1
|
Gupta C, Khullar V, Goyal N, Saini K, Baniwal R, Kumar S, Rastogi R. Cross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram. Diagnostics (Basel) 2023; 14:43. [PMID: 38201350 PMCID: PMC10795654 DOI: 10.3390/diagnostics14010043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 12/12/2023] [Accepted: 12/19/2023] [Indexed: 01/12/2024] Open
Abstract
In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning-based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.
Collapse
Affiliation(s)
- Chetna Gupta
- Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140417, Punjab, India; (C.G.); (V.K.)
| | - Vikas Khullar
- Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140417, Punjab, India; (C.G.); (V.K.)
| | - Nitin Goyal
- Department of Computer Science and Engineering, School of Engineering and Technology, Central University of Haryana, Mahendergarh 123031, Haryana, India;
| | - Kirti Saini
- Department of Electronics and Communication Engineering, University Institute of Engineering and Technology, Kurukshetra University, Kurukshetra 136119, Haryana, India;
| | - Ritu Baniwal
- Department of Computer Science, Jyotiba Phule Government College, Radaur, Yamunanagar 135133, Haryana, India;
| | - Sushil Kumar
- Department of Computer Science and Engineering, School of Engineering and Technology, Central University of Haryana, Mahendergarh 123031, Haryana, India;
| | - Rashi Rastogi
- Department of Computer Applications, Sir Chottu Ram Institute of Engineering & Technology, Ch. Charan Singh University, Meerut 250001, Uttar Pradesh, India;
| |
Collapse
|
2
|
Nagarajan B, Chakravarthy S, Venkatesan VK, Ramakrishna MT, Khan SB, Basheer S, Albalawi E. A Deep Learning Framework with an Intermediate Layer Using the Swarm Intelligence Optimizer for Diagnosing Oral Squamous Cell Carcinoma. Diagnostics (Basel) 2023; 13:3461. [PMID: 37998597 PMCID: PMC10670914 DOI: 10.3390/diagnostics13223461] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 11/07/2023] [Accepted: 11/08/2023] [Indexed: 11/25/2023] Open
Abstract
One of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient's histopathology images to identify abnormal oral lesions. A deep learning framework was designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely, normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed swarm intelligence technique called the Modified Gorilla Troops Optimizer. While there are many optimization algorithms used in the literature for feature selection, weight updating, and optimal parameter identification in deep learning models, this work focuses on using optimization algorithms as an intermediate layer to convert extracted features into features that are better suited for classification. Three datasets comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures, namely, InceptionV2, MobileNetV3, and EfficientNetB3, are investigated as feature extraction layers. Two fully connected Neural Network layers, batch normalization, and dropout are used as classification layers. With the best accuracy of 0.89 among the examined feature extraction models, MobileNetV3 exhibits good performance. This accuracy is increased to 0.95 when the suggested Modified Gorilla Troops Optimizer is used as an intermediary layer.
Collapse
Affiliation(s)
- Bharanidharan Nagarajan
- School of Computer Science Engineering and Information Systems (SCORE), Vellore Institute of Technology, Vellore 632014, India; (B.N.); (V.K.V.)
| | - Sannasi Chakravarthy
- Department of ECE, Bannari Amman Institute of Technology, Sathyamangalam 638401, India;
| | - Vinoth Kumar Venkatesan
- School of Computer Science Engineering and Information Systems (SCORE), Vellore Institute of Technology, Vellore 632014, India; (B.N.); (V.K.V.)
| | - Mahesh Thyluru Ramakrishna
- Department of Computer Science and Engineering, Faculty of Engineering and Technology, JAIN (Deemed-to-Be University), Bangalore 562112, India
| | - Surbhi Bhatia Khan
- Department of Data Science, School of Science Engineering and Environment, University of Salford, Manchester M5 4WT, UK
- Department of Engineering and Environment, University of Religions and Denominations, Qom 13357, Iran
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos P.O. Box 13-5053, Lebanon
| | - Shakila Basheer
- Department of Information Systems, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi Arabia;
| | - Eid Albalawi
- Department of Computer Science, School of Computer Science and Information Technology, King Faisal University, Al-Ahsa 31982, Saudi Arabia;
| |
Collapse
|