CDNet++: Improved Change Detection with Deep Neural Network Feature Correlation

Interstitial lung disease (ILD) refers to a group of various abnormal inflammations of lung tissues and early diagnosis of these disease patterns is crucial for the treatment. Yet it is difficult to make an accurate diagnosis due to the similarity among the clinical manifestations of these diseases. In order to assist the radiologists, computer-aided diagnosis systems have been developed. Besides, the potential of deep convolutional neural networks (CNNs) is also expected to exert on the medical image analysis in recent years. In this paper, we design a new deep convolutional neural network (CNN) architecture to achieve the classification task of ILD patterns. Furthermore, we also propose a novel two-stage transfer learning (TSTL) method to deal with the problem of the lack of training data, which leverages the knowledge learned from sufficient textural source data and auxiliary unlabeled lung CT data to the target domain. We adopt the unsupervised manner to learn the unlabeled data, by which the objective function composed of the prediction confidence and mutual information are optimized. The experimental results show that our proposed CNN architecture achieves desirable performance and outperforms most of the state-of-the-art ones. The comparative analysis demonstrates the promising feasibility and advantages of the proposed two-stage transfer learning strategy as well as the potential of the knowledge learning from lung CT data. Graphical Abstract The framework of the proposed two-stage transfer learning method.

The convolutional neural network (CNN) architecture has shown remarkable success in image classification and segmentation. Its popularity has increased promptly due to various factors such as exponential growth in computational resources, availability of benchmark datasets, supporting libraries, and open-source software. The efficiency of CNN architecture majorly depends on the complexity of the architecture, availability of datasets, and hyperparameter selection. But, due to the huge number of parameters in CNN architecture, its selection has completely remained ad hoc in the past works. In this article, a novel encoding technique has been proposed that can represent complex CNN architecture effectively. The article defines basic building blocks to represent CNN architecture such as the genesis block, transit block, agile block, and output block. This encoding structure is used to generate dynamic length chromosome structure and initialized using evolutionary algorithms. A comparative analysis is also presented that shows compared its effectiveness with existing encoding representations on the basis of the number of encoding parameters, training cost, and efficiency.

Chaos Game Representation (CGR) is an emerging means of visualising and representing genomic and proteomic sequences. There exist many open questions related to its effective application to various computational tasks. In this work, we begin to address some of these questions by comparing four variants of the Chaos Game to generate CGR imagery as part of a multi-class classification task to identify the source organism for a given protein. We propose a novel nodal configuration for icosagon and 20-flake CGRs. Using two datasets, we performed fine-tuning using seven deep convolutional neural network (CNN) architectures and report modest performance over random among the 56 test conditions, highlighting certain shortcomings in effectively leveraging CGR in conjunction with deep CNN architectures. Many of the insights from this work will serve to orient subsequent protein-related studies involving CGR-based encoding and be generally applicable to disparate domains seeking to leverage CGR for sequence-type data.

Early and accurate identification of brain tumors is essential for determining effective treatment strategies and improving patient outcomes. Artificial intelligence (AI) and deep learning (DL) techniques have shown promise in automating diagnostic tasks based on magnetic resonance imaging (MRI). This study evaluates the performance of four pre-trained deep convolutional neural network (CNN) architectures for the automatic multi-class classification of brain tumors into four categories: Glioma, Meningioma, Pituitary, and No Tumor. The proposed approach utilizes the publicly accessible Brain Tumor MRI Msoud dataset, consisting of 7023 images, with 5712 provided for training and 1311 for testing. To assess the impact of data availability, subsets containing 25%, 50%, 75%, and 100% of the training data were used. A stratified five-fold cross-validation technique was applied. The CNN architectures evaluated include DeiT3_base_patch16_224, Xception41, Inception_v4, and Swin_Tiny_Patch4_Window7_224, all fine-tuned using transfer learning. The training pipeline incorporated advanced preprocessing and image data augmentation techniques to enhance robustness and mitigate overfitting. Among the models tested, Swin_Tiny_Patch4_Window7_224 achieved the highest classification Accuracy of 99.24% on the test set using 75% of the training data. This model demonstrated superior generalization across all tumor classes and effectively addressed class imbalance issues. Furthermore, we deployed and benchmarked the best-performing DL model on embedded AI platforms (Jetson AGX Xavier and Orin Nano), demonstrating their capability for real-time inference and highlighting their feasibility for edge-based clinical deployment. The results highlight the strong potential of pre-trained deep CNN and transformer-based architectures in medical image analysis. The proposed approach provides a scalable and energy-efficient solution for automated brain tumor diagnosis, facilitating the integration of AI into clinical workflows.

