Network-Computation in Neural Systems最新文献

Owing to the epidemic growth of diabetes, ophthalmologists need to examine the huge fundus images for diagnosing the disease of Diabetic Retinopathy (DR). Without proper knowledge, people are too lethargic to detect the DR. Therefore, the early diagnosis system is requisite for treating ailments in the medical industry. Therefore, a novel deep model-based DR detection structure is recommended to fix the aforementioned difficulties. The developed deep model-based diabetic retinopathy detection process is performed adaptively. The DR detection process is imitated by garnering the images from benchmark sources. The gathered images are further preceded by the abnormality segmentation phase. Here, the Residual TransUNet with Enhanced loss function is used to employ the abnormality segmentation, and the loss function in this structure may be helpful to lessen the error in the segmentation procedure. Further, the segmented images are passed to the final phase of retinopathy detection. At this phase, the detection is carried out through the Adaptive Multiscale MobileNet. The variables in the AMMNet are optimized by the Adaptive Puzzle Optimization to obtain better detection performance. Finally, the effectiveness of the offered approach is confirmed by the experimentation procedure over various performance indices.

Cancer involves abnormal cell growth, with types like intestinal and oesophageal cancer often diagnosed in advanced stages, making them hard to cure. Symptoms are like burning sensations in the stomach and swallowing difficulties are specified as colorectal cancer. Deep learning significantly impacts the medical image processing and diagnosis, offering potential improvements in accuracy and efficiency. The Kruskal Szekeres Generative Adversarial Network Augmented Deep Autoencoder (KSGANA-DA) is introduced for early colorectal cancer detection and it comprises two stages; Initial stage, data augmentation uses Affine Transform via Random Horizontal Rotation and Geometric Transform via Kruskal-Szekeres that coordinates to improve the training dataset diversity, boosting detection performance. The second stage, a Deep Autoencoder Anatomical Landmark-based Image Segmentation preserves edge pixel spatial locations, improving precision and recall for early boundary detection. Experiments validate KSGANA-DA performance and different existing methods are implemented into Python. The results of KSGANA-DA are to provide higher precision by 41%, recall by 7%, and lesser training time by 46% than compared to conventional methods.

Tomato harvesting in intelligent greenhouses is crucial for reducing costs and optimizing management. Agricultural robots, as an automated solution, require advanced visual perception. This study proposes a tomato detection and counting algorithm based on YOLOv8 (TCAttn-YOLOv8). To handle small, occluded tomato targets in images, a new detection layer (NDL) is added to the Neck and Head decoupled structure, improving small object recognition. The ColBlock, a dual-branch structure leveraging Transformer advantages, enhances feature extraction and fusion, focusing on densely targeted regions and minimizing small object feature loss in complex backgrounds. C2fGhost and GhostConv are integrated into the Neck network to reduce model parameters and floating-point operations, improving feature expression. The WIoU (Wise-IoU) loss function is adopted to accelerate convergence and increase regression accuracy. Experimental results show that TCAttn-YOLOv8 achieves an mAP@0.5 of 96.31%, with an FPS of 95 and a parameter size of 2.7 M, outperforming seven lightweight YOLO algorithms. For automated tomato counting, the R² between predicted and actual counts is 0.9282, indicating the algorithm's suitability for replacing manual counting. This method effectively supports tomato detection and counting in intelligent greenhouses, offering valuable insights for robotic harvesting and yield estimation research.

This paper uses a multi-head neural transformer to present the text-to-text translation/interpretation of Sign Language (SL) in the context of glosses (written SL). A Spanish to Mexican Sign Language (MSL) gloss dataset was built based on simple and compound sentences and the corresponding interpretation in MSL gloss. The interpretation process was achieved by implementing state-of-the-art tools in the natural language processing (NLP) field called neural transformers. We tried different architectures, varying the number of encoder-decoder layers and hyperparameters. The best of our models achieved 0.68 BLEU in the training phase and 0.33 in the validation phase. MSL glosses are crucial as they rule the grammatical order in which MSL has to be executed. All these quantitative and qualitative results confirm the potential applicability of neural transformers to create effective automatic translators for the Spanish language to MSL, with similar effectiveness shown by other automatic translators for other more likely languages.

