Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm

Title:Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm

Volume: 18 Issue: 9

Author(s): Shitharth Selvarajan*, Manikandan Thirumalaisamy, Hariprasath Manoharan, Ramkumar Devendiran, S. Lakshmi Narayanan and Ashwani Kumar

Affiliation:

• Department of Computer Science, Kebri Dehar University, Kebri Dehar, 250, Ethiopia
• School of Computer Science Engineering and technology, Bennett University, U.P, India

Abstract:

Background: The majority of wearable technology that is present in various patents for Internet of Medical Things (IoMT) health monitoring systems is introduced to recognize various bodily indicators. The enumerated patents indicate that monitored values are sent to a central server, where they are all treated by experts at the appropriate moment. Therefore, a new patent technique by expanding the use of wireless devices, has been discovered that such communication technologies can recognize specific depression traits and mood swings.

Objectives: The major objective of the proposed method is to analyze the disputes that arise in the characteristics of an individual by observing the leveling periods that are identified from the processed image. In addition, the rate of data transfer in case of any dispute is maximized therefore recognition problem is solved at a minimized distance. Further, the steady state probability values are achieved at low delay thus minimizing the dropout packets in the monitored system using IoMT and LSTM.

Methods: A balanced record with four distinct parameters—such as livelihood, self-reliance, correlation, and precision—is employed with the projected model on IoMT for depression identification. As a result, high data transfer rates and low distance separation are used to process the identification framework. Additionally, by combining an original matrix representation with the input feature set using LSTM, a novel framework with great efficiency is created.

Results: In order to assess the results of IoMT using LSTM, four situations are split apart and their probability ratios are calculated. The results of each situation are then contrasted with the current methodology, and it is found that when there is a low dropout ratio, depression in a person is quickly diagnosed.

Conclusion: The comparison analysis demonstrates that the proposed method, when compared to the current method, offers the best-compromised outcomes at roughly 64%.

Cite this article as:

Selvarajan Shitharth*, Thirumalaisamy Manikandan, Manoharan Hariprasath, Devendiran Ramkumar, Narayanan S. Lakshmi and Kumar Ashwani, Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm, Recent Patents on Engineering 2024; 18 (9) : e051023221792 . https://dx.doi.org/10.2174/0118722121240855230926034148