Enhance Classification Accuracy Research Articles

A research on depression recognition based on voice pre-training model

For the increasing number of patients with depression, this paper proposes an artificial intelligence method to effectively identify depression through voice signals, with the aim of improving the efficiency of diagnosis and treatment. Firstly, a pre-training model called wav2vec 2.0 is fine-tuned to encode and contextualize the speech, thereby obtaining high-quality voice features. This model is applied to the publicly available dataset - the distress analysis interview corpus-wizard of OZ (DAIC-WOZ). The results demonstrate a precision rate of 93.96%, a recall rate of 94.87%, and an F1 score of 94.41% for the binary classification task of depression recognition, resulting in an overall classification accuracy of 96.48%. For the four-class classification task evaluating the severity of depression, the precision rates are all above 92.59%, the recall rates are all above 92.89%, the F1 scores are all above 93.12%, and the overall classification accuracy is 94.80%. The research findings indicate that the proposed method effectively enhances classification accuracy in scenarios with limited data, exhibiting strong performance in depression identification and severity evaluation. In the future, this method has the potential to serve as a valuable supportive tool for depression diagnosis.

An efficient consolidation of word embedding and deep learning techniques for classifying anticancer peptides: FastText+BiLSTM.

Anticancer peptides (ACPs) are a group of peptides that exhibit antineoplastic properties. The utilization of ACPs in cancer prevention can present a viable substitute for conventional cancer therapeutics, as they possess a higher degree of selectivity and safety. Recent scientific advancements generate an interest in peptide-based therapies which offer the advantage of efficiently treating intended cells without negatively impacting normal cells. However, as the number of peptide sequences continues to increase rapidly, developing a reliable and precise prediction model becomes a challenging task. In this work, our motivation is to advance an efficient model for categorizing anticancer peptides employing the consolidation of word embedding and deep learning models. First, Word2Vec, GloVe, FastText, One-Hot-Encoding approaches are evaluated as embedding techniques for the purpose of extracting peptide sequences. Then, the output of embedding models are fed into deep learning approaches CNN, LSTM, BiLSTM. To demonstrate the contribution of proposed framework, extensive experiments are carried on widely-used datasets in the literature, ACPs250 and independent. Experiment results show the usage of proposed model enhances classification accuracy when compared to the state-of-the-art studies. The proposed combination, FastText+BiLSTM, exhibits 92.50% of accuracy for ACPs250 dataset, and 96.15% of accuracy for the Independent dataset, thence determining new state-of-the-art.

An integrated deep-learning model for smart waste classification.

Efficient waste management is essential for human well-being and environmental health, as neglecting proper disposal practices can lead to financial losses and the depletion of natural resources. Given the rapid urbanization and population growth, developing an automated, innovative waste classification model becomes imperative. To address this need, our paper introduces a novel and robust solution - a smart waste classification model that leverages a hybrid deep learning model (Optimized DenseNet-121 + SVM) to categorize waste items using the TrashNet datasets. Our proposed approach uses the advanced deep learning model DenseNet-121, optimized for superior performance, to extract meaningful features from an expanded TrashNet dataset. These features are subsequently fed into a support vector machine (SVM) for precise classification. Employing data augmentation techniques further enhances classification accuracy while mitigating the risk of overfitting, especially when working with limited TrashNet data. The results of our experimental evaluation of this hybrid deep learning model are highly promising, with an impressive accuracy rate of 99.84%. This accuracy surpasses similar existing models, affirming the efficacy and potential of our approach to revolutionizing waste classification for a sustainable and cleaner future.

Classification of Cancer Microarray Data Based on Deep Learning: A Review

This review article delves into applying deep learning methodologies in conjunction with microarray data for cancer classification. The study provides a comprehensive overview of recent advancements in utilizing deep learning techniques to accurately categorize cancer types based on intricate patterns discerned from microarray datasets. Various aspects are covered, including integrating deep learning algorithms, exploring diverse cancer types, and analyzing microarray data to enhance classification accuracy. The review synthesizes findings from recent research, highlighting the efficacy of deep learning in uncovering subtle and complex relationships within microarray data that contribute to improved classification outcomes. Key insights into the strengths and limitations of employing deep learning in this context are discussed, offering a critical appraisal of the field's current state. This review aims to provide a valuable resource for researchers, clinicians, and practitioners interested in cutting-edge developments in cancer classification methodologies by exploring the intersection of deep learning and microarray technology. The synthesis of knowledge presented herein contributes to a deeper understanding of the potential and challenges associated with harnessing deep learning for enhanced classification accuracy in the realm of cancer research.

