Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people *** widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagn...
详细信息
Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people *** widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective *** learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and ***,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic *** the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological *** address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual ***,our model incorporates global features for extracting high-level contextual information from retinal ***,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR *** global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR *** model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.
Evolving from massive multiple-input multiple-output (MIMO) in current 5G communications, ultra-massive MIMO emerges as a seminal technology for fulfilling more stringent requirements of future 6G communications. Howe...
详细信息
This study explores a feature-engineering approach for classifying skin lesions as benign or malignant. Many other approaches regarding feature extraction can be applied: color, texture, shape, Gabor filters, Histogra...
详细信息
In distributed computing by mobile robots, robots are deployed over a region, continuous or discrete, operating through a sequence of look-compute-move cycles. An extensive study has been carried out to understand the...
详细信息
This paper presents StreamTag, a platform designed for the efficient management of labeled data in healthcare environments, particularly for activity recognition systems in residential and nursing home settings. Human...
详细信息
Classifying a person's emotional states is done using facial emotion recognition. The goal is to classify each face image into one of the 7 types of facial emotions: fear, disgust, surprise, sadness, neutral, happ...
详细信息
A major obstacle in the face of increasingly complex cyberattacks is network security. Proactive security measures require effective intrusion detection systems (IDS) that can precisely classify and categorize network...
详细信息
ISBN:
(纸本)9791188428137
A major obstacle in the face of increasingly complex cyberattacks is network security. Proactive security measures require effective intrusion detection systems (IDS) that can precisely classify and categorize network threats. In order to improve network attack detection and classification, this paper proposes a reliable method utilizing a Feedforward Neural Network (FFNN) supplemented with Adaptive Synthetic (ADASYN) sampling. We created a model using the UNSWNB15 dataset that efficiently handles high-dimensional datasets by preprocessing data using a combination of polynomial feature transformation and one-hot encoding. The FFNN model is optimized for binary and multi-class classification tasks. It consists of layers of dense units with dropout and batch normalization. Our method’s efficacy is proven by rigorous training and validation procedures, where the model significantly increased its ability to handle class imbalances and improve classification accuracy. The synthesis of new training data by ADASYN was crucial in improving model performance, especially in underrepresented classes. Evaluation measures that highlight the potential of deep learning in network security applications are ROC-AUC scores and classification reports, which show a notable improvement in our IDS’s detection capabilities. The results show that advanced machine learning techniques can be used to enhance conventional intrusion detection systems and provide a means to build stronger network security designs. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.
Medical data security refers to protecting and safeguarding sensitive patient data in healthcare. It encompasses various measures and protocols to ensure medical information’s confidentiality, integrity, and availabi...
详细信息
Medical data security refers to protecting and safeguarding sensitive patient data in healthcare. It encompasses various measures and protocols to ensure medical information’s confidentiality, integrity, and availability. This includes medical imaging data, electronic health records (EHRs), medical test results, patient demographics, and other personally identifiable information (PII). This paper introduces a medical data security framework based on key generation by deep learning-based methods, quantum key exchange, and modified Advanced Encryption Standard AES, which is a deep learning approach for random number generation through encryption keys. Medical data security is important in the following ways. For example, it holds the patient’s data confidential because it won’t allow unauthorised access and disclosure of individual health information, data breaches, and identity theft. This technology generates secure, unpredictable sequences of numbers for encryption keys by using various deep-learning classifiers. Traditionally, random number generators rely on algorithms or some physical process for randomness. It’s another area where deep learning becomes an alternative approach, and its basis is on how much neural networks can be a good learner of the pattern and produce random sequences. The randomly generated number in this protocol is the key in quantum key exchange. It is just a proposed framework using the BB84 protocol and putting down its principles based on the laws of quantum mechanics to ensure that keys would safely be exchanged to keep integrity and confidentiality in transferred data. AES algorithm replaces the conventional mix column operation with a low-complex algorithm for better performance. For medical data applications, the suggested framework offers a novel, hybrid encryption model that outperforms conventional security, effectiveness, and scalability techniques. It guarantees a future-proof solution that can handle both present and upcoming
To synthesize a safe and optimal controller for switched hybrid systems, one can first synthesize a shield that ensures safety, and then apply reinforcement learning within the constraints of the shield to obtain the ...
详细信息
Recess gate etching is a critical technique for achieving enhancement-mode (E-mode) AlGaN/GaN high-electron mobility transistors (HEMTs) because the interface is susceptible to the etching damage. This study fabricate...
详细信息
暂无评论