data volume grows explosively with the proliferation of powerful smartphones and innovative mobile *** ability to accurately and extensively monitor and analyze these data is *** concern in cellular data analysis is r...
详细信息
data volume grows explosively with the proliferation of powerful smartphones and innovative mobile *** ability to accurately and extensively monitor and analyze these data is *** concern in cellular data analysis is related to human beings and their *** to the potential value that lies behind these massive data,there have been different proposed approaches for understanding corresponding *** that end,analyzing people's activities,e.g.,counting them at fixed locations and tracking them by generating origindestination matrices is *** former can be used to determine the utilization of assets like roads and city *** latter is valuable when planning transport *** insights allow a government to predict the adoption of new roads,new public transport routes,modification of existing infrastructure,and detection of congestion zones,resulting in more efficient designs and *** data exploration can help research in various fields,e.g.,urban planning,transportation,health care,and business *** can also help organizations in decision making,policy implementation,monitoring,and evaluation at all *** work aims to review the methods and techniques that have been implemented to discover knowledge from mobile phone *** classify these existing methods and present a taxonomy of the related work by discussing their pros and cons.
Joint blind source separation (JBSS) techniques have been successfully applied for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. However, convergence in JBSS can be only guaranteed t...
Joint blind source separation (JBSS) techniques have been successfully applied for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. However, convergence in JBSS can be only guaranteed to a local optimum, since typically cost functions are non-convex. Also, iterative methods are usually implemented with random initialization for best performance, resulting in high variability, especially for more flexible solutions. Yet, the assessment of the reproducibility of JBSS has been limited in the literature, even though it has been demonstrated that when not taken into account, the solutions can be highly suboptimal. In this work, we propose a framework for the evaluation of the reproducibility of independent vector analysis, an important JBSS solution. We introduce a mechanism for selecting the model complexity that offers the most consistent and accurate solution, and demonstrate results to underline its importance using resting state fMRI data.
Now, there is a lot of research going on in the field of medical image analysis by using deep convolutional networks. Deep learning uses various models to extract the information from the images provided to deep learn...
详细信息
Now, there is a lot of research going on in the field of medical image analysis by using deep convolutional networks. Deep learning uses various models to extract the information from the images provided to deep learning model. The deep learning is now widely used in the field of medical to detect and diagnose the disease and after diagnosing classifying it into particular category of the disease. The most widely model used for medical image analysis is Convolutional neural network. So, this review paper focusses on how deep learning uses deep networks to detect the disease by retrieving or extracting the information from the images provided to the network and also give information about the clinical applications in the medical fields and the limitations of deep learning in image analysis process is also highlighted.
Coronary artery disease (CAD) is the leading cause of morbidity and death worldwide. Invasive coronary angiography is the most accurate technique for diagnosing CAD, but is invasive and costly. Hence, analytical metho...
详细信息
In order to keep the electric power system running smoothly and reliably, it is constantly monitored and controlled by an intelligent cyber layer that consists of data processing algorithms and a wide network of senso...
详细信息
ISBN:
(数字)9798350368949
ISBN:
(纸本)9798350368956
In order to keep the electric power system running smoothly and reliably, it is constantly monitored and controlled by an intelligent cyber layer that consists of data processing algorithms and a wide network of sensors. Cyberattacks on this data processing and collecting system might halt operations and have catastrophic physical consequences like system breakdowns. A common kind of attack is the FDIA. To avoid detection by the state estimator's inherent anomaly detection capabilities, an attacker tries to trick the grid's underlying control system into producing disturbances. On top of that, there are major issues with customer-end security. For instance, criminals might intercept, alter, or replay wireless transmissions of power consumption signals sent by consumers to their utility provider. Consequently, smart grid security and privacy are major apprehensions. In order to prevent cyberattacks on the vital infrastructures of the electrical system, this thesis helps. New detection systems for the generating and transmission side, as well as the end-user customer side infrastructure, are the primary focus of the study. To protect the generating and transmission sides from cyber-attack, we provide a system based on intelligent sensor weights and an optimization strategy based on sophisticated grey wolves. In addition, to safeguard end-user customer data from cyberattacks, we provide a gaussian mixture model–based privacy protection strategy and an artificial neural structure–based intelligent loop detection method.
Stock market is a dynamic and ever-changing environment that can be both exciting and challenging for investors. Equities, primarily referred to as stocks, are traded on stock exchanges around the world and reflect ow...
