Search

Logic Encryption is a hardware security technique that protects integrated circuit designs that are fabricated at untrusted pure play foundries from being pirated or maliciously modified. In the technique, logic gates are added to the design that are driven by an added key input bus, such that the correct behavior of the circuit is recovered with only the exact correct key input pattern. However, the power, performance, and area (PPA) cost of implementing logic encryption has often been ignored in the literature in favor of increasing the level of security provided. This has proved to be a significant hurdle in transitioning the method to use in commercial-grade designs and a systematic methodology of constraining the cost of logic encryption is needed. In this paper, we propose a generalized Constraint-Directed Logic Encryption (CDLE) methodology. In CDLE, the potential design space of encrypted versions of a circuit is searched to apply logic encryption under PPA constraints. Two example CDLE methods are proposed. The first is a concurrent tree search method which uses commercial tools to sample designs for their PPA cost and determine the optimal encryption strategy. In this method, PPA cost is accurately analyzed at the cost of heavy runtime. The second is a machine learning approach which estimates the PPA cost to predict the optimal encryption strategy. The machine learning model developed in this work is limited, but the results are promising as a direction for study in logic encryption. Detailed experimental results evaluating both methods are presented.

The evolution of manipulator robots has increased the complexity of their models and applications, requiring that the inverse kinematics (IK) methods integrated into their control systems to have features such as fast convergence, completeness, low computational cost, and the ability to avoid local minima and singularities. We propose in this paper a new probabilistic IK solver based on the probabilistic search method known as Rapidly-Exploring Random Tree (RRT), the Workspace-RRT. The technique grows the tree as a spatial representation of the manipulator on the workspace instead of the configuration space, which reduces the search space up to 3 dimensions. Based on this new representation we also present the Manipulator-Based Rapidly Random Tree (MB-RRT) by incorporating to the Workspace-RRT a new probability model and a new metric for the closest node. We evaluate the presented methods through simulated experiments in the Matlab software. First, we evaluate the impact of the proposed aspects through a comparison between the RRT-based IK solvers, which emphasizes the proposed changes as a key to make the method suitable for the IK problem. At last, we show the use of the MB-RRT for precision tasks and obstructed environments.

In dynamic unmanned aerial vehicle (UAV) networks, localization and clustering are fundamental functions for cooperative control. In this article, we propose bio-inspired localization (BIL) and clustering (BIC) schemes in UAV networks for wildfire detection and monitoring. First, we develop a hybrid gray wolf optimization (HGWO) method and propose an energy-efficient three-dimensional BIL algorithm based on the HGWO, which reduces localization errors, avoids flip ambiguity in bounded distance measurement errors, and achieves high localization accuracy. In BIL, the bounding cube method is applied to reduce the initial search space. Second, we propose an energy-efficient BIC algorithm based on the HGWO. The BIC algorithm utilizes the gray wolf leadership hierarchy to improve clustering efficiency. We also develop an analytical model for determining the optimal number of clusters that provide the minimum number of transmissions. Finally, we propose a GWO-based compressive sensing (CS-GWO) algorithm to transmit data from cluster heads (CHs) to the base station (BS). The proposed CS-GWO constructs an efficient routing tree from CHs to the BS, thereby reducing the routing delay and the number of transmissions. Our performance evaluation shows that the proposed BIL and BIC significantly outperform conventional schemes in terms of various performance metrics under different scenarios.

The third generation of Audio Video coding Standard (AVS3) is an emerging video coding standard that surpasses High Efficiency Video Coding (HEVC). AVS3 allows flexible block subdivision by applying Quad-Tree (QT), Binary-Tree (BT) plus Extend Quad-Tree (EQT) partition structure, while the increased flexibility comes at the cost of enormous coding complexity. In this paper, an ingenious early termination mechanism is proposed to skip unnecessary exhaustive searches of the whole tree branches. We carry out a series of restrictive measures based on Coding Unit (CU) size and iteration status to make the sophisticated EQT split mode concentrate more on small CUs with complex texture structure. Historical QTBT partition information is also adopted as an important factor to skip EQT split mode in advance. Meanwhile, a fast CU partition algorithm based on the gradient is proposed to skip horizontal or vertical BT/EQT partition of CUs with prominent texture structure in another direction, in which early termination can be directly conducted in homogenous areas at the same time. Extensive experiments demonstrate that the proposed method can save 43% encoding time with only 0.53% BDBR increase on average under All Intra(AI) configuration, which outperforms the preexisting fast algorithms.

To prevent privacy leakage, cloud services need to take corresponding methods, so participants often face the dilemma of service utility and privacy protection. In this paper, we propose a dynamic adaptive access control model based on trust permission and privacy protection to solve the problem of privacy disclosure and utility in the cloud service. Firstly, we add the concept of obligation and purpose into access control and establish the privacy information tree and privacy policy tree. Secondly, we establish a new trust evaluation and give the corresponding weight algorithm. Thirdly, we quantify the privacy information with the normal space and correlation coefficient method. Further, we propose a tradeoff relationship model between trust permission and privacy protection, each participant can select the corresponding parameters according to the actual requirement and personal preference. Experimental analysis and comparison results verify the feasibility, effectiveness, and superiority of our method. Finally, we summarize the work of this paper and point out the future development direction.

Software-Defined Networking (SDN) is a new type of technology that embraces high flexibility and adaptability. The applications in SDN have the ability to manage and control networks while ensuring load balancing, access control, and routing. These are considered the most significant benefits of SDN. However, SDN can be influenced by several types of conflicting flows which may lead to deterioration in network performance in terms of efficiency and optimisation. Besides, SDN conflicts occur due to the impact and adjustment of certain features such as priority and action. Moreover, applying machine learning algorithms in the identification and classification of conflicting flows has limitations. As a result, this paper presents several machine learning algorithms that include Decision Tree (DT), Support Vector Machine (SVM), Extremely Fast Decision Tree (EFDT) and Hybrid (DT-SVM) for detecting and classifying conflicting flows in SDNs. The EFDT and hybrid DT-SVM algorithms were designed and deployed based on DT and SVM algorithms to achieve improved performance. Using a range flows from 1000 to 100000 with an increment of 10000 flows per step in two network topologies namely, Fat Tree and Simple Tree Topologies, that were created using the Mininet simulator and connected to the Ryu controller, the performance of the proposed algorithms was evaluated for efficiency and effectiveness across a variety of evaluation metrics. The experimental results of the detection of conflict flows show that the DT and SVM algorithms achieve accuracies of 99.27% and 98.53% respectively while the EFDT and hybrid DT-SVM algorithms achieve respective accuracies of 99.49% and 99.27%. In addition, the proposed EFDT algorithm achieves 95.73% accuracy on the task of classification between conflict flow types. The proposed EFDT and hybrid DT-SVM algorithms show a high capability of SDN applications to offer fast detection and classification of conflict flows.

