Scalogram Images Research Articles

A comparative study of deep learning efficiency in the classification of electrical faults of permanent magnet synchronous motor

AbstractPermanent Magnet Synchronous Motors (PMSMs) are widely used in modern industrial applications due to their high efficiency, reliability, and compact size. However, faults in PMSMs, such as stator winding failures, can lead to significant performance degradation and operational failures. Traditional fault detection methods often rely on signal processing and manual analysis, which may be time-consuming and lacking in accuracy. This study explores the application of deep learning techniques for automated fault detection in PMSMs. The deep learning models based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are employed to classify electrical faults in the motor data, which includes the scalogram images of stator current signal allowing models to learn fault patterns. The performance of the used networks has been compared, in order to choose the reliable one for classification purposes and hence to be utilized for developing the prediction system. The experimental results show that the ResNet50 has better capability to classify the variation of data used where it could achieve 100% of accuracy, recall, precision, and F1 score as compared to other techniques.

Smart IoT-driven biosensors for EEG-based driving fatigue detection: A CNN-XGBoost model enhancing healthcare quality

Introduction: Drowsy driving is a significant contributor to accidents, accounting for 35 to 45% of all crashes. Implementation of an internet of things (IoT) system capable of alerting fatigued drivers has the potential to substantially reduce road fatalities and associated issues. Often referred to as the internet of medical things (IoMT), this system leverages a combination of biosensors, actuators, detectors, cloud-based and edge computing, machine intelligence, and communication networks to deliver reliable performance and enhance quality of life in smart societies. Methods: Electroencephalogram (EEG) signals offer potential insights into fatigue detection. However, accurately identifying fatigue from brain signals is challenging due to inter-individual EEG variability and the difficulty of collecting sufficient data during periods of exhaustion. To address these challenges, a novel evolutionary optimization method combining convolutional neural networks (CNNs) and XGBoost, termed CNN-XGBoost Evolutionary Learning, was proposed to improve fatigue identification accuracy. The research explored various subbands of decomposed EEG data and introduced an innovative approach of transforming EEG recordings into RGB scalograms. These scalogram images were processed using a 2D Convolutional Neural Network (2DCNN) to extract essential features, which were subsequently fed into a dense layer for training. Results: The resulting model achieved a noteworthy accuracy of 99.80% on a substantial driver fatigue dataset, surpassing existing methods. Conclusion: By integrating this approach into an IoT framework, researchers effectively addressed previous challenges and established an artificial intelligence of things (AIoT) infrastructure for critical driving conditions. This IoT-based system optimizes data processing, reduces computational complexity, and enhances overall system performance, enabling accurate and timely detection of fatigue in extreme driving environments.

Deep learning-based fault classification of rolling bearings under noisy conditions using CEEMD-VMD-IMF with magnitude scalogram images

Deep learning-based fault classification of rolling bearings under noisy conditions using CEEMD-VMD-IMF with magnitude scalogram images

2D-convolutional neural network based fault detection and classification of transmission lines using scalogram images

The reliable operation of power transmission systems is essential for maintaining the stability and efficiency of the electrical grid. Rapid and accurate detection of faults in transmission lines is crucial for minimizing downtime and preventing cascading failures. This research presents a novel approach to fault detection and classification in transmission lines employing 2D Convolutional Neural Networks (2D-CNN).The proposed methodology leverages the inherent spatial characteristics of fault signals, converting them as 2D scalogram images for input to the CNN model. By converting fault signals into scalogram representations, the network can capture both temporal and frequency domain features, enabling a more comprehensive analysis of fault patterns. The 2D-CNN architecture is designed to automatically learn hierarchical features, allowing for effective discrimination between different fault types. To evaluate the performance of the proposed approach, extensive simulations and experiments were conducted using MATLAB/SIMULINK modeled transmission line data. The results demonstrate the superior fault detection accuracy and classification capabilities of the 2D-CNN model. The performance of the proposed model is evaluated using 10-fold cross-validation, and its effectiveness is assessed by comparing it with current state-of-the-art techniques. Proposed 2D-CNN model has evidenced an accuracy of 99.9074 with ideal dataset for 12- class fault classification and performing consistently in presence of noise, having an accuracy of 99.629 %,99.72 % and 99.814 % in 20.30 and 40 dB noises respectively. The proposed model also verified in high resistance fault condition. The model exhibits robustness to noise and is capable of generalizing well to various fault scenarios. The proposed methodology offers a scalable and efficient solution for transmission line fault analysis, paving the way for the integration of advanced machine learning techniques into the operation and maintenance of power transmission infrastructure.

