Optical Memory and Neural Networks最新文献_第2页

Hybrid Attention Based Shuffle-Net V2 with Global Convolutional Context Networks and Improved Pyramid Scene Parsing Network for Image Forgery Detection 基于全局卷积上下文网络和改进金字塔场景分析网络的混合注意力的Shuffle-Net V2图像伪造检测

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-03-26 DOI: 10.3103/S1060992X25601459

Henerita Khumallambam, Durgamohon Polem, Rajeev Rajkumar

{"title":"Hybrid Attention Based Shuffle-Net V2 with Global Convolutional Context Networks and Improved Pyramid Scene Parsing Network for Image Forgery Detection","authors":"Henerita Khumallambam, Durgamohon Polem, Rajeev Rajkumar","doi":"10.3103/S1060992X25601459","DOIUrl":"10.3103/S1060992X25601459","url":null,"abstract":"Image forgery detection is the process of identifying manipulated or altered images to determine their authenticity, ensuring the integrity of digital media. Image forgery was predicted to maintain trust in digital media, prevent misinformation, and ensure the credibility of visual evidence in various fields like journalism and law enforcement. Traditional methods for predicting image forgery relied on manual inspection and basic image processing methods, those techniques were time-consuming, required expert knowledge, and were prone to human error, making them less reliable and efficient. Recently presented Artificial Intelligence (AI) techniques, automate the detection process by learning from large datasets, offering increased accuracy and faster processing times. However, such methods need large amounts of labelled data and a good amount of computational power to train the models properly. To address these limitations, proposed Global Convolutional Context Networks (GCCNet) were employed to identify a fake images. The image is first taken from a dataset that was used to detect copy moves. The Quantum Wavelet Transform Filter (QWTF) and RetiNex algorithm are used to pre-process the input image. That is the original image’s noise is eliminated using QWTF, and the pixel contrast is improved using RetiNex. The copied portion of the pre-processed images is then segmented using the Pyramid Scene Parsing Network (CAP-PSPNet), which is based on Contour Aware Processing to make the segmentation edges sharper. The image’s segmented portion is then passed to a hybrid Attention-based Shuffle-Net V2 (ATSNetV2) with Global Convolutional Context Networks (GCCNet) to predict real or fake images. As a result, the model attained an accuracy of 96.60%, an error rate of 3.40%, and F1-score of 96.7%. These highlight the proposed model offer high precision and reliability in image forgery detection.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"35 1","pages":"223 - 236"},"PeriodicalIF":0.8,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid QRE-RHIBE Encryption with Capability Based Access Control Model and Optimized ENN for Secure EHR Retrieval and Disease Detection in a Healthcare Cloud 混合QRE-RHIBE加密与基于能力的访问控制模型和优化的ENN，用于医疗保健云中的安全EHR检索和疾病检测

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-03-26 DOI: 10.3103/S1060992X25600211

Venkata Ramana Kaneti, P. Neelakantan, Malige Gangappa

{"title":"Hybrid QRE-RHIBE Encryption with Capability Based Access Control Model and Optimized ENN for Secure EHR Retrieval and Disease Detection in a Healthcare Cloud","authors":"Venkata Ramana Kaneti, P. Neelakantan, Malige Gangappa","doi":"10.3103/S1060992X25600211","DOIUrl":"10.3103/S1060992X25600211","url":null,"abstract":"Healthcare practitioners use Electronic Health Records (EHRs), which are digital records of a patient’s medical history that are kept up to date, to manage patient care. Integration of cloud computing in healthcare enables efficient storage, retrieval, and analysis of EHRs while ensuring robust security and enabling advanced disease detection. These days, security and control over data access are some of the main issues with cloud storage, particularly in the medical industry. To avoid these challenges Optimized Deep learning approach with hybrid cryptography algorithm is developed to secure EHR retrieval and disease detection. Initially, EHR data is collected and pre-processed using Linear Non-Gaussian Acyclic Model (LiNGAM) to fill the missing values and Local Context Normalization (LCN) approach to normalize the data. Then Modified Elman Neural Network (MENN) is used to detect the disease. To enhance the performance of Elman Neural Network, Social Spider Optimization Algorithm (SSOA) is utilized for optimally selecting the weight decay and dropout rate. Following that, to improve the security of data and safeguard patient privacy in the cloud server, a QRE-RHIBE is utilized. Quantum Resistant Encryption is used to generate a keys and the RHIBE is used for both encryption and decryption process based on the generated key. Then for accessing the data stored in the cloud server, Capability based Access Control Mechanism (CBACM) is employed for identifying and removing unwanted users’ access. The model that employed, which achieves an accuracy of 98.53%, precision of 98.02% and execution time of 1.2 sec. This approach ensures data privacy, precise access control, and enhanced diagnostic accuracy which promoting trust and innovation in healthcare systems.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"35 1","pages":"113 - 129"},"PeriodicalIF":0.8,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Attention-Residual Multi-Modal Fusion Framework for Crisis Categorization in Social Media Feeds 关注-残差多模态融合框架在社交媒体提要中的危机分类