In this paper, we address the problem of solving rearranging tasks using a robot. Rearranging tasks are challenging because they include many problems to solve at the same time, such as determining how to pick the items as well as planning how and where to place them. Solving a rearranging task usually consists of finding a set of pick-and-place instructions with a symbolic planner to perform the task. However, if the symbolic planner does not consider the robot’s capability to execute the instructions, it will likely generate many infeasible instructions, which wastes time in multiple trials and failures. Therefore, we propose to combine symbolic and motion planning to confirm a sequence of instructions before its execution by the robot. To achieve this combination, we use a Motion Feasibility Checker (MFC), which selects a set of feasible poses for the robot from a feasibility database. The MFC verifies that the instructions of the symbolic planning are valid and searches for a pick-and-place pair of poses to execute the instructions. We use a Monte Carlo Tree Search (MCTS) as the symbolic planner, and we combine it with the MFC when creating or expanding the states in the tree. After the MCTS finds a set of instructions for the rearranging task, we execute those instructions with the robot. As these instructions were previously validated, the robot is able to execute them. The proposed method was tested in a simulation environment that reproduces the scenario of rearranging products on a shelf of a convenience store. The experiment results show that the proposed method outperforms the conventional method in various initial states of increasing levels of difficulty.

Increasing human activities have caused serious disturbance to global forest resources, so how to accurately identify individual trees has become an important task of forest resources investigation. In order to get the accurate number of individual trees, this paper took coniferous forest and mixed coniferous and broad-leaved forest as experimental samples, as well as Digital Orthophoto Map and airborne LiDAR Point Cloud as research data. We propose a deep Learning individual tree segmentation method based on RetinaNet model and PCS algorithm by doing comparative analysis (classical Watershed Algorithm and Layer Stacking Algorithm) at the plots (with high, medium, and low densities). The experimental results show that the method proposed in this paper can solve the problem of individual tree segmentation in high density forest and improve its degree of automation. Compared with Watershed algorithm and Layer stacking algorithm, F-Measure is improved by 6%-29% and 7%-20%, respectively. In other words, the results of individual tree segmentation presented in this paper can not only improve the precision of individual tree segmentation, but also maintain a high detection rate, which can meet the accuracy and high efficiency of individual tree extraction, so as to meet the needs for modern forestry investigation.

In this paper, sentiment analysis of two critical events is presented using machine learning (ML) techniques. COVID-19 has put immense pressure across the globe and sentiment analysis of data from Twitter using ML techniques has become a hot topic. We extract the COVID-19 and Expo2020 data from twitter. First, we evaluate the Twitter data of these two significant events for sentiment analysis and then use the classification algorithm to find out the usefulness of the proposed methodology. A hybrid approach that uses supervised learning model Support Vector Machine (SVM) combined with Bayes Factor Tree Augmented Naive Bayes (BFTAN) technique is proposed to accurately classify the input tweet while keeping in mind the different challenges of sentiment analysis. Our study has four main contributions: a) hybrid classification techniques are thoroughly explored for sentiment analysis, b) a novel hybrid classification approach is proposed for sentiment analysis, c) a new Twitter dataset related to COVID-19 that can be used for future research, d) empirical study to show that the hybrid-classification approach can achieve comparable performance in improving accuracy, identifying the polarity of comparative sentences, distinguishing the intensity of opinion words, considering negative words, and handling sarcasm as well. The experimental results show that the proposed approach is robust in producing correct classification results with the tradeoff of poor time efficiency. Also, the accuracy of the proposed model is comparable to other classifiers, which is encouraging. Class distribution of each dataset demonstrates that more than 60% of tweets are negative.

The random fluctuation and non-uniformity of Photovoltaic (PV) power generation greatly affect the power grids’ stability and operation. This paper addresses the high volatility of PV power by proposing a precise and reliable ensemble learning model for short-term PV power generation forecasting. The proposed forecasting tool incorporates a base model and meta-model layers. The first-layer base learner combines extreme learning machines, extremely randomized trees, k-nearest neighbor, and mondrian forest models. The meta-model layer exploits deep belief network to generate the final outputs. The hyper-parameters of the proposed stacking ensemble are carefully tuned using the tree-structured of parzen estimators algorithm to achieve top-notch predictive performance. The proposed model is thoroughly assessed through an empirical study using a real data set from Australia. The simulation results confirm the performance superiority of the proposed model over the existing forecasting models with the lowest average root mean square error and mean absolute percentage error of 3.88kW and 2.30%, respectively.

Knowledge bases (KB), such as Probase and ConceptNet, play an important role in many natural language processing tasks. Compared with resource-poor languages such as Chinese, the scale and quality of English knowledge bases are obviously superior. To expand Chinese KBs by using English KB resources, translating English KBs into Chinese is an effective way. In this direction, two major challenges are how to model more structure semantics to improve translation quality and how to avoid labor-intensive feature engineering. We address these challenges by presenting a neural network approach, which learns tree representation by different structure features. We also build a new dataset for English-Chinese KB translation from Probase and ConceptNet, and compare our proposed approach with several baselines on it. Experimental results show that the proposed method improves the translation accuracy compared with baseline methods. Meanwhile, we translate Probase and ConceptNet into Zh-Probase and Zh-ConceptNet by our proposed model, and release them to the public, in hope of speeding up the research in Chinese natural language processing tasks.

The clustered shortest-path tree problem (CluSPTP) is an extension of the classical single-source shortest-path problem, in which, given a graph with the set of nodes partitioned into a predefined, mutually exclusive and exhaustive set of clusters, we are looking for a shortest-path spanning tree from a given source to all the other nodes of the graph, with the property that each cluster should induce a connected subtree. CluSPTP belongs to the class of generalized combinatorial optimization problems, and, in general, is proved to be a non-deterministic polynomial time hard (NP-hard) problem. In this paper, we propose a novel genetic algorithm (GA), which is designed to fit the challenges of the investigated problem. The main features of our GA are: the use of an innovative representation scheme that allows us to define meaningful genetic operators and the use of a hybrid initial population. Extensive computational results are reported and discussed for two sets of instances: euclidean and non-euclidean. The performance of the proposed algorithm was evaluated on six types of benchmark euclidean instances available in the literature and on six types of non-euclidean instances obtained from the corresponding euclidean ones. The obtained results show an improvement with respect to existing methods from the literature, both in terms of the quality of the achieved solutions and the computation times necessary to obtain them. They demonstrate that our genetic algorithm outperforms all the existing methods from the literature, providing for all the existing benchmark instances the optimal solutions in all 30 independent trials.

