Incorporating user satisfaction into the look-and-feel of mobile phone design

The look-and-feel of the mobile phone was investigated using a consumer survey. Seventy-eight participants evaluated the design of 50 different mobile telephones on the perceived scale of image/impression characteristics, including: luxuriousness, simplicity, attractiveness, colourfulness, texture, delicacy, harmoniousness, salience, rigidity, and overall satisfaction. Stepwise multiple linear regression analysis were used to evaluate results. The results showed that the image and impression characteristics of the products were closely related to the human-product interface specifications as well as overall shape of the product. Design variables such as texture, use of surface curvature, surface treatment, operating sound, and control response ratio were perceived as important by customers. This study also suggested a series of statistical processes for selecting and screening the critical design variables closely related to the customer's impression of a product. The product evaluation and analysis methods could be generalized to other consumer products.     

Incorporating user satisfaction into the look-and-feel of mobile phone design

The look-and-feel of the mobile phone was investigated using a consumer survey. Seventy-eight participants evaluated the design of 50 different mobile telephones on the perceived scale of image/impression characteristics, including: luxuriousness, simplicity, attractiveness, colourfulness, texture, delicacy, harmoniousness, salience, rigidity, and overall satisfaction. Stepwise multiple linear regression analysis were used to evaluate results. The results showed that the image and impression characteristics of the products were closely related to the human-product interface specifications as well as overall shape of the product. Design variables such as texture, use of surface curvature, surface treatment, operating sound, and control response ratio were perceived as important by customers. This study also suggested a series of statistical processes for selecting and screening the critical design variables closely related to the customer's impression of a product. The product evaluation and analysis methods could be generalized to other consumer products.     

社会化标签系统中个性化的用户建模方法

针对社会化标签系统中现有用户兴趣模型建立的缺陷,即：使用一些零散标签的集合来表示用户兴趣,而忽略标签的联合使用现象。提出一种将共现技术引入自然法的用户建模方法,该方法以自然法为基础,向用户模型中添加适量的标签对,较好地体现了标签之间的联系,又同时考虑了体现用户兴趣的标签自身的权重。在PKDD2009数据集上测试实验结果表明,该模型较之已提出的自然法和共现法,取得了更高的准确率和召回率。     

Keyframe-based user interfaces for digital video

Three visual interfaces that use keyframes - still images automatically pulled from video - to provide access points for efficient navigation of recorded content can help identify potentially useful or relevant video segments     

Exploiting multi-expression dependences for implicit multi-emotion video tagging

In this paper, a novel approach of implicit multiple emotional video tagging is proposed, which considers the relations between the users' facial expressions and emotions as well as the relations among multiple expressions. First, the audiences' expressions are inferred through a multi-expression recognition model, which consists of an image-driven expression measurement recognition and a Bayesian network representing the co-existence and mutual exclusion relations among multi-expressions. Second, the videos' multi-emotion tags are obtained from the recognized expressions by another Bayesian Network, capturing the relations between expressions and emotions. Results of the experiments conducted on the JAFFE and NVIE databases demonstrate that the performance of expression recognition is improved by considering the relations among multiple expressions. Furthermore, the relations between expressions and emotions help improve emotional tagging, as our approach outperforms the traditional expression-based or image-driven implicit tagging methods.     

基于用户标注行为的潜在好友推荐

目前多数社交网络主要根据已有好友关系推荐潜在好友,用户的兴趣爱好不作为主要考虑因素;此外,如何从大量数据中精确地提取用户的兴趣爱好是一项十分艰巨的任务。为此,提出一种在大量标注行为数据中精确挖掘出用户的兴趣爱好,并据此推荐具有相同兴趣爱好的潜在好友的算法--基于标注的好友推荐(FRBT)算法。首先使用词频-逆向文件频率(TF-IDF)对标签进行聚类,将语义相似的标签聚成话题;然后在话题的基础上提出一种新的相似度公式来计算用户相似度;再融合基于话题与基于物品的用户相似度,将相似度较高的用户作为潜在好友进行推荐。在Delicious数据集上以准确率和召回率为指标与item、tag和tri-graph三种算法进行比较,实验验证了该算法能够更准确地为用户推荐兴趣相似的好友。     