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-03-26 DOI: 10.3103/S1060992X25600764

S. Sheeba Rachel, S. Srinivasan

{"title":"Attention-Residual Multi-Modal Fusion Framework for Crisis Categorization in Social Media Feeds","authors":"S. Sheeba Rachel, S. Srinivasan","doi":"10.3103/S1060992X25600764","DOIUrl":"10.3103/S1060992X25600764","url":null,"abstract":"Crisis categorization in social media feeds perform an important part in modern disaster management and response techniques. With the increasing employ of social platforms as a primary source of information during crises, effective categorization algorithms are essential for quickly and accurately assessing the severity and impact of events. This study introduces the Attention Residual Multi Modal (ARMM) Fusion Framework, which addresses difficulties in MM data processing for damage assessment. For image processing, the system uses Visual Refinement with Feature Forge, which includes Bilateral Filtering for noise reduction and edge preservation, Bicubic Interpolation for upscaling, and Residual Network with Drop Block for detailed and robust image feature extraction. The framework cleans and pre-processes text using an LSTM-Residual with Embedding Network, converting it into compact vector representations, and then uses residual LSTM connections to capture temporal dependencies and maintain feature integrity for robust text feature extraction. Image and text information are then combined and processed using a MM channel attention method, which improves sensitivity to informative features. The proposed method produces outstanding performance metrics, including precision of 98.00%, recall of 94.12%, F1 score of 95.86%, and accuracy of 96.13%. This method efficiently identifies damage severity (severe, medium, or minor) in tweets that include both images and text, leading risk management strategies (rescue, volunteering and contribution) depending on the assessed damage.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"35 1","pages":"1 - 17"},"PeriodicalIF":0.8,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reinforcement-Trained Neural Network for Various Manufacturers AV Mixed Traffic Flow Simulation 多厂商自动驾驶混合交通流仿真的强化训练神经网络

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-03-26 DOI: 10.3103/S1060992X25603173

O. P. Bobrovskaya, T. V. Gavrilenko, V. A. Galkin

{"title":"Reinforcement-Trained Neural Network for Various Manufacturers AV Mixed Traffic Flow Simulation","authors":"O. P. Bobrovskaya, T. V. Gavrilenko, V. A. Galkin","doi":"10.3103/S1060992X25603173","DOIUrl":"10.3103/S1060992X25603173","url":null,"abstract":"The problem of modeling the movement of autopiloted vehicles in a mixed traffic stream of autopilots of various manufacturers, in which there are no collisions, is solved. A neural network model is proposed that implements reinforcement learning for an unmanned vehicle model integrated into a microscopic model of a mixed traffic flow. Computational experiments are being conducted with the proposed model. It was hypothesized that trained agents would work worse together than with the original automated objects in which they were trained. In the first experiment, for a closed multi-corridor circle, the percentage of implementation of trained agents gradually increased. In the second experiment, different trained agents were trained on a single-lane circle and then launched together. In the third experiment, agents are trained in different environments and run together on a track with multiple corridors. As a result of the experiments, the hypothesis was not confirmed. When using different learning environments, agents trained in these environments interact more effectively with each other in a common system than with other types of agents.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"35 1","pages":"55 - 77"},"PeriodicalIF":0.8,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Caged CrafText: Language-Grounded Safety Constraints for Multimodal Reinforcement Learning in CrafText Caged CrafText：基于语言的安全约束在CrafText中的多模态强化学习

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-03-26 DOI: 10.3103/S1060992X25602799

G. Gorbov, D. Lukashevsky, A. Skrynnik, A. Panov

{"title":"Caged CrafText: Language-Grounded Safety Constraints for Multimodal Reinforcement Learning in CrafText","authors":"G. Gorbov, D. Lukashevsky, A. Skrynnik, A. Panov","doi":"10.3103/S1060992X25602799","DOIUrl":"10.3103/S1060992X25602799","url":null,"abstract":"Safe reinforcement learning under natural language instructions remains challenging. Current benchmarks are limited by providing only safety constraints in natural language while using structured goal representations, and by focusing on simple navigation tasks in static environments. We introduce Caged CrafText, the first benchmark where both task objectives and safety constraints are specified entirely through natural language. Our benchmark features complex, long-horizon tasks requiring reasoning in dynamic environments, and is structured around two dataset levels: the Main dataset, designed to evaluate language understanding and safe exploration capabilities across aggregated constraint types, and the Debug dataset, which enables detailed diagnosis of specific failure modes in individual constraint scenarios. Evaluation of existing safety approaches reveals their insufficient safe exploration capability, highlighting the need for improved methods capable of handling complex language-guided constraints. Our experiments also demonstrate that while Large Language Model(LLM) agents show promising reasoning capabilities, they suffer from grounding issues that lead to frequent constraint violations.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"35 1","pages":"18 - 30"},"PeriodicalIF":0.8,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modelling the Tight Focusing of Laser Beams with Radial Polarization Using Binary Mask with Optimal Configuration 用最优构型二元掩模模拟径向偏振激光束的紧密聚焦

