The Internet has opened new interesting scenarios in the fields of e-commerce, marketing and on-line transactions. In particular, thanks to mobile technologies, customers can make purchases in a faster and cheaper way...
详细信息
The Internet has opened new interesting scenarios in the fields of e-commerce, marketing and on-line transactions. In particular, thanks to mobile technologies, customers can make purchases in a faster and cheaper way than visiting stores, and business companies can increase their sales volume due to a world-wide visibility. Moreover, online trading systems allow customers to gather all the required information about product quality and characteristics, via customer reviews, and make an informed purchase. Due to the fact that these reviews are used to determine the extent of customers acceptance and satisfaction of a product or service, they can affect the future selling performance and market share of a company because they can also be used by companies to determine the success of a product, and predict its demand. As a consequence, tools for efficiently classifying textual customer reviews are becoming a key component of each e-commerce development framework to enable business companies to define the most suitable selling strategies and improve their market capabilities. This paper introduces an innovative framework for efficiently analysing customer sentiments in textual reviews in order to compute their corresponding numerical rating to allow companies to better plan their future business activities. The proposed approach addresses different issues involved in this significant task: the dimension and imprecision of ratings data. As shown in experimental results, the proposed hybrid approach yields better learning performance than other state of the art rating predictors.
The relation between visual motion information and temporal perception has a significant effect on the development of man-machine interface. However, the relation is still not fully understood. This study aims to inve...
详细信息
The relation between visual motion information and temporal perception has a significant effect on the development of man-machine interface. However, the relation is still not fully understood. This study aims to investigate temporal processing of audiovisual simultaneity during perception of apparent motion, which is the fundamental unit of human motion perception. Participants performed an audiovisual temporal order judgment (TOJ) task under two conditions: apparent motion condition and non-apparent motion condition. Our result shows that visual motion information contributes to the acceleration of visual processing and the increase of temporal resolution in temporal processing of audiovisual simultaneity. Our findings will provide useful information to construct the frame of temporal processing in man-machine interface.
We consider the path planning problem of a mobile robot that has to travel towards a given target location. The robot shares the environment with other mobile robots, altogether forming a wireless mobile ad hoc networ...
详细信息
We consider the path planning problem of a mobile robot that has to travel towards a given target location. The robot shares the environment with other mobile robots, altogether forming a wireless mobile ad hoc network relaying data in a multi-hop fashion. In this scenario, the robot's path planner has to optimally balance two potentially conflicting goals: keep the traveled distance within an assigned maximum value while letting the robot effectively communicate with the other robots in the network. We propose a solution method relying on the use of a link quality predictor built offline through a supervised learning approach. Together with the information gathered online from the other robots, the predictor allows to adaptively build a spatial map of expected communication quality, for both local and distant areas. In turn, the map is used by the path planner, based on a mixed integer linear formulation and an intelligent strategy for discretizing the environment, to iteratively find the best network-aware path to follow. The proposed approach is evaluated in various realistic simulation scenarios, showing the effectiveness of using the link quality map and the robustness to different restrictions regarding available information and computational resources.
Dedispersion is a basic algorithm to reconstruct impulsive astrophysical signals. It is used in high sampling-rate radio astronomy to counteract temporal smearing by intervening interstellar medium. To counteract this...
