Alain Tiedeu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Alain Tiedeu has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Guillaume Honoré Kom
Unité de Recherche d’Automatique et d’Informatique Appliquée (UR-AIA), Department of Electrical Engineering, IUT-Fotso Victor Bandjoun, University of Dschang (Cameroon), Bandjoun, Cameroon
2 shared publications Janvier Fotsing
Department of Physics, Faculty of Science, University of Buea, Buea, Cameroon
2 shared publications- Lee Mariel Heucheun Yepdia
Signal Image and Systems Laboratory, HTTTC of EBOLOWA, University of Yaounde 1, P.O. BOX 886, Ebolowa, Cameroon
2 shared publications Richel T. Nguimdo
2 shared publicationsAlain F. Djomo
Instrumentation, Signal and Image Laboratory, National Advanced School of Engineering, University of Yaoundé I, Yaoundé, Cameroon
1 shared publicationAlain Fanda Djomo
Instrumentation, Signal and Image Laboratory, National Advanced School of Engineering University of Yaoundé I Yaoundé Cameroon
1 shared publication
Latest Publications
- Open Access
- 9 October 2026
- Published by IntechOpen
Computer-Aided-Diagnosis of Cardiac Arrhythmia Using a Three-Channel Convolutional Neural Network
Cardiac arrhythmias are a serious health challenge. This paper presents a new algorithm for automated detection of cardiac arrhythmias using a three-channel convolutional neural network (CNN) classifier. After the CNN was designed, features extracted from the ECG signals to be analyzed were fed into it as follows. The first channel received the short-time Fourier transform (STFT) spectrogram using the Kaiser window with a length of 200 points and a factor (β) of 30, and the second channel received a Tunable Q-Factor Wavelet Transform (TQWT)-filtered ECG signal. Finally, entropy data computed from the ECG signals were fed into the third channel of the CNN. A 5-fold cross-validation technique was used during the fine-tuning of the model. Tests carried out on the fully trained and validated model proved that the proposed algorithm successfully classified rhythms into atrial fibrillation (AFB), atrial flutter (AFL), normal sinus rhythms (NOR), other rhythms (OTH), and noisy recording (NOI) signals. The method was evaluated using both the PhysioNet/Computing in Cardiology (CinC) 2017 and MIT-BIH AFDB databases. Experimental results yielded an F1 score of 99.54% for AFB, 96.85% for AFL, and 99.64% for the MIT-BIH database. Tests with samples from the CinC 2017 gave F1 scores of 95.98% (AFB) and 98.29% (NOR). The good performance on two different databases suggests that the proposed model is robust and accurate enough to consider using it as an aid for cardiologists.
- 9 October 2026
- Published by IntechOpen
Open AccessComputer-Aided-Diagnosis of Cardiac Arrhythmia Using a Three-Channel Convolutional Neural Network
Cardiac arrhythmias are a serious health challenge. This paper presents a new algorithm for automated detection of cardiac arrhythmias using a three-channel convolutional neural network (CNN) classifier. After the CNN was designed, features extracted from the ECG signals to be analyzed were fed into it as follows. The first channel received the short-time Fourier transform (STFT) spectrogram using the Kaiser window with a length of 200 points and a factor (β) of 30, and the second channel received a Tunable Q-Factor Wavelet Transform (TQWT)-filtered ECG signal. Finally, entropy data computed from the ECG signals were fed into the third channel of the CNN. A 5-fold cross-validation technique was used during the fine-tuning of the model. Tests carried out on the fully trained and validated model proved that the proposed algorithm successfully classified rhythms into atrial fibrillation (AFB), atrial flutter (AFL), normal sinus rhythms (NOR), other rhythms (OTH), and noisy recording (NOI) signals. The method was evaluated using both the PhysioNet/Computing in Cardiology (CinC) 2017 and MIT-BIH AFDB databases. Experimental results yielded an F1 score of 99.54% for AFB, 96.85% for AFL, and 99.64% for the MIT-BIH database. Tests with samples from the CinC 2017 gave F1 scores of 95.98% (AFB) and 98.29% (NOR). The good performance on two different databases suggests that the proposed model is robust and accurate enough to consider using it as an aid for cardiologists.
