Complex & Intelligent Systems
Latest Publications


TOTAL DOCUMENTS

508
(FIVE YEARS 499)

H-INDEX

19
(FIVE YEARS 19)

Published By Springer-Verlag

2198-6053, 2199-4536
Updated Saturday, 18 September 2021

Author(s):  
Peng Lu ◽  
Zhuo Zhang ◽  
Mengdi Li

AbstractUnder the mobile internet and big data era, more and more people are discussing and interacting online with each other. The forming process and evolutionary dynamics of public opinions online have been heavily investigated. Using agent-based modeling, we expand the Ising model to explore how individuals behave and the evolutionary mechanism of the life cycles. The big data platform of Douban.com is selected as the data source, and the online case “NeiYuanWaiFang” is applied as the real target, for our modeling and simulations to match. We run 10,000 simulations to find possible optimal solutions, and we run 10,000 times again to check the robustness and adaptability. The optimal solution simulations can reflect the whole life cycle process. In terms of different levels and indicators, the fitting or matching degrees achieve the highest levels. At the micro-level, the distributions of individual behaviors under real case and simulations are similar to each other, and they all follow normal distributions; at the middle-level, both discrete and continuous distributions of supportive and oppositive online comments are matched between real case and simulations; at the macro-level, the life cycle process (outbreak, rising, peak, and vanish) and durations can be well matched. Therefore, our model has properly seized the core mechanism of individual behaviors, and precisely simulated the evolutionary dynamics of online cases in reality.


Author(s):  
Nian Zhang ◽  
Zhaojie Ju ◽  
Chenguang Yang ◽  
Dingguo Zhang ◽  
Jinguo Liu
Keyword(s):  

Author(s):  
Shanshan Li ◽  
Yong He ◽  
Li Zhou

AbstractThis paper considers a make-to-order system where production gets disrupted due to a random supply failure. To avoid potential stock-out risk and responding price increase during disruption, customers might decide to stockpile extra units for future consumption. We investigate the contingent sourcing strategy for the manufacturer to cope with the disruption. To this end, we first discuss the optimal post-disruption stockpiling decision for customers. In view of expected disruption duration, price rise, and inventory holding cost, three types of stockpiling behavior are analytically provided for the customers: non-stockpiling, gradual stockpiling, and instantaneous stockpiling. Next, a model is formulated to optimize the joint decision of contingent sourcing time and quantity, with the objective of maximizing profit expectation. Finally, by conducting numerical analysis, we generate further insights into the role of relative factors and provide specific managerial suggestions on how to adapt dynamic contingent sourcing strategies to alleviate different disruptions, under different market environments and customer behaviors.


Author(s):  
Rabia Latif ◽  
Malik Uzair Ahmed ◽  
Shahzaib Tahir ◽  
Seemab Latif ◽  
Waseem Iqbal ◽  
...  

AbstractEdge computing is a distributed architecture that features decentralized processing of data near the source/devices, where data are being generated. These devices are known as Internet of Things (IoT) devices or edge devices. As we continue to rely on IoT devices, the amount of data generated by the IoT devices have increased significantly due to which it has become infeasible to transfer all the data over to the Cloud for processing. Since these devices contain insufficient storage and processing power, it gives rise to the edge computing paradigm. In edge computing data are processed by edge devices and only the required data are sent to the Cloud to increase robustness and decrease overall network overhead. IoT edge devices are inherently suffering from various security risks and attacks causing a lack of trust between devices. To reduce this malicious behavior, a lightweight trust management model is proposed that maintains the trust of a device and manages the service level trust along with quality of service (QoS). The model calculates the overall trust of the devices by using QoS parameters to evaluate the trust of devices through assigned weights. Trust management models using QoS parameters show improved results that can be helpful in identifying malicious edge nodes in edge computing networks and can be used for industrial purposes.


Author(s):  
Machbah Uddin ◽  
Farah Jahan ◽  
Mohammad Khairul Islam ◽  
Md. Rakib Hassan

AbstractNowadays, data are the most valuable content in the world. In the age of big data, we are generating quintillions of data daily in the form of text, image, video, etc. Among them, images are highly used in daily communications. Various types of images, e.g., medical images, military images, etc. are highly confidential. But, due to data vulnerabilities, transmitting such images in a secured way is a great challenge. For this reason, researchers proposed different image cryptography algorithms. Recently, biological deoxyribonucleic acid (DNA)-based concepts are getting popular for ensuring image security as well as encryption as they show good performance. However, these DNA-based methods have some limitations, e.g., these are not dynamic and their performance results are far from ideal values. Further, these encryption methods usually involve two steps, confusion and diffusion. Confusion increases huge time complexity and needs to send one or more additional map tables with a cipher to decrypt the message. In this research, we propose a novel and efficient DNA-based key scrambling technique for image encryption that addresses the above limitations. We evaluate our proposed method using 15 different datasets and achieved superior performance scores of entropy, keyspace, cipher pixel correlations, variance of histogram, time complexity and PSNR. The experimental results show that our method can be used for image encryption with a high level of confidentiality.


Author(s):  
Jue Wang ◽  
Ping Guo ◽  
Yanjun Li

AbstractAutoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren’t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.