Semantic segmentation of very-high spatial resolution satellite images: A comparative analysis of 3D-CNN and traditional machine learning algorithms for automatic vineyard detection

The Erzincan (Cimin) grape, which is an endemic product, plays a significant role in the economy of both the region it is cultivated in and the overall country. Therefore, it is crucial to closely monitor and promote this product. The objective of this study was to analyze the spatial distribution of vineyards by utilizing advanced machine learning and deep learning algorithms to classify high-resolution satellite images. A deep learning model based on a 3D Convolutional Neural Network (CNN) was developed for vineyard classification. The proposed model was compared with traditional machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest (RF), and Rotation Forest (ROTF). The accuracy of the classifications was assessed through error matrices, kappa analysis, and McNemar tests. The best overall classification accuracies and kappa values were achieved by the 3D CNN and RF methods, with scores of 86.47% (0.8308) and 70.53% (0.6279) respectively. Notably, when Gabor texture features were incorporated, the accuracy of the RF method increased to 75.94% (0.6364). Nevertheless, the 3D CNN classifier outperformed all others, yielding the highest classification accuracy with an 11% advantage (86.47%). The statistical analysis using McNemar's test confirmed that the χ2 values for all classification outcomes exceeded 3.84 at the 95% confidence interval, indicating a significant enhancement in classification accuracy provided by the 3D CNN classifier. Additionally, the 3D CNN method demonstrated successful classification performance, as evidenced by the minimum-maximum F1-score (0.79-0.97), specificity (0.95-0.99), and accuracy (0.91-0.99) values.

Knowledge‐based deep learning system for classifying Alzheimer's disease for multi‐task learning

AbstractDeep learning has recently become a viable approach for classifying Alzheimer's disease (AD) in medical imaging. However, existing models struggle to efficiently extract features from medical images and may squander additional information resources for illness classification. To address these issues, a deep three‐dimensional convolutional neural network incorporating multi‐task learning and attention mechanisms is proposed. An upgraded primary C3D network is utilised to create rougher low‐level feature maps. It introduces a new convolution block that focuses on the structural aspects of the magnetic resonance imaging image and another block that extracts attention weights unique to certain pixel positions in the feature map and multiplies them with the feature map output. Then, several fully connected layers are used to achieve multi‐task learning, generating three outputs, including the primary classification task. The other two outputs employ backpropagation during training to improve the primary classification job. Experimental findings show that the authors’ proposed method outperforms current approaches for classifying AD, achieving enhanced classification accuracy and other indicators on the Alzheimer's disease Neuroimaging Initiative dataset. The authors demonstrate promise for future disease classification studies.

Scalar invariant transform based deep learning framework for detecting heart failures using ECG signals

Heart diseases are leading to death across the globe. Exact detection and treatment for heart disease in its early stages could potentially save lives. Electrocardiogram (ECG) is one of the tests that take measures of heartbeat fluctuations. The deviation in the signals from the normal sinus rhythm and different variations can help detect various heart conditions. This paper presents a novel approach to cardiac disease detection using an automated Convolutional Neural Network (CNN) system. Leveraging the Scale-Invariant Feature Transform (SIFT) for unique ECG signal image feature extraction, our model classifies signals into three categories: Arrhythmia (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR). The proposed model has been evaluated using 96 Arrhythmia, 30 CHF, and 36 NSR ECG signals, resulting in a total of 162 images for classification. Our proposed model achieved 99.78% accuracy and an F1 score of 99.78%, which is among one of the highest in the models which were recorded to date with this dataset. Along with the SIFT, we also used HOG and SURF techniques individually and applied the CNN model which achieved 99.45% and 78% accuracy respectively which proved that the SIFT–CNN model is a well-trained and performed model. Notably, our approach introduces significant novelty by combining SIFT with a custom CNN model, enhancing classification accuracy and offering a fresh perspective on cardiac arrhythmia detection. This SIFT–CNN model performed exceptionally well and better than all existing models which are used to classify heart diseases.

