Novel Cuckoo Search-Based Metaheuristic Approach for Deep Learning Prediction of Depression

被引:23
|
作者
Jawad, Khurram [1 ]
Mahto, Rajul [2 ]
Das, Aryan [2 ]
Ahmed, Saboor Uddin [2 ]
Aziz, Rabia Musheer [3 ]
Kumar, Pavan [3 ]
机构
[1] Saudi Elect Univ, Coll Comp & Informat, Riyadh 11673, Saudi Arabia
[2] VIT Bhopal Univ, Sch Comp Sci & Engn, Bhopal Indore Highway, Kothrikalan, Sehore 466116, India
[3] VIT Bhopal Univ, Sch Adv Sci & Languages, Bhopal Indore Highway, Kothrikalan, Sehore 466116, India
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 09期
关键词
particle swarm-cuckoo search (PS-CS); convolutional neural network (CNN); visual geometry group (VGG); residual neural network (ResNet); simple neural network (LeNet);
D O I
10.3390/app13095322
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Depression is a common illness worldwide with doubtless severe implications. Due to the absence of early identification and treatment for depression, millions of individuals worldwide suffer from mental illnesses. It might be difficult to identify those who are experiencing mental health illnesses and to provide them with the early help that they need. Additionally, depression may be associated with thoughts of suicide. Currently, there are no clinically specific diagnostic biomarkers that can identify the severity and type of depression. In this research paper, the novel particle swarm-cuckoo search (PS-CS) optimization algorithm is proposed instead of the traditional backpropagation algorithm for training deep neural networks. The backpropagation algorithm is widely used for supervised learning in deep neural networks, but it has limitations in terms of convergence speed and the possibility of getting trapped in local optima. These problems were addressed by using a deep neural network architecture for depression detection tasks along with the PS-CS optimization technique. The PS-CS algorithm combines the strengths of both particle swarm optimization and cuckoo search algorithms, which allows for a more efficient and effective optimization of the network parameters. We also evaluated how well the suggested methods performed against the most widely used classification models, including (K-nearest neighbor) KNN, (support vector regression) SVR, and decision trees, as well as the most widely used deep learning models, including residual neural network (ResNet), visual geometry group (VGG), and simple neural network (LeNet). The findings show that the suggested method, PS-CS, in conjunction with the CNN model, outperformed all other models, achieving the maximum accuracy of 99.5%. Other models, such as the KNN, decision trees, and logistic regression, achieved lower accuracies ranging from 69% to 97%.
引用
收藏
页数:27
相关论文
共 50 条
  • [1] A Search-Based Testing Approach for Deep Reinforcement Learning Agents
    Zolfagharian, Amirhossein
    Abdellatif, Manel
    Briand, Lionel C.
    Bagherzadeh, Mojtaba
    Ramesh, S.
    [J]. IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2023, 49 (07) : 3715 - 3735
  • [2] Prediction of IGBT junction temperature using improved cuckoo search-based extreme learning machine
    Liu, Boying
    Chen, Guolong
    Lin, Hsiung-Cheng
    Zhang, Weipeng
    Liu, Jiaqi
    [J]. MICROELECTRONICS RELIABILITY, 2021, 124
  • [3] Computer vision model with novel cuckoo search based deep learning approach for classification of fish image
    Aziz, Rabia Musheer
    Desai, Nishq Poorav
    Baluch, Mohammed Farhan
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (03) : 3677 - 3696
  • [4] Computer vision model with novel cuckoo search based deep learning approach for classification of fish image
    Rabia Musheer Aziz
    Nishq Poorav Desai
    Mohammed Farhan Baluch
    [J]. Multimedia Tools and Applications, 2023, 82 : 3677 - 3696
  • [5] An Automated Hyperparameter Search-Based Deep Learning Model for Highway Traffic Prediction
    Yi, Hongsuk
    Bui, Khac-Hoai Nam
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 22 (09) : 5486 - 5495
  • [6] Cuckoo Search-Based Optimization for Cancer Classification: A New Hybrid Approach
    Aziz, Rabia Musheer
    [J]. JOURNAL OF COMPUTATIONAL BIOLOGY, 2022, 29 (06) : 565 - 584
  • [7] A multi-objective metaheuristic approach to search-based stress testing
    Gois, Nauber
    Porfirio, Pedro
    Coelho, Andre
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (CIT), 2017, : 55 - 62
  • [8] Modified Cuckoo Search-Based Image Enhancement
    Maurya, Lalit
    Mahapatra, Prasant Kumar
    Saini, Garima
    [J]. PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON FRONTIERS IN INTELLIGENT COMPUTING: THEORY AND APPLICATIONS (FICTA) 2015, 2016, 404 : 625 - 634
  • [9] Exploring hybrid Sisko nanofluid on a stretching sheet: an improved cuckoo search-based machine learning approach
    Waseem, Wang
    Yun, Wang
    Boulaaras, Salah
    Rahman, Mati Ur
    [J]. EUROPEAN PHYSICAL JOURNAL PLUS, 2024, 139 (08):
  • [10] A Novel Approach For Search-Based Program Repair
    Trujillo, Leonardo
    Villanueva, Omar M.
    Hernandez, Daniel Eduardo
    [J]. IEEE SOFTWARE, 2021, 38 (04) : 36 - 42