicles as the surveillance assets of choice to improve the effectiveness of their use. Starting with the area map and geographical data, the target terrain is first digitized for space representation. Then the data of nine geographical parameters are used to formulate five contributing risk factors. These factors are incorporated in an analytical framework to generate a composite map with risk scores that reveal the potential high-risk spots in the terrain. The proposed method is also applied to a real-life case study of COP Kahler in Afghanistan, which was a target for insurgent attacks in 2008. The results confirm that when evaluated with the developed method, the region that the insurgents used to approach COP Kahler has high concentration of high-risk cells.