| 书目名称 | Machine Intelligence and Smart Systems | | 副标题 | Proceedings of MISS | | 编辑 | Shikha Agrawal,Kamlesh Kumar Gupta,Manish Gupta | | 视频video | | | 概述 | Presents research works in the field of machine intelligence.Discusses the results of MISS 2020 held in Gwalior, India, during 24–25 September 2020.Serves as a reference for researchers and practition | | 丛书名称 | Algorithms for Intelligent Systems | | 图书封面 |  | | 描述 | This book is a collection of peer-reviewed best selected research papers presented at the First International Conference on Machine Intelligence and Smart Systems 2020 (MISS 2020), organized during September 24–25, 2020, in Gwalior, India. The book presents new advances and research results in the fields of machine intelligence, artificial intelligence and smart systems. It includes main paradigms of machine intelligence algorithms, namely (1) neural networks, (2) evolutionary computation, (3) swarm intelligence, (4) fuzzy systems and (5) immunological computation.. | | 出版日期 | Conference proceedings 2021 | | 关键词 | Computational Intelligence; Machine Learning; Deep Learning; Evolutionary Computation; Biological Comput | | 版次 | 1 | | doi | https://doi.org/10.1007/978-981-33-4893-6 | | isbn_softcover | 978-981-33-4895-0 | | isbn_ebook | 978-981-33-4893-6Series ISSN 2524-7565 Series E-ISSN 2524-7573 | | issn_series | 2524-7565 | | copyright | The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapor |
| 1 |
Front Matter |
|
|
Abstract
|
| 2 |
,Synesthetic LearningPedagogy (SLP)—An Exploratory Investigation, |
V. Lakshmi Narasimhan,G. Vasistha Bhargavi,C. Lakshmi,Liza Lee |
|
Abstract
Synesthesia is a phenomenon wherein the stimulation of one sensory modality leads to a percept in another non-stimulated modality—for example, classical music triggers an additional memory percept hidden in that the particular tune can be called as auditory synesthesia, which encompasses the variants in memory and audio synesthesia. Until recently, it was assumed that synesthesia occurs strictly in a unidirectional manner, and although the perception of a particular topic induces a video, audio and image percept in synesthetes, they typically do not report as to what really triggered the percept of memory. Recent data on number processing in synesthesia suggest, however, that colors can implicitly elicit numerical representations in digit–color synesthetes, thereby questioning unidirectional models of synesthesia. Using a video/audio/imagery fragment completion paradigm in synesthetes, we demonstrate in this paper that video/audio/imagery can implicitly influence memory and their recall performance. Our data provide strong support for a bidirectional nature of video/audio/imagery synesthesia and, in general, may allude to the mechanisms of cross-modality interactions in the human b
|
| 3 |
,MSB/LSB Prediction Based Reversible Data Hiding in Encrypted Images: A Survey, |
Rama Singh,Ankita Vaish |
|
Abstract
Encryption provides security to authentic data that is transmitted from sender to receiver for a particular task. Reversible Data hiding in Encrypted Images (RDHEI) has attained interest as per its assured reliability. The technique make use of secret key to encrypt original image for embedding secret information in it and recuperate original image perfectly with unaltered secret information when extracted. A sort of trade-off persists between embedding capacity and recuperation of original image. Many of the techniques existing in literature use Least Significant Bit (LSB) or Most Significant Bit (MSB) to embed secret information. In plaintext domain, LSB embedding is easy since there is minute change in pixel value of original image which attains less distortion in original image after embedding. Encrypted domain is less restricted than plaintext domain where embedding of secret information can be done either in LSB or MSB. Reason for the previous statement is that after encryption, original image pixel gets evolved as pseudo random numbers and any modification in MSB or LSB are insignificant. This paper reviews prediction error based reversible data hiding (RDH) techniques that
|
| 4 |
,A Review of Image Enhancement Techniques in Medical Imaging, |
Anand Jawdekar,Manish Dixit |
|
Abstract
Image enhancement is a crucial methodology in the field of image processing. The foremost purpose of the image enhancement is to get a clearer picture of the image which will further used in image processing technologies. The image features easier by removing noise and other artifacts in a picture. Image processing is an emerging field which deals with different types of images such as medical image, underwater images, and acoustic images. In image processing, persons are facing several problems to deal with actual image because it contains noise, so it is improving its contrast and noise and maintains its image quality. Medical imaging is a promising field in image processing. A medical image gives sensitive information about the health of the person. This paper focuses on various medical image enhancement techniques.