基于社会标注系统的Web用户聚类算法

针对Web用户聚类时, 社会标注系统中用户访问资源数据稀疏从而导致传统聚类算法效率不高的问题, 提出了一种三向迭代聚类算法, 对用户、标签和资源分别聚类, 利用三者之间的关联关系不断相互交叉迭代调整, 直到各聚类簇达到稳定为止。实验表明, 该方法调整后类的内聚性更强, 区分度更大, 能有效解决数据稀疏性问题, 提高用户聚类效果。     

Analysing user physiological responses for affective video summarisation

Video summarisation techniques aim to abstract the most significant content from a video stream. This is typically achieved by processing low-level image, audio and text features which are still quite disparate from the high-level semantics that end users identify with (the ‘semantic gap’). Physiological responses are potentially rich indicators of memorable or emotionally engaging video content for a given user. Consequently, we investigate whether they may serve as a suitable basis for a video summarisation technique by analysing a range of user physiological response measures, specifically electro-dermal response (EDR), respiration amplitude (RA), respiration rate (RR), blood volume pulse (BVP) and heart rate (HR), in response to a range of video content in a variety of genres including horror, comedy, drama, sci-fi and action. We present an analysis framework for processing the user responses to specific sub-segments within a video stream based on percent rank value normalisation. The application of the analysis framework reveals that users respond significantly to the most entertaining video sub-segments in a range of content domains. Specifically, horror content seems to elicit significant EDR, RA, RR and BVP responses, and comedy content elicits comparatively lower levels of EDR, but does seem to elicit significant RA, RR, BVP and HR responses. Drama content seems to elicit less significant physiological responses in general, and both sci-fi and action content seem to elicit significant EDR responses. We discuss the implications this may have for future affective video summarisation approaches.     

融合用户属性信息的冷启动推荐算法

协同过滤算法广泛应用于个性化推荐系统中。现有的基于社群相似性的协同过滤算法在新用户新商品的冷启动场景中难以使用,性能较差。对此,提出了一种基于矩阵分解和神经网络映射的冷启动推荐算法。首先,使用矩阵分解方法求出用户在潜在兴趣空间的向量表示;然后,训练神经网络学习从用户属性数据到潜在兴趣向量的映射关系;最后,融合用户的历史评分数据与属性数据各自生成的兴趣向量,给出平滑的推荐预测值。实验表明,当用户的评分记录很少时,预测性能有明显提升,融合用户的属性信息能较好地改善"冷启动"情况下推荐系统的性能。     

Structural approach to design user interface

The analysis of the interactive relations among interface elements using a structuralized method can help user interface designers to satisfy the different requirements of design and improve design efficiency. This study develops a three-stage structured user interface design approach for complex information systems consisting of multiple components. First, the Quality Function Development (QFD) approach is used to confirm the user's design demand and its mapping components. Next, the Interpretive Structural Model (ISM) technique is adopted to construct a clear model of a hierarchical structure. Finally, the Impact Matrix Cross-Reference Multiplication Applied to a Classification (MICMAC) approach is employed to analyze the effect and dependence among the overall design components, and to consider the relationship network graph of distribution of components in the system. The research approach applies the Web mail system as its case study. Through the empirical study of web-based system, interface designers can effectively grasp a user's differentiated demand that changes rapidly and reflect it in the combination of designed components. This study establishes a strategy for creating an information system design pattern with multiple components is by building a hierarchical structure and analyzing the component distribution.     

Accurate online video tagging via probabilistic hybrid modeling

Accurate video tagging has been becoming increasingly crucial for online video management and search. This article documents a novel framework called comprehensive video tagger (CVTagger) to facilitate accurate tag-based video annotation. The system applies both multimodal and temporal properties combined with a novel classification framework with hierarchical structure based on multilayer concept model and regression analysis. The advanced architecture enables effective incorporation of both video concept dependency and temporal dynamics. Using a large-scale test collection containing 50,000 YouTube videos, a set of empirical studies have been carried out and experimental results demonstrate various advantages of CVTagger over the state-of-the-art techniques.     