详细信息
ISBN:
(数字)9798350386578
ISBN:
(纸本)9798350386585
Stock market is a dynamic and ever-changing environment that can be both exciting and challenging for investors. Equities, primarily referred to as stocks, are traded on stock exchanges around the world and reflect ownership in a business. The stock market is an essential tool for companies to raise capital, and investors use it to grow their wealth. Investing in stocks requires a thorough understanding of the market and the individual companies in which you are interested. The financial health of a company must be taken into account and can be analyzed using financial statements and other data. Another critical factor is the overall economic climate, as market conditions can significantly impact stock prices. It’s crucial to have a long-term outlook and avoid being influenced by momentary market changes when making equity investments. A random walk is a mathematical model used to describe a sequence of steps or movements where each step is determined by chance. It is often used in various fields, including physics, finance, and statistics. Random walk theory has important implications in various fields, including the efficient market hypothesis in finance and the modeling of diffusion processes in physics. To effectively predict the future stock price using conventional and modern machine learning models. Compare the performance of different models and identify a higher accuracy prediction model using the selected important factors from disparate data sources.
Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasti...
详细信息
Recent advances in deep learning algorithms and wearable sensor technology have opened the door for creative methods to improve human-machine interaction (HMI) on virtual platforms. The use of wearable sensors and dev...
Recent advances in deep learning algorithms and wearable sensor technology have opened the door for creative methods to improve human-machine interaction (HMI) on virtual platforms. The use of wearable sensors and devices in conjunction with hybrid deep learning algorithms is presented in detail in this abstract. Real-time physiological and contextual data from users can be collected with the help of wearable sensors integrated into devices like smartwatches, augmented reality goggles, and biometric monitoring equipment. This information can then be used to improve augmented reality (AR) and virtual reality (VR) systems, enabling more effortless and intuitive user interactions. A seamless connection between the user and the virtual platform is made possible by the combination of sensor data and deep learning models, which enables the creation of complex algorithms that can decipher user intent, gestures, emotions, and physical actions. These hybrid models may efficiently learn complicated patterns from wearable sensor data by combining standard feature extraction techniques with convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). Wearable sensors and hybrid deep learning techniques have numerous and significant applications in virtual platforms. They make it possible for, among other things, real-time activity recognition for individualized virtual fitness coaching, emotion recognition for adaptive and sympathetic virtual characters, and gesture recognition for intuitive control of virtual objects. In summary, combining wearable sensors and devices with hybrid deep learning algorithms has enormous potential to change how humans and machines interact on virtual platforms.
The significance of communication networks is growing in tandem with the proliferation of communication technologies. Present methods for maintaining 5G Wireless Sensor Networks are still restricted to routine mainten...
详细信息
ISBN:
(数字)9798350361537
ISBN:
(纸本)9798350361544
The significance of communication networks is growing in tandem with the proliferation of communication technologies. Present methods for maintaining 5G Wireless Sensor Networks are still restricted to routine maintenance and post-maintenance tasks. They lack a comprehensive function for monitoring the network's status, are unable to assess the network's health, and are difficult to maintain before the 5G-based WSNs seriously degrade. 5G Wireless Sensor Network faults can only be resolved by highly trained technicians due to low maintenance efficiency. As a result, errors cannot be detected or located promptly or accurately, leading to forced repairs that incur the expense of new network cables. First, the article lays forth the basics of network fault analysis. Then, it uses deep learning to simulate communication network problem diagnosis. Lastly, the experimental section compares various methodologies and analyses the findings of fault location. The results of the simulation demonstrate that the suggested approach mitigates the created model's flaws to a certain degree while simultaneously enhancing the network fault detection model's accuracy, universality, and robustness. A novel approach to autonomous placement, the Fault Node Recovery Protocol is described in this study. It is implemented in 5G mobile communications to detect faulty data according to wireless sensor network standards, and it is made to fix the problems with conventional techniques, such poor positioning precision and lengthy running time. The automated localization model for 5G mobile communication fault data, constructed using the suggested FNRP approach, is presented in this work. By comparing it to the standard Adhoc On-Demand Distance Vector Routing protocol, we can see how well the suggested system performs.
We introduce a sketch-and-solve approach to speed up the Peng-Wei semidefinite relaxation of k-means clustering. When the data is appropriately separated we identify the k-means optimal clustering. Otherwise, our appr...
详细信息
暂无评论