Author(s):  
Jun Ye ◽  
Shigui Du ◽  
Rui Yong

AbstractAlthough a single-valued neutrosophic multi-valued set (SVNMVS) can reasonably and perfectly express group evaluation information and make up for the flaw of multi-valued/hesitant neutrosophic sets in group decision-making problems, its information expression and group decision-making methods still lack the ability to express and process single- and interval-valued hybrid neutrosophic multi-valued information. To overcome the drawbacks, this study needs to propose single- and interval-valued hybrid neutrosophic multi-valued sets (SIVHNMVSs), correlation coefficients of consistency interval-valued neutrosophic sets (CIVNSs), and their multi-attribute group decision-making (MAGDM) method in the setting of SIVHNMVSs. First, we propose SIVHNMVSs and a transformation method for converting SIVHNMVSs into CIVNSs based on the mean and consistency degree (the complement of standard deviation) of truth, falsity and indeterminacy sequences. Then, we present two correlation coefficients between CIVNSs based on the multiplication of both the correlation coefficient of interval-valued neutrosophic sets and the correlation coefficient of neutrosophic consistency sets and two weighted correlation coefficients of CIVNSs. Next, a MAGDM method is developed based on the proposed two weighted correlation coefficients of CIVNSs for performing MAGDM problems under the environment of SIVHNMVSs. At last, a selection case of landslide treatment schemes demonstrates the application of the proposed MAGDM method under the environment of SIVHNMVSs. By comparative analysis, our new method not only overcomes the drawbacks of the existing method, but also is more extensive and more useful than the existing method when tackling MAGDM problems in the setting of SIVHNMVSs.


Author(s):  
Hassan Khaled ◽  
Osama Abu-Elnasr ◽  
Samir Elmougy ◽  
A. S. Tolba

AbstractIn recent years, the adoption of machine learning has grown steadily in different fields affecting the day-to-day decisions of individuals. This paper presents an intelligent system for recognizing human’s daily activities in a complex IoT environment. An enhanced model of capsule neural network called 1D-HARCapsNe is proposed. This proposed model consists of convolution layer, primary capsule layer, activity capsules flat layer and output layer. It is validated using WISDM dataset collected via smart devices and normalized using the random-SMOTE algorithm to handle the imbalanced behavior of the dataset. The experimental results indicate the potential and strengths of the proposed 1D-HARCapsNet that achieved enhanced performance with an accuracy of 98.67%, precision of 98.66%, recall of 98.67%, and F1-measure of 0.987 which shows major performance enhancement compared to the Conventional CapsNet (accuracy 90.11%, precision 91.88%, recall 89.94%, and F1-measure 0.93).


Author(s):  
Vivek Mehta ◽  
Seema Bawa ◽  
Jasmeet Singh

AbstractA massive amount of textual data now exists in digital repositories in the form of research articles, news articles, reviews, Wikipedia articles, and books, etc. Text clustering is a fundamental data mining technique to perform categorization, topic extraction, and information retrieval. Textual datasets, especially which contain a large number of documents are sparse and have high dimensionality. Hence, traditional clustering techniques such as K-means, Agglomerative clustering, and DBSCAN cannot perform well. In this paper, a clustering technique especially suitable to large text datasets is proposed that overcome these limitations. The proposed technique is based on word embeddings derived from a recent deep learning model named “Bidirectional Encoders Representations using Transformers”. The proposed technique is named as WEClustering. The proposed technique deals with the problem of high dimensionality in an effective manner, hence, more accurate clusters are formed. The technique is validated on several datasets of varying sizes and its performance is compared with other widely used and state of the art clustering techniques. The experimental comparison shows that the proposed clustering technique gives a significant improvement over other techniques as measured by metrics such Purity and Adjusted Rand Index.


Author(s):  
Xiaofang Zhao ◽  
Yuhong Liu ◽  
Zhigang Jin

AbstractAs one of the hot research directions in natural language processing, sentiment analysis has received continuous and extensive attention. Different from explicit sentiment words indicating sentiment polarity, implicit sentiment analysis is a more challenging problem due to the lack of sentiment words, which makes it inadequate to use traditional sentiment analysis method to judge the polarity of implicit sentiment. This paper takes sentiment analysis as a special sign link prediction problem, which is different from traditional text-based method. In particular, by performing the word graph-based text level information embedding and heterogeneous social network information embedding (i.e. user social relationship network embedding, and user-entity sentiment network embedding), the proposed scheme learns the highly nonlinear representations of network nodes, explores early fusion method to combine the strength of these two types of embedding modeling, optimizes all parameters simultaneously and creates enhanced context representations, leading to better capture of implicit sentiment polarity. The proposed method has been examined on real-world dataset, for implicit sentiment link prediction task. The experimental results demonstrate that the proposed method outperforms state-of-the-art schemes, including LINE, node2vec, and SDNE, by 20.2%, 19.8%, and 14.0%, respectively, on accuracy, and achieves at least 14% gains on AUROC. For sentiment analysis accuracy, the proposed method achieves AUROC of 80.6% and accuracy of 78.3%, which is at least 31% better than other models. This work can provide useful guidance on the implicit sentiment analysis.


Sign in / Sign up

Export Citation Format

Share Document