The robustness of graph neural networks（GNNs） is a critical research topic in deep *** researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theoretical...
详细信息
The robustness of graph neural networks（GNNs） is a critical research topic in deep *** researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theoretical analysis on the principle of *** order to tackle the weakness of current robustness designing methods,this paper gives new insights into how to guarantee the robustness of GNNs.A novel regularization strategy named Lya-Reg is designed to guarantee the robustness of GNNs by Lyapunov *** results give new insights into how regularization can mitigate the various adversarial effects on different graph *** experiments on various public datasets demonstrate that the proposed regularization method is more robust than the state-of-theart methods such as L1-norm,L2-norm,L2-norm,Pro-GNN,PA-GNN and GARNET against various types of graph adversarial attacks.
Histopathological images serve as pivotal assets within the domain of breast cancer diagnosis, demanding profound comprehension for precise interpretation. This paper introduces a histopathological image classificatio...
详细信息
Phishing is one form of cyber attack used to obtain sensitive information from targeted individuals. Through this process, the attacker masquerades as a domain similar to an official legitimate website. Perpetrators c...
详细信息
Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple *** these achieve-ments,LLMs have inherent limitat...
详细信息
Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple *** these achieve-ments,LLMs have inherent limitations including outdated information,hallucinations,inefficiency,lack of interpretability,and challenges in domain-specific *** address these issues,this survey explores three promising directions in the post-LLM era:knowledge empowerment,model collaboration,and model ***,we examine methods of integrating external knowledge into LLMs to enhance factual accuracy,reasoning capabilities,and interpretability,including incorporating knowledge into training objectives,instruction tuning,retrieval-augmented inference,and knowledge ***,we discuss model collaboration strategies that leverage the complementary strengths of LLMs and smaller models to improve efficiency and domain-specific performance through techniques such as model merging,functional model collaboration,and knowledge ***,we delve into model co-evolution,in which multiple models collaboratively evolve by sharing knowledge,parameters,and learning strategies to adapt to dynamic environments and tasks,thereby enhancing their adaptability and continual *** illustrate how the integration of these techniques advances AI capabilities in science,engineering,and society—particularly in hypothesis development,problem formulation,problem-solving,and interpretability across various *** conclude by outlining future pathways for further advancement and applications.
Glaucoma is currently one of the most significant causes of permanent blindness. Fundus imaging is the most popular glaucoma screening method because of the compromises it has to make in terms of portability, size, an...
详细信息
Glaucoma is currently one of the most significant causes of permanent blindness. Fundus imaging is the most popular glaucoma screening method because of the compromises it has to make in terms of portability, size, and cost. In recent years, convolution neural networks (CNNs) have revolutionized computer vision. Convolution is a "local" CNN technique that is only applicable to a small region surrounding an image. Vision Transformers (ViT) use self-attention, which is a "global" activity since it collects information from the entire image. As a result, the ViT can successfully gather distant semantic relevance from an image. This study examined several optimizers, including Adamax, SGD, RMSprop, Adadelta, Adafactor, Nadam, and Adagrad. With 1750 Healthy and Glaucoma images in the IEEE fundus image dataset and 4800 healthy and glaucoma images in the LAG fundus image dataset, we trained and tested the ViT model on these datasets. Additionally, the datasets underwent image scaling, auto-rotation, and auto-contrast adjustment via adaptive equalization during preprocessing. The results demonstrated that preparing the provided dataset with various optimizers improved accuracy and other performance metrics. Additionally, according to the results, the Nadam Optimizer improved accuracy in the adaptive equalized preprocessing of the IEEE dataset by up to 97.8% and in the adaptive equalized preprocessing of the LAG dataset by up to 92%, both of which were followed by auto rotation and image resizing processes. In addition to integrating our vision transformer model with the shift tokenization model, we also combined ViT with a hybrid model that consisted of six different models, including SVM, Gaussian NB, Bernoulli NB, Decision Tree, KNN, and Random Forest, based on which optimizer was the most successful for each dataset. Empirical results show that the SVM Model worked well and improved accuracy by up to 93% with precision of up to 94% in the adaptive equalization preprocess
This study aims to evaluate how SiO2 fiber additions affect the mechanical properties of hybrid nanocomposites composed of polypropylene (PP), sisal, and Kevlar fibers. Different concentrations of SiO2 are integrated ...