The number of process models in process repositories has grown in recent years. For this reason, it is becoming increasingly important to efficiently retrieve process models from the repositories for management purposes. In fact, the method of retrieval is also essential to increase the potential of additional analysis such as similarity and behavioral analysis and compliance checking. Most retrieval methods can be classified as structural or behavioral retrieval. Behavioral retrieval considers the relationships between activities during process execution. In this paper, we introduce such a new behavior-based retrieval method called Partitioning Behavioral Retrieval. It is the first retrieval method that allows process models to contain inclusive (OR) gateways. The method is based on the dominance relation and a node-based process structure tree known from compiler theory. Although it uses instance subgraph checking as a computational basis, it derives new behavioral relations by using transitive rules. Currently, the method is limited to acyclic process models for ease of introduction. Experiments show the time advantage offered by our new method.

Monte Carlo Tree Search (MCTS) algorithms show outstanding strengths in decision-making problems such as the game of Go. However, MCTS requires significant computing loads to evaluate many nodes in the decision tree to make a good decision. Parallelizing MCTS node evaluations is challenging because MCTS is a sequential process that each round of tree traversal depends on the previous node evaluations. In this work, we present SpecMCTS, a new approach for accelerating MCTS by speculatively traversing the search tree. Many MCTS applications, such as AlphaGo Zero, use a deep neural network (DNN) model to evaluate the tree nodes during the search. SpecMCTS uses a pair of DNN models, the speculation model and the main model. The faster (but less accurate) speculation model accelerates the sequential tree search while the more accurate main model improves the decision quality. SpecMCTS accelerates MCTS for the game of Go by up to $2.09\times {}$ on the NVIDIA T4 GPU. This performance improvement can be translated into a better decision quality by performing a larger number of tree traversals within the time limit. For a fixed decision time, SpecMCTS shows stronger gameplay (higher win rate) than the original sequential MCTS and state-of-the-art MCTS parallelization approaches.

Nowadays, many industrial companies visually record workers’ activities for the purposes of streamlining their work processes. However, since untrimmed raw videos are hard to use, it is desired to automatically divide the videos into segments and recognize which kind of operation is performed on each segment. This task is called temporal video segmentation. We propose a method for achieving it, particularly targeting videos of manufacturing work with a specialized vehicle such as a hydraulic excavator. To make the performance of temporal video segmentation high, it is quite essential to extract good visual features from input videos. This can be hardly achieved by unsupervised methods, whereas supervised methods have another drawback that collecting a sufficient amount of training data is difficult due to its labor-intensiveness. To overcome these drawbacks, the proposed method employs a semi-supervised approach. We assume that a set of weakly-labeled videos whose frames only sparsely have a category label are given as input, where the labeled frames are used as training data to train a desirable feature extractor. Under this assumption, the proposed method first divides the input videos into short segments called primitive segments having the fixed length and then clusters them using visual features extracted by the above feature extractor. To achieve higher performance, we also use a hierarchical tree of the category labels and recursively perform the above process at each branch in the tree, where the tree is automatically built by the proposed method. In our experiments, we achieved a segmentation performance of 0.947 on the F-measure, even when only 1.25% of all the frames in the input videos are labeled.

The due-date quotation is a key performance indicator for managing customer orders which would influence customer acceptance and/or the future potential lateness penalty. The production cycle time and allowance time are added and used as the due date of order. The objective is to maximize the hit rate which is the percentage of the orders fulfilled within the time limit of quoted due date. Under the framework of supervised machine learning, we explore the new developments in feature selection and the optimal decision tree to predict cycle time by using mixed-integer optimization. Cycle time allowance could be added to the predicted cycle time or incorporated in an optimization problem as a managerial decision variable. Case studies are used to demonstrate the effectiveness of this approach, and their performances are comparable to the other popular ensemble tree approaches, such as random forests and gradient boosting.

In the literature of Economics, Engineering and Operations Research, the estimation of production frontiers is a current hot topic. Many parametric and nonparametric methodologies have been introduced for estimating technical efficiency of a set of units (for example, firms) from the production frontier. However, few of these methodologies are based upon machine learning techniques, despite being a rising field of research. Recently, a bridge has been built between these literatures, machine learning and production theory, through a new technique proposed in Esteve et al. (2020), called Efficiency Analysis Trees (EAT). The algorithm developed from EAT, based on the well-known Classification and Regression Trees (CART) machine learning technique, is a greedy technique that uses a particular heuristic for the selection of the next node to be split during the decision tree development process. Nevertheless, as we show in this paper, for different sample sizes and number of variables, the heuristic used by EAT is not capable of obtaining the tree with the minimum mean square error (MSE). For this reason, in this paper, a backtracking technique is implemented to improve the MSE obtained by the EAT algorithm. Additionally, a pair of new algorithms are introduced which combine the heuristic technique used by the standard EAT and the backtracking algorithm to enhance the reduction of the MSE, while decreasing the computation time. Our research is based on some simulated experiments. According to our computational results, the combination of the heuristic and the backtracking algorithm, in particular, that in which the tree growth starts with heuristics and ends with backtracking, has achieved an accuracy similar to that of backtracking and within a reasonable computational time. The contribution of the paper could be of special interest for industrial engineers interested in measuring efficiency and productivity of industrial processes in many sectors, such as energy, agri-food or service industries.

In sensor-cloud applications, a huge amount of time series are generated. Efficient similarity search approaches are necessary for processing these sensor time series data. Concerning of time series search, whole matching similarity search and subsequence similarity search are two main research focuses. In this paper, we study the whole matching similarity search problem. We propose EPLA-DSTree, which extends piecewise linear approximation on a dynamic segmentation tree index for whole matching on time series. Compared with DSTree, EPLA-DSTree improves data locality of nodes by a better time series representation. EPLA-DSTree has a tighter lower bound for nodes which leads to a better query performance. Experiments show that it has a less index building time and a better query performance. To meet the requirements of sensor-cloud applications, we present an parallel EPLA-DSTree on MapReduce, which is a popular cloud programming model.

Cloud Content Delivery Networks (CCDNs) scale their content delivery services by taking advantage of the flexible cloud resources and management mechanisms so that users can get the content nearby and reduce traffic of the central network. The content delivery efficiency of CCDNs and quality of service can be improved by rationally planning routing. However, the existing routing planning strategies are not suitable for CCDNs because the number of nodes and the network traffic in CCDNs are dynamic. In this paper, we propose a routing planning method that considers the influence of these factors. In our method, we first build a new framework called the collaborative reinforcement learning based CCDN to capture the dynamic characteristics of the above factors through the $V$ -value feedback model, and we quantify the node transmission efficiency with the $Q$ value. Based on this framework, we propose a collaborative reinforcement learning based delivery tree construction algorithm to obtain a delivery tree. Through numerical simulation, it is found that the delivery path constructed by this method can effectively improve the efficiency of content delivery.

