Zhixiao Wang

1. Coagulation, as a fundamental process in water treatment, plays a pivotal role in both drinking water purification and industrial wastewater treatment [1, 2]. In aqueous systems, colloidal and f...

A smart gateway, which plays a crucial role in a smart home, generally bridges the inside and outside home networks, as well as collaboratively manages the intelligent Internet of things (IoT) devices equipped in the smart home, due to it can convert different communication protocols, gather generated data from surrounding devices, and even conduct some local data processing tasks. In this survey, we first review the whole smart home research area with a focus on a framework based on edge computing and multiple intelligent agents. Then, relying on the time‐line and different metrics including quality of experience (QoE), artificial intelligence support, software‐defined network, and so on, we divide the evolution of smart gateways into three generations. Considering recent smart gateways mainly belong to the second generation, we further investigate and classify them into two categories from another perspective of user‐awareness and data‐awareness. Afterward, we discussed the key enabling technologies and components of smart gateways, such as operating systems, wireless communication protocols, and security. At last, we explore the challenges and trends of smart gateways and point out that maximizing QoE as well as data‐awareness is the key feature of future gateways. This survey has practical significance for building a smart home system, broadly speaking, even for constructing the IoT and smart space.

Cloud computing attracts users with its advantage of unlimited resource supply where resources can be elastically expanded on demand and balanced-load at the same time. This means that the application in the cloud environment should run in the way of elastic expansion cluster. At present, most of the elastic expansion and load balancing technologies provided by IaaS level are oriented to virtual machines (VM), with little consideration of application level, which does not fundamentally meet the needs of users. Based on this, starting from the motivation of cloud migration, we first analyse the cloud migration technology from three aspects: migration object, migration means and migration objectives, then explore the cloud migration criteria and four cloud migration strategies at the application level in the cloud environment, and point out that cloud migration should be optimized and maintained in terms of elastic expansion, load balancing, security, etc.

The automatic evaluation of Chinese character writing quality has a wide application prospect. Most of the existing evaluation methods of Chinese character writing quality are based on radical segmentation and feature judgment, which require the high accuracy of Chinese character segmentation. However, there are many problems in the real handwriting, such as continuous writing, uneven strength of writing, personalized writing style and so on, which lead to the difficulty of segmentation in the ordinary handwriting. To solve the above problems, we propose an effective method based on image texture where the uniformity of writing lines and writing style is taken as an effective criterion. In our method, Gabor transform is used to extract the image features of writing samples, and finally the statistical learning method of support vector machine is used to effectively evaluate the writing quality. Experiments on multiple real datasets including CHAED show that our method is effective and accurate. The advantage of this method is that it does not need to segment fonts, and the cost of global feature extraction is small.

Based on the huge volumes of user check-in data in LBSNs, users’ intrinsic mobility patterns can be well explored, which is fundamental for predicting where a user will visit next given his/her historical check-in records. As there are various types of nodes and interactions in LBSNs, they can be treated as Heterogeneous Information Network (HIN) where multiple semantic meta-paths can be extracted. Inspired by the recent success of meta-path context based embedding techniques in HIN, in this paper, we design a deep neural network framework leveraging various meta-path contexts for fine-grained user location prediction. Experimental results based on two real-world LBSN datasets demonstrate the best effectiveness of the proposed approach using various evaluation metrics than others.

Ad-Hoc network which is one kind of self-organized networks is much more vulnerable than the infrastructural network with the properties of highly changeable linkage, dynamic structure, and wireless connections so that the tradition intrusion detection system (IDS) should be improved to adapt in such network with limited computing resources and open channels. To ensure the security in Ad-Hoc network, the efficient anomaly detection methods should be probed. Over the past years, many studies have implemented anomaly detection methods (intrusion detection techniques) based on machine-learning methods in this field. This article analyzes the existing security problem in Ad-Hoc network, presents the basic theory of intrusion detection for Ad-Hoc network, and reviews the current and recent anomaly detection methods used machine learning techniques in the intrusion detection system.

Network intrusion detection is a relatively mature research topic, but one that remains challenging particular as technologies and threat landscape evolve. Here, a semi-supervised tri-Adaboost (STA) algorithm is proposed. In the algorithm, three different Adaboost algorithms are used as the weak classifiers (both for continuous and categorical data), constituting the decision stumps in the tri-training method. In addition, the chi-square method is used to reduce the dimension of feature and improve computational efficiency. We then conduct extensive numerical studies using different training and testing samples in the KDDcup99 dataset and discover the flows demonstrated that (1) high accuracy can be obtained using a training dataset which consists of a small number of labeled and a large number of unlabeled samples. (2) The algorithm proposed is reproducible and consistent over different runs. (3) The proposed algorithm outperforms other existing learning algorithms, even with only a small amount of labeled data in the training phase. (4) The proposed algorithm has a short execution time and a low false positive rate, while providing a desirable detection rate.