In this paper, a novel human localization approach called Human Position Estimation based on Filtered Sonar Scan Matching (HPE-FSSM) is proposed for the purposes of estimating the trajectory of a walking person in hum...
详细信息
In this paper, a novel human localization approach called Human Position Estimation based on Filtered Sonar Scan Matching (HPE-FSSM) is proposed for the purposes of estimating the trajectory of a walking person in human-robot coexisting environments, by matching consecutive pairs of sonar scans obtained with a mobile robot. The work proposes a novel concept of removing large amounts of noise and spurious readings present in two consecutive raw scans by using a spatial clustering method called DENCLUE (DENsity-based clustering). Moreover, an Edge Feature Based Leg Recognition (EFBLR) algorithm is developed, which, in both scans, extracts the data points characterizing the human legs. Finally, a Likelihood field (LF) based scan matching technique is implemented to estimate the roto-translation of leg pair between the refined scans. This procedure is repeatedly implemented to estimate human position, required for following. Extensive experiments carried out in different environments establish the supremacy of the proposed algorithm, compared to other state-of-the-art algorithms.
In non-cooperative frequency hopping communication system, the frequency hopping network station sorting of the received hybrid signals plays an important role and becomes an active research area in recent years. In o...
详细信息
In non-cooperative frequency hopping communication system, the frequency hopping network station sorting of the received hybrid signals plays an important role and becomes an active research area in recent years. In order to solve the problem that the currently widely used clustering algorithm cannot achieve satisfactory accuracy. In this paper, we propose a signal sorting method for hybrid frequency hopping network stations by applying the neural network to classify the frequency hopping description words of signals. Additionally, the conjugate gradient algorithm is utilized in the neural network training process to improve the convergence speed. Once the neural network training is finished, only one frequency hopping description word of the input signal is required to obtain its own network station label in real time. Simulation results demonstrate that when compared with the clustering algorithm, the proposed algorithm converges with less iterations and delivers better sorting accuracy, especially in a low signal to noise ratio environment.
This paper discusses an evolutionary clustering algorithm that uses dynamic representative points as the core of sample cluster (DRPEC). DRPEC algorithm calculates the similarity between samples and representative poi...
详细信息
With the rapid development of economic globalization and the Internet, international exchanges and cooperation have become increasingly extensive and in-depth. Language differences have become the biggest obstacle to ...
详细信息
Vector Quantization (VQ) is a classical block coding technique used for image compression which achieves high compression using simple encoding and decoding process. Codebook generation is an important factor in VQ de...
详细信息
Vector Quantization (VQ) is a classical block coding technique used for image compression which achieves high compression using simple encoding and decoding process. Codebook generation is an important factor in VQ design, which directly influences computational cost and the quality of the reconstructed image. Linde-Buzo-Gray (LBG) is considered as a state of art technique, which uses k-mean clustering algorithm for codebook design. Various optimization techniques are applied for searching the optimal codebook, such as Bat Algorithm (BA), Particle swarm optimization (PSO), and Firefly Algorithm (FA). These algorithm suffers mainly with high time consumption due to unavailability of the optimal solution in search space. This research proposes a novel approach, where peak values of the histogram are applied to predefined pattern masks to predict the image patterns for codebook design. From the experimental results, it is indicated that when compared with other algorithms, the proposed pattern based masking (PBM) algorithm requires fewer iterations and converges at a faster speed, particularly at the bitrates >= 0.375 without compromising on peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM).
In the event-driven wireless sensor networks (EWSNs), the event of interests occurs irregularly and at random in the network. Then, sensor nodes near the event sense the event and send out data packets of the event. N...
详细信息
In the event-driven wireless sensor networks (EWSNs), the event of interests occurs irregularly and at random in the network. Then, sensor nodes near the event sense the event and send out data packets of the event. Next, router nodes (RNs) forward those packets to the sink node (SN) by multi-hop communications. Compromised RNs would become malicious and launch selective forwarding attacks by dropping part of or all the packets from other nodes. On the other hand, a harsh environment makes the channel poor, so the routing nodes under a harsh environment have low packet forwarding rates because they sometimes have to give up forwarding the current packets after many tries to forward them due to poor channel. If the malicious nodes' forwarding rates become close to those of nodes under a harsh environment, the schemes based on packet forwarding rates for detecting selective forwarding attack may fail because they cannot differentiate the low data packet forwarding rates resulting from the malicious behaviors or harsh environment. To solve this problem, we provide a combined scheme for detecting selective forwarding attack in wireless sensor networks (WSNs) under harsh environments. This scheme employs a data clustering algorithm (DCA) to screen the malicious nodes out by clustering their cumulative forwarding rates (CFRs) and designs a voting decision method to protect the nodes under a harsh environment from being judged as malicious nodes. The simulation results show that our scheme has a low false detection rate (FDR) of 1% and a low missed detection rate (MDR) of 5% respectively with negligible energy consumption in WSNs under a local variable harsh environment.
Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be difficult to obtain and are inherently ...
详细信息
clustering is the most promised technique used for data analysis. It is an unsupervised machine learning technique, means it does not require any target class. In the recent years so many clustering algorithms are inv...
详细信息
This article proposes an optimal zone clustering algorithm of islanded microgrids (IMG) based on supply adequacy taking into account the dynamic performance of distributed state estimation units. The IMG is partitione...
详细信息
This article proposes an optimal zone clustering algorithm of islanded microgrids (IMG) based on supply adequacy taking into account the dynamic performance of distributed state estimation units. The IMG is partitioned into several localized, yet coupled zones, where each zone is responsible for its local state estimate and performs data fusion to reach consensus for shared state variables between zones. The technique proposes a novel algorithm to optimally define the placement of the virtual boundaries of the zones by minimizing the potential power transfer between adjacent zones. The proposed algorithm adopts the distributed particle filter (DPF) technique for the state estimation process. The proposed algorithm also has the ability to come up with one optimal configuration considering different events and scenarios that might occur in the IMG. Monte Carlo simulations demonstrate the efficacy of the proposed technique in the presence of severely corrupted measurements and state values as well as displaying tolerance to major load changes within the IMG. The DPF shows similar performance when compared to its centralized implementation while also providing computational savings by a factor of the number of zones.
In recent years, network operators are receiving an outsize amount of data due to the increasing number of mobile network subscribers, network services and device signalling. This trend increases with the deployment o...
详细信息
In recent years, network operators are receiving an outsize amount of data due to the increasing number of mobile network subscribers, network services and device signalling. This trend increases with the deployment of 5G that will provide advanced connectivity to wireless devices and develop new services. Network analytics must allow telecommunications operators to improve their services and the infrastructure extracting useful information from large amounts of data. A methodology based on orthogonal projections was developed in order to analyze the network information and facilitate the management and the operations to network providers. In the current study, different key points selection algorithms are investigated in order to make a quantitative and qualitative evaluation and analyze the performance of those algorithms which use different approaches to select these points, which will be utilized in the methodology. A novel synthetic data set has also been developed to statistically evaluate the effect of the key points selection algorithms in the clustering, as well as, measure the performance of the aforementioned methodology. Finally, these key points selection algorithms are used in a real scenario to evaluate the impact of the different approaches in the analysis.
暂无评论