Examining Tongue Movement Intentions in EEG-Based BCI with Machine and Deep Learning: An Approach for Dysphagia Rehabilitation

Abstract Dysphagia, a common swallowing disorder particularly prevalent among older adults and often associated with neurological conditions, significantly affects individuals’ quality of life by negatively impacting their eating habits, physical health, and social interactions. This study investigates the potential of brain-computer interface (BCI) technologies in dysphagia rehabilitation, focusing specifically on motor imagery paradigms based on EEG signals and integration with machine learning and deep learning methods for tongue movement. Traditional machine learning classifiers, such as K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, Naive Bayes, Random Forest, AdaBoost, Bagging, and Kernel were employed in discrimination of rest and imagination phases of EEG signals obtained from 30 healthy subjects. Scalogram images obtained using continuous wavelet transform of EEG signals corresponding to the rest and imagination phases of the experiment were used as the input images to the CNN architecture. As a result, KNN (79.4%) and SVM (63.4%) exhibited lower accuracy rates compared to ensemble methods like AdaBoost, Bagging, and Random Forest, all achieving high accuracy rates of 99.8%. These ensemble techniques proved to be highly effective in handling complex EEG datasets, particularly in distinguishing between rest and imagination phases. Furthermore, the deep learning approach, utilizing CNN and Continuous Wavelet Transform (CWT), achieved an accuracy of 83%, highlighting its potential in analyzing motor imagery data. Overall, this study demonstrates the promising role of BCI technologies and advanced machine learning techniques, especially ensemble and deep learning methods, in improving outcomes for dysphagia rehabilitation.

MD-DCNN: Multi-Scale Dilation-Based Deep Convolution Neural Network for epilepsy detection using electroencephalogram signals

Approximately 65 million individuals experience epilepsy globally. Surgery or medication cannot cure more than 30% of epilepsy patients.However, through therapeutic intervention, anticipating a seizure can help us avoid it. According to previous studies, aberrant activity inside the brain begins a few minutes before the onset of a seizure, known as a pre-ictal state. Many researchers have attempted to anticipate the pre-ictal condition of a seizure; however, achieving high sensitivity and specificity remains challenging. Therefore, deep learning-based early diagnostic tools for epilepsy therapies using electroencephalogram (EEG) signals are urgently needed. Traditional methods perform well in binary epilepsy scenarios, such as normal vs. ictal, but poorly in ternary situations, such as ictal vs. normal vs. inter-ictal. This study proposes a multi-scale dilated convolution-based network (MD-DCNN) to predict seizures or epilepsy. Traditional DCNNs for epilepsy classification overfit due to insufficient training data (fewer subjects). Windowing 2-sec EEG recordings and extracting the frequency sub-band from each window prevents overfitting in deep networks, which lack training data. We convert each segmented window and its sub-bands into scalogram images and input them into MD-DCNN. The proposed MD-DCNN combines data from several scales without narrowing the acquisition domain. Integrating detailed information into high-level semantic features improves network interpretation and classification. The proposed MD-DCNN is evaluated for two-class, three-class, and cross-database strategy problems using three publicly accessible databases. Experiments show that the MD-DCNN statistically performs better than 13 other current approaches. This demonstrates its potential for developing equipment capable of measuring, monitoring, and recording EEG signals to diagnose epilepsy.

Fault diagnosis of monoblock centrifugal pumps using pre-trained deep learning models and scalogram images

The monoblock centrifugal pump (MCP) is widely utilized in a diverse range of applications encompassing residential and industrial usage. Sectors such as agriculture, civil projects, mine dewatering, and numerous other industrial applications have employed centrifugal pumps. Despite their extensive usage, these pumps are susceptible to faults and failures due to the presence of critical components that are prone to issues such as bearing faults, sealing problems, cavitation and impeller faults. Therefore, conducting timely fault diagnosis becomes crucial to ensure uninterrupted operation. To address this, the technique of transfer learning, a form of deep learning, is employed. This method entails utilizing prior knowledge from previous operations to improve fault diagnostic performance in monoblock centrifugal pumps. Specifically, scalogram images derived from vibration signals collected during experimental setups were used in fault diagnosis. The study classified faults in monoblock centrifugal pumps using fifteen pre-trained networks including DenseNet-201, GoogLeNet, VGG-19, InceptionResNetV2, Xception, ShuffleNet, VGG-16, InceptionV3, ResNet101, ResNet-50, EfficientNetb0, NasNetmobile, ResNet-18, AlexNet and MobileNet-v2. The highest classification accuracy was obtained by carefully adjusting the hyperparameters which were subsequently employed in the fault classification process. AlexNet, one of the pre-trained network models, showcased remarkable capabilities by achieving a perfect classification accuracy of 100% within a relatively fast computation time of 18 s. This approach employs a reliable and effective process for discovering defects from the start, lowering the risk of possible damage and ensuring the seamless operation of the system.