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-02-27 DOI: 10.3103/S1060992X25602337

D. Y. Kalashnikov, S. S. Stafeev, V. V. Kotlyar

引用次数: 0

Simulating the Behavior of Forest Animal Groups to Generate Synthetic Data in Unreal Engine 5 在虚幻引擎5中模拟森林动物群体的行为以生成合成数据

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-02-27 DOI: 10.3103/S1060992X25602994

K. E. Vorobyev, D. A. Sharin, L. A. Taskina

{"title":"Simulating the Behavior of Forest Animal Groups to Generate Synthetic Data in Unreal Engine 5","authors":"K. E. Vorobyev, D. A. Sharin, L. A. Taskina","doi":"10.3103/S1060992X25602994","DOIUrl":"10.3103/S1060992X25602994","url":null,"abstract":"The article presents the development of a system for simulating the behavior of groups of forest animals in the three-dimensional environment of Unreal Engine 5 in order to generate synthetic data for computer vision tasks. The simulation includes realistic animal behavior, group dynamics, and the use of a virtual drone with a camera to simulate aerial photography. Annotations are automatically generated for each object, suitable for subsequent training of neural networks. The experiments demonstrated the effectiveness of mixed datasets containing both real and synthetic images when training the YOLO model. The results obtained confirm that the generation of synthetic data can significantly improve the quality of learning with a limited amount of real data. The experiments demonstrated that adding 30% synthetic data to real datasets increased mAP50 from 0.1866 to 0.3605, while Precision improved from 0.7529 to 0.8411. In contrast, training solely on synthetic data reduced mAP50 to 0.0286, confirming the necessity of combining real and generated data. The results indicate that synthetic data can significantly enhance training effectiveness under conditions of limited real-world images.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"34 3","pages":"S450 - S456"},"PeriodicalIF":0.8,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Random Bit Generation in VCSEL with Delayed Optoelectronic Feedback 延迟光电反馈VCSEL中随机位的产生

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-02-27 DOI: 10.3103/S1060992X25601964

A. A. Krents, E. A. Yarunova, N. E. Molevich

引用次数: 0

Methods of Anomalous Data Detection in Datasets 数据集中异常数据的检测方法

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-02-27 DOI: 10.3103/S1060992X25603045

Akbar Soliev, Akmal Akhatov, Akbar Rashidov

引用次数: 0

Modeling the Behavior of a Flock of Birds to Generate Synthetic Data in Unreal Engine 5 在虚幻引擎5中建模一群鸟的行为以生成合成数据

IF 0.8

Optical Memory and Neural Networks Pub Date : 2026-02-27 DOI: 10.3103/S1060992X25700274

D. A. Sharin, K. E. Vorobyev, T. D. Kazarkin, L. A. Taskina

{"title":"Modeling the Behavior of a Flock of Birds to Generate Synthetic Data in Unreal Engine 5","authors":"D. A. Sharin, K. E. Vorobyev, T. D. Kazarkin, L. A. Taskina","doi":"10.3103/S1060992X25700274","DOIUrl":"10.3103/S1060992X25700274","url":null,"abstract":"The paper proposes a system for modeling the collective behavior of flocks of birds to generate synthetic data in Unreal Engine 5. The system provides flexible adjustment of flock dynamics parameters, including species, speed and flight radius, as well as simulation of complex interactions in a virtual environment. Automated data markup is performed in YOLO (You Only Look Once) formats and with the preservation of spatial metadata of objects. A comparative analysis of the influence of the proportion of synthetic data in training samples on the quality of detection of computer vision models using the example of YOLOv11 is carried out. The results showed that the inclusion of up to 60 to 80 percent of synthetically generated data in the training dataset allows achieving an optimal balance between the accuracy of the model and the cost of collecting real data. The experiments showed that combining real and synthetic data significantly improves detection quality. For example, with 20% real and 80% synthetic data the YOLO v11 model achieved mAP@0.5 = 0.7157, Precision = 0.8157, and Recall = 0.6396, which substantially exceeds the results obtained when training only on real images. The developed system opens up prospects for application in the tasks of airspace monitoring, environmental research and virtual reality.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"34 3","pages":"S457 - S464"},"PeriodicalIF":0.8,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0