Humans can understand a novel sentence by parsing it into known components like phrases and clauses. To achieve human-level artificial intelligence, compositional generalization tasks are suggested and used to assess machine learning models. Among those tasks, the SCAN tasks are challenging for the standard deep learning models, such as RNN sequence-to-sequence models and Transformers, that show great success across many natural language processing tasks. Even though a long line of deep learning research has developed memory augmented neural networks aimed at the SCAN tasks, their generalities remain questionable for more complex and realistic applications where the standard seq2seq models dominate. Hence, one needs to propose a method that helps the standard models to discover compositional rules. To this end, we propose a data augmentation technique using paring trees. Our technique annotates targets by inserting a new delimiter token in between them according to their parsing trees. For the training stage, the technique needs prior knowledge about the targets' semantic or syntactic compositionality. On the other hand, for the test stage, the technique uses no such knowledge. Experiments show that our technique enables the standard models to achieve compositional generalization on the SCAN tasks. Furthermore, we validate our technique on a synthetic task and confirm the standard models' strong performance gains without using prior knowledge about semantic compositionality. As one way to infuse parsing tree information into sequences, our technique can be used for tasks with structured targets like program code generation tasks.

Machine learning has recently become a popular algorithm in building reliable intrusion detection systems (IDSs). However, most of the models are static and trained using datasets containing all targeted intrusions. If new intrusions emerge, these trained models must be retrained using old and new datasets to classify all intrusions accurately. In real-world situations, new threats continuously appear. Therefore, machine learning algorithms used for IDSs should have the ability to learn incrementally when these new intrusions emerge. To solve this issue, we propose T-DFNN. T-DFNN is an algorithm capable of learning new intrusions incrementally as they emerge. A T-DFNN model is composed of multiple deep feedforward neural network (DFNN) models connected in a tree-like structure. We examined our proposed algorithm using CICIDS2017, an open and widely used network intrusion dataset covering benign traffic and the most common network intrusions. The experimental results showed that the T-DFNN algorithm can incrementally learn new intrusions and reduce the catastrophic forgetting effect. The macro average of the F1-score of the T-DFNN model was over 0.85 for every retraining process. In addition, our proposed T-DFNN model has some advantages in several aspects compared to other models. Compared to the DFNN and Hoeffding tree models trained with a dataset containing only the latest targeted intrusions, our proposed T-DFNN model has higher F1-scores. Moreover, our proposed T-DFNN model has significantly shorter training times than a DFNN model trained using a dataset containing all targeted intrusions. Even though several factors can affect the duration of the training process, the T-DFNN algorithm shows promising results in solving the problem of ever-evolving network intrusion variants.

With the widespread application of Geographic Information System (GIS), three-dimensional spatial data, as the reflection of the real world entity, has an increasing amount of data, and the phenomenon of uneven data distribution appears. If a single spatial index structure is used to store and manage these data, there will be a waste of storage space and low query efficiency. A hybrid index structure based on 3D multi-level adaptive grid and R+ tree was proposed to solve these problems. The index structure was mainly composed of two structures, multi-level grid and R+ tree. Firstly, the data set was processed by the multi-level automatic grid algorithm based on normal distribution, and the length, width and height of the grid were obtained. Secondly, a multi-level adaptive grid structure was used to partition the data space quickly and effectively, and the advantage of zero overlap of the intermediate nodes of the R+ tree was used for efficient indexing. Finally, the maintenance and query algorithms of the index structure were given in detail, which solved the problem of low index establishment and retrieval efficiency under the condition of uneven distribution of massive data sets. In this paper, a data set subject to Gauss distribution was used to simulate the distribution of three-dimensional data. Through a large number of experimental comparison tests, it was proved that the hybrid index structure based on 3D multi-level adaptive grid-R+ tree proposed in this paper had good performance in both index structure construction and query in the case of massive data sets or uneven data distribution.

It is an important activity for our society to create new value by combining materials. From daily cooking to manufacturing for industry, we often describe the way to do it as a procedural text. As pointed by some previous studies for natural language understanding, one important property of the procedural text is its dependency of the context, which is the merging operations of materials and can be represented by a graph or tree structure. This paper aims to investigate the impact of explicitly introducing such a structure on the vision and language task of procedural text generation from an image sequence. To this end, we propose (1) a new dataset, which extends a definition of a tree structure merging tree to a vision and language version and (2) a novel structure-aware procedural text generation model, which learns the context dependency efficiently. Experimental results show that the proposed method can boost the performance of traditional versatile methods.

Extended belief rule-based (EBRB) system has a better ability to model complex problems than belief rule-based (BRB) system. However, the storage of rules in EBRB system is out of order, which leads to the low efficiency of rule retrieval during the reasoning process. Therefore, to improve the efficiency of rule retrieval, this study introduces K-means clustering tree algorithm into the construction of rule base, then proposes a multi-layer weighted reasoning approach based on K-means clustering tree. The proposed approach seeks out a path on the tree during the rule retrieval process, and then figures out several reasoning results according to the nodes on the path. These results are weighted and aggregated to obtain the final conclusion of the system, thus ensure both the efficiency of reasoning and the sufficient utilization of information. In addition, the differential evolution (DE) algorithm is used to train the parameters of EBRB system in this study. Several experiments are conducted on commonly used classification datasets from UCI, and the results are compared with some existing works of EBRB system and conventional machine learning methods. The comparison results illustrate that the proposed method can make an obvious improvement in the performance of EBRB system.

The increasing popularity of social media has made the creation and spread of rumors much easier. Widespread rumors on social media could cause devastating damages to society and individuals. Automatically detecting rumors in a timely manner is greatly needed but also very challenging technically. In this paper, we propose a new deep feature fusion method that employs the linguistic characteristics of the source tweet text and the underlying patterns of the propagation tree of the source tweet for Twitter rumor detection. Specifically, the pre-trained Transformer-based model is applied to extract context-sensitive linguistic features from the short source tweet text. A novel sequential encoding method is proposed to embed the propagation tree of a source tweet into the vector space. A convolutional neural network (CNN) architecture is then developed to extract temporal-structural features from the encoded propagation tree. The performance of the proposed deep feature fusion method is evaluated with two public Twitter rumor datasets. The results demonstrate that the proposed method achieves significantly better detection performance than other state-of-the-art baseline methods.

Textual information is ubiquitous in our lives and is becoming an important component of our cognitive society. In the age of big data, we consistently need to traverse substantial amounts of data even to find a little information. To quickly acquire effective information, it is necessary to implement a textual similarity search based on an appropriate index structure to efficiently find results. In this article, we study top-k textual similarity search and develop a tree-based indexing approach that can construct indices to support various similarity functions. Our indexing approach clusters similar records in the same branch offline to improve the performance of online search. Based on the index tree, we present a top-k search algorithm with efficient pruning techniques. The experimental results demonstrate that our algorithm can achieve higher performance and better scalability than the baseline method.

