Search results
1 – 10 of 77Minchen Zhu, Weizhi Wang and Jingshan Huang
It is well known that the selection of initial cluster centers can significantly affect K-means clustering results. The purpose of this paper is to propose an improved, efficient…
Abstract
Purpose
It is well known that the selection of initial cluster centers can significantly affect K-means clustering results. The purpose of this paper is to propose an improved, efficient methodology to handle such a challenge.
Design/methodology/approach
According to the fact that the inner-class distance among samples within the same cluster is supposed to be smaller than the inter-class distance among clusters, the algorithm will dynamically adjust initial cluster centers that are randomly selected. Consequently, such adjusted initial cluster centers will be highly representative in the sense that they are distributed among as many samples as possible. As a result, local optima that are common in K-means clustering can then be effectively reduced. In addition, the algorithm is able to obtain all initial cluster centers simultaneously (instead of one center at a time) during the dynamic adjustment.
Findings
Experimental results demonstrate that the proposed algorithm greatly improves the accuracy of traditional K-means clustering results and, in a more efficient manner.
Originality/value
The authors presented in this paper an efficient algorithm, which is able to dynamically adjust initial cluster centers that are randomly selected. The adjusted centers are highly representative, i.e. they are distributed among as many samples as possible. As a result, local optima that are common in K-means clustering can be effectively reduced so that the authors can achieve an improved clustering accuracy. In addition, the algorithm is a cost-efficient one and the enhanced clustering accuracy can be obtained in a more efficient manner compared with traditional K-means algorithm.
Details
Keywords
Padmavati Shrivastava, K.K. Bhoyar and A.S. Zadgaonkar
The purpose of this paper is to build a classification system which mimics the perceptual ability of human vision, in gathering knowledge about the structure, content and the…
Abstract
Purpose
The purpose of this paper is to build a classification system which mimics the perceptual ability of human vision, in gathering knowledge about the structure, content and the surrounding environment of a real-world natural scene, at a quick glance accurately. This paper proposes a set of novel features to determine the gist of a given scene based on dominant color, dominant direction, openness and roughness features.
Design/methodology/approach
The classification system is designed at two different levels. At the first level, a set of low level features are extracted for each semantic feature. At the second level the extracted features are subjected to the process of feature evaluation, based on inter-class and intra-class distances. The most discriminating features are retained and used for training the support vector machine (SVM) classifier for two different data sets.
Findings
Accuracy of the proposed system has been evaluated on two data sets: the well-known Oliva-Torralba data set and the customized image data set comprising of high-resolution images of natural landscapes. The experimentation on these two data sets with the proposed novel feature set and SVM classifier has provided 92.68 percent average classification accuracy, using ten-fold cross validation approach. The set of proposed features efficiently represent visual information and are therefore capable of narrowing the semantic gap between low-level image representation and high-level human perception.
Originality/value
The method presented in this paper represents a new approach for extracting low-level features of reduced dimensionality that is able to model human perception for the task of scene classification. The methods of mapping primitive features to high-level features are intuitive to the user and are capable of reducing the semantic gap. The proposed feature evaluation technique is general and can be applied across any domain.
Details
Keywords
Chunyan Zeng, Dongliang Zhu, Zhifeng Wang, Zhenghui Wang, Nan Zhao and Lu He
Most source recording device identification models for Web media forensics are based on a single feature to complete the identification task and often have the disadvantages of…
Abstract
Purpose
Most source recording device identification models for Web media forensics are based on a single feature to complete the identification task and often have the disadvantages of long time and poor accuracy. The purpose of this paper is to propose a new method for end-to-end network source identification of multi-feature fusion devices.
Design/methodology/approach
This paper proposes an efficient multi-feature fusion source recording device identification method based on end-to-end and attention mechanism, so as to achieve efficient and convenient identification of recording devices of Web media forensics.
