-
Chapter and Conference Paper
You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding
Stochastic rounding is a critical technique used in low-precision deep neural networks (DNNs) training to ensure good model accuracy. However, it requires a large number of random numbers generated on the fly....
-
Chapter and Conference Paper
Research and Optimization of Skin Design for Mobile Terminal Input Method Based on Emotional Experience
Objective: To provide ideas and schemes for the emotional design of mobile input method skin. Methods: The emotional experience evaluation experiment was designed according to the selected representative skin ...
-
Chapter and Conference Paper
Semi-supervised Context Discovery for Peer-Based Anomaly Detection in Multi-layer Networks
User-related cyber security attacks could cause tremendous losses to any organization. Detecting such threat can be formulated as anomaly detection problem in multilayer networks where each layer of the multil...
-
Chapter and Conference Paper
An Ensemble Fuzziness-Based Online Sequential Learning Approach and Its Application
Traditional deep learning algorithms are difficult to deploy on most IoT terminal devices due to their limited computing power. To solve this problem, this paper proposes a novel ensemble fuzziness-based onlin...
-
Chapter and Conference Paper
LTRRS: A Learning to Rank Based Algorithm for Resource Selection in Distributed Information Retrieval
Resource selection is a key task in distributed information retrieval. There are many factors that affect the performance of resource selection. Learning to rank methods can effectively combine features and a...
-
Chapter and Conference Paper
Fine-Grained Image Recognition from Click-Through Logs Using Deep Siamese Network
Image recognition using deep network models has achieved remarkable progress in recent years. However, fine-grained recognition remains a big challenge due to the lack of large-scale well labeled dataset to tr...
-
Chapter and Conference Paper
Topic-Aware Visual Citation Tracing via Enhanced Term Weighting for Efficient Literature Retrieval
Efficient retrieval of scientific literature related to a certain topic plays a key role in research work. While little has been done on topic-enabled citation filtering in traditional citation tracing, this ...
-
Chapter and Conference Paper
A Quality Evaluation Scheme to 3D Printing Objects Using Stereovision Measurement
The paper presents a comprehensive evaluation method on shape consistency by using three-dimensional scanning, reverse engineering and post-processing. The complete evaluation scheme includes data collection,...
-
Chapter and Conference Paper
Research on Influence Factors of the Formation of Virtual Innovation Clusters
With the development of science and technology and the increasingly fierce competition of innovation, the virtual innovation cluster (VIC) has become an important way of innovation. This paper studies the infl...
-
Chapter and Conference Paper
Heuristics for Non-dominated Sets of Two-Agent Scheduling on a Single Parallel-Batching Machine
We study a bi-objective problem of scheduling the jobs from two agents on a single parallel-batching machine with the objective of minimizing the makespans of the both agents. All jobs have an equal processing...
-
Chapter and Conference Paper
Plant Leaves Extraction Method Under Complex Background Based on Closed-Form Matting Algorithm
The extraction of plant leaves is a technique to separate the captured leaves from the background. In natural scene, the captured picture of plant leaves always contain of complex background and it’s hard to e...
-
Chapter and Conference Paper
A Multiple Image Group Adaptation Approach for Event Recognition in Consumer Videos
Event recognition in the consumer videos is a challenging task since it is difficult to collect a large number of labeled training videos. In this paper, we propose a novel Multiple kernel Image Group Adaptati...
-
Chapter and Conference Paper
Contractive De-noising Auto-Encoder
De-noising auto-encoder (DAE) is an improved auto-encoder which is robust to the input by corrupting the original data first and then reconstructing the input by minimizing the error function. And contractive ...
-
Chapter and Conference Paper
Known-Key Distinguisher on Round-Reduced 3D Block Cipher
3D block cipher is an AES-based block cipher which has a three-dimensional state. Besides some traditional attacks, Knudsen and Rijmen introduced a new tool, known-key distinguisher, to identify the weak pseud...
-
Chapter and Conference Paper
Design a Partner Robot with Emotions in the Mixed Reality Learning Environment
In this paper, we propose a partner robot with emotions in the mixed reality learning environment. The learning environment is designed into a task-based scenario. Students can acquire knowledge by interacting...
-
Chapter and Conference Paper
An Interactive Synchronous E-Learning System for Corporate Knowledge Management: Lessons Learned from SaveCom
This research discusses the interactive synchronous e-learning system and its implications for corporate knowledge management. Using a case study of a Taiwanese Telecom company, qualitative data was gathered o...
-
Chapter and Conference Paper
Chaotic Hybrid Algorithm and Its Application in Circle Detection
An evolutionary circle detection method based on a novel Chaotic Hybrid Algorithm (CHA) is proposed. The method combines the strengths of particle swarm optimization, genetic algorithms and chaotic dynamics, a...
-
Chapter and Conference Paper
Scheme of Defending Against DDoS Attacks in Large-Scale ISP Networks
A scheme that defending against distributed denial of service (DDoS) attacks adopts the mechanism of Distribution-based Secure Overlay Nodes (DSON) to a large-scale ISP (Internet Service Provider) network is p...
-
Chapter and Conference Paper
Kernel Fisher LPP for Face Recognition
Subspace analysis is an effective approach for face recognition. Locality Preserving Projections (LPP) finds an embedding subspace that preserves local structure information, and obtains a subspace that best d...
-
Chapter and Conference Paper
A Virtual Organization Based Mobile Agent Computation Model
Mobile agent has developed for decade, and widely implemented in distribute computation. However, traditional mobile agents including strong-migration and weak-migration mobile agents still have some weakness....