WALDATA: Wavelet transform based adversarial learning for the detection of anomalous trading activities

Detecting manipulative activities in stock market trading poses a significant challenge due to the complex temporal correlations inherent to the dynamically changing stock price data. This challenge is further exacerbated by the limited availability of labelled anomalous trading data instances. Stock price manipulations, which consist of infrequent anomalies in stock price trading data, are challenging to capture due to their sporadic occurrence and dynamically evolving nature. This scarcity and inherent complexity significantly complicate the creation of labelled datasets hence hinders the development of robust detection of different stock price manipulation schemes through supervised learning methods. Overcoming these challenges is crucial for enhancing our understanding of market dynamics and implementing robust market surveillance systems. To address these challenges, we introduce a novel stock price manipulation detection approach called WALDATA (Wavelet Transform based Adversarial Learning for the Detection of Anomalous Trading Activities). We leverage the Wavelet Transform (WT) to decompose non-stationary stock price time series into informative features and capture multi-scale dynamics within the data. We encode stock price data by transforming it into scalogram images through the Continuous Wavelet Transform, effectively converting stock price time series data into a 2D image representation. Subsequently, we employ a Generative Adversarial Network (GAN) architecture, originally applied to computer vision, to learn the underlying distribution of normal trading behaviour from the encoded images. We then train the discriminator as an anomaly detector for identifying manipulative trading activities in the stock market. The efficacy of WALDATA is rigorously evaluated on diverse real-world stock datasets using 1-level tick data from the LOBSTER project and the experimental results demonstrate the significant performance of our approach achieving an average AUC of 0.99 while maintaining low false alarm rates across various market conditions. These findings not only validate the effectiveness of the proposed WALDATA approach in accurately identifying stock price manipulations but also provide investors and regulators alike with valuable insights for the development of advanced market surveillance systems. This research demonstrates the promising potential of combining wavelet-based feature extraction and stock price time series to image representation with generative adversarial learning frameworks for anomaly detection in financial time series data. The successful implementation of WALDATA contributes to the development of advanced market surveillance systems and paves the way for further advancements in market surveillance, contributing towards a more efficient and robust financial system and a fair market environment.

Vibration-based SHM of railway steel arch bridge with orbit-shaped image and wavelet-integrated CNN classification

The study presents the data-driven applications of continuous wavelet transforms (CWT), orbit-shaped analysis and convolutional neural networks (CNN) using GoogLeNet for Dębica railway bridge health monitoring in Poland. Training and validation data sets are the dynamic behavior of the bridge deck recorded through an IEPE vibration sensor with a sampling frequency of 128 Hz from vibration-based structural health monitoring (SHM) system over a nine-month period from December 2019 to September 2020. Utilizing Morse, Morlet, and Bump wavelet, the vibration signal scalogram images are produced in the frequency–time domain as the input for CNN classification models, while the output is to predict health states based on the experimental tension force of eight hangers using label thresholds developed by calibrated finite element model. Moreover, the vibration-based orbit-shaped image patterns, acquired through a bidirectional sensor on each hanger are processed with CNN classification models for automated hanger health diagnostic. The accuracies and weighted F1-scores of the wavelet-assisted and orbit-shaped CNN models are more than 83% on imbalanced validation images. The results show that the proposed CNN approaches can classify the potential structural problems.