This work explores the suitability of various deep convolutional neural network (CNN) architectures for semantic segmentation of agricultural crops such as cotton, maize etc. from multi-spectral UAV (unmanned aerial vehicle) data. Initially, the UAV data were preprocessed and training samples for each crop type were manually annotated from multiple UAV scenes. Different CNN architectures such as U-Net, SegNet and PSPNet (Pyramid Scene Parsing Network) were trained with various combinations of input spectral bands along with select band derived indices such as NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index) as additional features. The experimental results indicated that inclusion of NIR (near-infrared) band and NDVI in the input data yielded high segmentation accuracy of more than 90%. U-Net proved to be the best among the three architectures with 97% overall accuracy while dealing with three classes separation problem. This study demonstrated the scope of deep neural network based semantic segmentation techniques in crop classification from multi-spectral UAV data.KeywordsCrop classificationUAV (unmanned aerial vehicle)Multi-spectral dataDeep learningU-NetSegNetPSPNetImage analysis

In this paper, an efficient deep convolutional neural network (CNN) architecture is proposed based on depthwise temporal convolution along with a robust end-to-end scheme to automatically detect and classify arrhythmia from denoised electrocardiogram (ECG) signal, which is termed as `DeepArrNet'. Firstly, considering the variational pattern of wavelet denoised ECG data, a realistic augmentation scheme is designed that offers a reduction in class imbalance as well as increased data variations. A structural unit, namely PTP (Pontwise-Temporal-Pointwise Convolution) unit, is designed with its variants where depthwise temporal convolutions with varying kernel sizes are incorporated along with prior and post pointwise convolution. Afterward, a deep neural network architecture is constructed based on the proposed structural unit where series of such structural units are stacked together while increasing the kernel sizes for depthwise temporal convolutions in successive units along with the residual linkage between units through feature addition. Moreover, multiple depthwise temporal convolutions are introduced with varying kernel sizes in each structural unit to make the process more efficient while strided convolutions are utilized in the residual linkage between subsequent units to compensate the increased computational complexity. This architecture provides the opportunity to explore the temporal features in between convolutional layers more optimally from different perspectives utilizing diversified temporal kernels. Extensive experimentations are carried out on two publicly available datasets to validate the proposed scheme that results in outstanding performances in all traditional evaluation metrics outperforming other state-of-the-art approaches.

Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and confidentiality of user data within the general public when their data is processed and stored in an external server which has further fueled the need for developing such efficient neural networks for real-time inference on local embedded systems. The scope of our work presented in this paper is limited to image classification using a convolutional neural network. A Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN) widely used in the analysis of visual images captured by an image sensor, designed to extract information and convert it into meaningful representations for real-time inference of the input data. In this paper, we propose a neoteric variant of deep convolutional neural network architecture to ameliorate the performance of existing CNN architectures for real-time inference on embedded systems. We show that this architecture, dubbed CondenseNeXt, is remarkably efficient in comparison to the baseline neural network architecture, CondenseNet, by reducing trainable parameters and FLOPs required to train the network whilst maintaining a balance between the trained model size of less than 3.0 MB and accuracy trade-off resulting in an unprecedented computational efficiency.

As the aging of concrete structures becomes increasingly severe, crack detection has become a crucial aspect of maintaining their sustainable use. This paper investigates an automatic detection and analysis method for concrete cracks based on deep convolutional neural network architecture. The study utilized drones equipped with high-definition cameras to capture images of concrete structures such as bridges and roads, collecting over 10,000 original images containing cracks. Using Labelme software for point-by-point image annotation and applying data augmentation techniques like rotation and scaling, the dataset was expanded to 30,000 images to meet the requirements of deep learning model training. An improved AlexNet model was developed, replacing the fully connected layer with global average pooling to enhance robustness and reduce overfitting. The model achieved an average accuracy of 95.42% on the test set, outperforming traditional methods by 15%. The model also proved effective in noisy environments. Additionally, a semantic segmentation model based on Fully Convolutional Network (FCN) was introduced, incorporating atrous convolution and spatial pyramid pooling, achieving a pixel-level accuracy of 97.6%, surpassing benchmark models such as FCN and U-Net. The model accurately estimated crack width, with an error rate within ±2% compared to field measurements. This method improves detection efficiency and accuracy while reducing manual intervention, providing strong support for the maintenance of concrete structures.