- 31 July 2025
- Published by Springer Nature in Physical and Engineering Sciences in Medicine
- Vol. 48 (4) , 1667-1678
Automated analysis of ECG signals using nonlinearity and nonstationarity features fed into the MobilenetV2 CNN powered by transfer learning
Atrial fibrillation (AFB) and atrial flutter (AFL) are cardiac arrhythmias very often associated with the aggravation of other cardiac pathologies and increase the risk of stroke and heart failure. Their detection is therefore crucial. Automated analysis of the ECG signal has been suggested to assist cardiologists in the diagnosis of AFB and AFL. In this paper, a novel automated electrocardiogram (ECG) signal analysis method to aid in the detection of AFB and AFL is presented. The first step of the method consists of processing the original ECG signal. The second step carries out the classification using a modified MobileNetV2 convolutional neural network (CNN) powered by transfer learning. This CNN classifies the fed-in ECG signals into atrial fibrillation (AFB), atrial flutter (AFL), other (OTH), normal sinus rhythms (NOR), and noisy (NOI) recordings. The performance of the proposed method was assessed and scored using the Physio Net/Computing in Cardiology (CinC) 2017 dataset and the MIT-BIH Atrial Fibrillation Database (MIT-BIH). The experimental results showed that the proposed method gave an F1 score of 96.08%, sensitivity of 97.1%, specificity of 99.53%, and accuracy of 95.1% for atrial fibrillation, for the CinC 2017 dataset. For the MIT-BIH dataset, an F1 score of 99.54%, sensitivity of 99.51%, specificity of 99.64%, and accuracy of 99.5% were obtained. The results disclosed above on 2 databases prove that the proposed algorithm is efficient, robust, and can be used to assist cardiologists.
- 31 July 2025
- Published by Springer Nature in Physical and Engineering Sciences in Medicine
- Vol. 48 (4) , 1667-1678
Automated analysis of ECG signals using nonlinearity and nonstationarity features fed into the MobilenetV2 CNN powered by transfer learning
Atrial fibrillation (AFB) and atrial flutter (AFL) are cardiac arrhythmias very often associated with the aggravation of other cardiac pathologies and increase the risk of stroke and heart failure. Their detection is therefore crucial. Automated analysis of the ECG signal has been suggested to assist cardiologists in the diagnosis of AFB and AFL. In this paper, a novel automated electrocardiogram (ECG) signal analysis method to aid in the detection of AFB and AFL is presented. The first step of the method consists of processing the original ECG signal. The second step carries out the classification using a modified MobileNetV2 convolutional neural network (CNN) powered by transfer learning. This CNN classifies the fed-in ECG signals into atrial fibrillation (AFB), atrial flutter (AFL), other (OTH), normal sinus rhythms (NOR), and noisy (NOI) recordings. The performance of the proposed method was assessed and scored using the Physio Net/Computing in Cardiology (CinC) 2017 dataset and the MIT-BIH Atrial Fibrillation Database (MIT-BIH). The experimental results showed that the proposed method gave an F1 score of 96.08%, sensitivity of 97.1%, specificity of 99.53%, and accuracy of 95.1% for atrial fibrillation, for the CinC 2017 dataset. For the MIT-BIH dataset, an F1 score of 99.54%, sensitivity of 99.51%, specificity of 99.64%, and accuracy of 99.5% were obtained. The results disclosed above on 2 databases prove that the proposed algorithm is efficient, robust, and can be used to assist cardiologists.
