Network-Computation in Neural Systems最新文献

In contemporary times, content-based image retrieval (CBIR) techniques have gained widespread acceptance as a means for end-users to discern and extract specific image content from vast repositories. However, it is noteworthy that a substantial majority of CBIR studies continue to rely on linear methodologies such as gradient-based and derivative-based edge detection techniques. This research explores the integration of bioinspired Spiking Neural Network (SNN) based edge detection within CBIR. We introduce an innovative, computationally efficient SNN-based approach designed explicitly for CBIR applications, outperforming existing SNN models by reducing computational overhead by 2.5 times. The proposed SNN-based edge detection approach is seamlessly incorporated into three distinct CBIR techniques, each employing conventional edge detection methodologies including Sobel, Canny, and image derivatives. Rigorous experimentation and evaluations are carried out utilizing the Corel-10k dataset and crop weed dataset, a widely recognized and frequently adopted benchmark dataset in the realm of image analysis. Importantly, our findings underscore the enhanced performance of CBIR methodologies integrating the proposed SNN-based edge detection approach, with an average increase in mean precision values exceeding 3%. This study conclusively demonstrated the utility of our proposed methodology in optimizing feature extraction, thereby establishing its pivotal role in advancing edge centric CBIR approaches.

Demosaicking is a popular scientific area that is being explored by a vast number of scientists. Current digital imaging technologies capture colour images with a single monochrome sensor. In addition, the colour images were captured using a sensor coupled with a Colour Filter Array (CFA). Furthermore, the demosaicking procedure is required to obtain a full-colour image. Image denoising and image demosaicking are the two important image restoration techniques, which have increased popularity in recent years. Finding a suitable strategy for multiple image restoration is critical for researchers. Hence, a deep learning (DL) based image denoising and image demosaicking is developed in this research. Moreover, the Autoregressive Circle Wave Optimization (ACWO) based Demosaicking Convolutional Neural Network (DMCNN) is designed for image demosaicking. The Quantum Wavelet Transform (QWT) is used in the image denoising process. Similarly, Quantum Wavelet Transform (QWT) is used to analyse the abrupt changes in the input image with noise. The transformed image is then subjected to a thresholding technique, which determines an appropriate threshold range. Once the threshold range has been determined, soft thresholding is applied to the resulting wavelet coefficients. After that, the extraction and reconstruction of the original image is carried out using the Inverse Quantum Wavelet Transform (IQWT). Finally, the fused image is created by combining the results of both processes using a weighted average. The denoised and demosaicked images are combined using the weighted average technique. Furthermore, the proposed QWT+DMCNN-ACWO model provided the ideal values of Peak signal-to-noise ratio (PSNR), Second derivative like measure of enhancement (SDME), Structural Similarity Index (SSIM), Figure of Merit (FOM) of 0.890, and computational time of 49.549 dB, 59.53 dB, 0.963, 0.890, and 0.571, respectively.

The early diagnosis of tumour is significant in biomedical research field to lower the severity level and restrict the process extension from cancer. Moreover, the detection of early sign of cancer is undertaken with extensive research efforts that dedicated to the disclosure and recognition of tumours. However, the limited data size as well as diverse appearance of images lowered the detection performance and failed to detect complex stage of tumour. So to solve these issues, a Weighted Adaptive Random Ensemble Support Vector-based Partial Reinforcement Search (WARES-PRS) algorithm is proposed that detected bone lesions accurately and also predicted the severity level stage efficiently. Further, the detection is performed with varied stages to diminish the presence of noise and undertaken effective classification. The performance is validated with CNUH dataset that enhanced image pre-processing tasks. Despite the proposed method uncover the mutual relationships between each pixel's local texture and the overall image's global context. The detection and classification efficiency is validated with various measures and the experimental results revealed that the detection accuracy is enhanced for the proposed approach by 98.5%. The outcomes of our study have exhibited a substantial contribution to assisting physicians in the detection of knee bone tumours.