|
| 5 |
,Smartphone User Identification and Authentication Based on Raw Accelerometer Walking Activity Data |
Prabhat Kumar,S. Suresh |
|
Abstract
The biometrical characteristics of the human being such as fingerprints, eye (iris and retina), DNA, palm veins, and face recognition are competent to distinguish uniquely. Similarly, human activity recognition also carries research challenges to furnish an alternative way to identify and authenticate the human beings. The activity recognition contains a two-step process: sensing the raw data and extracting the features and classification. The experimental data used with this paper contains a single accelerometer embedded smartphone for sensing the walking patterns of users. We have intentionally excluded handicraft feature extracting techniques. The deep learning approach is used rather than classical machine learning algorithms. The automatic effective feature learning characteristics of deep learning reduce the barrier to be a domain expert. We have proposed a novel CNN model for user identification based on their activity patterns. The publically available user identification from the walking activity dataset on UCI repository has been used as the experimental dataset. Our model achieved 99.88% accuracy while user recognition based on walking patterns. This paper also includes
|
| 6 |
,Elastic Optical Network: A Promising Solution for Future Communication Networks Considering Differe |
Shruti Dixit,Deepak Batham,Ravindra Pratap Narwaria |
|
Abstract
In optical communication networks, Internet traffic is increasing day by day. This is due to an increase in the number of users and emerging data demanding applications like cloud and fog computing, Internet of Things (IoT), large size bulk data transfer using store and forward data center applications, and many more. This traffic can be classified as different class of service (CoS) which requires flexible bandwidth and high-speed transmission. To fulfill the present need, the orthogonal frequency division multiplexing (OFDM) technology-based elastic optical network (EON) is a promising solution for the future communication networks. EON provides huge bandwidth capacity and flexible data rate. For establishing a lightpath in an EON, routing and spectrum allocation (RSA) is a necessity which is done separately as routing sub-problem and spectrum allocation sub-problem. In this paper, we proposed a new cost-based CoS RSA strategy in order to reduce blocking probability (BP) in EON. Also, we briefly review the concept of EON, issues, and challenges and compared the simulation results of the proposed strategy with the existing non-cost CoS RSA strategy which shows significant reductio
|
| 7 |
,Smart Home Energy Prediction with GRU Recurrent Neural Network Model, |
Dimpal Tomar,Jai Prakash Bhati,Pradeep Tomar |
|
Abstract
Nowadays, smart environment in the residential sector coined as ‘smart home’ catches all attention around the globe and emerged as a solution for the rising electricity demand. But, technology can only provide a methodology to deal with the usage of energy in a very deliberately manner but not at all enough, to change the way people are consuming the electrical energy in the housing sector. However, energy usage prediction plays a significant role to come up as an intelligence to the smart gird and helps in regulating the supply and demand of the electricity in housing sector. In this paper, our contribution is to predict the household energy consumption using gated rate unit recurrent neural network model. The root mean square error (RMSE) is used as a performance measure and able to attain smallest root mean square error for smart home energy data.
|
| 8 |
,A Survey on Watermarking and Its Techniques, |
Sanjay Patsariya,Manish Dixit |
|
Abstract
In the present digital era, digital watermarking concept came into demand due to information sharing over Internet. Digital data such as image, voice and video can be easily modified by anyone. Most prone to such malicious attacks are the digital images published on the Internet. Watermarking is the art of hiding relevant information. It is the technique of embedding watermark into the digital records. The application of this is copyright protection, source finding, broadcast tracking, such as watermarked video from global news organization and hidden communication.
|
| 9 |
,Analysis of Emotion Recognition with Gesture Analysis Through the Machine Learning and Fuzzy Concep |
Samta Jaın Goyal,Rajeev Goyal |
|
Abstract
Human facial expressions play a very important role to develop any interactive system, especially in artificial intelligence and computer vision field. Human-computer interaction (HCI) based applications are working on the same issues. HCI applications nowadays play a very major, interesting as well as challenging role in the present scenario of the world. To develop such a system where it can understand human expressions, emotions, intentions, body language with the help of gesture and posture will benefit greatly in the society. Being a human, many times we do not get actual intension of other person. So, for a machine, it is a big challenge. Since many approaches, techniques are developed to recognize and predict human emotions. So, in this regard, this paper presents a method to identify human emotions through hand gesture. This work uses the upper part of the body. This combined approach is based on the machine learning and fuzzy logic concepts.
|
| 10 |
,Dyslexia Detection Using Android Application, |
Pardeep,Jagrit Kalra,Aman Jatain,Yojan Arora |
|
Abstract
Dyslexia is a learning inability that basically influences the capacity to figure out how to spell and read. The advantages of early detection of dyslexia will help these youngsters in getting the suitable administrations. In this paper, we have given an attempt to discuss various available methods and techniques for detecting dyslexia. The objective of writing this paper is to analyze available methods and to discuss the use of an android application which will be helpful in early detection of dyslexia. We have also discussed the different modules used in our android application.