Findings
The authors conducted sufficient experiments to prove the effectiveness of the models that they have proposed. The experiments show that the end-to-end system is improved by 7.1% compared to the baseline i-vector system, compared to the authors’ previous system, the accuracy is improved by 0.4%, and the training time is reduced by 50%.
Research limitations/implications
With the development of Web media forensics and internet technology, the use of Web media as evidence is increasing. Among them, it is particularly important to study the authenticity and accuracy of Web media audio.
Originality/value
This paper aims to promote the development of source recording device identification and provide effective technology for Web media forensics and judicial record evidence that need to apply device source identification technology.
Details
Keywords
Huajun Liu, Cailing Wang and Jingyu Yang
– This paper aims to present a novel scheme of multiple vanishing points (VPs) estimation and corresponding lanes identification.
Abstract
Purpose
This paper aims to present a novel scheme of multiple vanishing points (VPs) estimation and corresponding lanes identification.
Design/methodology/approach
The scheme proposed here includes two main stages: VPs estimation and lane identification. VPs estimation based on vanishing direction hypothesis and Bayesian posterior probability estimation in the image Hough space is a foremost contribution, and then VPs are estimated through an optimal objective function. In lane identification stage, the selected linear samples supervised by estimated VPs are clustered based on the gradient direction of linear features to separate lanes, and finally all the lanes are identified through an identification function.
Findings
The scheme and algorithms are tested on real data sets collected from an intelligent vehicle. It is more efficient and more accurate than recent similar methods for structured road, and especially multiple VPs identification and estimation of branch road can be achieved and lanes of branch road can be identified for complex scenarios based on Bayesian posterior probability verification framework. Experimental results demonstrate VPs, and lanes are practical for challenging structured and semi-structured complex road scenarios.
Originality/value
A Bayesian posterior probability verification framework is proposed to estimate multiple VPs and corresponding lanes for road scene understanding of structured or semi-structured road monocular images on intelligent vehicles.
Details
Keywords
J.R. Llata, E.G. Sarabia and J.P. Oria
This paper presents an evaluation of several types of neural networks for object recognition by means of ultrasonic sensors. Initially, in order to obtain information from the…
Abstract
This paper presents an evaluation of several types of neural networks for object recognition by means of ultrasonic sensors. Initially, in order to obtain information from the ultrasonic signal, a parametric method is proposed and a set of features is extracted from the ultrasonic echo envelope. Then, it is necessary to evaluate how much information is provided for each characteristic obtained. Therefore, it has been necessary to carry out an analysis in order to detect the most relevant features. Results about information provided for each feature are presented by order of preference. Subsequently, using these features extracted from the echo signal, an experimental set‐up has been carried out in order to highlight the capabilities of different types of neural networks with this information. Finally, results obtained from experimental tests are presented, and the pattern recognition capabilities of each neural network type, using the selected features, are shown.
Details
Keywords
Decision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the emotional…
Abstract
Purpose
Decision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the emotional states of people. However, the representation and classification of emotions is a very challenging task. The study used customized methods of deep learning models to aid in the accurate classification of emotions and sentiments.
Design/methodology/approach
The present study presents affective computing model using both text and image data. The text-based affective computing was conducted on four standard datasets using three deep learning customized models, namely LSTM, GRU and CNN. The study used four variants of deep learning including the LSTM model, LSTM model with GloVe embeddings, Bi-directional LSTM model and LSTM model with attention layer.
Findings
The result suggests that the proposed method outperforms the earlier methods. For image-based affective computing, the data was extracted from Instagram, and Facial emotion recognition was carried out using three deep learning models, namely CNN, transfer learning with VGG-19 model and transfer learning with ResNet-18 model. The results suggest that the proposed methods for both text and image can be used for affective computing and aid in decision-making.
Originality/value
The study used deep learning for affective computing. Earlier studies have used machine learning algorithms for affective computing. However, the present study uses deep learning for affective computing.
Details
Keywords
Rakesh Venkitasubramony and Gajendra Kumar Adil
This paper aims to develop an approach to design a warehouse that uses class-based storage policy in a way that minimizes both space cost and material handling cost.