- Open Access
- 27 July 2025
- Published by Springer Nature in Discover Electronics
- Vol. 2 (1) , 1-33
Introducing a novel 3D Chen-Rössler map for NTRU-based image encryption with OFDM transmission over a noisy channel
- 27 July 2025
- Published by Springer Nature in Discover Electronics
- Vol. 2 (1) , 1-33
Open AccessIntroducing a novel 3D Chen-Rössler map for NTRU-based image encryption with OFDM transmission over a noisy channel
- Open Access
- 21 March 2025
- Published by Elsevier in Franklin Open
- Vol. 10
Dynamic analysis and image encryption using a novel 4D map for secure transmission using WDM 4*20 Gbps techniques
- 21 March 2025
- Published by Elsevier in Franklin Open
- Vol. 10
Open AccessDynamic analysis and image encryption using a novel 4D map for secure transmission using WDM 4*20 Gbps techniques
- 17 January 2025
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 44 (5) , 3599-3624
Automated ECG Analysis with Dual-Channel SqueezeNet Using Hilbert Huang Transform, Fuzzy Entropy, and Hurst Exponent
- 17 January 2025
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 44 (5) , 3599-3624
Automated ECG Analysis with Dual-Channel SqueezeNet Using Hilbert Huang Transform, Fuzzy Entropy, and Hurst Exponent
- 8 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (20) , 22809-22826
Deep learning-based algorithm for automated detection of glaucoma on eye fundus images
- 8 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (20) , 22809-22826
Deep learning-based algorithm for automated detection of glaucoma on eye fundus images
- Open Access
- 3 March 2024
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 18 (7) , 1823-1843
Design and implementation in an Altera's cyclone IV EP4CE6E22C8 FPGA board of a fast and robust cipher using combined 1D maps
This paper proposes an image encryption algorithm based on combined 1D chaotic maps. First, a permutation technique was applied. It was then reorganized into 1D matrices along the rows and columns respectively, which were then shuffled by computing the substituted position indices to obtain the scrambled image. Subsequently, a method of confusion of the scrambled image was used through another generated data map, combined with random sub‐matrices for diffusion, then resulting in an encrypted image. Finally, the proposed cryptosystem was implemented in a single kernel platform developed using the Nios II Software Build Tools processor for Eclipse. A hardware architecture was designed using the Qsys‐built tool which is available in the Quartus II 13.0sp1 environment. The developed single‐core system was implemented using the Cyclone IV EP4CE6E22C8. Robustness evaluation of the cryptosystem was performed through security analysis tests such as histogram analysis, correlation coefficient, differential analysis, and key space analysis to prove that it is of good quality, efficient, fast, and successfully resisting brute force attacks. The hardware performance analysis was also carried out. Then the cryptosystem is compared with those in the literature both in the hardware and security performance aspects.
- 3 March 2024
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 18 (7) , 1823-1843
Open AccessDesign and implementation in an Altera's cyclone IV EP4CE6E22C8 FPGA board of a fast and robust cipher using combined 1D maps
This paper proposes an image encryption algorithm based on combined 1D chaotic maps. First, a permutation technique was applied. It was then reorganized into 1D matrices along the rows and columns respectively, which were then shuffled by computing the substituted position indices to obtain the scrambled image. Subsequently, a method of confusion of the scrambled image was used through another generated data map, combined with random sub‐matrices for diffusion, then resulting in an encrypted image. Finally, the proposed cryptosystem was implemented in a single kernel platform developed using the Nios II Software Build Tools processor for Eclipse. A hardware architecture was designed using the Qsys‐built tool which is available in the Quartus II 13.0sp1 environment. The developed single‐core system was implemented using the Cyclone IV EP4CE6E22C8. Robustness evaluation of the cryptosystem was performed through security analysis tests such as histogram analysis, correlation coefficient, differential analysis, and key space analysis to prove that it is of good quality, efficient, fast, and successfully resisting brute force attacks. The hardware performance analysis was also carried out. Then the cryptosystem is compared with those in the literature both in the hardware and security performance aspects.
- 21 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (31) , 75955-75994
Medical image cryptosystem using a new 3-D map implemented in a microcontroller
- 21 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (31) , 75955-75994
Medical image cryptosystem using a new 3-D map implemented in a microcontroller
- 7 March 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (13) , 17849-17874
A robust algorithm for white blood cell nuclei segmentation
- 7 March 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (13) , 17849-17874
A robust algorithm for white blood cell nuclei segmentation
- 5 March 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (12) , 17131-17154
Image encryption using the logistic map coupled to a self-synchronizing streaming
- 5 March 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (12) , 17131-17154
Image encryption using the logistic map coupled to a self-synchronizing streaming