The social interaction is one of the necessary skills for social robots to better integrate into human society. However, current social robots interact mainly through audio and visual means with little reliance on haptic interaction. There still exist many obstacles for social robots to interact through touch: 1) the complex manufacturing process of the tactile sensor array is the main obstacle to lowering the cost of production; 2) the haptic interaction mode is complex and diverse. There are no social robot interaction standards and data sets for tactile interactive behavior in the public domain. In view of this, our research looks into the following aspects of tactile perception system: 1) Development of low-cost tactile sensor array, including sensor principle, simulation, manufacture, front-end electronics, examination, then applied to the social robot’s whole body; 2) Establishment of the tactile interactive model and an event-triggered perception model in a social interactive application for the social robot, then design preprocessing and classification algorithm. In this research, we use k-nearest neighbors, tree, support vector machine and other classification algorithms to classify touch behaviors into six different classes. In particular, the cosine k-nearest neighbors and quadratic support vector machine achieve an overall mean accuracy rate of more than 68%, with an individual accuracy rate of more than 80%. In short, our research provides new directions in achieving low-cost intelligent touch interaction for social robots in a real environment. The low-cost tactile sensor array solution and interactive models are expected to be applied to social robots on a large scale.

Several clustering methods have been proposed for analyzing numerous mixed-type data sets composed of numeric and categorical attributes. However, existing clustering methods are not suitable for clustering very large mixed-type data sets because they require a high computational cost or a large memory size. We propose a novel clustering method for very large data sets using a mixed-type clustering feature (MCF) vector with summary information about a cluster. The MCF vector consists of the CF vector and a histogram to summarize the mixed-type values. Based on the MCF vector, we propose an MCF tree, along with a distance measure between the MCF vectors representing two clusters. Unlike previous studies that summarize a data set based on a fixed memory size, we estimate a small initial memory size of the data set for building the tree. Then, the memory size is adaptively increased to estimate a more accurate threshold by reflecting the size reduction in the re-built tree. Our theoretical analysis demonstrates the efficiency of the proposed approach. Experimental results on very large synthetic and real data sets demonstrate that the proposed approach clusters the data sets significantly faster than existing clustering methods while maintaining similar or better clustering accuracy.

Air quality prediction is an important reference for meteorological forecast and air controlling, but over fitting often occurs in prediction algorithms based on a single model. Aiming at the complexity of air quality prediction, a prediction method based on integrated dual LSTM (Long Short-Term Memory) model was proposed in this paper. Firstly, the Seq2Seq (Sequence to Sequence) technology is used to establish a single-factor prediction model which can obtain the predicted value of each component in air quality data, independently. Each component of air quality is regarded as time series data in the forecasting process. Then, the LSTM model with attention mechanism is used as the multi-factor prediction model. The influencing factors of air quality, like the data of neighboring stations and weather data, are considered in the model. Finally, XGBoosting (eXtreme Gradient Boosting) tree is used to integrate two models. The final prediction results can be obtained by accumulating the predicted values of the optimal subtree nodes. Through evaluation and analysis using five evaluation methods, the proposed method has better performance in terms of error and model expression power. Compared with other various models, the precision of prediction data has been greatly improved in our model.

Path planning plays a key role in the application of mobile robots and it is an important way to achieve intelligent mobile robots. Traditional path planning algorithms need to model environmental obstacles in a deterministic space, which is complex and easily trapped in local minimal. The sampling-based path planning algorithm performs collision detection on the environment and it is able to quickly obtain a feasible path. In order to solve the problem of inefficient search of the sampling-based Rapidly Expanding Random Tree (RRT-Connect) path planning algorithm, an improved RRT-Connect mobile robot path planning algorithm (IRRT-Connect) is proposed in this paper. In order to continue to speed up the search of the algorithm, a simple and efficient third node is generated in the configuration space, allowing the algorithm to be greedily extended with a quadruple tree in the proposed algorithm. Further, the method of adding guidance is proposed to make the algorithm have the characteristics of biasing towards the target point when expanding, which improves the exploration efficiency of the algorithm. In order to verify the effectiveness of the proposed algorithm, this paper compares the execution performance of the four algorithms in six environments of different complexity. The results of the simulation experiments show that the proposed improved algorithm outperforms the RRT, RRT-Connect and RRT* algorithms in terms of the number of algorithm iterations, planning time and final path length in different environments. In addition, the improved algorithm was ported to the ROS mobile robot for experiments with real-world scenarios.

Non-intrusive and automated detection of pig breeds, particularly from visual standpoint, is important from a food quality tracking perspective. In this work, colour as well as texture based visual descriptors from muzzle images have been identified, which, serve as breed-identifiers to separate four common pig-breeds: Duroc, Ghungroo, Hampshire and Yorkshire. While these handcrafted visual descriptors by themselves are fairly robust and discriminative, it is recognized that by controlling the decision space by choosing the feature-type based on colour or texture or both and the order in which particular breeds are siphoned, classification accuracy can be improved considerably. In that light, a stable, relatively data-independent, breed-specific, hierarchical tree synthesis and feature selection procedure is proposed based on a breed-pair cluster separation table. The proposed approach has been compared with the state of the art Phylogenetic distance based Hierarchical Agglomerative Clustering algorithm (AGNES) and also with the standard decision tree classification algorithm. On cross-validation, When completely different sets of pigs were used for training and testing (50-50 split), the proposed algorithm reported relatively high mean classification accuracies of 86.45% for Duroc, 93.02% for Ghungroo, 86.91% for Hampshire and 98.54% for Yorkshire, respectively.

3D-HEVC (The 3D Extension of High Efficiency Video Coding), the latest international standard for 3D video coding, supports multiview plus depth 3D video format to enrich multimedia applications. For the texture coding, 3D-HEVC utilizes not only the information of temporal and spatial domains but also that of inter-view domain. However, the time consumption and complexity of 3D-HEVC also increase significantly. In this paper, fast texture coding algorithm for 3D-HEVC is proposed. We individually calculate the Pearson correlation coefficients by the rate-distortion costs (RD-costs) of coding tree units (CTUs) in the temporal, spatial and inter-view domains to analyze the correlations for independent view and dependent view. The proposed coding algorithm is based on the coding information of CTUs with higher correlations. The fast algorithm predicts and dynamically adjusts the depth range of the coding unit (CU). The prediction unit (PU) mode decision is proposed according to the complexity and partition direction of the best PU modes obtained from the highly correlated CTUs. The search range is adaptively adjusted for motion estimation. In addition, the RD-cost threshold is estimated to early terminate the CU split. Experimental results show that the proposed fast texture coding algorithm reduces the texture coding time significantly and outperforms numerous previous works.

