Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level dictionary. The approach uses ConceptNet as framework propagate values, based on assumption that semantically related concepts share common sentiment.

In this paper, we explore the challenges in applying and investigate methodologies to improve direct-touch interaction on intangible displays. Direct-touch simplifies object manipulation, because it combines input display into a single integrated interface. While traditional tangible display-based technology is commonplace, similar within an paradigm presents many challenges. Given lack of tactile feedback, may show poor performance even simplest target acquisition tasks. order study...

The capability of interpreting the conceptual and affective information associated with natural language through different modalities is a key issue for enhancement human-agent interaction. proposed methodology, termed sentic blending, enables continuous interpretation semantics sentics (i.e., language) based on integration an common-sense knowledge base any multimodal signal-processing module. In this work, in particular, blending interfaced facial emotional classifier opinion mining...

Failover for service-oriented distributed networks is a prerequisite to enabling Internet-of-Things (IoT) in the sense of deploy-once, run forever. Resource reconfiguration required achieve failover mechanisms upon replacement devices or failure services. It can be particularly challenging when services applications have more than end-to-end transmissions between that are heterogeneous versatile, which duplications costly and redundant. Specifically, device with failed service shall taken...

In this paper, we propose a competitive human computation game, KissKissBan (KKB), for image annotation. KKB is different from other games since it integrates both collaborative and elements in the game design. one player, blocker, competes with two players, couples; while couples try to find consensual descriptions about an image, blocker's mission prevent reaching consensus. Because of its design, possesses nice properties over traditional game. First, blocker encouraged stop descriptions,...

Games with A Purpose have successfully harvested information from web users. However, designing games that encourage sustainable and quality data contribution remains a great challenge. Given many online communities enjoyed active participation loyal following, this research explores how human computation may benefit rich interactions inherent in community. We experimented by implementing two for commonsense collection on the leading social community platforms: Rapport Game Facebook Virtual...

Recognition of appliances states is an import building block for making energy-efficiency schemes and providing energy-saving advice performing automatic control. Several existing approachs use smart outlets or detectors to acquire the information individual appliance recognize operating state. However, such have install numerous devices if they want monitor all appliances. This will increase cost complexity installation maintenance. Therefore, we develop recognition system which minimizing...

Abstract Objective Preterm infants are at high risk of neuromotor disorders. Recent advances in digital technology and machine learning algorithms have enabled the tracking recognition anatomical key points human body. It remains unclear whether proposed pose estimation model skeleton-based action for adult movement classification applicable accurate infant motor assessment. Therefore, this study aimed to develop validate an artificial intelligence (AI) framework full-term preterm infants....

Ubiquitous sensing and actuating devices are now everywhere in our living environment as part of the global cyber–physical ecosystem. Sensing capabilities can be modeled services to compose intelligent Internet Things (IoT) applications. An issue for perpetually running managing these IoT is energy cost. One saving strategy co-locate several on one device order reduce computing communication energy. In this paper, we propose a service merging mapping co-locating multiple devices. multi-hop...

Building contextual models for new "smart" environments is not considered cost effective if data model training must be collected from scratch. It more practical to transfer as much learned knowledge possible an existing environment the target in order reduce collection effort. In reuse original environment, this study proposed a feature-based framework. The framework makes use of learning, which relaxes constraint requiring and testing datasets highly similar distribution. Experimental...

Chinese calligraphy is the writing of characters as an art form performed with brushes so are rich shapes and details. Recent studies show that can be generated through image-to-image translation for multiple styles using a single model. We propose novel method this approach by incorporating characters' component information into its also improved network to convert their embedding space. Experiments proposed generates high-quality over state-of-the-art methods measured numerical evaluations...

This paper presents a novel approach to solving the single-vehicle pickup and delivery problem with time windows capacity constraints. While dynamic programming has been used find optimal routing given problem, it requires exponential in number of tasks. Therefore, often fails solutions under real-time conditions an automated factory. research explores anytime using genetic algorithms. By utilizing but possibly partial from programming, hybrid algorithms can produce near-optimal for problems...

Multi-resident activity recognition is among a key enabler in many context-aware applications smart home. However, most of prior researches ignore the potential interactions residents order to simplify problem complexity. On other hand, multiple-resident activities are usually recognized using cameras or wearable sensors. due human-centric concerns, it more preferable avoid obtrusive In this paper, we propose dynamic Bayesian networks which extend coupled hidden Markov models (CHMMs) by...

The Reflexive Printer is a physical artifact combined with mobile application. It allows digital-photo natives to enrich their experiences of daily reminiscence. Each day, the system takes one picture from user's smartphone album, prints it on thermal paper as halftone image, and deletes smartphone. With critical lens, we reframe technology-mediated reminiscence an intersubjective interaction between human artifact. In this mutually informed relationship, propose perceived drawbacks design...

Parent-child communication is an essential element in behavioral and character development early childhood; however, parents may find it difficult to be aware of how they talk their children. Through extensive field studies with experts parents, we found that are more likely experience conflict preschool children (3-6 years old) on school mornings. In consultation domain professionals families, designed WAKEY, a technology-based approach helps use better strategies teach carry out morning...