Search results

This work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λ_max method for weight initialization, as a data normalization technique, to achieve high accuracy of classification.

The major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λ_max method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λ_max method.

The effectiveness of the proposed FDCNN model with λ_max method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795.

The proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λ_max method.

Contributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition.

A novel FDCNN architecture is implemented with appropriate FAL kernel structures.

A stroke is a serious, life-threatening condition that occurs when the blood supply to a part of the brain is cut off. The earlier a stroke is treated, the less damage is likely to occur. One of the methods that can lead to faster treatment is timely and accurate prediction and diagnosis. This paper aims to compare the binary integer programming-data envelopment analysis (BIP-DEA) model and the logistic regression (LR) model for diagnosing and predicting the occurrence of stroke in Iran.

In this study, two algorithms of the BIP-DEA and LR methods were introduced and key risk factors leading to stroke were extracted.

The study population consisted of 2,100 samples (patients) divided into six subsamples of different sizes. The classification table of each algorithm showed that the BIP-DEA model had more reliable results than the LR for the small data size. After running each algorithm, the BIP-DEA and LR algorithms identified eight and five factors as more effective risk factors and causes of stroke, respectively. Finally, predictive models using the important risk factors were proposed.

The main objective of this study is to provide the integrated BIP-DEA algorithm as a fast, easy and suitable tool for evaluation and prediction. In fact, the BIP-DEA algorithm can be used as an alternative tool to the LR model when the sample size is small. These algorithms can be used in various fields, including the health-care industry, to predict and prevent various diseases before the patient’s condition becomes more dangerous.

As social networking services are popular, the need for recognizing reliable people has become the main concern. Quantifying the relationships between the users of social networks is also one of the important challenges with the increasing number of users. So, trust plays an important role in social networks in order to recognize trustworthy people. The purpose of this paper is to propose an approach to recognize trustworthy users and protect users from abuse by untrustable users.

In this paper, the authors suggest a method to measure the trust value between users of social networks based on call log histories such as abundance, novelty, and sincerity and quality of service (QoS) requirements such as accessibility, response ability, tend to respond, and agility. After that, the authors calculate error-hit, precision, and recall to evaluate the trust value.

The results indicate that the proposed approach has better performance in terms of error-hit, precision, and recall than FIFO, combined, QoS-based, and call log-based method.

In this paper, the trust issue in social networks is pointed out and a new approach to evaluate the trust value is proposed based on call log histories and QoS requirements.

Cloud services have become very popular among researchers and people recently. In such a scenario, identifying reliable cloud services has become very important. The trust value plays a significant role in recognizing reliable providers. The purpose of this paper is to propose a new method to evaluate the trust metric among the cloud providers. The main goal is to increase the precision and accuracy of the trust evaluation method in the cloud environments.

This paper evaluates the trust metric among the cloud providers and entities by grouping the services and using a behavioral graph. Four parameters, availability, reliability, interaction evolution and identity, are used for evaluating the trust value. The performance of the proposed method is assessed using a simulator which is programmed in the cloud Azure 2013 based on C# codes.

The method is evaluated through various experiments in terms of precision, recall, error-hit, reliability and availability. The obtained results show that the proposed method has better reliability and availability than the FIFO and QoS models. Also, the results show that increasing the number of groups leads to increasing values of trust, precision and availability, and decreasing values of error-hit.

This paper proposes a trust evaluation method in the cloud environment by grouping the services and using a behavioral graph for improving the amount of availability, error-hit, precision and reliability values.