Enhanced text classification through an improved discrete laying chicken algorithm

AbstractThe exponential growth of digital text documents presents a significant challenge for text classification algorithms, as the vast number of words in each document can hinder their efficiency. Feature selection (FS) is a crucial technique that aims to eliminate irrelevant features and enhance classification accuracy. In this study, we propose an improved version of the discrete laying chicken algorithm (IDLCA) that utilizes noun‐based filtering to reduce the number of features and improve text classification performance. Although LCA is a newly proposed algorithm, it has not been systematically applied to discrete problems before. Our enhanced version of LCA employs different operators to improve both exploration and exploitation of this algorithm to find better solutions in discrete mode. To evaluate the effectiveness of the proposed method, we compared it with some conventional nature‐inspired feature selection methods using various learning models such as decision trees (DT), K‐nearest neighbor (KNN), Naive Bayes (NB), and support vector machine (SVM) on five benchmark datasets with three different evaluation metrics. The experimental results demonstrate the effectiveness of the proposed algorithm in comparison to the existing one. The code is available at https://github.com/m0javad/Improved-Discrete-Laying-Chicken-Algorithm.

The Effect of Using a Geopedological Approach in Determining Land Quality Indicators, Land Degradation, and Development (Case Study: Caspian Sea Coast)

This study addresses the escalating global concern surrounding land degradation (LD) and its far-reaching implications on water and nutrient availability, as well as on human health and well-being. Focused on the southeastern Caspian Sea region, this research employs a novel remote sensing geo-pedological methodology to comprehensively assess soil and land quality dynamics, particularly influenced by salts, and investigates the intricate relationship between LD and soil development. The study area, marked by a susceptibility to seawater level fluctuations and diverse landforms (lagoons, barriers, and coastal plains) offers a unique opportunity for geopedologic analysis. Utilizing particle size distribution data, six distinct landforms are identified, providing insights into the region’s complex sedimentary history. A soil quality assessment is conducted remotely through the calculation of two indexes—the Integrated Quality Index (IQI) and the Nemoro Quality Index (NQI)—employing both Total Data Set (TDS) and Minimum Data Set (MDS) methodologies. The investigation highlights the role of soluble salts in shaping soil quality, thereby influencing LD and development dynamics. The differentiation of landforms significantly enhances classification accuracy, providing a more nuanced understanding of the multifaceted factors governing LD. The study’s implications extend beyond the southeastern Caspian Sea region, and demonstrate that the potential for incorporating a geopedologic approach when assessing soil and land quality dynamics in arid regions globally. Our analytic approach can inform policymakers and land managers when making decisions to combat LD and foster sustainable land development. This research also contributes towards advancing knowledge in geopedology by providing a robust foundation for future studies aimed at enhancing land management practices in the face of ongoing environmental challenges.

Deep learning-based classification of eye diseases using Convolutional Neural Network for OCT images

Deep learning shows promising results in extracting useful information from medical images. The proposed work applies a Convolutional Neural Network (CNN) on retinal images to extract features that allow early detection of ophthalmic diseases. Early disease diagnosis is critical to retinal treatment. Any damage that occurs to retinal tissues that cannot be recovered can result in permanent degradation or even complete loss of sight. The proposed deep-learning algorithm detects three different diseases from features extracted from Optical Coherence Tomography (OCT) images. The deep-learning algorithm uses CNN to classify OCT images into four categories. The four categories are Normal retina, Diabetic Macular Edema (DME), Choroidal Neovascular Membranes (CNM), and Age-related Macular Degeneration (AMD). The proposed work uses publicly available OCT retinal images as a dataset. The experimental results show significant enhancement in classification accuracy while detecting the features of the three listed diseases.

A novel end-to-end chromosome classification approach using deep neural network with triple attention mechanism

The automated karyotyping analysis serves as a crucial tool in diagnosing genetic disorders stemming from chromosome abnormalities. Chromosome classification, a pivotal step in this diagnostic process encounters challenges due to the non-rigid structure and unpredictable curved shapes of chromosomes. Extracting features with discriminative power for enhanced classification accuracy becomes difficult, impacting the practical results of karyotyping analyses in clinical applications. In this paper, we propose a novel end-to-end chromosome classification approach based on deep neural network with a triple attention mechanism (TAM). The approach unfolds in three stages. Firstly, deep CNNs and modified Multiscale Feature Fusion (MFF) blocks collaborate to generate informative multi-scale global representations. In the second stage, to uncover finer features that enhance chromosome differentiation, TAM is devised. It learns channel-wise, spatial-wise and point-wise attention feature maps fully extracting valuable information from multi-scale global features. Finally, a probability-weighted prediction scheme is incorporated to synthetically estimate classification branches at all scales, facilitating type identification. The evaluation results, based on a clinical G-band chromosome dataset comprising 52,808 single chromosome images, indicate that the proposed chromosome classification approach attains an impressive accuracy of 99.4%. In conclusion, our method exhibits strong robustness and high stability in effectively classifying multiple types of chromosomes.