Autism Spectrum Disorder (ASD) poses a significant challenge in early diagnosis and intervention due to its multifaceted clinical presentation and lack of objective biomarkers. This research presents a novel approach, termed Neuro Connect, which integrates data-driven techniques with Bidirectional Gated Recurrent Unit (BiGRU) classification to enhance the prediction of ASD using functional Magnetic Resonance Imaging (fMRI) data. This study uses both structural and functional neuroimaging data to investigate the complex brain underpinnings of autism spectrum disorder (ASD). They use an Auto-Encoder (AE) to efficiently reduce dimensionality while retaining critical information by learning and compressing important characteristics from high-dimensional data. We treat the feature-extracted data using a BiGRU model for the classification task of predicting ASD. They provide a new optimization strategy, the Horse Herd Algorithm (HHA), and show that it outperforms other established optimizers, such SGD and Adam, in order to improve classification accuracy. The model's performance is greatly enhanced by the HHA's novel optimization technique, which more precisely refines weight modifications made during training. The proposed ASD and EEG dataset accuracy value is 99.5%, and 99.3 compared to the existing method the proposed has a high accuracy value.

Interpretable machine learning models are instrumental in disease diagnosis and clinical decision-making, shedding light on relevant features. Notably, Boruta, SHAP (SHapley Additive exPlanations), and BorutaShap were employed for feature selection, each contributing to the identification of crucial features. These selected features were then utilized to train six machine learning algorithms, including LR, SVM, ETC, AdaBoost, RF, and LR, using diverse medical datasets obtained from public sources after rigorous preprocessing. The performance of each feature selection technique was evaluated across multiple ML models, assessing accuracy, precision, recall, and F1-score metrics. Among these, SHAP showcased superior performance, achieving average accuracies of 80.17%, 85.13%, 90.00%, and 99.55% across diabetes, cardiovascular, statlog, and thyroid disease datasets, respectively. Notably, the LGBM emerged as the most effective algorithm, boasting an average accuracy of 91.00% for most disease states. Moreover, SHAP enhanced the interpretability of the models, providing valuable insights into the underlying mechanisms driving disease diagnosis. This comprehensive study contributes significant insights into feature selection techniques and machine learning algorithms for disease diagnosis, benefiting researchers and practitioners in the medical field. Further exploration of feature selection methods and algorithms holds promise for advancing disease diagnosis methodologies, paving the way for more accurate and interpretable diagnostic models.

As the number of patients increases, physicians are dealing with more and more cases of degenerative spine pathologies on a daily basis. To reduce the workload of healthcare professionals, we propose a modified Swin-UNet network model. Firstly, the Swin Transformer Blocks are improved using a residual post-normalization and scaling cosine attention mechanism, which makes the training process of the model more stable and improves the accuracy. Secondly, we use the log-space continuous position biasing method instead of the bicubic interpolation position biasing method. This method solves the problem of performance loss caused by the large difference between the resolution of the pretraining image and the resolution of the spine image. Finally, we introduce a segmentation smooth module (SSM) at the decoder stage. The SSM effectively reduces redundancy, and enhances the segmentation edge processing to improve the model's segmentation accuracy. To validate the proposed method, we conducted experiments on a real dataset provided by hospitals. The average segmentation accuracy is no less than 95%. The experimental results demonstrate the superiority of the proposed method over the original model and other models of the same type in segmenting the spinous processes of the vertebrae and the posterior arch of the spine.

Railway Point Machine (RPM) is a fundamental component of railway infrastructure and plays a crucial role in ensuring the safe operation of trains. Its primary function is to divert trains from one track to another, enabling connections between different lines and facilitating route selection. By judiciously deploying turnouts, railway systems can provide efficient transportation services while ensuring the safety of passengers and cargo. As signal processing technologies develop rapidly, taking the easy acquisition advantages of audio signals, a fault diagnosis method for RPMs is proposed by considering noise and multi-channel signals. The proposed method consists of several stages. Initially, the signal is subjected to pre-processing steps, including cropping and channel separation. Subsequently, the signal undergoes noise addition using the Random Length and Dynamic Position Noises Superposition (RDS) module, followed by conversion to a greyscale image. To enhance the data, Synthetic Minority Oversampling Technique (SMOTE) module is applied. Finally, the training data is fed into a Dual-input Attention Convolutional Neural Network (DIACNN). By employing various experimental techniques and designing diverse datasets, our proposed method demonstrates excellent robustness and achieves an outstanding classification accuracy of 99.73%.