详细信息
Automatic timetable generation is a complex optimization problem with practical applications in various domains such as education, healthcare, and event management. The challenge lies in efficiently scheduling activit...
详细信息
ISBN:
(纸本)9798350318609
Automatic timetable generation is a complex optimization problem with practical applications in various domains such as education, healthcare, and event management. The challenge lies in efficiently scheduling activities while satisfying numerous constraints and objectives. In this study, we propose an OptiSchedule algorithm for automatic timetable generation. The algorithm employs a combination of heuristic search techniques and metaheuristic optimization methods to iteratively improve timetable solutions. It starts with initializing a timetable grid and iteratively refines the solution by generating neighbouring solutions and selecting the most promising ones based on an evaluation function. Through extensive testing and validation, our OptiSchedule algorithm demonstrates significant improvements in timetable quality and efficiency compared to existing approaches. The algorithm effectively minimizes conflicts, optimizes resource utilization, and balances workload distribution. Furthermore, it provides flexibility for users to input constraints and preferences, allowing customization to specific scheduling requirements. The OptiSchedule algorithm represents a significant advancement in the field of automatic timetable generation. Its ability to produce high-quality schedules while considering complex constraints makes it a valuable tool for educational institutions, healthcare facilities, and businesses alike. By streamlining scheduling processes and optimizing resource allocation, OptiSchedule contributes to improved operational efficiency and overall organizational performance. Through rigorous experimentation and evaluation, our study demonstrates the effectiveness of the OptiSchedule algorithm in improving timetable quality and reducing scheduling overhead. Compared to traditional methods, OptiSchedule generates timetables with fewer conflicts and better resource utilization, leading to enhanced productivity and satisfaction among stakeholders. Moreover, its fl
Chatbots use artificial intelligence (AI) and natural language processing (NLP) algorithms to construct a clever system. By copying human connections in the most helpful way possi-ble, chatbots emulate individuals and...
详细信息
This paper investigates the performance of solar PV system by implementing MPPT algorithm. The IV and PV characteristics of solar photovoltaic system have been analyzed for various parameters of temperature and irradi...
详细信息
Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various ***,certain limitations need to be addressed *** provisioning of detection mechanism wit...
详细信息
Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various ***,certain limitations need to be addressed *** provisioning of detection mechanism with learning approaches provides a better solution more broadly by saluting multi-objective *** bots’patterns or features over the network have to be analyzed in both linear and non-linear *** linear and non-linear features are composed of high-level and low-level *** collected features are maintained over the Bag of Features(BoF)where the most influencing features are collected and provided into the classifier ***,the linearity and non-linearity of the threat are evaluated with Support Vector Machine(SVM).Next,with the collected BoF,the redundant features are eliminated as it triggers overhead towards the predictor ***,a novel Incoming data Redundancy Elimination-based learning model(RedE-L)is built to classify the network features to provide robustness towards BotNets *** simulation is carried out in MATLAB environment,and the evaluation of proposed RedE-L model is performed with various online accessible network traffic dataset(benchmark dataset).The proposed model intends to show better tradeoff compared to the existing approaches like conventional SVM,C4.5,RepTree and so ***,various metrics like Accuracy,detection rate,Mathews Correlation Coefficient(MCC),and some other statistical analysis are performed to show the proposed RedE-L model's *** F1-measure is 99.98%,precision is 99.93%,Accuracy is 99.84%,TPR is 99.92%,TNR is 99.94%,FNR is 0.06 and FPR is 0.06 respectively.
暂无评论