Dilated Spectral–Spatial Gaussian Transformer Net for Hyperspectral Image Classification

In recent years, deep learning-based classification methods for hyperspectral images (HSIs) have gained widespread popularity in fields such as agriculture, environmental monitoring, and geological exploration. This is owing to their ability to automatically extract features and deliver outstanding performance. This study provides a new Dilated Spectral–Spatial Gaussian Transformer Net (DSSGT) model. The DSSGT model incorporates dilated convolutions as shallow feature extraction units, which allows for an expanded receptive field while maintaining computational efficiency. We integrated transformer architecture to effectively capture feature relationships and generate deep fusion features, thereby enhancing classification accuracy. We used consecutive dilated convolutional layers to extract joint low-level spectral–spatial features. We then introduced Gaussian Weighted Pixel Embedding blocks, which leverage Gaussian weight matrices to transform the joint features into pixel-level vectors. By combining the features of each pixel with its neighbouring pixels, we obtained pixel-level representations that are more expressive and context-aware. The transformed vector matrix was fed into the transformer encoder module, enabling the capture of global dependencies within the input data and generating higher-level fusion features with improved expressiveness and discriminability. We evaluated the proposed DSSGT model using five hyperspectral image datasets through comparative experiments. Our results demonstrate the superior performance of our approach compared to those of current state-of-the-art methods, providing compelling evidence of the DSSGT model’s effectiveness.

A novel classification method for GPR B-scan images based on weak-shot learning

Ground Penetrating Radar (GPR) is extensively employed for underground target detection, and the advancements in this domain have been hastened by the utilization of deep learning methodologies. Despite advancements in deep learning, practical engineering applications often face challenges in meeting the demanding requirements of large-scale data and high data quality. In this study, based on cross-domain transfer learning, we proposed a method for underground target classification of weak labeled GPR data. It combined strongly annotated source domain data with weakly annotated target domain data through adversarial learning to leverage the prior knowledge from existing large datasets and addressed the classification problem of small-sample GPR data. By employing adversarial learning to integrate strongly labeled source domain data with weakly labeled target domain data, we leverage prior knowledge from existing large datasets, thereby enhancing classification accuracy on a small GPR dataset. This approach reduces the requirements for annotation quality and sample quantity in the GPR B-scan dataset of underground targets. Additionally, it exhibits robustness to label noise, making it applicable to real-world GPR data classification tasks. Compared to some well-known networks, the proposed model achieved the best classification performance in multiclass classification problems, with an accuracy of 87.62% and an F1macro score of 87.60% on the test set. These results represent an improvement of 17.14 and 17.20 percentage points, respectively, over the best-performing classical classification networks. Additionally, the proposed model's reliability in cross-domain transfer learning, even with limited data, was substantiated through a comparison with other few-shot learning networks.

Revealing brain connectivity: graph embeddings for EEG representation learning and comparative analysis of structural and functional connectivity.

This study employs deep learning techniques to present a compelling approach for modeling brain connectivity in EEG motor imagery classification through graph embedding. The compelling aspect of this study lies in its combination of graph embedding, deep learning, and different brain connectivity types, which not only enhances classification accuracy but also enriches the understanding of brain function. The approach yields high accuracy, providing valuable insights into brain connections and has potential applications in understanding neurological conditions. The proposed models consist of two distinct graph-based convolutional neural networks, each leveraging different types of brain connectivities to enhance classification performance and gain a deeper understanding of brain connections. The first model, Adjacency-based Convolutional Neural Network Model (Adj-CNNM), utilizes a graph representation based on structural brain connectivity to embed spatial information, distinguishing it from prior spatial filtering approaches dependent on subjects and tasks. Extensive tests on a benchmark dataset-IV-2a demonstrate that an accuracy of 72.77% is achieved by the Adj-CNNM, surpassing baseline and state-of-the-art methods. The second model, Phase Locking Value Convolutional Neural Network Model (PLV-CNNM), incorporates functional connectivity to overcome structural connectivity limitations and identifies connections between distinct brain regions. The PLV-CNNM achieves an overall accuracy of 75.10% across the 1-51 Hz frequency range. In the preferred 8-30 Hz frequency band, known for motor imagery data classification (including α, μ, and β waves), individual accuracies of 91.9%, 90.2%, and 85.8% are attained for α, μ, and β, respectively. Moreover, the model performs admirably with 84.3% accuracy when considering the entire 8-30 Hz band. Notably, the PLV-CNNM reveals robust connections between different brain regions during motor imagery tasks, including the frontal and central cortex and the central and parietal cortex. These findings provide valuable insights into brain connectivity patterns, enriching the comprehension of brain function. Additionally, the study offers a comprehensive comparative analysis of diverse brain connectivity modeling methods.

