have been developed for classification of expressions from EEG signals from brain and facial expressions from static images, as well as real time videos. Deep Learning plays an important role for this kind of task. This chapter provides a review of research work carried out in the field of facial expression recognition and EEG Signal classification.
In Chapter 4, the main motivation of the proposed work is to improve the efficiency of wind power generation with the use of solar panels and utilize the power generated by solar cells effectively by powering the electrical components used inside the wind mill, such as revolving motor, elevators, etc. In this paper, various literatures have been reviewed and the remarkable features of the proposed system are highlighted. At the end, the data analysis is done using deep learning and all the results are visualized in graphical form. In the analysis, the power generation from our proposed system and traditional methods is visualized.
Chapter 5 discusses mosaicing; a method of assembling multiple overlapping images of the same scene into a larger, wider image of a scene which overcomes the above issues. In the real-time monitoring, a major problem is that the field of vision is completely too small to capture the target and a larger field of vision results in low resolution. Ability to handle all the above issues, which includes management of quantity and quality feature extraction, is proposed. In this paper, Speeded Up Robust Features (SURF) are used to construct a mosaiced background model for foreground segmentation through deep learning.
In Chapter 6, Chronic Kidney Disease shows slow and periodical loss of kidney function over a period of time and will develop into permanent kidney failure when left untreated. The proposed work aims at presenting the use of Deep Learning for the prediction of Chronic Kidney Disease. Training has been performed using 16 attributes of about 400 patients. Three Deep Learning techniques like Random Forest, Support Vector Machine, and the Naive Bayes Classifier are helpful in predicting the stages. A comparative analysis of these three classifiers is performed.
Chapter 7 provides a cognizance into the implementation of a support vector machine algorithm of Deep Learning to diagnose neurological conditions. With advancement of emerging technologies, the means of diagnosing neurological conditions is substantially more complex than it used to be. Procedures and diagnostic tests are tools that help doctors to identify a neurological illness or other medical condition. Precise identification of neurological pathologies can be done by adhering to an autopsy after the person’s passing.
In Chapter 8 we define what convolution is needed in neural networks and the application of pooling on different data sets. This chapter also addresses how to use a CNN and the kind of operations it applies on the data-set. In this chapter, CNN are applied on image assets for feature extraction and dimensionality reduction.
In Chapter 9, we discuss Deep Learning standard confronter issues on which shallow models, like SVM, are highly affected by the menace of dimensionality. As a module of a two-phase learning plan counts numerous layers of non-straight management, a lot of noticeably robust highpoints are logically unglued from the evidence. The existing instructional workout awarding the ESANN Deep Learning unusual consultation delicacies the cutting-edge models and results in the present understanding of this learning method which is an orientation for some difficult classification activities. So, in this chapter, we will learn about how Cloud Computing and Deep Learning have taken over the world with their new and improved technologies and will learn about their applications, advantages, disadvantages, and correlations regarding different applications.
In Chapter 10, we show a progression of examination concentrates on the best way to quicken the preparation of a disseminated AI Deep Learning model dependent on remote administration. Circulated Deep Learning has become the standard method of present deep learning models preparation. In conventional appropriated deep learning dependent on mass simultaneous equal, the impermanent log jam of any hub in the group will defer the estimation of different hubs in view of the successive event of coordinated hindrances, bringing about, generally speaking, execution debasement. Our paper proposes a heap adjusting methodology named versatile quick reassignment (AdaptQR).
In Chapter 11, we discuss that Deep Learning and big data are the two very emerging technologies. The large amount of data gathered by organizations are used for many purposes like resolving problems in marketing, medical science, technology, national intelligence, etc. In this current world, the old house data processing units are not very efficient to handle, process, and analyze because the collected data is unstructured and very complex. Because of this, deep learning algorithms which are fast and efficient in solving the backlogs of the traditional algorithms are in use now a days. Biometrics uses the pattern recognition technology of Digital Image Processing for identifying unique features in humans. Most commonly applied or considered biometric modalities comprise fingerprint impression, facial landmarks, iris anatomy, speech recognition, hand writing detection, hand geometry recognition, finger vein detection, and signature identification.
In Chapter 12 we discuss that security as an important issue in the cloud and a proper algorithm is needed; with the cloud, security is secure. This method is based on two algorithms: one based on machine learning and the other on a neural system. A machine learning algorithm is based on a KNN algorithm and neural system strategy based on data fragment and hashing technology; both of these processes should optimize cloud security by using cloud data encryption to the cloud server. There are seven applications used for in-depth study described, namely, customer relationship management, image recognition, natural language processing, recommendation programs, automated speech recognition, drug discovery, and toxicology and bioinformatics.
Chapter 13 explains the classification and prediction of network assaults through an algorithm. The real time intrusion detection system finds the network attack using different deep learning algorithms to calculate the accuracy detection rate, false alarm rate, and generate higher accuracy and efficient prediction of network attacks.
In Chapter 14, we discuss that in today’s situation, mysterious structures are initiated to empower clients to store and procedurelize their information utilizing distributed computing. These structures are commonly developed utilizing cryptosystems, appropriated frameworks, and, some of the time, a mix of both. To be explicit, homomorphic cryptosystems, Attribute-Based Encryption (ABE), Service-Oriented Architecture (SOA), Secure Multi-Party Computation (SMC), and Secret Share Schemes (SSS) are the significant security systems being gotten to by practically all current usage. The principle issues being looked during the time spent on gigantic information investigation over cloud utilizing these methods are the computational expenses related with all handling errands, violations from other users of the cloud, insufficient security of internet channels, and absence of accessibility of resources.
Pramod Singh Rathore
Assistant Professor, Aryabhatta College of Engineering and Research Center, Ajmer Visiting Faculty, Department of Computer Science & Engineering MDSU Ajmer, India
Dr. Vishal Dutt
Assistant Professor, Aryabhatta College, Ajmer, India| Visiting Faculty, Department of Computer Science, MDSU Ajmer, India
