Foundation University Journal of Engineering and Applied Sciences
Not a member yet
56 research outputs found
Sort by
MFCC and Machine Learning Based Speech Emotion Recognition Over TESS and IEMOCAP Datasets
Get PDFEmotions in speech provide a lot of information about the speaker’s emotional state. This paper presents a classification of emotions using a support vector machine (SVM) with Mel Frequency Cepstrum Coefficient (MFCC) features extracted from the voice signal. We have considered the following five emotions, namely anger, happy, neutral, pleasant surprise and sadness, for classification purposes. The proposed methodology, including SVM-Gaussian and SVM-Quadratic, is tested for its performance on the Toronto Emotion Speech Set (TESS) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) datasets. Our proposed methodology achieved 97% accuracy with TESS and 86% with IEMOCAP datasets, respectively
Assessing Research Collaboration in Database Systems and Computer Networks by Analysis of Coauthorship Network
Get PDFCommunity detection is a fundamental problem in social networks. These networks detect communities based on link analysis and strong connection strengths, but cannot reflect Author’s from different research areas. To address the problem of community detection, we have done a study for “Analyzing patterns of collaboration in co-authorship network using Modularity and Centrality Measures”. This analysis study uses combine features of Modularity with centrality measure to effectively detect community of different author’s having different research collaboration with different interests in domain of Computer Networks and Database Systems. Experiment of Dataset shown that this approach is better detect best authors from specific domain having high collaboration with other coauthors and presents information to the researcher’s that have relative interest in relative author’s community
Applying Centrality Measures for Impact Analysis in Coauthorship Network
Get PDFNowadays social networking is an essential part of everyone’s life to communicate with different people around the globe. Due to improvement in expertise networks are growing rapidly and becoming more complex. Through social networking, we can identify different communities that help us to get information about different people and their work in different fields. In social networks, community detection is one of the hot areas. In this paper, we have analyzed a co-authorship network of political science and ranked the authors on the basis of common centrality measures. Finding reveals that these common centrality measures can be useful indicators for impact analysis
Privacy Threats on Social Networking Websites
Get PDFWidespread use of social networking sites has increased the privacy threat for every individual. Privacy and security problem are two major issues associated with social networks, as the majority of the social network users are not cautious about the usability of the social websites. Social media sites have become latent target regarding offenders because of the occurrence of sensitive information and lack of user awareness of privacy settings. The overall aim of this paper is to enhance awareness about privacy and security issues associated with social networks and to provide guidelines to users for secure usage of social websites. Descriptive research has been conducted as it takes up the majority of online surveying and because of its quantitative nature, it is considered as conclusive. The survey results show that most of the users have their real information on social networking sites and they don’t change privacy settings of their accounts on regular basis. Moreover, as per survey findings, most users accept friend requests and invitations of unknown persons on social networking sites. Results of this research study will be helpful to bring awareness among users about privacy setting and they will learn how to control the privacy settings of their accounts and what type of content should be uploaded on social networking sites
A Word Embedding Model for Fault Localization using Bug and Software Change Repositories
Get PDFSoftware developed and then deployed in a real world environment is inevitable to exhibit some undesirable behavior. Therefore, developers need to provide maintenance facilities to enable the bugs causing the undesirable behavior to be fixed. However, prior to fixing the bug, the suspicious part of the code needs to be identified. For this purpose, they usually perform fault localization. This can be done manually as well as automatically. Several techniques exist in the literature for fault localization. However, most of them are static based techniques because they do not depend on a specific programming language along with the possibility to work on underdeveloped software and some other benefits. These techniques are largely based on lexical matching of terms which leads to mismatch of terms, large precision value because of limited vocabulary of a programming language and some techniques consider the semantics but it is computationally expensive to localize faults through this. In this paper we have proposed a fault localization technique which is based on the machine learning concept of word embedding. Our proposed approach aims at looking at the relatedness between the bug terms and source code artifact. We mined the bug repositories and software change repositories to train the word embedding model on the mined repositories data. On the arrival of a new bug, the cluster of the bugs from the model is searched and the files from the software change repositories are retrieved which are used for fixing those bugs. We have compared the results of our approach with the latest technique proposed in year 2018 Pointwise Mutual Information (PMI) and Normalized Google Distance (NGD) which consider the context and also with existing lexical techniques Vector Space Model (VSM) and the semantic based method Latent Semantic Indexing (LSI). We have used the benchmark dataset “MoreBugs” which has been widely used in this domain. The results show that our approach outperforms other techniques
Impact of Social Media Addiction on Social Behavior
Get PDFoai:ojs201.localhost:article/197This report is about impact of social media addiction on behavior of individuals currently in universities. Web compulsion and the ethical ramifications of introverted Internet conduct will be researched in this paper. An ever increasing number of individuals utilize the Internet in their day by day life. The study has been conducted using survey in my own university where I have used qualitative and quantitative feedback of students. Major findings in this report are the attitude of students towards this issue which is surprisingly Extra ordinary in good sense. Lamentably, the level of individuals who utilize the web unnecessarily likewise increments. The idea of Internet compulsion or obsessive utilization of the Internet is talked about in detail, and the attributes of Internet addicts are additionally outlined. The social (particularly the reserved) utilization of the Internet is talked about. It is contended that the conduct of Internet use is like day by day life social conduct. The accompanying practices are viewed as reserved Internet conduct the utilization of the Internet to complete unlawful exercises, for example, selling faked items or hostile explicit materials, the utilization of Internet to menace others (i.e., cyber bullying, for example, disseminating derogatory explanations against someone in particular, The utilization of Internet to swindle others, and the utilization of Internet to do illicit betting). The qualities of the ethical stages that are related with these introverted Internet practices are examined in detail