Human Flesh Search is an explosive Web phenomenon these years in China, especially when new media, such as Weibo, appeared. In this research, we present the empirical studies about growing patterns of participated Hum...
详细信息
This paper proposes a novel sparse variant of auto-encoders as a building block to pre-train deep neural networks. Compared with sparse auto-encoders through KL-divergence, our method requires fewer hyper-parameters a...
详细信息
This paper proposes a novel sparse variant of auto-encoders as a building block to pre-train deep neural networks. Compared with sparse auto-encoders through KL-divergence, our method requires fewer hyper-parameters and the sparsity level of the hidden units can be learnt automatically. We have compared our method with several other unsupervised leaning algorithms on the benchmark databases. The satisfactory classification accuracy (97.92% on MNIST and 87.29% on NORB) can be achieved by a 2-hidden-layer neural network pre-trained using our algorithm, and the whole training procedure (including pre-training and fine-tuning) takes far less time than the state-of-art results.
Subspace learning has long been a fundamental yet important problem of modeling data distributions. In this paper, we propose to learn multiple linear subspaces in a supervised way for multi-class classification. To t...
详细信息
ISBN:
(纸本)9781479925667
Subspace learning has long been a fundamental yet important problem of modeling data distributions. In this paper, we propose to learn multiple linear subspaces in a supervised way for multi-class classification. To this end, a discriminative term redefining decision margin in terms of reconstruction error is incorporated into the model. The term enjoys similar properties of hinge loss function to the benefit of classification and leads to a training process seeking the balance between unsupervised learning and supervised learning. In the experiments on written digits dataset, our algorithm outperforms other methods proposed recently in both accuracy and computation efficiency.
Classifying Micro-blog content is a popular research topic in social media, which can help users access their favorite information quickly. Much research focuses on classifying Micro-blog content with short text datas...
详细信息
Online change detection in datastreams has attracted many researchers and is becoming a very hot topic whose relevance will further increase with research on Big Data. Concept drift is induced by changes in stationari...
详细信息
ISBN:
(纸本)9781467361279
Online change detection in datastreams has attracted many researchers and is becoming a very hot topic whose relevance will further increase with research on Big Data. Concept drift is induced by changes in stationarity of the process generating the data caused by faults, time variance of the environment and inaccuracy of the change detection mechanism. Here, we propose a recurrent auto-associative Encode-Decode machine trained to reconstruct input data. The generated residual is then inspected for structural changes with a Change Detection Test (CDT). Although any CDT can be used, in the paper we focus the attention on the Hierarchical Intersection of Confidence Intervals change detection test for its capability of controlling false positives with a two layered test and an online version of the Lepage Change Point Model. Once concept drift is detected, the designed Encode-Decode machine, globally acting as an Encode-Decode CDT, is retrained on new data to detect subsequent changes.
A bi-branchiate robot is presented for the inspection of the high-voltage power transmission lines. With a symmetrical mechanical structure, the robot can roll along the power lines and negotiating all the obstacles i...
详细信息
A bi-branchiate robot is presented for the inspection of the high-voltage power transmission lines. With a symmetrical mechanical structure, the robot can roll along the power lines and negotiating all the obstacles in the lines to complete the inspection work. A hierarchical structure based on modular approach are used to design the control system of the robot. A combination mode composed of teleoperation via RF module and local intelligence based on visual servoing is developed to control the inspection robot. Using an image feature acquisition method based on Otsu adaptive threshold, the position and width of the power line in image plane are extracted as the basis of controller design. Experiments of obstacle negotiation and automatic line grasping in laboratory prove the effectiveness of the proposed robot prototype and the relative control method.
A wireless power transmission technique based robotic power management system for prolonging continuous working time of one transmission line inspection robot is introduced in this paper. Magnetic resonance coupled WP...
详细信息
ISBN:
(纸本)9781467351942
A wireless power transmission technique based robotic power management system for prolonging continuous working time of one transmission line inspection robot is introduced in this paper. Magnetic resonance coupled WPT (wireless power transmission) unit is designed and analyzed in form of electrical circuit mode theory. Impedance matching is introduced and a special matching method for four coils resonance coupled based WPT is given. The output power of WPT unit is modeled and relationship between coupled coefficient, angular frequency and amount of output power is given and energy consumption of each unit in power management system is quantified. Experiment shows that models can precisely describe the character of WPT system and it performs to be applicable for charging the inspection robot wirelessly.
Inspired by the characteristics of high agility and stability of live jellyfish, a novel biomimetic robotic jellyfish based on multi-linkage mechanism is developed in this paper. The robotic jellyfish consists of a st...
详细信息
ISBN:
(纸本)9781479900305
Inspired by the characteristics of high agility and stability of live jellyfish, a novel biomimetic robotic jellyfish based on multi-linkage mechanism is developed in this paper. The robotic jellyfish consists of a streamlined head, a cavity shell, four driving devices with bevel gears, four actuators based on multi-linkage mechanism, a regulating mechanism for adjusting barycenter and a skin. The four centrosymmetric actuators is used to imitate the locomotion of jellyfish, including the relaxation phase and the contraction phase. The mutually independent and coordinated control of the four actuators is able to achieve diversified movements such as swimming forward, pitching and yawing. As a new type of bio-inspired robots, the robotic jellyfish with high agility, stability and low noise, will serve as a platform for underwater reconnaissance and environmental monitoring.
Generally, surgeons of minimally invasive surgery should possess good ability to coordinate their both hands. The manipulation of guide wire is considered a core skill. Obtaining that core skill to perform minimally i...
详细信息
ISBN:
(纸本)9781479927456
Generally, surgeons of minimally invasive surgery should possess good ability to coordinate their both hands. The manipulation of guide wire is considered a core skill. Obtaining that core skill to perform minimally invasive surgery requires training. In minimally invasive surgery, a surgical robot can assist doctors to position precisely and provide stable operation platform. Therefore, to develop a virtual reality simulators for training purpose based on a robotic guide wire operating system is an important and challenging subject. In this paper, a multi-body mass-spring model for simulating guide wire is presented and evaluated. In order to overcome the disadvantage of using mass-spring approach to model the guide wire, we propose a new collision detection algorithm and a new collision response algorithm. Finally, we test our guide wire with a complex and realistic 3D vascular model, which is selected from computer tomography database of real patients. The result shows that the virtual reality training simulators is effective and promising.
This paper presents a collision-free path planning approach based on Bezier curve for a mobile manipulator with the endpoints restricted by the manipulator. Based on these candidate endpoints and the initial posture o...
详细信息
ISBN:
(纸本)9781479927456
This paper presents a collision-free path planning approach based on Bezier curve for a mobile manipulator with the endpoints restricted by the manipulator. Based on these candidate endpoints and the initial posture of mobile manipulator, a series of feasible Bezier paths are obtained with the constraints from velocity, acceleration and environment. And then the optimal collision-free path is determined according to the related information of the path as well as obstacles. The mobile manipulator has the ability to adapt to the environment and the optimal path will be updated once the new detected obstacles block this path. The path planning approach is verified by simulations.
暂无评论