Utilizing portable electroencephalography to screen for pathology of Alzheimer’s disease: a methodological advancement in diagnosis of neurodegenerative diseases

BackgroundThe current biomarker-supported diagnosis of Alzheimer’s disease (AD) is hindered by invasiveness and cost issues. This study aimed to address these challenges by utilizing portable electroencephalography (EEG). We propose a novel, non-invasive, and cost-effective method for identifying AD, using a sample of patients with biomarker-verified AD, to facilitate early and accessible disease screening.MethodsThis study included 35 patients with biomarker-verified AD, confirmed via cerebrospinal fluid sampling, and 35 age- and sex-balanced healthy volunteers (HVs). All participants underwent portable EEG recordings, focusing on 2-minute resting-state EEG epochs with closed eyes state. EEG recordings were transformed into scalogram images, which were analyzed using “vision Transformer(ViT),” a cutting-edge deep learning model, to differentiate patients from HVs.ResultsThe application of ViT to the scalogram images derived from portable EEG data demonstrated a significant capability to distinguish between patients with biomarker-verified AD and HVs. The method achieved an accuracy of 73%, with an area under the receiver operating characteristic curve of 0.80, indicating robust performance in identifying AD pathology using neurophysiological measures.ConclusionsOur findings highlight the potential of portable EEG combined with advanced deep learning techniques as a transformative tool for screening of biomarker-verified AD. This study not only contributes to the neurophysiological understanding of AD but also opens new avenues for the development of accessible and non-invasive diagnostic methods. The proposed approach paves the way for future clinical applications, offering a promising solution to the limitations of advanced diagnostic practices for dementia.

Transfer learning for servomotor bearing fault detection in the industrial robot

In consequence of their superior performance and durability, industrial robots have enjoyed widespread adoption across a variety of industries. However, despite their sturdy build, they are susceptible to malfunction. The servomotor is a fundamental component of industrial robots, and to ensure smooth and uninterrupted functioning, it is essential to detect any defects it may develop. Although research has addressed methods for detecting bearing failure, diagnosis of a servomotor bearing failure in the industrial robot remains difficult and requires intensive research. In this paper, a novel method for detecting servomotor bearing defects in the industrial robot is provided by integrating knowledge transfer via transfer learning. Initially, current signals of the servomotor are transformed to scalogram images. This processed data is utilized to build the model for fault detection. Applying transfer learning eliminates model training from scratch and streamlined operations. The purported approach shows an average accuracy of more than 99 %.

Application of continuous wavelet transform and convolutional neural networks in fault diagnosis of PMSM stator windings

Efficiency, reliability, and durability play a key role in modern drive systems in line with the Industry 4.0 paradigm and the sustainability trend. To ensure this, highly efficient motors and appropriate systems must be deployed to monitor their condition and diagnose faults during the operation. For these reasons, in recent years, more and more research has been focused on developing new methods for fault diagnosis of permanent magnet synchronous motors (PMSMs). This paper proposes a novel hybrid method for the automatic detection and classification of PMSM stator winding faults based on combining the continuous wavelet transform (CWT) analysis of the negative sequence component of the stator phase currents with a convolutional neural network (CNN). CWT scalogram images are used as the inputs of the CNN-based interturn short circuits fault classifier model. Experimental tests were carried out to verify the effectiveness of the proposed approach under various motor operating conditions and at an incipient stage of fault propagation. In addition, the effects of the input image format, CNN structure, and training process parameters on model accuracy and classification effectiveness were investigated. The results of the experimental tests confirmed the high effectiveness of fault detection (99.4%) and classification (97.5%), as well as other important advantages of the developed method.

Transfer learning and self-distillation for automated detection of schizophrenia using single-channel EEG and scalogram images.

Schizophrenia (SZ) has been acknowledged as a highly intricate mental disorder for a long time. In fact, individuals with SZ experience a blurred line between fantasy and reality, leading to a lack of awareness about their condition, which can pose significant challenges during the treatment process. Due to the importance of the issue, timely diagnosis of this illness can not only assist patients and their families in managing the condition but also enable early intervention, which may help prevent its advancement. EEG is a widely utilized technique for investigating mental disorders like SZ due to its non-invasive nature, affordability, and wide accessibility. In this study, our main goal is to develop an optimized system that can achieve automatic diagnosis of SZ with minimal input information. To optimize the system, we adopted a strategy of using single-channel EEG signals and integrated knowledge distillation and transfer learning techniques into the model. This approach was designed to improve the performance and efficiency of our proposed method for SZ diagnosis. Additionally, to leverage the pre-trained models effectively, we converted the EEG signals into images using Continuous Wavelet Transform (CWT). This transformation allowed us to harness the capabilities of pre-trained models in the image domain, enabling automatic SZ detection with enhanced efficiency. To achieve a more robust estimate of the model's performance, we employed fivefold cross-validation. The accuracy achieved from the 5-s records of the EEG signal, along with the combination of self-distillation and VGG16 for the P4 channel, is 97.81. This indicates a high level of accuracy in diagnosing SZ using the proposed method.