Deep neural networks have been proved a success in multiple fields. However, researchers still favor traditional approaches to obtain more interpretable models, such as Bayesian methods and decision trees when processing heterogeneous tabular data. Such models are hard to differentiate, thus inconvenient to be integrated into end-to-end settings. On the other hand, traditional neural networks are differentiable but perform poorly on tabular data. We propose a hierarchical differentiable neural regression model, Soft Decision Tree Regressor (SDTR). SDTR imitates a binary decision tree by a differentiable neural network and is plausible for ensemble schemes like bagging and boosting. The SDTR method was evaluated on multiple tabular-based regression tasks (YearPredictionMSD, MSLR-Web10K, Yahoo LETOR, SARCOS and Wine quality). Its performance is comparable with non-differentiable models (gradient boosting decision trees) and better than uninterpretable models (regular FCNN). On top of that, it can produce fair results with a restricted number of parameters, only using a small forest or even a single tree. We also propose an “average entropy” metric to evaluate the level of interpretability of a trained, soft decision tree neural network. This metric also helps to select proper structure and hyperparameters for such networks.

The establishment of reliable water level prediction models is vital for urban flood control and planning. In this paper, we develop hybrid models (GA-XGBoost and DE-XGBoost) that couple two evolutionary models, a genetic algorithm (GA) and a differential evolution (DE) algorithm, with the extreme gradient boosting (XGBoost) model for hourly water level prediction. The Jungrang urban basin located on the Han River, South Korea, was selected as a case study for the proposed models. Hourly rainfall and water level data were collected between 2003 and 2020 to construct and evaluate the performance of the selected models. To compare the prediction efficiency, two other tree-based models were chosen: classification and registration tree (CART) and random forest (RF) models. A comparison of the results showed that two hybrid models, GA-XGBoost and DE-XGBoost, outperformed RF and CART in the multistep-ahead prediction of water level, and the relative errors of the hybrid model ranged from [2.18%-9.21%], compared to [3.76%-10.41%] and [2.99%-11.88%] for the RF and CART, respectively. Reliable performance was also supported by other measures. In general, the GA-XGBoost and DE-XGBoost models displayed relatively similar performance despite their small differences. The CART model was not preferable for multistep-ahead water level predictions, even though it yielded the lowest Akaike information criterion (AIC) value. This study verifies that despite having some drawbacks when considering long step-ahead prediction and model complexity, hybrid XGBoost models might be superior to many existing models for hourly water level prediction.

Collaborative filtering (CF) is one of the most practical approaches on recommendation systems by predicting users' preferences for items based on the user-item interaction information. Besides the connections between users and items, social networks among users can provide auxiliary information to improve the performance of recommender systems. Here, we propose an end-to-end deep learning framework by learning latent social features to embed in a CF approach. First, representation learning is employed on the rating matrix to extract the latent social features. Then, a novel deep learning approach based on cascade tree forest is used in the recommendation process. Experiments on real-world datasets from different domains demonstrate that the proposed Collaborative Deep Forest Learning (CDFL) outperforms the state-of-the-art CF recommendation methods.

Microgrids are one important lever to increase power system resilience and to tightly integrate renewable energies at the same time. Commonly, an optimization-based proactive scheduling controls assets in advance in a cost-effective way and ensures that contingencies may be successfully mitigated. However, often strong simplifications are introduced to manage the high computational complexity of scheduling, which can adversely impact fault mitigation. To consider essential phenomena such as power flow limitations and low-level control capabilities in detail, a novel hybrid scheduling approach is presented that integrates mathematical programming and arbitrary nonlinear constraint models via decision trees. A detailed case study compares the new method to an extended hybrid scheduling approach from literature. It is demonstrated that hybrid optimization can efficiently solve proactive resilient scheduling problems and that the tree-based algorithm provides a feasible solution, even in case the reference algorithm fails. Details on the convergence of both algorithms give further insights into the working principles and show that the novel method quickly finds a feasible solution that is successively improved afterwards. By the novel combination of highly-developed solvers for both mathematical programming and detailed asset models it is expected that this study further supports the operation of power systems and reduces costly reserve requirements.

In recent years, with the continuous development of online geographic information services, the multiscale online expression of geographic elements and topological information has become a hot research topic. Currently, a large amount of research focuses mainly on the compression of vector line elements. The main shortcoming of current algorithms is that vector data compression does not consider the optimality of line simplification. In the face of terabytes or even petabytes of data, problems arise such as low processing efficiency and long transmission time. Based on the shape-tree principle, the proposed method aims to reconstruct the organizational structure of a geographic element and establish a hierarchical representation model of the element based on its structure, realizing multiscale shape recognition and matching and searching geographic elements. Finally, the proposed method is compared with a model based on the wavelet transform and discrete Fourier transform. The results demonstrate the applicability and effectiveness of the proposed method in morphological expression with geospatial big data.

The mining of frequent weighted patterns (FWPs) that considers the different semantic significance (weight) of items is more suitable for practice than the mining of frequent patterns. Therefore, it plays a vital role in real-world scenarios. However, there exist several limitations when applying methods for mining FWPs designed for static data on growth datasets, especially data streams. Hence, this study proposes an algorithm for mining FWPs over data streams. First, we introduce the concept of mining FWPs over data streams via a sliding window model. Then, we introduce a modification of the weighted node tree (WN-tree) named SWN-tree that has the ability to maintain the information over data streams. Next, this study develops a method for mining FWPs over data streams employing a sliding window model based on SWN-tree. This method is called FWPODS (Frequent Weighted Patterns Over Data Stream) algorithm. Finally, we conduct empirical experiments to compare the performances of our approach and the state-of-the-art algorithm (NFWI) for mining FWPs over data streams. The results of experiment indicate that our approach outperforms the NFWI algorithm when running in batch mode in a sliding window.

Recently, researchers are being more interested in performing operations directly on the encrypted database with the help of the $O$ rder- $P$ reserving $E$ ncryption (OPE) scheme. This mechanism enables executing many types of queries efficiently, such as range query and comparison, since it can preserve the relative order of underlying plaintext on ciphertexts. However, traditional OPE schemes cannot achieve ideal security against IND-OCPA ( IND istinguishability under $O$ rdered $C$ hosen- $P$ laintext $A$ ttack) in a linear length of static encoding. Popa’s mutable scheme (namely, mOPE) is an effective solution to perform the range query in the database environment. In this paper, we propose a novel scheme, $B$ oundary $O$ rder- $P$ reserving $E$ ncryption (BOPE), to achieve high performance under ideal security. BOPE comprises two algorithms. One is a searching algorithm in which we propose a data structure, the boundary tree, to optimize the algorithm by cutting the scope of each iteration and reducing the rounds of interaction. The second algorithm is an updating algorithm for stale encoding, which determines whether to update the lookup table according to the type of each query, in order to avoid the time cost of redundant updates. We implemented and evaluated BOPE on a practical environment where we have achieved a performance increase of more than 10% from mOPE.