Supervised diagnostic classification of cognitive attributes using data augmentation.

Over recent decades, machine learning, an integral subfield of artificial intelligence, has revolutionized diverse sectors, enabling data-driven decisions with minimal human intervention. In particular, the field of educational assessment emerges as a promising area for machine learning applications, where students can be classified and diagnosed using their performance data. The objectives of Diagnostic Classification Models (DCMs), which provide a suite of methods for diagnosing students' cognitive states in relation to the mastery of necessary cognitive attributes for solving problems in a test, can be effectively addressed through machine learning techniques. However, the challenge lies in the latent nature of cognitive status, which makes it difficult to obtain labels for the training dataset. Consequently, the application of machine learning methods to DCMs often assumes smaller training sets with labels derived either from theoretical considerations or human experts. In this study, the authors propose a supervised diagnostic classification model with data augmentation (SDCM-DA). This method is designed to utilize the augmented data using a data generation model constructed by leveraging the probability of correct responses for each attribute mastery pattern derived from the expert-labeled dataset. To explore the benefits of data augmentation, a simulation study is carried out, contrasting it with classification methods that rely solely on the expert-labeled dataset for training. The findings reveal that utilizing data augmentation with the estimated probabilities of correct responses substantially enhances classification accuracy. This holds true even when the augmentation originates from a small labeled sample with occasional labeling errors, and when the tests contain lower-quality items that may inaccurately measure students' true cognitive status. Moreover, the study demonstrates that leveraging augmented data for learning can enable the successful classification of students, thereby eliminating the necessity for specifying an underlying response model.

A fast and data-efficient deep learning framework for multi-class fruit blossom detection

Automatic fruit blossom detection plays a crucial role in agricultural intelligence to predict fruit yield. Existing deep learning methods for vision-based fruit blossom detection oftentimes rely on large labeled samples and are tailor for a single category of fruit blossoms, limiting their flexibility and adaptability in real applications. In this paper, a fast and data-efficient framework is proposed to achieve multi-class fruit blossom detection using few labeled samples, which not only enhances the flexibility of model training by reducing the need for extensive samples but also extends the model’s applicability to a wider range of blossom categories. Specifically, the proposed framework incorporates the paradigm of few-shot object detection into a lightweight two-stage detector named CenterNet2. To improve the recall of blossom proposals, we introduce a location guidance module (LGM) to highlight foreground regions in query images that bear resemblance to the blossom reference provided by support images. Moreover, a contrastive learning scheme (CLS) is introduced to further distinguish fruit blossom categories with similar appearances, enhancing classification accuracy. Experimental results demonstrated that our framework achieved comparable performance to existing state-of-the-art models, with a mean average precision of 74.33% over 12 categories of fruit blossoms and a frame per second rate of 47. In summary, our proposed framework can reduce data dependency and enhance flexibility of existing deep learning detectors, making it a promising solution for automatic monitoring in real-world agricultural applications.

Pine wood nematode disease area identification based on multi-temporal multi-source remote sensing images and BIT model

Pine wood nematode (PWN) disease is a severe contagious disease in forests which endangers the health of forests, as it can rapidly kill trees. The detection of regions impacted by this disease plays a crucial role in forest management, remediation efforts and ensuring the overall ecological security of forests. With the advancements in remote sensing technology, remote sensing images offer distinct advantages such as extensive coverage, timely data acquisition and high spatial resolution, making them highly suitable for accurately and efficiently identifying PWN disease areas. This article introduces a deep learning approach for the identification of PWN disease areas using multi-temporal and multi-source remote sensing images. Specifically, a specialized model called the bitemporal image transformer (BIT) model is developed and trained using multi-temporal Beijing-2 and Beijing-3 images acquired at different stages of PWN disease. BIT is a twin network for semantic segmentation with transformer structure and its backbone utilizes the Resnet structure. The input bitemporal image can be represented by several semantic tokens and encoded using a transformer encoder. The contextual information learned from the tokens is subsequently applied back to the pixel space. Finally, transformer decoder is utilized to refine the original features. To evaluate the model’s generalization ability, the best-trained model for different regions affected by pine nematode disease is identified using a transfer learning mechanism. The experimental results demonstrate a significant enhancement in classification accuracy using the proposed method, with a noteworthy 15.23% improvement in F1-score, 9.34% in accuracy, 11.7% in precision, 12.88% in recall, compared to traditional methods. Moreover, the model exhibits impressive generalization ability across various forest regions. In summary, this research introduces a promising approach that utilizes remote sensing images and deep learning techniques as a powerful tool for precisely identifying and managing areas affected by PWN disease.

