A QoS-driven approach for service-oriented device anycasting in ubiquitous environments

The vision of pervasive computing is to let users enjoy ICT-enabled services in an “any time, anywhere, on any device” manner. It aims to supply ubiquitous services through communications among a set of devices deployed in a ubiquitous environment. Due to the diverse QoS needs of different kinds of ubiquitous services and users, it is a critical challenge to select an optimal set of devices with the objective of achieving service-specific QoS goals like low packet loss, short packet delay, and high energy efficiency. In this paper, the problem is first formulated as the service-oriented device anycasting problem (SDAP) and then proved as an NP-complete problem. By adopting a tree-based service representation model, Basu et al. proposed the dynamic task-embedding anycasting (DTA) approach. This approach effectively solves the SDAP in a distributed way. However, the service quality is likely sacrificed because the tree scheme does not sufficiently describe a ubiquitous service. In this paper, we propose a novel approach called the service-oriented device anycasting (SDA) approach that adopts a graph-based service representation model called the service profile (SP). By introducing a layered structure into the SP, the SDA approach can reach a compromise between service quality and computational complexity. In addition, the QoS-driven utility function is proposed to quantify service quality by matching the capabilities of heterogeneous devices to various QoS needs. Finally, the simulation results show that the SDA approach outperforms the DTA approach by saving roughly 20% of device energy and prolonging the network lifetime. Packet loss and packet delay are also improved by roughly 25% and 8%, respectively. The advantage of the SDA approach is more obvious in environments with highly mobile devices and multiple users.     

Neural network based method for image halftoning and inverse halftoning

A hybrid neural network based method for halftoning and inverse halftoning of digital images is presented. The halftone image is performed by single-layer perceptron neural network (SLPNN), and its corresponding continuous-tone image is reconstructed by radial-basis function neural network (RBFNN). The combined training procedure produces halftone images and the corresponding continuous tone images at the same time. The PSNR performance and visual image quality of these contone images achieved is comparable to the well-known inverse halftoning methods. The resultant halftone images compared with the error diffusion halftone are visually good, too. Furthermore, we apply different kinds of halftone images to a bi-level image compression method, called Block Arithmetic Coding for Image Compression (BACIC), which is better than the current facsimile methods.     

Integrated microblog sentiment analysis from users’ social interaction patterns and textual opinions

Traditional post-level opinion classification methods usually fail to capture a person’s overall sentiment orientation toward a topic from his/her microblog posts published for a variety of themes related to that topic. One reason for this is that the sentiments connoted in the textual expressions of microblog posts are often obscure. Moreover, a person’s opinions are often influenced by his/her social network. This study therefore proposes a new method based on integrated information of microblog users’ social interactions and textual opinions to infer the sentiment orientation of a user or the whole group regarding a hot topic. A Social Opinion Graph (SOG) is first constructed as the data model for sentiment analysis of a group of microblog users who share opinions on a topic. This represents their social interactions and opinions. The training phase then uses the SOGs of training sets to construct Sentiment Guiding Matrix (SGM), representing the knowledge about the correlation between users’ sentiments, Textual Sentiment Classifier (TSC), and emotion homophily coefficients of the influence of various types of social interaction on users’ mutual sentiments. All of these support a high-performance social sentiment analysis procedure based on the relaxation labeling scheme. The experimental results show that the proposed method has better sentiment classification accuracy than the textual classification and other integrated classification methods. In addition, IMSA can reduce pre-annotation overheads and the influence from sampling deviation.     

An opportunistic resource allocation approach for mixed QoS and non-QoS connections in OFDMA wireless networks

An opportunistic resource allocation approach is proposed to guarantee both fair resource allocation and high system throughput under combinations of QoS and non-QoS connections in OFDMA networks. This approach features dynamic connection classification and packet prioritization based on real-time network conditions and QoS constraints. A classifier is first employed to prioritize QoS connections by observing the channel state of each subscriber station and the utilization of network resources. It performs a finite-horizon Markov decision process with dynamic rules affected by system load. The transmission order of packets is then determined by an opportunistic multiservice scheduler according to the QoS requirements of connections and the output of the classifier. Having the scheduling result, an allocator assigns slots to the scheduled packets, and its output is linked back to the connection classifier through a resource usage observer for all subscriber stations. The sub-channel allocation problem is also solved by cooperation between the slot allocator and the packet scheduler. Results of numerical analysis and NS2 simulation confirm the advantages claimed above. The same conclusion can also be drawn from the comparison with several existing approaches in terms of system throughput, service successful ratio, average spectral efficiency, and system revenue.     