Transfer learning based epileptic seizure classification using scalogram images of EEG signals

Transfer learning based epileptic seizure classification using scalogram images of EEG signals

Transmission Line Fault Classification Based on the Combination of Scaled Wavelet Scalograms and CNNs Using a One-Side Sensor for Data Collection.

This research focuses on leveraging wavelet transform for fault classification within electrical power transmission networks. This study meticulously examines the influence of various parameters, such as fault resistance, fault inception angle, fault location, and other essential components, on the accuracy of fault classification. We endeavor to explore the interplay between classification accuracy and the input data while assessing the efficacy of combining wavelet analysis with deep learning methodologies. The data, sourced from network recorders, including phase currents and voltages, undergo a scaled continuous wavelet transform (S-CWT) to generate scalogram images. These images are subsequently utilized as inputs for pretrained deep learning models. The experiments encompass various fault scenarios, spanning distinct fault types, locations, times, and resistance values. A remarkable feature of the proposed work is the attainment of 100% classification accuracy, obviating the need for additional algorithmic enhancements. The foundation of this achievement is the deliberate selection of the right input. The decision to employ an identical number of samples as the number of scales for the CWT emerges as a pivotal factor. This approach underpins the high accuracy and renders supplementary algorithms superfluous. Furthermore, this research underscores the versatility of this approach, showcasing its effectiveness across diverse networks and scenarios. Wavelet transform, after rigorous experimentation, emerges as a reliable tool for capturing transient fault characteristics with an optimal balance between time and frequency resolutions.

Detection of epileptic seizure using EEG signals analysis based on deep learning techniques

The brain neurons' electrical activities represented by Electroencephalogram (EEG) signals are the most common data for diagnosing Epilepsy seizure, which is considered a chronic nervous disorder that cannot be controlled medically using surgical operation or medications with more than 40 % of Epilepsy seizure case. With the progress and development of artificial intelligence and deep learning techniques, it becomes possible to detect these seizures over the observation of the non-stationary-dynamic EEG signals, which contain important information about the mental state of patients. This paper provides a concerted deep machine learning model consisting of two simultaneous techniques detecting the activity of epileptic seizures using EEG signals. The time-frequency image of EEG waves and EEG raw waves are used as input components for the convolution neural network (CNN) and recurrent neural network (RNN) with long- and short-term memory (LSTM). Two processing signal methods have been used, Short-Time Fourier Transform (STFT) and Continuous Wavelet Transformation (CWT), have been used for generating spectrogram and scalogram images with sizes of 77 × 75 and 32 × 32, respectively. The experimental results showed a detection accuracy of 99.57 %, 99.57 % using CWT Scalograms, and 99.26 %, 97.12 % using STFT spectrograms as CNN input for the Bonn University dataset and the CHB-MIT dataset, respectively. Thus, the proposed models provide the ability to detect epileptic seizures with high success compared to previous studies.

A new approach for heart disease detection using Motif transform-based CWT's time-frequency images with DenseNet deep transfer learning methods.

Electrocardiogram (ECG) signals are extensively utilized in the identification and assessment of diverse cardiac conditions, including congestive heart failure (CHF) and cardiac arrhythmias (ARR), which present potential hazards to human health. With the aim of facilitating disease diagnosis and assessment, advanced computer-aided systems are being developed to analyze ECG signals. This study proposes a state-of-the-art ECG data pattern recognition algorithm based on Continuous Wavelet Transform (CWT) as a novel signal preprocessing model. The Motif Transformation (MT) method was devised to diminish the drawbacks and limitations inherent in the CWT, such as the issue of boundary effects, limited localization in time and frequency, and overfitting conditions. This transformation technique facilitates the formation of diverse patterns (motifs) within the signals. The patterns (motifs) are constructed by comparing the amplitudes of each individual sample value in the ECG signals in terms of their largeness and smallness. In the subsequent stage, the obtained one-dimensional signals from the MT transformation were subjected to CWT to obtain scalogram images. In the last stage, the obtained scalogram images were subjected to classification using DenseNET deep transfer learning techniques. The combined approach of MT+CWT+DenseNET yielded an impressive success rate of 99.31 %.