An Improved Extreme Learning Machine (ELM) Algorithm for Intent Recognition of Transfemoral Amputees With Powered Knee Prosthesis.

To overcome the challenges posed by the complex structure and large parameter requirements of existing classification models, the authors propose an improved extreme learning machine (ELM) classifier for human locomotion intent recognition in this study, resulting in enhanced classification accuracy. The structure of the ELM algorithm is enhanced using the logistic regression (LR) algorithm, significantly reducing the number of hidden layer nodes. Hence, this algorithm can be adopted for real-time human locomotion intent recognition on portable devices with only 234 parameters to store. Additionally, a hybrid grey wolf optimization and slime mould algorithm (GWO-SMA) is proposed to optimize the hidden layer bias of the improved ELM classifier. Numerical results demonstrate that the proposed model successfully recognizes nine daily motion modes including low-, mid-, and fast-speed level ground walking, ramp ascent/descent, sit/stand, and stair ascent/descent. Specifically, it achieves 96.75% accuracy with 5-fold cross-validation while maintaining a real-time prediction time of only 2 ms. These promising findings highlight the potential of onboard real-time recognition of continuous locomotion modes based on our model for the high-level control of powered knee prostheses.

Melanoma Skin Cancer Detection Using Ensemble of Machine Learning Models Considering Deep Feature Embeddings

In today’s AI-driven era, deep learning (DL) algorithms play a crucial role in automatically detecting life-threatening skin cancers, thereby significantly enhancing survival rates. It makes skin cancer detection using DL algorithms an exciting area of exploration. While much of the prior research has focused on single-model approaches, combining ensembles of multiple models can enhance classification accuracy. Previous studies mainly relied on deep convolutional neural networks (DCNNs), which have limitations in capturing global features. Recent advancements have introduced capsule networks (Caps-Net) and vision transformers (ViT) for more effective feature extraction. In our study, we harness the power of DCNN, Caps-Net, and ViT frameworks to extract diverse image embeddings. These obtained feature vectors work as input data to train an ensemble model based on a majority voting mechanism. This ensemble model consists of five machine-learning models, including Random Forest, XGBoost, SVM, KNN, and logistic regression. The incorporation of this ensemble mechanism leads to a significant improvement in the overall model’s performance. It is noteworthy that the proposed ensemble model serves as a lightweight model, which achieves an impressive accuracy of 91.6% when considering the melanoma skin cancer dataset. These results underscore the superiority of our proposed mechanism over individual state-of-the-art (SOTA) models.

Cocoa Diseases Classification using Deep Learning Algorithm

This work addresses the critical issue of cocoa plant diseases, which pose a significant threat to global agriculture and the livelihood of millions of farmers. Convolutional Neural Networks (CNN) has been utilized for classifying cocoa diseases, focusing on combating the significant agricultural and economic impacts of black pod rot and pod borer. Utilizing a dataset of 4390 images, five CNN architectures—Custom CNN, VGG-16, EfficientNetB0, ResNet50, and LeNet-5—were assessed for their ability to accurately identify disease presence. The Custom CNN model was found to be the most effective, achieving an accuracy of 91.79%, precision of 91.79%, recall of 91.79%, F1 score of 82.08%, sensitivity of 96.69%, and specificity of 98.40%, indicating its strong capability in correctly classifying both healthy and diseased plants. The work methodically approached data preprocessing, model parameter tuning, and a structured machine learning evaluation process. While EfficientNetB0 and ResNet50 also displayed commendable performances, VGG-16 and LeNet-5 lagged, suggesting the need for further model refinement. This work underscores the importance of the F1 score in evaluating model performance, especially given the class imbalance within the dataset. The findings suggest future exploration into other pre-trained models and data augmentation strategies to further enhance classification accuracy. The goal of this work is the implementation of a realtime system to minimize cocoa production losses due to disease.