Speech emotion recognition approaches in human computer interaction

Speech Emotion Recognition (SER) represents one of the emerging fields in human-computer interaction. Quality of the human-computer interface that mimics human speech emotions relies heavily on the types of features used and also on the classifier employed for recognition. The main purpose of this paper is to present a wide range of features employed for speech emotion recognition and the acoustic characteristics of those features. Also in this paper, we analyze the performance in terms of some important parameters such as: precision, recall, F-measure and recognition rate of the features using two of the commonly used emotional speech databases namely Berlin emotional database and Danish emotional database. Emotional speech recognition is being applied in modern human-computer interfaces and the overview of 10 interesting applications is also presented in this paper to illustrate the importance of this technique.     

Intelligent agent based artificial immune system for computer security—a review

Since its introduction in the 1990s the internet has proliferated in the life of human kind in many numbers of ways. The two by-products of the internet are intelligent agents and intrusions which are far away from each other in the intention of their creation while similar in their characteristics. With automated code roaming the network intruding the users on one side as worms, viruses, and Trojans and autonomous agents tending to help the users on the other side, the internet has given great research challenges to the computer scientists. The greatest challenge of the internet is intrusion, which has increased and never decreased. There are various security systems for the internet. As the Human Immune System protects human body from external attacks, these security systems tend to protect the internet from intruders. Thus the internet security systems are comparable with human immune systems in which autonomous cells move throughout the body to protect it while learning to tackle new threats and keeping them in their memory for the future. These properties are comparable with that of autonomous agents in the internet. Thus intelligent agent technology combined with ideas from human immune system is a great area of research which is still in its developing phase. In this paper, state of the art of security systems which use both these technologies of intelligent agents and artificial immune system i.e., Agent Based Artificial Immune System (ABAIS) for security are reviewed, paying special attention to features of human immune system used in the system, the role of the agents in the ABAIS and the security mechanisms provided against intrusions.     

Effect of compositional modifications on the piezoelectric properties of spray dried lead zirconate titanate ceramics

Lead zirconate titanate powders of different compositions varying from 50 to 55 atomic percent zirconium in the solid solution have been prepared by spray-drying technique. The compositions were varied by changing the zirconium-to-titanium ratio in the solid solution and also with the addition of strontium. The amorphous character of the as-prepared powders and the formation of single phase lead zirconate titanate during calcination were also confirmed by x-ray diffraction technique. These powders were then converted to piezoelectric ceramics by compaction and sintering followed by electroding and poling. Effect of the variation of zirconium to titanium ratio and strontium additions on the piezoelectric properties of the finished ceramics have been explained on the basis of improved sintering, uniform grain size, formation of morphotropic phase boundary and subsequent shift to rhombohedral structure.     

Compression, clustering, and pattern discovery in very high-dimensional discrete-attribute data sets

This paper presents an efficient framework for error-bounded compression of high-dimensional discrete-attribute data sets. Such data sets, which frequently arise in a wide variety of applications, pose some of the most significant challenges in data analysis. Subsampling and compression are two key technologies for analyzing these data sets. The proposed framework, PROXIMUS, provides a technique for reducing large data sets into a much smaller set of representative patterns, on which traditional (expensive) analysis algorithms can be applied with minimal loss of accuracy. We show desirable properties of PROXIMUS in terms of runtime, scalability to large data sets, and performance in terms of capability to represent data in a compact form and discovery and interpretation of interesting patterns. We also demonstrate sample applications of PROXIMUS in association rule mining and semantic classification of term-document matrices. Our experimental results on real data sets show that use of the compressed data for association rule mining provides excellent precision and recall values (above 90 percent) across a range of problem parameters while reducing the time required for analysis drastically. We also show excellent interpretability of the patterns discovered by PROXIMUS in the context of clustering and classification of terms and documents. In doing so, we establish PROXIMUS as a tool for both preprocessing data before applying computationally expensive algorithms and directly extracting correlated patterns.     

A survey: hybrid evolutionary algorithms for cluster analysis

Clustering is a popular data analysis and data mining technique. It is the unsupervised classification of patterns into groups. Many algorithms for large data sets have been proposed in the literature using different techniques. However, conventional algorithms have some shortcomings such as slowness of the convergence, sensitive to initial value and preset classed in large scale data set etc. and they still require much investigation to improve performance and efficiency. Over the last decade, clustering with ant-based and swarm-based algorithms are emerging as an alternative to more traditional clustering techniques. Many complex optimization problems still exist, and it is often very difficult to obtain the desired result with one of these algorithms alone. Thus, robust and flexible techniques of optimization are needed to generate good results for clustering data. Some algorithms that imitate certain natural principles, known as evolutionary algorithms have been used in a wide variety of real-world applications. Recently, much research has been proposed using hybrid evolutionary algorithms to solve the clustering problem. This paper provides a survey of hybrid evolutionary algorithms for cluster analysis.     

Integration of rate and credit schemes for ATM flow control

The authors make the case in favor of an integrated approach to ATM flow control. They contend that both rate and credit schemes have advantages and disadvantages, and that to a large extent they can be viewed as complementary