Finding the nearest parking location in road networks is one of the most commonly faced challenges in everyday life of green transportation. A main challenge faced by the state-of-the-art existing parking allocation methods is to optimally offer the nearest parking location for a group of $m$ users at the cost of minimal overall traveling time to ensure the traffic and environmental sustainability. In this article, we model it as a Multiple Nearest Parking Location Allocation (MNPLA) problem, and devise a spatial index tree, called SCP-tree, to accelerate the nearest parking location allocation within the users’ time constraints. During the search process in SCP-tree, we build a pruning strategy relevant to the Geographical Preference Estimation, travel time and parking capacity to determine which branch to visit so that the search accuracy can be improved. Considering the users’ behaviors are often impacted by the geographical location and some personalized attribute information, we set the user priority based on them to help the parking officer determine the allocation sequence. We evaluate our allocation scheme using large real-world dataset with on-street parking sensor data, and extensive experimental results reveal (i) a minimum improvement of 15.9%, 1.4%, 96.9%, 160% in parking allocation time, average traveling time, I/O cost and service utility compared to the progressive methods, and (ii) a minimum improvement of 8.9%, 11.1%, 78.2%, 714% in parking allocation time, average traveling time, I/O cost and service utility compared to the baseline methods.

One of the most challenging tasks in association rule mining is that when a new incremental database is added to an original database, some existing frequent itemsets may become infrequent itemsets and vice versa. As a result, some previous association rules may become invalid and some new association rules may emerge. We designed a new, more efficient approach for incremental association rule mining using a Fast Incremental Updating Frequent Pattern growth algorithm (FIUFP-Growth), a new Incremental Conditional Pattern tree (ICP-tree), and a compact sub-tree suitable for incremental mining of frequent itemsets. This algorithm retrieves previous frequent itemsets that have already been mined from the original database and their support counts then use them to efficiently mine frequent itemsets from the updated database and ICP-tree, reducing the number of rescans of the original database. Our algorithm reduced usages of resource and time for unnecessary sub-tree construction compared to individual FP- Growth, FUFP-tree maintenance, Pre-FUFP, and FCFPIM algorithms. From the results, at 3% minimum support threshold, the average execution time for pattern growth mining of our algorithm performs 46% faster than FP- Growth, FUFP-tree, Pre-FUFP, and FCFPIM. This approach to incremental association rule mining and our experimental findings may directly benefit designers and developers of computer business intelligence methods.

Currently, research work is primarily dependent on the collection of large sets of data from systems and making predictions based on the knowledge obtained from the data, which is generally termed as ‘data mining’. These data mining algorithms are of great importance in improving the performance of different applications. In this regard, Machine Learning (ML) algorithms have been demonstrated to be excellent tools to cope with difficult problems. In this paper, a classification learner based supervised ML algorithm is proposed for intentional islanding of DERs based on the live data collected from supervisory control and data acquisition (SCADA) system in post disaster situations. Literature presents various islanding detection techniques and also intentional islanding algorithms to address different problems in AC networks. These algorithms majorly work based on the control of current source or voltage source inverters. On the other hand, a low voltage DC distribution system allowing the removal of inverter is proposed, which is supposed to be more advantageous by reducing losses and is also economical when working with DERs. In this paper, ML based intentional islanding algorithm for DERs based low voltage DC distribution system is proposed by considering the effects of natural disasters. The learner models trained are fine tree, linear SVM, quadratic SVM and Gaussian SVM. The training of fine tree model is achieved with higher accuracy of 99.8%. The main objective of this work is to achieve a faster and accurate decision making. The performance of the ML based intentional islanding algorithm is compared with the earlier proposed artificial intelligence (AI) based intentional islanding algorithms. The AI algorithms proposed earlier are fuzzy inference systems (FIS), artificial neural networks (ANN) and adaptive network based fuzzy inference system (ANFIS). The comparison shows that, the decision making with ML based intentional islanding algorithm is faster and accurate than all other algorithms.

Fuzzy Time Series (FTS) models are commonly used in time series forecasting, where they do not require any statistical assumptions on time series data. FTS models can handle data sets with a small number of observations or with uncertainty. This is a general advantage of FTS as compared with other techniques. However, FTS models still have some criticisms, such as the optimal lengths of intervals and the proper weights, which always influence the model accuracy and still have been of many concerns in literature. The work in this paper proposes a novel FTS forecasting model based on a new tree partitioning method (TPM) and Markov chain (MC), called FTSMC-TPM, for determining the optimal partitions of intervals and the proper weights vectors respectively, and this will greatly improve the model accuracy. The efficiency of the FTSMC-TPM model is tested using two types of time series consisting of the air pollution index (API) data, which is collected from Kuala Lumpur, Malaysia and the benchmark data of the yearly enrollments for the University of Alabama. Three statistical criteria have been used for investigating the accuracy of the proposed model. The results indicate that the proposed model outperforms the existing classic and advanced time series models in terms of forecasting accuracy. In addition, the proposed model shows the ability to successfully deal with forecasting problems to obtain higher model accuracy, which is examined in comparison with the existing models to validate its superiority. Hence, this study demonstrates that the proposed model is more suitable for the accurate prediction of air pollution events as well as for forecasting any type of random time series.

As the amount of data increases, it is more likely that the assumptions in the existing economic analysis model are unsatisfied or make it difficult to establish a new analysis model. Therefore, there has been increased demand for applying the machine learning methodology to bankruptcy prediction due to its high performance. By contrast, machine learning models usually operate as black-boxes but credit rating regulatory systems require the provisioning of appropriate information regarding credit rating standards. If machine learning models have sufficient interpretablility, they would have the potential to be used as effective analytical models in bankruptcy prediction. From this aspect, we study the explainability of machine learning models for bankruptcy prediction by applying the Local Interpretable Model-Agnostic Explanations (LIME) algorithm, which measures the feature importance for each data point. To compare how the feature importance measured through LIME differs from that of models themselves, we first applied this algorithm to typical tree-based models that have ability to measure the feature importance of the models themselves. We showed that the feature importance measured through LIME could be a consistent generalization of the feature importance measured by tree-based models themselves. Moreover, we study the consistency of the feature importance through the model’s predicted bankruptcy probability, which suggests the possibility that observations of important features can be used as a basis for the fair treatment of loan eligibility requirements.