详细信息
ISBN:
(纸本)9781479938018
Dedispersion is a basic algorithm to reconstruct impulsive astrophysical signals. It is used in high sampling-rate radio astronomy to counteract temporal smearing by intervening interstellar medium. To counteract this smearing, the received signal train must be dedispersed for thousands of trial distances, after which the transformed signals are further analyzed. This process is expensive on both computing and data handling. This challenge is exacerbated in future, and even some current, radio telescopes which routinely produce hundreds of such data streams in parallel. There, the compute requirements for dedispersion are high (petascale), while the data intensity is extreme. Yet, the dedispersion algorithm remains a basic component of every radio telescope, and a fundamental step in searching the sky for radio pulsars and other transient astrophysical objects. In this paper, we study the parallelization of the dedispersion algorithm on many-core accelerators, including GPUs from AMD and NVIDIA, and the Intel Xeon Phi. An important contribution is the computational analysis of the algorithm, from which we conclude that dedispersion is inherently memory-bound in any realistic scenario, in contrast to earlier reports. We also provide empirical proof that, even in unrealistic scenarios, hardware limitations keep the arithmetic intensity low, thus limiting performance. We exploit auto-tuning to adapt the algorithm, not only to different accelerators, but also to different observations, and even telescopes. Our experiments show how the algorithm is tuned automatically for different scenarios and how it exploits and highlights the underlying specificities of the hardware: in some observations, the tuner automatically optimizes device occupancy, while in others it optimizes memory bandwidth. We quantitatively analyze the problem space, and by comparing the results of optimal auto-tuned versions against the best performing fixed codes, we show the impact that auto-tuning ha
In natural human-human task descriptions, the verbal and the non-verbal parts of communication together comprise the information necessary for understanding. When robots are to learn tasks from humans in the future, t...
详细信息
In natural human-human task descriptions, the verbal and the non-verbal parts of communication together comprise the information necessary for understanding. When robots are to learn tasks from humans in the future, the detection and integrated interpretation of both of these cues is decisive. In the present paper, we present a qualitative study on essential verbal and non-verbal cues by means of which information is transmitted during explaining and showing a task to a learner. In order to collect a respective data set for further investigation, 16 (human) teachers explained to a human learner how to mount a tube in a box with holdings, and six teachers did this to a robot learner. Detailed multi-modal analysis revealed that in both conditions, information was more reliable when transmitted via verbal and gestural references to the visual scene and via eye gaze than via the actual wording. In particular, intra-speaker variability in wording and perspective taking by the teacher potentially hinders understanding of the learner. The results presented in this paper emphasize the importance of investigating the inherently multi-modal nature of how humans structure and transmit information in order to derive respective computational models for robot learners.
Support Vector Machine (SVM) has been widely used in data-mining and bigdata applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was...
详细信息
ISBN:
(纸本)9781479938018
Support Vector Machine (SVM) has been widely used in data-mining and bigdata applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. Advanced multi- and many-core architectures offer massive parallelism with complex memory hierarchies which can make runtime training possible, but form a barrier to efficient parallel SVM design. To address the challenges above, we designed and implemented MIC-SVM, a highly efficient parallel SVM for x86 based multi-core and many-core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi co-processor (MIC). We propose various novel analysis methods and optimization techniques to fully utilize the multilevel parallelism provided by these architectures and serve as general optimization methods for other machine learning tools. MIC-SVM achieves 4.4-84x and 18-47x speedups against the popular LIBSVM, on MIC and Ivy Bridge CPUs respectively, for several real-world data-mining datasets. Even compared with GPUSVM, run on a top of the line NVIDIA k20x GPU, the performance of our MIC-SVM is competitive. We also conduct a cross-platform performance comparison analysis, focusing on Ivy Bridge CPUs, MIC and GPUs, and provide insights on how to select the most suitable advanced architectures for specific algorithms and input data patterns.
This book constitutes the refereed proceedings of the 13th China National Conference on computational Linguistics, CCL 2014, and of the First International symposium on Natural Language Processing Based on Naturally A...
详细信息
ISBN:
(数字)9783319122779
ISBN:
(纸本)9783319122762
This book constitutes the refereed proceedings of the 13th China National Conference on computational Linguistics, CCL 2014, and of the First International symposium on Natural Language Processing Based on Naturally Annotated bigdata, NLP-NABD 2014, held in Wuhan, China, in October 2014. The 27 papers presented were carefully reviewed and selected from 233 submissions. The papers are organized in topical sections on word segmentation; syntactic analysis and parsing the Web; semantics; discourse, coreference and pragmatics; textual entailment; language resources and annotation; sentiment analysis, opinion mining and text classification; large‐scale knowledge acquisition and reasoning; text mining, open IE and machine reading of the Web; machine translation; multilinguality in NLP; underresourced languages processing; NLP applications.
暂无评论