|
| 11 |
,Prediction of Indian River Water Temperature Using Convolutional Neural Network and Reliable Data T |
K. Sujatha,T. Godhavari,K. Senthil Kumar,B. Deepa Lakshmi |
|
Abstract
The forecast of river water temperature has been carried out based on a variety of weather reports and reports on water bodies on earth. Currently, a range of numerical modeling procedures is used for forecast of river water temperature. For this, the range of input parameters like hourly temperature of river water (.) and atmospheric temperature (.) relating to rivers in India is considered. Thus, to develop an indigenous river water prediction model, certain autoregressive inputs based on meteorological and hydrological models are considered. Each neural network type like feed forward neural network (FFNN) with backpropagation algorithm (BPA) and convolution neural network (CNN) is calibrated independently for 1000 iterations and the mean, median and standard deviation are computed and used for the comparison. Finally, all the models are collectively tested. The results demonstrate that CNN in majority cases outperformed the results obtained from the FFNN trained with BPA. The selection of artificial neural network (ANN) models relies on the method by which the river models are evaluated. Hence, one should consider this constraint so as to propose any other equivalent river model
|
| 12 |
,Performance Evaluation of Conventional and Systematic IT Services Automation, |
Said Masihullah Hashimi,Khushboo Tripathi,Deepthi Sehrawat |
|
Abstract
Task automation and configuration systems have been vastly used in this rapidly growing industry of cloud computing which has increased the number of instances. In the meantime, some small- and medium-scale businesses are still using conventional methods of automation, which uses scripting languages to automate their repetitive tasks and software installations. This paper explores the evaluation and resource utilization of conventional automation, namely shell scripting with a systematic automation system (Ansible). The performance parameters of both systems in terms of automation deployment time, CPU usage, Memory usage, and network status will be evaluated. The scenario has been built using a virtualized environment with the VMware workstation hypervisor. CentOS distribution of Linux has been used for both server and client nodes in the topology. Findings and scenarios in this paper are based on real-world IT tasks that are being automated to reduce the time and make the job easily done in a working environment by an IT administrator.
|
| 13 |
,Internet of Things (IoT): State-of-the-Art Technologies, Challenges and Applications, |
Ranjit Rajak,Kritika Selot |
|
Abstract
IoT is an extension of technology world, and it is growing at rapid speed in our daily-life routine works. The primary objective of IoT is to provide service as fast as require with minimum manpower or without manpower which makes human life more comfort. It is burning field where a large number of sensors are interconnected via high-speed Internet through which information is transmitted to global database. These sensors are basically concerned with the daily routine objects such as AC power, health issue, gas connection. IoT usage is in various fields such as healthcare, industry, Smart City, etc. There are two important factors for IoT to establish communication between the heterogeneous technologies and to understand various taxonomies which require for IoT. This paper presents basic elements of IoT, different architectures, technologies, challenges and issues and applications.
|
| 14 |
,Analysis on Protocol-Based Intrusion Detection System Using Artificial Intelligence, |
Savitri Mandal,A. Sai Sabitha,Deepti Mehrotra |
|
Abstract
One of the major challenges in every field is the network security, so for preventing system, its data and sensitive information from any unauthorized access or harmful activity, intrusion detection systems are used. The objective of this research work is threefold. First objective is to applying various machine learning approaches such as Bayes classifier and random forests on the intrusion detection system for detecting any type of malicious activity. Second objective is to do the comparison for the accuracy of both random forest and Bayes classifier method. Third objective is to find out which algorithm will be fast and provide best result for intrusion detection systems to detect various attacks. In this, working on a protocol-based intrusion detection system understands the HTTP that is running in the particular net server or system. It can be used on the online server which is monitoring the HTTP or HTTPS. As we know that HTTP is a basic protocol that is used for communication between the client and server, attackers can exclusively make use of these protocols to exploit web application vulnerabilities. This system will analyze and monitor the dynamic state and behavior of th
|
| 15 |
,Neural AutoML with Convolutional Networks for Diabetic Retinopathy Diagnosis, |
V. K. Harikrishnan,Meenu,Ashima Gambhir |
|
Abstract
Diabetic retinopathy is one of the common eye diseases caused as a result of diabetics. There are mainly four types of retinopathy conditions—mild, moderate, severe, and proliferative. Once retinopathy reaches proliferative stage, the person will have vision loss. In this study, random wired AutoML model is trained to predict diabetic retinopathy from retina images. Using architecture search technique and random graph models, optimized architecture is achieved. A comparative analysis was done between ER, BA and WS graph theory models, to understand how each graph algorithm impacts the architecture. Model was trained on 3652 images. The trained model achieved sensitivity and specificity above 80% on E-Ophtha database when trained for up to 80 epochs.