In this paper, a method is proposed for colonic polyp classification which can perform a virtual biopsy for assessing the stage of malignancy in polyps. Geometry, texture, and colour of a polyp give sufficient cue of its nature. The proposed framework characterizes geometry or shape of a polyp by pyramid histogram of oriented gradient (PHOG) features. To encapsulate the texture of the polyp surface, a fractal weighted local binary pattern (FWLBP) descriptor is employed, which is robust to affine transformation. It is also partially robust to illumination variations which is generally encountered during endoscopy. The optimal feature fusion is done using a feature ranking algorithm based on fuzzy entropy. Finally, to evaluate the classification performance of the proposed model, kernel-based support vector machines (SVM) and RUSBoosted tree are used. Experimental results carried on two databases clearly indicate that the proposed method can be used in the colonoscopic polyps classification. The proposed method can give polyp classification accuracies of 90.12% and 84.1%, and AUC of 0.91 and 0.92 for publicly available database and our own database, respectively.

In this article, we address the task of multi-target regression (MTR), where the goal is to predict multiple continuous variables. We approach MTR by learning global models that simultaneously predict all of the target variables, as opposed to learning a separate model for predicting each of the target variables. Specifically, we learn rule ensembles by generating many candidate rules and assigning them weights that are then optimized in order to select the best performing subset of rules. Candidate rules are generated by transforming ensembles of generalized decision trees, called predictive clustering trees (PCTs), into rules. We propose to extend an existing multi-target regression rule learning method named FIRE by learning tree ensembles that use random output selections (ROS). Such ensembles force individual PCTs to focus only on randomly selected subsets of target variables. The rules obtained from the tree ensemble also focus on various subsets of the target variables (FIRE-ROS). We use three different ensemble methods to generate candidate rules: bagging and random forests of PCTs, and ensembles of extremely randomized PCTs. An experimental evaluation on a range of benchmark datasets has been conducted, where FIRE-ROS is compared to three interpretable methods, namely predictive clustering rules, MTR trees and the original FIRE method, as well as state-of-the-art MTR methods, in particular ensembles of extremely randomized PCTs with ROS, random linear combinations and extremely randomized MTR trees with random projections of the target space. The results show that FIRE-ROS can improve the predictive performance of the FIRE method and that it performs on par with state-of-the-art (non-interpretable) MTR methods.

An early and reliable estimation of crop yield is essential in quantitative and financial evaluation at the field level for determining strategic plans in agricultural commodities for import-export policies and doubling farmer’s incomes. Crop yield predictions are carried out to estimate higher crop yield through the use of machine learning algorithms which are one of the challenging issues in the agricultural sector. Due to this developing significance of crop yield prediction, this article provides an exhaustive review on the use of machine learning algorithms to predict crop yield with special emphasis on palm oil yield prediction. Initially, the current status of palm oil yield around the world is presented, along with a brief discussion on the overview of widely used features and prediction algorithms. Then, the critical evaluation of the state-of-the-art machine learning-based crop yield prediction, machine learning application in the palm oil industry and comparative analysis of related studies are presented. Consequently, a detailed study of the advantages and difficulties related to machine learning-based crop yield prediction and proper identification of current and future challenges to the agricultural industry is presented. The potential solutions are additionally prescribed in order to alleviate existing problems in crop yield prediction. Since one of the major objectives of this study is to explore the future perspectives of machine learning-based palm oil yield prediction, the areas including application of remote sensing, plant’s growth and disease recognition, mapping and tree counting, optimum features and algorithms have been broadly discussed. Finally, a prospective architecture of machine learning-based palm oil yield prediction has been proposed based on the critical evaluation of existing related studies. This technology will fulfill its promise by performing new research challenges in the analysis of crop yield prediction and the development of an extremely effective model for the prediction of palm oil yields with the most minimal computational difficulty.

Electrical trees are one of the main degradation processes leading to failure of high voltage polymeric insulation. Electrical trees grow under the effect of partial discharges (PD), which can be measured and analyzed for condition monitoring of electrical insulation. In this paper, techniques that are normally used for classification of PD and noise separation were explored in their ability to determine the stage of growth of electrical trees: Spectral Power Clustering Technique (SPCT), Time-Frequency (TF) maps and Chromatic Technique (CT). The techniques allowed to analyze PD signals captured in ultra-high frequency (UHF) range with an antenna during tree growth. Laboratory treeing-samples were made of epoxy resin and trees were generated at six different excitation frequencies: 0.1, 10, 50, 150, 250 and 350 Hz. The results showed that two parameters, part of SPCT and TF maps, were sensitive to the tree progression and showed a consistent relation with the length of the tree: the low-frequency power ratio and the equivalent bandwidth. These two parameters were selected to create a new map, proposed for the characterization of electrical tree growth, which is more consistent and robust than the original separation maps. It was found that the low-frequency content of PD pulses proportionally increased with tree propagation.

With the rapid development of cloud storage, cloud users are willing to store data in the cloud storage system, and at the same time, the requirements for the security, integrity, and availability of data storage are getting higher and higher. Although many cloud audit schemes have been proposed, the data storage overhead is too large and the data cannot be dynamically updated efficiently when most of the schemes are in use. In order to solve these problems, a cloud audit scheme for multi-copy dynamic data integrity based on red-black tree full nodes is proposed. This scheme uses ID-based key authentication, and improves the classic Merkel hash tree MHT to achieve multi-copy storage and dynamic data manipulation, which improves the efficiency of real-time dynamic data update (insertion, deletion, modification). The third-party audit organization replaces users to verify the integrity of data stored on remote cloud servers, which reduces the computing overhead and system communication overhead. The security analysis proves that the security model based on the CDH problem and the DL problem is safe. Judging from the results of the simulation experiment, the scheme is safe and efficient.

Sequence pattern mining is a core task of data mining in various fields. Clickstream pattern mining, a variant of sequence pattern mining, is very useful in e-commerce, and is used to analyze, evaluate and predict online customer behaviors, attracting the interest of many researchers. Clickstream pattern mining has become important due to its wide range of applications. However, most previous approaches are not suitable to apply when clickstreams are inserted into a database, because this task is too time consuming. The challenge of this problem is how to find a solution to minimize the runtimes and reduce the number of times the original databases are scanned to reduce the computational cost in the mining process on incremental databases. In this paper, we propose two effective methods for mining clickstream patterns from incremental databases, named inCMUB and Eff-inCMUB, based on the pre-large concept. inCMUB inserts new clickstreams from an inserted database into the existing tree and mines all frequent clickstream patterns, while Eff-inCMUB is a new approach, and builds a new tree from the inserted database to find pre-large 1-patterns and then it updates the pre-large clickstream patterns mined from the original database to extract frequent clickstream patterns. The experiments show that our proposed methods outperform the SMUB algorithm in terms of runtimes, memory usage and scalability on real-word clickstream databases.