视频会议系统用户申请模式的研究

在分析H.323系统的基础上,提出了多路视频传输与显示的新方法,实现了用户申请工作模式。在用户申请模式下,MCU将与会人员列表发送给各终端,用户可以向MCU申请一路或多路视频流。MCU对被申请的视频流进行复合和转发,它们在终端可以被独立显示。用户申请模式增强了系统的交互性,保持了图像原有尺寸。实验表明,作为一种扩展的工作模式,它具有良好的兼容性,在CPU和内存占用等方面也明显优于混图模式。     

Neural correlates of affective content: application to perceptual tagging of video

Neural Computing and Applications - Over the past years, a digital multimedia uprising has been experienced in every walk of life, due to which the un-annotated or unstructured multimedia content...     

Tag recommendation method in folksonomy based on user tagging status

A folksonomy consists of three basic entities, namely users, tags and resources. This kind of social tagging system is a good way to index information, facilitate searches and navigate resources. The main objective of this paper is to present a novel method to improve the quality of tag recommendation. According to the statistical analysis, we find that the total number of tags used by a user changes over time in a social tagging system. Thus, this paper introduces the concept of user tagging status, namely the growing status, the mature status and the dormant status. Then, the determining user tagging status algorithm is presented considering a user’s current tagging status to be one of the three tagging status at one point. Finally, three corresponding strategies are developed to compute the tag probability distribution based on the statistical language model in order to recommend tags most likely to be used by users. Experimental results show that the proposed method is better than the compared methods at the accuracy of tag recommendation.     

Applying visual psychophysics to user interface design

Abstract

Electronic displays are ubiquitous as the interface between people and computers. By far the most important perceptual sense used to interpret and analyse information provided by such displays is vision. This area has a vast and distinguished history, stretching back through names as eminent as Da Vinci, Descartes, Newton, Helmholtz and Young; this makes a thorough review of the area impossible in the space available here. Instead this review is limited to those areas of perception relevant to users of electronic displays. The purpose of this paper is to make designers of user interfaces aware of certain issues in visual perception and to provide a discussion of what psychophysics has to offer interface design.     

Applying user modeling to human-computer interaction design

Since the early 1980's, intelligent and adaptive systems have appeared and have been written about in a variety of guises. Although there are many differences between such systems as adaptive user interfaces, intelligent help systems and explanation systems, there are many similarities as well. The most notable of these is that they all require user models to be maintained and exploited as part of their designs. Furthermore, they share the same high level architecture. This paper discusses the use of models in human-computer interaction design and offers a common architecture for these adaptive systems. A methodology for the development of these systems is presented.This is based on our experimental work which is reported fully in Jennings, Benyon and Murray, 1991 and Jennings and Benyon, in press)     

Incorporating user preferences in ant colony optimization for the next release problem

The selection of which requirements should be implemented in the next software release is an important and complex task in the software development process, considering the presence of budget constraints and other conflicting aspects. In this context, search based software engineering, has the main objective of applying automatic search methods to solve complex software engineering problems. However, most of these methods do not consider human expertise during the search, especially due to the difficulty in mathematically modeling the user's preferences. Consequently, the user can present some resistance or place little confidence in the final results, given that his/her knowledge and domain expertise was not properly considered in the solution construction. This paper aims at proposing an interactive model for the next release problem using ant colony optimization, where the user can define which requirements he/she would like to include or not in the next release. Employing humans and a simulator, an empirical study was performed that considers real-world and artificial instances. The achieved results demonstrate that the loss of score was, on average, 12% when it was compared with a solution with no human intervention. On the other hand, the algorithm generates solutions that have more than 80% of the met preferences, as defined by the users. Furthermore, the results showed that ACO can be an interesting choice as an interactive search engine, given the low quantity of interactions that are required to reach good solutions.     

Two-stage hierarchical video summary extraction to match low-level user browsing preferences

A compact summary of video that conveys visual content at various levels of detail enhances user interaction significantly. In this paper, we propose a two-stage framework to generate MPEG-7-compliant hierarchical key frame summaries of video sequences. At the first stage, which is carried out off-line at the time of content production, fuzzy clustering and data pruning methods are applied to given video segments to obtain a nonredundant set of key frames that comprise the finest level of the hierarchical summary. The number of key frames allocated to each shot or segment is determined dynamically and without user supervision through the use of cluster validation techniques. A coarser summary is generated on-demand in the second stage by reducing the number of key frames to match the low-level browsing preferences of a user. The proposed method has been validated by experimental results on a collection of video programs.