Recent decade, Parkinson’s disease (PD),which impairs the life quality for millions of older people worldwide, has quickly emerged as a serious condition affecting the brain and spinal cord. Appropriate treatment and...
Recent decade, Parkinson’s disease (PD),which impairs the life quality for millions of older people worldwide, has quickly emerged as a serious condition affecting the brain and spinal cord. Appropriate treatment and management of the disease depend on early discovery and an accurate diagnosis. Due to PD’s close resemblance to other neurological disorders, the precise diagnosis of PD has until now been difficult. These same characteristics account for 25% of incorrect manual PD diagnosis. Brain MRI (Magnetic Resonance Imaging) has shown great potential in the detection and diagnosis of Parkinson’s disease. Proposed study uses convolutional neural networks (CNN), a type of deep neural network architecture, to classify Parkinson disease in order to differentiate between PD patients and healthy controls. Parkinson Progression Markers Initiative (PPMI)dataset is used as input to classify the disease. Here, the median filtering technique is used to remove the noise from the images and preserve the edges which help to provide a letter image and able to predict it easily. The Parkinson disease recognition system is done by using CNN. Accuracy, sensitivity, specificity, and AUC (Area Under Curve) are used to assess the performance of the suggested approach.
Feature reduction is an important aspect of big data analytics today, and neighborhood rough set is a classic attribute reduction method. The traditional neighborhood rough set finds out the radius suitable for proble...
详细信息
The COVID-19 pandemic underscored the necessity for disease surveillance using group testing. Novel Bayesian methods using lattice models were proposed, which offer substantial improvements in group testing efficiency...
The COVID-19 pandemic underscored the necessity for disease surveillance using group testing. Novel Bayesian methods using lattice models were proposed, which offer substantial improvements in group testing efficiency by precisely quantifying uncertainty in diagnoses, acknowledging varying individual risk and dilution effects, and guiding optimally convergent sequential pooled test selections using a Bayesian Halving Algorithm. Computationally, however, Bayesian group testing poses considerable challenges as computational complexity grows exponentially with sample size. This can lead to shortcomings in reaching a desirable scale without practical limitations. We propose a new framework for scaling Bayesian group testing based on Spark: SBGT. We show that SBGT is lightning fast and highly scalable. In particular, SBGT is up to 376x, 1733x, and 1523x faster than the state-of-the-art framework in manipulating lattice models, performing test selections, and conducting statistical analyses, respectively, while achieving up to 97.9% scaling efficiency up to 4096 CPU cores. More importantly, SBGT fulfills our mission towards reaching applicable scale for guiding pooling decisions in wide-scale disease surveillance, and other large scale group testing applications.
The Internet of Things (IoT) applied solutions are changing the way the world perceives technology. IoT devices are now being used in a wide range of applications to transfer or share relevant information, hence reduc...
详细信息
The increasing penetration of renewable energy poses significant challenges to power grid reliability. There have been increasing interests in utilizing financial tools, such as insurance, to help end-users hedge the ...
详细信息
Due to the tremendous increase in vehicles, more attention is required to Intelligent Transport Systems (ITS). License Plate Recognition (LPR) is one such method in ITS. Although there are several researches on LPR, s...
详细信息
ISBN:
(数字)9798331518394
ISBN:
(纸本)9798331518400
Due to the tremendous increase in vehicles, more attention is required to Intelligent Transport Systems (ITS). License Plate Recognition (LPR) is one such method in ITS. Although there are several researches on LPR, still the issues are partially solved. This is because license plate images suffer from low illumination, side view, etc. This paper developed a method to recognize license plates. It consists of license plate localization, segmentation and recognition. A Convolutional Neural Network (CNN) is designed for recognition. The proposed method is tested on the Chinese City Parking dataset (CCPD), Chinese License Plate dataset (CLPD), Application Oriented License Plate (AOLP) and PKUdatadatasets. The performance of the proposed LPR method is evaluated using accuracy. It outperforms other recent methods by achieving an accuracy of 95%
Early recurrence (ER) after surgery is one of the main causes of death in Hepatocellular Carcinoma (HCC). Making an effective prediction of the risk of ER is important in developing treatment strategies. The...
详细信息
English Language-Based Virtual Assistants (ELB-VAs) are AI-powered systems designed to comprehend and respond to user queries in the English language, exemplified by virtual assistants like Siri or Alexa. The need for...
详细信息
Machine Learning (ML) algorithms have experienced a significant increase in popularity owing to the digitisation of analogue processes and other technological advancements, like the Internet of Things (IoT). Dependabl...
详细信息
ISBN:
(数字)9798331508456
ISBN:
(纸本)9798331508463
Machine Learning (ML) algorithms have experienced a significant increase in popularity owing to the digitisation of analogue processes and other technological advancements, like the Internet of Things (IoT). Dependable datasets are crucial for the precise forecasting and resolution abilities of these algorithms, which are indispensable in healthcare, cloud computing, engineering, and finance. Conversely, training datasets are vulnerable to manipulation, thereby skewing the results. To address this issue, blockchain-based approaches have been proposed to enhance the reliability and security of cloud-stored E-Health data generated by the Internet of Things. To improve the accuracy and efficacy of healthcare prediction models, our study focusses on an advanced strategy that integrates feature selection with model training. Optimal input data is refined by feature selection employing entropy and correlation coefficient methodologies. The proposed model, employing BiGRU and BiLSTM, surpasses conventional CNNs and BiRNNs, with an average accuracy of 94.57%. When integrated with the Internet of Things (IoT), blockchain technology ensures the secure storage and transmission of electronic health records (EHRs). This strategy enhances predictive accuracy and safeguards sensitive health data in cloud infrastructures by amalgamating feature selection techniques with robust deep learning models.
This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously colle...
详细信息
暂无评论