Scene change detection is the process of identifying the differences between the multi-temporal image scenes at the semantic level, which has significant potential in the application of urban development and land management. In this paper, we propose a novel deep convolution canonical correlation analysis neural network (DCCANet) architecture, which could consider the spectral-spatial-temporal correlation feature for scene change detection in remote sensing images. For this purpose, we put together the convolutional neural networks (CNNs) and the deep canonical correlation analysis (DCCA) into the end-to-end network. The CNN could get the spectral-spatial feature information for scene representation, while the later could enhance the temporal correlation by nonlinear high- dimensional transformations between the multi-temporal image scenes for scene change detection. Experiments with high-resolution remote sensing image scene datasets demonstrated that our proposed approach can get a better performance in scene classification and change detection.

PurposeTo determine whether convolutional neural networks can detect morphological differences between images of microbiologically positive and negative corneal ulcers.MethodsA cross-sectional comparison of prospectively collected data consisting of bacterial and fungal cultures and smears from eyes with acute infectious keratitis at Aravind Eye Hospital. Two convolutional neural network architectures (DenseNet and MobileNet) were trained using images obtained from handheld cameras collected from culture-positive and negative images and smear-positive and -negative images. Each architecture was trained on two image sets: (1) one with labels assigned using only culture results and (2) one using culture and smear results. The outcome measure was area under the receiver operating characteristic curve for predicting whether an ulcer would be microbiologically positive or negative.ResultsThere were 1970 images from 886 patients were included. None of the models were better than random chance at predicting positive microbiologic results (area under the receiver operating characteristic curve ranged from 0.49 to 0.56; all confidence intervals included 0.5).ConclusionsThese two state-of-the-art deep convolutional neural network architectures could not reliably predict whether a corneal ulcer would be microbiologically positive or negative based on clinical photographs. This absence of detectable morphological differences informs the future development of computer vision models trained to predict the causative agent in infectious keratitis using corneal photography.Translational RelevanceThese deep learning models were not able to identify morphological differences between microbiologically positive and negative corneal ulcers. This finding suggests that similar artificial intelligence models trained to identify the causative pathogen using only microbiologically positive cases may have potential to generalize well, including to cases with falsely negative microbiologic testing.

In recent times, drastic changes in the climate have brought about a dramatic increase in the prevalence of crop diseases. Such diseases are a huge threat to sustainable agriculture, especially for third-world countries whose economies still rely much on agriculture. Proper disease detection is an essential prerequisite to get timely treatment of crops and prevent reduction in crop yield. In most plant diseases, the leaves may contain some texture variations, which may help in identifying the diseases. However, an identical disease may not appear in a similar fashion for different plant species and visible texture differences may be very negligible. In most cases, plant diseases are classified for all species together, which may miss the species-specific symptoms. In this paper, we propose a two-stage classification scheme to classify plant diseases that divides the whole classification pipeline into two parts: a plant species detection part and a subsequent species-specific disease detection part. In both stages, we employ some efficient deep convolutional neural network (CNN) architectures, namely EfficeintNetB3, NASNetLarge, DenseNet201, MobileNetV2, VGG16 and InceptionV3 with effective transfer learning. Two publicly available datasets, namely Plant Village and IPM, are considered in this paper. Comparative analysis reveals that the proposed two-stage method can perform better than the conventional single-stage methods reported in the literature for plant disease detection.

Introduction Catathrenia is a rare sleep-related breathing disorder characterized by recurrent monotonous groaning during sleep. The acoustic characteristics of groaning and snoring sounds have been investigated. This study aims to propose a deep convolutional neural network (CNN) for automatic binary classification. Methods This study consisted of 3728 episodes of groaning sounds and 4577 episodes of snoring sounds obtained from synchronized audio of full-night polysomnography. Four features extracted from log-scaled mel-spectrograms were used as input. The background gaussian noise and the time-shifting were used to augment the dataset. The dataset was randomly split into training (70%), validation (15%), and testing datasets (15%). A deep learning convolutional neural network architecture was trained and evaluated. Results The proposed CNN model achieves an accuracy of 95.0% on the binary classification of groaning and snoring sounds. The model attains a sensitivity/recall of 96.4%, a specificity of 93.4%, and an F1 score of 94.84%. Conclusion The proposed CNN architecture has performed well in the automatic binary classification of groaning and snoring sounds, which could reduce difficulties in acoustic analyses of groaning episode detection. The model needs to be verified with more audio data before it can be put into clinical use better. Support (if any)