In the farming sector, the automatic detection of plant leaf disease is considered a vital landmark. Farmers move long distances to consult pathologists to observe the disease, which is expensive and time-consuming. Moreover, detection of disease in a premature period is a difficult process in the existing model. Thus, all these challenges motivate us to develop an inventive plant leaf disease detection model. In the developed model, the data is gathered initially and given as input to the pre-processing step using Contrast Limited Adaptive Histogram Equalization (CLAHE). Next, the leaves are segmented from the pre-processed images, and then abnormality segmentation is done by the K-means clustering system. Here, parameters are optimized using the Opposition-based Bird Swarm Algorithm (O-BSA). Further, features were extracted from abnormality-segmented images in feature extraction. The extracted features are given in the classification step, where leaf disease detection is carried out using Optimized Ensemble Machine Learning (OEML), where, parameter optimization is done by O-BSA. Finally, the developed plant leaf detection approach is evaluated with various performance metrics, and given an accuracy of up to 92.26. These findings show that the developed model is promising over conventional methods and its effectiveness in detecting plant leaf disease.

Convolutional neural networks (CNNs) have reached their peak of complex structures, but until now, few researchers have addressed the problem of relying on one filter size. Mainly a 3 × 3 filter is the most common one used in any structure. Only at the first layers of the CNN model, filters bigger than 3 × 3 could be partially used. Most researchers work with filters (size, values, etc.) as a black box. To the best of our knowledge, this research is the first pilot study that proposes a new multi-filter layer in which different filters with variant sizes are used to replace the 3 × 3 filter layers. Our proposed multi-filter layer has yielded encouraging results, demonstrating notable improvements ranging from 1% to 5% in performance. This achievement was realized by developing two innovative structures, namely the fixed structure and the decreasing structure. Both of them leverage the multi-filter layer. Although the two structures exhibit promising outcomes, the later structure offers the additional advantages of reduced computational requirements and enhanced learner strength.

One of the most familiar types of disease is Alzheimer's disease (AD) and it mainly impacts people over the age limit of 60. AD causes irreversible brain damage in humans. It is difficult to recognize the various stages of AD, hence advanced deep learning methods are suggested for recognizing AD in its initial stages. In this experiment, an effective deep model-based AD detection approach is introduced to provide effective treatment to the patient. Initially, an essential MRI is collected from the benchmark resources. After that, the gathered MRIs are provided as input to the feature extraction phase. Also, the important features in the input image are extracted by Vision Transformer-based Residual DenseNet (ViT-ResDenseNet). Later, the retrieved features are applied to the Alzheimer's detection stage. In this phase, AD is detected using an Adaptive Deep Bayesian Network (Ada-DBN). Additionally, the attributes of Ada-DBN are optimized with the help of Enhanced Golf Optimization Algorithm (EGOA). So, the implemented Alzheimer's detection model accomplishes relatively higher reliability than existing techniques. The numerical results of the suggested framework obtained an accuracy value of 96.35 which is greater than the 91.08, 91.95, and 93.95 attained by the EfficientNet-B2, TF- CNN, and ViT-GRU, respectively.

In Diabetic Retinopathy (DR), the retina is harmed due to the high blood pressure in small blood vessels. Manual screening is time-consuming, which can be overcome by using automated techniques. Hence, this paper proposed a new method for classifying the multi-level severity of DR. Initially, the input fundus image is pre-processed by Non-local means Denoising (NLMD). Then, lesion segmentation is carried out by the Recurrent Prototypical-squeeze U-SegNet (RP-squeeze U-SegNet). Next, feature extraction is effectuated to mine image-level features. DR is categorized as abnormal or normal by ShuffleNet and it is tuned by Fractional War Royale Optimization (FrWRO), and later, if DR is detected, severity classification is performed. Furthermore, the FrWRO-SqueezeNet obtained the maximum performance with sensitivity of 97%, accuracy of 93.8%, specificity of 95.1%, precision of 91.8%, and F-Measure of 94.3%. The devised scheme accurately visualizes abnormal regions in the fundus images. Also, it has the ability to identify the severity levels of DR effectively, which avoids the progression risk to vision loss and proliferative disease.

Deep brain stimulation(DBS) has become an effective intervention for advanced Parkinson's disease(PD), but the exact mechanism of DBS is still unclear. In this review, we discuss the history of DBS, the anatomy and internal architecture of the basal ganglia (BG), the abnormal pathological changes of the BG in PD, and how computational models can help understand and advance DBS. We also describe two types of models: mathematical theoretical models and clinical predictive models. Mathematical theoretical models simulate neurons or neural networks of BG to shed light on the mechanistic principle underlying DBS, while clinical predictive models focus more on patients' outcomes, helping to adapt treatment plans for each patient and advance novel electrode designs. Finally, we provide insights and an outlook on future technologies.