Abstract
Purpose
This paper aims to develop an approach to design a warehouse that uses class-based storage policy in a way that minimizes both space cost and material handling cost.
Design/methodology/approach
The authors argue for and develop an optimization model for joint determination of lane depth, lateral width and product partitions for minimizing the sum of handling and space costs. In doing so, the assumption of perfect sharing is also relaxed. Using computational experiments, the authors characterize the operating conditions based on pick density and cost ratio. The authors further outline an approach to decide the conditions under which it is advantageous to implement multiple classes.
Findings
More classes are preferred when both the pick density and cost ratio are higher and vice versa. Factors such as demand skewness, lane depth and stacking height affect the space-sharing dynamics.
Practical implications
The paper gives the practical insights on when the conditions under which it is advisable to partition a warehouse into a certain number of classes instead of maintaining and when to maintain as a single-class block. It also gives a method to estimate the space-sharing factor, given a combination of operating parameters.
Originality/value
Very few studies have seen class-based storage policy in the context of block stacked warehouse layout. Further, block stacking designs have mostly been approached with the objective of minimizing just the space cost. This study contributes to the literature by developing an integrated model, which has the practical utility.
Details
Keywords
Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification…
Abstract
Purpose
Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics.
Design/methodology/approach
The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value.
Findings
Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared.
Originality/value
To the best of the author’s knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression.
Details
Keywords
Chih-Hsien Hsia, Chin-Feng Lai and Yu-Sheng Su
The purpose of this study, we present a robot used in education. Influenced by the epoch of revolutionary digital technology, the methodology of education has gone boundless. The…
Abstract
Purpose
The purpose of this study, we present a robot used in education. Influenced by the epoch of revolutionary digital technology, the methodology of education has gone boundless. The robot programming sustainability and ability to solve problems is one an important skill that coding students require to learn programming. This educational have been integrated into curriculum instruction in clubs.
Design/methodology/approach
Robotics education has been regarded as a potential approach to enhance students' Science, technology, engineering, and mathematics learning competencies. The popular platform of robots diversifies educational practices by its advantages of reorganizational and logical forms. In this paper, we focus on the effects of applying blended instructional approaches to robot education on students' programming sustainability and ability.
Findings
The students of department of mechanical engineering at the University in Taipei city, who participate elective educational robot courses, prove through surveys that the problem-based leaning method with robot programming can effectively enhance students' interests and learning motivations in learning new knowledge and promote students' designing skills for a sustainable society.
Originality/value
In this paper, the authors focus on the effects of applying blended instructional approaches to robot education on students' programming sustainability and ability.
Details
Keywords
The purpose of this paper is to describe the programs of status leveling – such as through the elimination of executive washrooms, reserved parking, and so forth – are a…
Abstract
Purpose
The purpose of this paper is to describe the programs of status leveling – such as through the elimination of executive washrooms, reserved parking, and so forth – are a taken‐for‐granted feature of many workplace involvement and quality improvement programs, yet no prior research has investigated the presumed effects.
Design/methodology/approach
This conceptual paper enumerates devices commonly used to level status in organizations, and presents a number of propositions intended to capture the major effects. The paper draws on extant literatures from social psychology, sociology, and organizational theory to account for processes and effects of leveling.
Findings
Leveling devices lead to several proximate outcomes: increased cross‐status interaction and contact, literal blurring of status, role flexibility, and low power distance perceptions. These in turn mediate the relation between leveling and several broader organizational outcomes, including distributive justice based upon equality, community, communication, and empowerment. Factors moderating the effects of leveling are explored.
Research limitations/implications
While the salutary effects of leveling tend to be taken for granted, it is possible to specify how leveling generates specific behavioral, attitudinal, and performance related outcomes. The model should be empirically tested.
Practical implications
The findings provide managers with a fine‐grained understanding of this important set of organizational practices.
Originality/value
No prior scholarship has focused on this most important topic.
Details