Formalization for Granular Computing Based on Logical Formulas

In order to make formalization for granular computing,some kinds of formulas are constructed on a universe by a logical method. Every formula expresses a property, and can separate a semantic set which consists of all of the objects satisfying the formula.Therefore a granular space on the universe is produced based on the formulas, and the semantic sets separated by the formulas are taken as a formal definition for granules,and are called abstract granules.Furthermore,it is proved that any specific granule from an extended mathematical system can be formalized into an abstract granule,the conclusions is obtained that specific granules from approximate spaces and information systems can also be formalized into abstract granules. Based on a granular space and abstract granules,granular computing is defined,which finally realizes the goal of formalization for granular computing.

User Informatics Optimized Search and Retrieval-Congestion Avoidance Scheme for 4G Networks

The objective of 4G network is to provide best services to the users which in turn made the performance of existing network more critical. Further, the large traffic generated in such networks creates congestion resulting in overloading of the system. Frequent delays, loss of packets, and in addition the number of retransmission/paging also increases the computational cost of the system. This paper proposes a novel way to reduce overloading and retrieval mechanism for VLR through optimized search, based on the information of users mobility pattern (User profiles based (UPB)) to track the user. This not only improves the overall performance of the system, especially in the events when the visitor location register (VLR) is overloaded due to heavy traffic and congestion of the network. It was also established through simulation studies that the proposed UPB scheme optimizes the search and reduces the average waiting time in a queue. In addition, the provision of VLRW (waiting visitor location register) avoids the overloading of main VLR and provides a recovery/retrieval mechanism for VLR failure.

Improved Manta Ray Foraging Optimizer-based SVM for Feature Selection Problems:A Medical Case Study

Support Vector Machine(SVM)has become one of the traditional machine learning algorithms the most used in prediction and classification tasks.However,its behavior strongly depends on some parameters,making tuning these parameters a sensitive step to maintain a good performance.On the other hand,and as any other classifier,the performance of SVM is also affected by the input set of features used to build the learning model,which makes the selection of relevant features an important task not only to preserve a good classification accuracy but also to reduce the dimensionality of datasets.In this paper,the MRFO+SVM algorithm is introduced by investigating the recent manta ray foraging optimizer to fine-tune the SVM parameters and identify the optimal feature subset simultaneously.The proposed approach is validated and compared with four SVM-based algorithms over eight benchmarking datasets.Additionally,it is applied to a disease Covid-19 dataset.The experimental results show the high ability of the proposed algorithm to find the appropriate SVM’s parameters,and its acceptable performance to deal with feature selection problem.

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.