Wavelet entropy-based damage characterization and material phase differentiation in concrete using acoustic emissions

Damage evolution in concrete is a complex phenomenon involving micro-cracks that originate from different material phases (mortar matrix, ITZ and aggregate), and culminate into a major crack. The information about the individual damaged material phases can provide major insights into the global failure behaviour, cracking path, and fracture processes. The evolution of damage, damage mechanisms and the material phase of origin of micro-cracks is highly influenced by the type of concrete (Normal and high strength). In order to investigate the evolution of damage in concrete of varying strength, notched beam specimens with different water-to-cement ratios have been prepared and tested under CMOD control. The evolution and growth of damage have been continuously monitored during testing through acoustic emission techniques. Based on acoustic emission results, it has been demonstrated that the damage progression in concrete can be better described as a function of the wavelet entropy of the AE events occurring during the entire loading duration, and therefore, an analytical model for the damage evolution has been proposed. The study reveals that, under the high-strength category, the level of deterioration reduces as the w/c ratio rises, while in normal-strength concrete, a reverse trend is observed. Furthermore, a novel approach has been proposed that utilizes wavelet entropy and amplitude to differentiate amongst various damaged material phases with the help of an unsupervised clustering algorithm. Normal-strength concrete with a w/c ratio of 0.4 has been used to demonstrate the proposed methodology and has been validated with the help of experiments performed on the mortar and the parent stone of aggregate. A higher occurrence of mode-I cracks compared to mode-II cracks across all material phases has been observed for the specimen. Additionally, ITZ and aggregate exhibit a greater proportion of tensile and shear cracking events than the matrix phase. In the end, a deep learning convolutional neural network (CNN) model is devised utilizing labelled scalogram images of the AE waveforms to discriminate between the various damaged material phases. A 10-fold training cross-validation of the dataset has been carried out to achieve a stable performance. The deep learning model performs well in discriminating the damaged material phases with high training, validation, and testing accuracy.

Multi-Feature Automatic Extraction for Detecting Obstructive Sleep Apnea Based on Single-Lead Electrocardiography Signals.

Obstructive sleep apnea (OSA), a prevalent sleep disorder, is intimately associated with various other diseases, particularly cardiovascular conditions. The conventional diagnostic method, nocturnal polysomnography (PSG), despite its widespread use, faces challenges due to its high cost and prolonged duration. Recent developments in electrocardiogram-based diagnostic techniques have opened new avenues for addressing these challenges, although they often require a deep understanding of feature engineering. In this study, we introduce an innovative method for OSA classification that combines a composite deep convolutional neural network model with a multimodal strategy for automatic feature extraction. This approach involves transforming the original dataset into scalogram images that reflect heart rate variability attributes and Gramian angular field matrix images that reveal temporal characteristics, aiming to enhance the diversity and richness of data features. The model comprises automatic feature extraction and feature enhancement components and has been trained and validated on the PhysioNet Apnea-ECG database. The experimental results demonstrate the model's exceptional performance in diagnosing OSA, achieving an accuracy of 96.37%, a sensitivity of 94.67%, a specificity of 97.44%, and an AUC of 0.96. These outcomes underscore the potential of our proposed model as an efficient, accurate, and convenient tool for OSA diagnosis.

Investigation of Scalograms with a Deep Feature Fusion Approach for Detection of Parkinson’s Disease

Parkinson’s disease (PD) is a neurological condition that millions of people worldwide suffer from. Early symptoms include a slight sense of weakness and a propensity for involuntary tremulous motion in body limbs, particularly in the arms, hands, and head. PD is diagnosed based on motor symptoms. Additionally, scholars have proposed various remote monitoring tests that offer benefits such as early diagnosis, ease of application, and cost-effectiveness. PD patients often exhibit voice disorders. Speech signals of the patients can be used for early diagnosis of the disease. This study proposed an artificial intelligence–based approach for PD diagnosis using speech signals. Scalogram images, generated through the Continuous Wavelet Transform of the speech signals, were employed in deep learning techniques to detect PD. The scalograms were tested with various deep learning techniques. In the first part of the experiment, AlexNet, GoogleNet, ResNet50, and a majority voting-based hybrid system were used as classifiers. Secondly, a deep feature fusion method based on DenseNet and NasNet was investigated. Several evaluation metrics were employed to assess the performance. The deep feature fusion system achieved an accuracy of 0.95 and an F1 score with stratified 10-fold cross-validation, improving accuracy by 38% over the ablation study. The key contributions of this study include the investigation of scalogram images with a comprehensive analysis of deep learning models and deep feature fusion for PD detection.