Speech controlled home mechanization framework  using android gadgets

Kavitha, M.; Manideep, Y; Krishna, M. V. Rama; Prabhuram, P

doi:10.14419/ijet.v7i1.1.10821

Cited by 7 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech recognition is useful in many domains, like security and the speech-controlled home mechanization framework [21]. The voice of a person is a valuable biometric feature and can be used for identity verification [22].…”

Section: Related Workmentioning

confidence: 99%

Depression Symptom Identification Through Acoustic Speech Analysis: A Transfer Learning Approach

Narayanrao,

Kohirker,

Preeth

et al. 2024

View full text Add to dashboard Cite

In the field of mental health diagnostics, the acoustic characteristics of speech have been recognized as potent markers for the identification of depressive symptoms. This study harnesses the power of transfer learning (TL) to discern depression-related sentiments from speech. Acoustic features such as rhythm, pitch, and tone form the core of this analysis. The methodology unfolds in three distinct phases. Initially, a Multi-Layer Perceptron (MLP) network employing stochastic gradient descent is applied to the RAVDESS dataset, yielding an accuracy of 65%. This finding catalyzes the second phase, wherein a comprehensive hyperparameter optimization via grid search (GS) is conducted on the MLP Classifier. This step primarily focuses on detecting emotions commonly associated with depression, including neutrality, sadness, anger, fear, and disgust. The optimized MLP classifier indicates an improved accuracy of 71%. In the final phase, to enhance precision further, the same GS-based model, underpinned by TL principles, is applied to the TASS dataset. This application astonishingly achieves an accuracy of 99.80%, suggesting a high risk of depression. This comparative study establishes the proposed framework as a vanguard in the application of TL for depression prediction, showcasing a significant leap in accuracy over previous methodologies.

show abstract

Section: Related Workmentioning

confidence: 99%

Depression Symptom Identification Through Acoustic Speech Analysis: A Transfer Learning Approach

Narayanrao,

Kohirker,

Preeth

et al. 2024

View full text Add to dashboard Cite

show abstract

“…They have taken DATAMALL datasets for the experiment and have demonstrated that this approach gives higher accuracy and classifies at greater speed. Nurul et al, [12] has done an analysis on Naive Bayes Classifier across different Datasets. The authors have incorporated SPAMBASE and Spam Data for their experiment using WEKA tool.…”

Section: Literature Surveymentioning

confidence: 99%

An Efficient Email Spam Detection using Support Vector Machine

Prasanthi*¹,

Deepika²,

Anudeep³

et al. 2019

IJITEE

View full text Add to dashboard Cite

This research paper proposes the electronics mail is small known as E-mail is used for communication between the people to person. E mail is providing as an necessary contribution for messaging by internet. Spam e mails are the unwanted messages that arise in high volume and are used by spammers for revealing users personal credentials. These e mails are regularly some sort of company/control announcement or viruses that the user receive without any notification. So as to defeat it, there need aid exactly existing frameworks that still don't keep them from striking. Therefore, there is a require should manufacture and proficient framework that adequately detects and more keeps the spam messages In those server utilizing the Naïve bayes classifier. Naïve bayes classifier is a mainstream statistical classifier utilized fundamentally for content arrangement

show abstract

“…Forensics now-a-days are enforcing its impact and need in many diverse areas like software affected during natural disasters [14], cloud applications where the third party storage kind of works related [16], medicine [17] [19] and other diverse application areas [15] [18][19] [20].…”

Section: Introductionmentioning

confidence: 99%

Automated Collection of Artifacts from a Live Windows System using e-Triage Tool

Kota¹

2020

IJATCSE

View full text Add to dashboard Cite

The evolution of computers and technology is outpacing the effectiveness of forensic techniques. In traditional computer forensic methodology, when an organization is effected by a cyber-attack, the systems were plugged off at the scene which results in loss of acquiring volatile memory and further seized media are analyzed at forensic laboratories to get report. In the current work, a novel e-Triage tool is developed which extracts artifacts present within a defined live windows system. It yields on-site identification and interpretation of digital evidences in a short period of time. The e-Triage tool follows live forensic methodology and facilitates to extract and collect artifacts related to system information, registry, events and network information, Random Access Memory, browsing history, shell bag, page file, hibernation file, swap file and also records the changes done by tool on registry whose novelty improves the forensic report. The current proposed e-Triage tool carries out prioritizing and collecting artifacts in preliminary investigation until a potential source is being identified and from then it accelerates further investigation.

show abstract

Speech controlled home mechanization framework using android gadgets

Cited by 7 publications

References 5 publications

Depression Symptom Identification Through Acoustic Speech Analysis: A Transfer Learning Approach

Depression Symptom Identification Through Acoustic Speech Analysis: A Transfer Learning Approach

An Efficient Email Spam Detection using Support Vector Machine

Automated Collection of Artifacts from a Live Windows System using e-Triage Tool

Contact Info

Product

Resources

About