Fuzzy-Based Knowledge Discovery from Heterogeneous Data in Planting Systems for Elderly LOHAS

In this paper, we propose a knowledge discovery method based on the fuzzy set theory to help elders with plant cultivation. Initially, the fuzzy sets are constructed by using the feature selection and statistical interval estimation. The min-max inference and the center of gravity defuzzification method are then used to output a candidate pattern set. Finally, a pattern discovery is adopted to obtain the patterns from the candidate set for the cultivation suggestions by considering the frequency weight and user's experience. In order to demonstrate the performance of our method in planting systems, we conduct a clicks-and-mortar cultivation platform, namely Eden Garden, for the elderly lifestyles of health and sustainability (LOHAS). The experimental results show that the accuracy rate of our knowledge discovery method can reach up to 85%. Moreover, the results of the LOHAS index scale table present that the happiness of the elders is increasing while the elders are using our proposed method.     

A parallel fuzzy inference model with distributed prediction schemefor reinforcement learning

This paper proposes a three-layered parallel fuzzy inference model called reinforcement fuzzy neural network with distributed prediction scheme (RFNN-DPS), which performs reinforcement learning with a novel distributed prediction scheme. In RFNN-DPS, an additional predictor for predicting the external reinforcement signal is not necessary, and the internal reinforcement information is distributed into fuzzy rules (rule nodes). Therefore, using RFNN-DPS, only one network is needed to construct a fuzzy logic system with the abilities of parallel inference and reinforcement learning. Basically, the information for prediction in RFNN-DPS is composed of credit values stored in fuzzy rule nodes, where each node holds a credit vector to represent the reliability of the corresponding fuzzy rule. The credit values are not only accessed for predicting external reinforcement signals, but also provide a more profitable internal reinforcement signal to each fuzzy rule itself. RFNN-DPS performs a credit-based exploratory algorithm to adjust its internal status according to the internal reinforcement signal. During learning, the RFNN-DPS network is constructed by a single-step or multistep reinforcement learning algorithm based on the ART concept. According to our experimental results, RFNN-DPS shows the advantages of simple network structure, fast learning speed, and explicit representation of rule reliability.     

Generic LR fuzzy cells for fuzzy hardware synthesis

A novel primitive cell structure for high-performance hardware realization of fuzzy computations is proposed in this paper. Such a cell structure is called generic LR fuzzy cell because it is an integral unit that encapsulates an LR fuzzy set and a basic fuzzy operation such as implication or arithmetic operation. Based on the proposed cell structure, we can develop two major kinds of fuzzy cell-LR fuzzy implication cell and LR fuzzy arithmetic cell-for the systematic synthesis of fuzzy application specific integrated circuits (ASICs) or general purposed fuzzy processors. The fuzzy systems synthesized with LR fuzzy cells possess the characteristics of decentralized knowledge manipulations and massively parallel inference. The system expandability and reconfigurability are also warrantable. This paper emphasizes on the design and application of fuzzy implication cell. The LR fuzzy implication cell is implemented with analog current mode technology. By this technology, an implication cell has the characteristics including small circuit area, high performance, low-power dissipation, etc. Moreover, the implication cell manipulates continuous data so that the realization of a pure fuzzy system is possible. In this paper, the key circuit characteristics of fuzzy implication cell are evaluated in details and there are two cases-fuzzy knowledge system and fuzzy mean filter-implemented to confirm the effectiveness and efficiency of fuzzy hardware synthesis by the LR fuzzy cells     

KMDS: an expert system for integrated hardware/software design ofmicroprocessor-based digital systems

A design automation system called KMDS, which makes use of a knowledge-based expert system and external algorithmic procedures to realize a modularized and flexible design automation tool, is presented. Its system configuration and characteristics, knowledge base and device libraries, top-down design methodology, and external utilities are described. Besides aiding the design of single-board microcomputers, KMDS helps designers of intelligence interface cards such as color display adapters and printer server cards. KMDS is flexible enough to incorporate various types of knowledge into the system and to overcome the problems that result from the existence of a large number of candidate solutions under a very high-level design specification. KMDS automatically generates a control program, making the fully automatic design of digital systems possible     

Automated ontology construction for unstructured text documents

Ontology is playing an increasingly important role in knowledge management and the Semantic Web. This study presents a novel episode-based ontology construction mechanism to extract domain ontology from unstructured text documents. Additionally, fuzzy numbers for conceptual similarity computing are presented for concept clustering and taxonomic relation definitions. Moreover, concept attributes and operations can be extracted from episodes to construct a domain ontology, while non-taxonomic relations can be generated from episodes. The fuzzy inference mechanism is also applied to obtain new instances for ontology learning. Experimental results show that the proposed approach can effectively construct a Chinese domain ontology from unstructured text documents.