Search

Speech-based Interaction systems contribute to the growing class of contemporary interactive techniques (Human-Computer Interactive system), which have emerged quickly in the last few years. Versatility, multi-channel synchronization, sensitivity, and timing are all notable characteristics of speech recognition. In addition, several variables influence the precision of voice interaction recognition. However, few researchers have done a significant study on the five eco-condition variables that tend to affect speech recognition rate (SRR): ambient noise, human noise, utterance speed, and frequency. The principal strategic goal of this research is to analyze the influence of the four variables mentioned earlier on SRR, and it includes many stages of experimentation on mixed noise speech data. The sparse representation-based analyzing technique is utilized to analyze the effects. Speech recognition is not noticeably affected by a person’s usual speaking pace. As a result, high-frequency voice signals are more easily recognized (∼∼98.12%) than low-frequency speech signals in noisy environments. By performing the experiments, the test results may help design the distributive controlling and commanding systems.

Approximate Membership Localization (AML) is concerned with locating non-overlapped substrings thus avoiding redundancies. This overcomes the drawback of Approximate Membership Extraction (AME) process which has low efficiency for real world application. An algorithm called P-Prune is used in Blog search. This prunes most of the overlapped redundant substrings before generating them. Here we use the opinion retrieval scheme which analyses the viewers' comments on Blog contents. Our experimental study on blogs reveals the efficiency of P-Prune over AME method. We also work AML in application to a proposed Blog search framework, a search-based approach joining two tables using dictionary-based entity recognition from blogs. Apart from the advantage of AML over AME, the experiment also proves the efficiency of the search-based approach. This algorithm can be extended to video blogs (vlog) also.

An increasing number of ontology extraction based on domain knowledge are adopted in E-learning. It is critical that domain ontologies cannot sufficiently handle imprecise and vague knowledge, but fuzzy ontology can effectively resolve data with uncertainty. This paper proposes novel fuzzy domain ontology acquisition algorithm for E-Learning application. The knowledge construction mechanism constructs fuzzy concept and relation based on concepts. We have then proposed our design for extracting concepts from heterogeneous text documents.

Efficient utilization of resources is a vital factor for any environment. The grid environment is dynamic and it allows the clusters to move around freely. Grid acts as a supercomputer to the users by handling voluminous data. So proper allocation of the available resources is important. Hence resource discovery and scheduling of jobs is a challenging area in grid. This paper presents a new approach for scheduling jobs in grid using Bee Colony algorithm and the discovered resources are advancely reserved for future. Bee Colony is a recently popular heuristic algorithm used for optimization. Grid consists of many clusters which contains the resources. Clusters are formed using K-means algorithm. K-means is a partitioning method for cluster formation. The results shows that performance of resource discovery is greatly improved using this algorithm and total throughput is increased with advance reservation of resources.

Grid Computing has emerged as an important field by its focus on resource sharing. It provides highly scalable, strict secure and high performance. Many of the parallel applications submitted to grid environment may benefit from the allocation of multiple resources such as processors in multiple sites simultaneously. This Processor Co-allocation potentially leads to higher system utilizations and lower queue wait times by allowing parallel jobs to run when they need more processors than are available in a single cluster. However with processor co-allocation advanced processor reservation is needed. But this becomes one of the challenges in processor co-allocation. The aim of this paper is to provide advance reservation of jobs based on the priority.