Journal of Ambient Intelligence and Humanized Computing

Massive amounts of unstructured content have been generated day-by-day on social media platforms like Facebook, Twitter and blogs. Analyzing and extracting useful information from this vast amount of text content is a challenging process. Social media have currently provided extensive opportunities for researchers and practitioners to do adequate research on this area. Most of the text content in social media tend to be either in English or code-mixed regional languages. In a multilingual country like India, code-mixing is the usual fashion witnessed in social media discussions. Multilingual users frequently use Roman script, an convenient mode of expression, instead of the regional language script for posting messages on social media and often mix it with English into their native languages. Stylistic and grammatical irregularities are significant challenges in processing the code-mixed text using conventional methods. This paper explains the new word embedding via character level representation as features for POS tagging the code-mixed text in Indian languages using the ICON-2015, ICON-2016 NLP tools contest data set. The proposed word embedding features are context-appended, and the well-known Support Vector Machine (SVM) classifier has been used to train the system. We have combined the Facebook, Twitter, and WhatsApp code-mixed data of three Indian languages to train the Transfer learning based language-independent and source independent POS tagging. The experimental results demonstrated that the proposed transfer method achieved state-of-the-art accuracy in 12 systems out of 18 systems for the ICON data set.

The security concerns due to the September 11 and later terroristic attacks, fostered the development of more advanced techniques for biometric identification. This had a positive impact to research and deployment of these technologies, founding a basis for security-related applications. At the same time, the privacy concerns for the misuse of personal information have hindered the application of the same technologies wherever their introduction could not be enforced. The risk is for the scientific development to be blocked by contradictory needs, which, in turn, often derive from misconceptions or misunderstanding of the real potential of biometric technologies. Within this context, ambient intelligence allows to consider the relation between biometrics and privacy under a different perspective. In fact, as most of times we are able to maintain social relations without the need to know each other’s identity (consider for example the case of a customer relating with an attendant at a department store), in the same way biometric technologies can facilitate the man–machine interaction (to better provide useful services) without the need to determine the user’s full identity. Also in the case of security applications, most often may be sufficient to retrieve ancillary information about a subject rather than determining his/her identity. This paper analyzes the potential of biometric technologies within the general scope of ambient intelligence, trying to identify some key technological issues which may respond to privacy concerns. Some example applications are considered where by exploiting the information contained in biometric data, such as the facial expression or other, non visual, measurements, it is possible to better relate the user with the environment and provide a substantial input to drive the services provided, without compromising his privacy.

High speed communication and application requirements are rapidly increasing, and the quality of physical layer is more and more important to realize real reliable communications. It requires accurate and reliable hardware devices, or else communications may be unstable and unsure. In this paper, we focus on the high speed network hardware integrated circuit systems to obtain good electrical, mechanical and procedural characters. Very large scale integrations (VLSI) form the basis for the implementation of high-performance, low-power, and low-cost wireless computing and mobile application systems. In integrated circuit (IC) design flow, distributed electromagnetic effects at high frequencies become prominent and decisively impact overall IC performance. To solve this problem, this paper presents an electronic design automation tool capable of automatic capacitance extraction for IC interconnections. This tool integrates electromagnetic field based two-dimensional (2-D) and three-dimensional (3-D) interconnect capacitance extraction solvers. It can be used for VLSI parasitic capacitance parameters extraction. The system architecture, capacitance extraction process flow and some important data structures will be discussed. Some extraction experimental results will demonstrate the accuracy and high efficiency of our 2-D and 3-D solvers.

In this article, a new idea of fuzzy fractional coloring of fuzzy graph is presented and fuzzy fractional chromatic number is defined. A relationship between fuzzy fractional chromatic number and fuzzy fractional clique number is established. Some properties of fuzzy chromatic number of fuzzy graphs and fuzzy fractional chromatic number of fuzzy graphs are proved and the concept of k-strong adjacent vertices is introduced. Fuzzy chromatic number and fuzzy fractional chromatic number have been calculated on lexicographic product of two fuzzy graphs. Also, fuzzy chromatic number, independence number and fuzzy fractional chromatic number have been investigated on disjoint union of two fuzzy graphs. Lastly, a real life application of fuzzy fractional coloring on fuzzy graph is discussed.

Local descriptors play a vital role in face analysis. This paper proposes a modified dimensionality reduced local directional pattern (MDR-LDP) for face analysis that includes both face and facial expression recognition. MDR-LDP is an updated version of dimensionality reduced local directional pattern (DR-LDP) for face recognition. DR-LDP assigns a single code for every $$3 \times 3$$ region of local directional pattern (LDP) encoded image. It is a compact and efficient code to recognize faces but gives only satisfactory results for facial expression recognition. Every $$3 \times 3$$ LDP encoded region is reduced to a $$2 \times 2$$ region and labeled as MDR-LDP. The MDR-LDP descriptor considers the micro structure patterns in the image. The resultant MDR-LDP encoded image is further divided into regions and histograms are generated for each region. The bins of each histogram form the feature vector. The concatenation of all the feature vectors forms the MDR-LDP descriptor and is used for facial expression. The proposed MDR-LDP is robust to noise, illumination changes and pose variations. The experiments were carried out on standard databases and the objective evaluation using the standard metrics prove that MDR-LDP performs superior to the other local descriptors for face analysis.