The Internet of Things (IoT) is a network that connects various hardware, software, data storage, and applications. These interconnected devices provide services to businesses and can potentially serve as entry points for cyber-attacks. The privacy of IoT devices is increasingly vulnerable, particularly to threats like viruses and illegal software distribution lead to the theft of critical information. Ant Colony-Optimized Artificial Neural-Adaptive Tensorflow (ACO-ANT) technique is proposed to detect malicious software illicitly disseminated through the IoT. To emphasize the significance of each token in source duplicate data, the noise data undergoes processing using tokenization and weighted attribute techniques. Deep learning (DL) methods are then employed to identify source code duplication. Also the Multi-Objective Recurrent Neural Network (M-RNN) is used to identify suspicious activities within an IoT environment. The performance of proposed technique is examined using Loss, accuracy, F measure, precision to identify its efficiency. The experimental outcomes demonstrate that the proposed method ACO-ANT on Malimg dataset provides 12.35%, 14.75%, 11.84% higher precision and 10.95%, 15.78%, 13.89% higher f-measure compared to the existing methods. Further, leveraging block chain for malware detection is a promising direction for future research the fact that could enhance the security of IoT and identify malware threats.

In this paper, Quaternion Fractional Order Meixner Moments-based Deep Siamese Domain Adaptation Convolutional Neural Network-based Big Data Analytical Technique is proposed for improving Cloud Data Security (DSDA-CNN-QFOMM-BD-CDS). The proposed methodology comprises six phases: data collection, transmission, pre-processing, storage, analysis, and security of data. Big data analysis methodologies start with the data collection phase. Deep Siamese domain adaptation convolutional Neural Network (DSDA-CNN) is applied to categorize the types of attacks in the cloud database during the data analysis process. During data security phase, Quaternion Fractional Order Meixner Moments (QFOMM) is employed to protect the cloud data for encryption with decryption. The proposed method is implemented in JAVA and assessed using performance metrics, including precision, sensitivity, accuracy, recall, specificity, f-measure, computational complexity information loss, compression ratio, throughput, encryption time, decryption time. The performance of the proposed method offers 23.31%, 15.64%, 18.89% better accuracy and 36.69%, 17.25%, 19.96% less information loss. When compared to existing methods like Fractional order discrete Tchebyshev encryption fostered big data analytical model to maximize the safety of cloud data depend on Enhanced Elman spike neural network (EESNN-FrDTM-BD-CDS), an innovative scheme architecture for safe authentication along data sharing in cloud enabled Big data Environment (LZMA-DBSCAN-BD-CDS).

Brain-controlled robotic arm systems are designed to provide a method of communication and control for individuals with limited mobility or communication abilities. These systems can be beneficial for people who have suffered from a spinal cord injury, stroke, or neurological disease that affects their motor abilities. The ability of a person to control a robotic arm to reach and grasp multiple objects using their brain signals. This technology involves the use of an electroencephalogram (EEG) cap that captures the electrical activity in the user's brain, which is then processed by an artificial intelligent to translate it into commands that control the movements of the robotic arm. With this technology, individuals who are unable to move their limbs due to paralysis or other conditions can still perform daily activities such as feeding themselves, drinking from a glass, or grasping objects. In this paper, we propose an artificial intelligent-based control strategy for reach and grasp of multi-objects using brain-controlled robotic arm system. The proposed control strategy consists of threefold process: feature extraction, feature optimization, and control strategy classification. Initially, we design an improved ResNet pre-trained architecture for deep feature extraction from the given EEG signal.