Kezhong Lu - IEEE Xplore Author Profile

Showing 1-23 of 23 results

Filter Results

Show

Results

Blockchain technology has garnered increasing attention from researchers. Because blockchain systems may contain malicious or spatially limited nodes that may delay block verification and reduce block transmission rate, this work proposes a block transmission model by designing and using special clusters. This work proposes the cluster formation and selection mechanisms. Nodes are grouped into clu...Show More
Extreme learning machines (ELM) has been widely used in data stream processing, but because the parameters of ELM are generated randomly, the general approximation ability of randomized neural network depends on hidden layer nodes and random parameter range, if the parameters are improperly set, the objective function can not be approximated with high probability. Stochastic Configuration Network(...Show More
Attributed graphs are graphs, where the vertices have attributes. Such graphs encompass, e.g., social network graph, citation graphs, and knowledge graphs, which have numerous real-world applications. Keyword-based search is a prominent and user-friendly way of querying attributed graphs. One widely used approach to keyword search adopts tree-based query semantics that relies on scoring functions ...Show More
Smart home devices generate a substantial amount of local data, and finding effective ways to utilize this data while ensuring privacy has become an increasingly pressing concern. Technologies such as Smart Homes, Federated Learning and Blockchain offer promising solutions to address this challenge. We introduce a blockchain-based federated learning approach that leverages edge nodes to maintain a...Show More
The proliferation of event-based social networking (EBSN) motivates studies on topics such as event, venue, and friend recommendation as well as event creation and organization. In this setting, the notion of event-partner recommendation has attracted attention. When recommending an event to a user, this functionality allows the recommendation of partners with whom to attend the event. However, in...Show More
Flow prediction attracts intensive research interests, since it can offer essential support to many crucial problems in public safety and smart city, e.g., epidemic spread prediction and medical resource allocation optimization. Among all the models in flow prediction, deep learning models (e.g., convolutional neural networks, recurrent neural networks, and graph neural networks) are popular and o...Show More
So-called spatial web queries retrieve web content representing points of interest, such that the points of interest have descriptions that are relevant to query keywords and are located close to a query location. Two broad categories of such queries exist. The first encompasses queries that retrieve single spatial web objects that each satisfy the query arguments. Most proposals belong to this ca...Show More
Involved in the impending era of “Internet + ” and big data, educational informatization has been driving the modernization of education and promoting the deep integration of information technology and teaching. The “Fundamentals of College Computer” course is a public compulsory course for medical colleges. In order to meet the professional requirements of medical colleges, benefitting from the m...Show More
A new bionic algorithm named as Flower Pollination algorithm (FPA) was proposed by Yang. FPA has some shortcomings, such as premature convergence, low precision, et al. So an improved flower pollination algorithm (IFPA) is proposed in this paper. IFPA combines three aspects: global pollination with quantum search mechanics, local pollination with DE/rand/1 mutation, and switch on dimensions. The e...Show More
Among the many biometric recognition techniques, finger vein recognition has many advantages, such as in-vivo recognition, high anti-counterfeiting, high acceptability, and high stability, etc., but the structure of finger vein is simple and the available information is less. The traditional feature extraction method is not fully used to extract finger vein structure information. In this paper, di...Show More
In wireless sensor networks, sensor nodes collect data from the surrounding environment and transfer it to the base station. If a sensor node cannot communicate with the base station directly, it needs to select one of the senor nodes that it can communicate with and transfer the data to it. The above process will go on until the data arrive at the base station. It may cause too many relays during...Show More
Relay node placement in wireless sensor networks has potential application value in terms of establishing connected topologies, reducing data latency, and prolonging network life time. This paper studies the relay node placement problem which opts to deploy the optimum number of relay nodes into single-tiered WSN to meet network connectivity. We firstly draw on ideas of Delaunay Triangle and Voron...Show More
Software reliability growth models (SRGMs) are non-linear in nature, so they are difficult to estimate the proper parameters. An estimation method based on modified Whale Optimization Algorithm (MWOA) in which parameters are estimated is discussed in this paper. The proposed MWOA shows significant advantages in handling variety of modeling problems such as the exponential model (EXPM), power model...Show More
The FP-tree based edge weight computation (EWC for short) with MapReduce has demonstrated its remarkable performance for extracting weighted graphs from big data for data analysis. However, our investigation finds that existing algorithm includes unnecessary scan on the datasets as well as unnecessary information for the FP-tree construction, which prolong the runtime execution. In addition, apply...Show More
Near threshold voltage computing enables transistor voltage scaling to continue with Moore's Law projection and dramatically improves power and energy efficiency. However, reducing the supply voltage to near-threshold level significantly increases the susceptibility of on-chip caches to process variations, leading to the high error rate. Most existing fault-tolerant schemes significantly sacrifice...Show More
Flower Pollination algorithm (FPA) is a new nature-inspired algorithm, based on the characteristics of flowering plants. In this paper, a new hybrid optimization method called quantum-behaved flower pollination algorithm (QFPA) is proposed. The method combines the standard Flower Pollination algorithm (FPA) with the quantum-behaved search mechanism to improve the global searching ability and accur...Show More
In traditional radio-based localization methods, the target object has to carry a transmitter (e.g., active RFID), a receiver (e.g., 802.11 × detector), or a transceiver (e.g., sensor node). However, in some applications, such as safe guard systems, it is not possible to meet this precondition. In this paper, we propose a model of signal dynamics to allow the tracking of a transceiver-free object....Show More
To overcome the problem of premature convergence on particle swarm optimization(PSO), an improved particle swarm optimization(IPSO) was proposed, which was called keeping particles active PSO. It was guaranteed to keep the diversity of the particle swarm. When particles lose activity, a special mutation or perturbation was used to activate particles and to make particles explore the search space m...Show More
Energy is one of most critical resources in wireless sensor networks. Clustering is an effective method to reduce energy consumption of sensor nodes. In this paper we propose a cell base clustering algorithm. The target field is divided into small non-overlapping cells. Sensor node set in each cell is a cluster. The size of cell is well selected so that any node in adjacent cell can communicate wi...Show More
Data dissemination from data source to data sink is very important in wireless sensor networks. Present data dissemination scheme that construct a dissemination tree isnpsilat most energy-efficient in the case that data sinks have different requests of data updating rate. In order to share data transmission path furthest, this paper proposes a multiple tree-based data dissemination scheme. In the ...Show More
The K-harmonic means (KHM) is a center-based clustering algorithm which uses the harmonic averages of the distances from each data point to the centers as components to its performance function. Unlike K-means, KHM is less sensitive to initial conditions. However, KHM as a center-based clustering algorithm can only generate a local optimal solution. In this paper, we present a hybrid clustering al...Show More
Minimum disc cover problem which is NP-hard is kernel of node scheduling protocol in wireless sensor networks. Size of disc cover set obtained by approximate algorithm determines performance of node scheduling protocol. But the approximation ratios of present approximate algorithms aren't good. This paper proposes a local Voronoi diagrams-based approximate algorithm which can obtain a minimal disc...Show More
In wireless sensor networks, sensor nodes collect local data and transfer to the base station often relayed by other nodes. If deploying sensor nodes evenly, sensor nodes nearer to the base station will consume more energy and use up their energy faster that reduces system lifetime. By analyzing energy consumption, a density formula of deploying nodes is proposed. The ratio of whole energy of sens...Show More