|
| 16 |
,The Promise of Deep Learning for Indian Roads: A Comparative Evaluation of Architectures, |
Mriganka Sharma,Jai Sehgal,Joyjit Chatterjee,Anu Mehra |
|
Abstract
With the recent advances in the move towards autonomous vehicles, detecting vehicles through computer vision techniques is set to be an area of paramount importance. While existing studies apply artificial intelligence techniques for detecting vehicles in foreign road scenarios, most studies do not leverage the representational power of deep learning for Indian roads, wherein, the situation is often more challenging and complex. In this paper, we utilize an Indian road dataset to assess various deep learning models, focusing specifically on the condition of Indian roads at present. Alongside common vehicle classes like car, bus, motorcycle, etc., our dataset additionally consists of autorickshaws, trucks, person, and cycle, which are highly prevalent on Indian roads. Two detection algorithms: Faster RCNN and Single Shot Detector (SSD) have been incorporated with convolution neural net classifiers MobileNet, ResNet, and Inception Net, forming four detection models—Faster RCNN ResNet101, Faster RCNN ResNet50, SSD Inception NetV2, and SSD MobileNetV1. A comparative analysis of the algorithms shows that Faster RCNN ResNet 101 is the best performing model, achieving an accuracy of up to
|
| 17 |
,To Reduce Gross NPA and Classify Defaulters Using Shannon Entropy, |
Nikhil Sonavane,Ambarish Moharil,Chirag Kedia,Mansimran Singh Anand |
|
Abstract
Non-performing asset (NPA) has been in a serious attention by banks over the past few years. NPA causes a huge loss to the banks; hence, it becomes an extremely critical step in deciding which loans have the capabilities to become an NPA, and thereby deciding which loans to grant and which ones to reject. In this paper, which focuses on the exact crux of the matter, an algorithm is proposed which is designed to handle the financial data very meticulously to predict with a very high accuracy whether a particular loan would be classified as an NPA in future or not. Instead of the conventional, less accurate classifiers used to decide which loans can turn to be NPA, a unique modeling of entropy-based classifier model is built using the logic of Shannon entropy. The classifier model categorizes the data points in two categories, ‘accepted’ or ‘rejected’. The use of local entropy and global entropy is also exerted to help determine the output. The entropy classifier model is then compared with existing classifiers used to predict NPAs, thereby giving an idea about the performance.
|
| 18 |
,Long-Distance Optical Communication Network with Linear Chirped Fiber Bragg Grating, |
Rajkumar Gupta,M. L. Meena |
|
Abstract
An optical fiber communication model is presented in this paper that contains transmitter, channel and receiver. When a signal is transmitted from transmitter to receiver through long-distance optical fiber, the signal gets dispersed and attenuated. To overcome the problem of dispersion, fiber Bragg gating is used and to overcome the problem of attenuation erbium-doped fiber amplifier is used. This model contains 10 Gbps bit rate and returns to zero (RZ) pulse generator. In this paper, different optical fiber length with varying grating length is taken, and then performance of proposed model is calculated with reference to bit error rate (BER) and quality factor. A comparison is additionally accomplished for the 210 km length of single mode fiber with recently accomplished work regarding quality factor and BER. The simulations of this work are implemented on Optisystem 7.
|
| 19 |
,Covid-19 Containment: Demystifying the Research Challenges and Contributions Leveraging Digital Int |
Chellammal Surianarayanan,Pethuru Raj Chelliah |
|
Abstract
The whole world is in distress due to the uninhibited spread of the COVID-19 virus. Medical practitioners are striving to develop drugs and vaccines for the infection. In contrast, IT specialists are leveraging digital intelligence technologies and tools to surmount the endemic. Specially, mathematicians are developing models for infection spread, computer science experts and data scientists are working with artificial intelligence to predict insights out of growing data, electronics engineers are instrumenting IoT based systems, IT professionals are setting up clouds for real-time data storage and processing to extricate actionable intelligence, security experts are ensuring data security through blockchain, etc. Several collaborative initiatives are on to arrive at strategically sound solutions for COVID-19. This is a best practices paper with the following contributions.The proposed architecture facilitates various stakeholders such as physicians, molecular biologists, IT professionals, and researchers by providing decision enabling, value-adding patterns, and other knowledge to take the right countermeasures in time against COVID-19 infection
|
| 20 |
,Power-Efficient Combinational Circuits Using Reversible Gate, |
Prashant Kumar,Neeraj Gupta,Rashmi Gupta |
|
Abstract
With the advancement, the demand for more efficient power circuits is increasing in electronic industries. The alternative technology gains this aim as reversible logics which helps to design various digital circuits with almost zero power loss. In this paper, a new 3 × 3 gate has been proposed which have multiple functions and is universal in nature. There is one on one mapping in reversible gate that is every input has its unique output. The standard combinational circuits have been verified by using the proposed reversible gate. This proposed gate is highly efficient based on the performance comparison and can be used in various nano-electronic application.
|
|
|
发表于 2025-3-21 18:01:20