Deep learning has been successfully applied in classification of white blood cells (WBCs), however, accuracy and processing time are found to be less than optimal hindering it from getting its full potential. This is due to imbalanced dataset, intra-class compactness, inter-class separability and overfitting problems. The main research idea is to enhance the classification and prediction accuracy of blood images while lowering processing time through the use of deep convolutional neural network (DCNN) architecture by using the modified loss function. The proposed system consists of a deep neural convolution network (DCNN) that will improve the classification accuracy by using modified loss function along with regularization. Firstly, images are pre-processed and fed through DCNN that contains different layers with different activation function for the feature extraction and classification. Along with modified loss function with regularization, weight function aids in the classification of WBCs by considering weights of samples belonging to each class for compensating the error arising due to imbalanced dataset. The processing time will be counted by each image to check the time enhancement. The classification accuracy and processing time are achieved using the dataset-master. Our proposed solution obtains better classification performance in the given dataset comparing with other previous methods. The proposed system enhanced the classification accuracy of 98.92% from 96.1% and a decrease in processing time from 0.354 to 0.216 s. Less time will be required by our proposed solution for achieving the model convergence with 9 epochs against the current convergence time of 13.5 epochs on average, epoch is the formation white blood cells (WBCs) and the development of granular cells. The proposed solution modified loss function to solve the adverse effect caused due to imbalance dataset by considering weight and use regularization technique for overfitting problem.

In the future, vehicles will be equipped with increasingly advanced interactive intelligent electronic devices, which will induce drivers to conduct secondary tasks, thereby leading to distractions. Therefore, the detection and early warning of driver distraction are essential for improving driving safety and pose an important challenge in intelligent transportation systems. Previous studies used traditional machine learning and deep learning transfer models, which have the disadvantages of complicated and time-consuming manual feature engineering, strong subjectivity, and weak generalization performance. In this paper, we propose a fine-grained detection method for driver distraction based on neural architecture search. First, we design an automatic construction algorithm for deep convolutional neural networks based on neural architecture search, which automatically searches for the optimal deep convolutional neural network architecture without human involvement. In addition, we fuse driver-related multisource perception information, use an automatically constructed deep convolutional neural network to extract high-dimensional mapping features, and implement fine-grained detection of various types of driver distraction states. The results on a large-scale multimodal driver distraction dataset demonstrate that our method can efficiently search an optimal deep convolutional neural network, which can quickly converge, and can accurately detect the considered types of driver distraction states, the average detection accuracy reaches 99.7796%; moreover, it has satisfactory robustness.

Due to the smaller size, low cost, and easy operational features, small unmanned aerial vehicles (SUAVs) become more popular for various defence as well as civil applications. They can also give threat to national security if intentionally operated by any hostile-actor(s). Since, all the SUAV targets have a high degree of resemblances in their micro-Doppler (m-D) space, their accurate detection/classification can be highly guaranteed by the appropriate deep convolutional neural network (DCNN) architecture. In this work, a lightweight novel DCNN model (named “DIAT-RadSATNet”) is designed for the accurate SUAV targets: RC plane, 3-short-blade rotor, 3-long-blade rotor, quadcopter, bionic bird, and mini-helicopter + bionic bird; detection/classification based on their m-D signatures. A diversified, X-band (10GHz) continuous wave (CW) radar based, open-field-collected m-D signatures dataset (named as “DIAT-μSAT”) is used for the design/testing of “DIAT-RadSATNet”. A set-of new design principles is proposed through which multi-factors: layers, #parameters, floating point operations (FLOPs), no. of blocks, filter dimension, memory size, no. of parallel paths, and accuracy; optimization is applied via a series of in-depth ablation studies. The novel “DIAT-RadSATNet” module consists of 0.45M trainable parameters, 40 layers, 2.21Mb memory size, 0.59G FLOPs, and 0.21s computation-time complexity. The detection/classification accuracy of “DIAT-RadSATNet”, based on the open-field unknown dataset experiments, falls within 97.1% and 97.3%. A comparative analysis with state-of-the-art (SOTA) DCNN models evidences the betterness, more efficiency, and more accuracy of our novel “DIAT-RadSATNet” architecture.