Ebook: Intelligent Systems and Computer Technology
Recent developments in soft-computation techniques have paved the way for handling huge volumes of data, thereby bringing about significant changes and technological advancements.
This book presents the proceedings of the 3rd International Conference on Emerging Current Trends in Computing & Expert Technology (COMET 2020), held at Panimalar Engineering College, Chennai, India on 6 and 7 March 2020. The aim of the book is to disseminate cutting-edge developments taking place in the technological fields of intelligent systems and computer technology, thereby assisting researchers and practitioners from both institutions and industry to upgrade their knowledge of the latest developments and emerging areas of study. It focuses on technological innovations and trendsetting initiatives to improve business values, optimize business processes and enable inclusive growth for corporates, industries and education alike.
The book is divided into two sections; ‘Next Generation Soft Computing’ is a platform for scientists, researchers, practitioners and academics to present and discuss their most recent innovations, trends and concerns, as well as the practical challenges encountered in the field. The second section, ‘Evolutionary Networking and Communications’ focuses on various aspects of 5G communications systems and networking, including cloud and virtualization solutions, management technologies, and vertical application areas. It brings together the latest technologies from all over the world, and also provides an excellent international forum for the sharing of knowledge and results from theory, methodology and applications in networking and communications.
The book will be of interest to all those working in the fields of intelligent systems and computer technology.
This book presents high-quality research papers delivered at the 3rd International conference, COMET 2020, organized by Panimalar Engineering College, Chennai, Tamil Nadu, India on 6th and 7th March, 2020. The aim of publishing these proceedings is to disseminate cutting-edge developments taking place in the technological fields of Intelligent Systems and Computer Technology which will assist researchers and practitioners from both institutions and industry to exchange information, cross-fertilize ideas and upgrade their knowledge of the latest developments and emerging areas of study. Researchers are now working in the relevant areas, and these proceedings of COMET 2020 play a major role by assembling significant work in a single volume. The theme of the book, Intelligent Systems and Computer Technology, focuses on technological innovations and trendsetting initiatives to improve business values, optimize business processes and enable inclusive growth for corporates, industries and education alike. Proven IT governance, standards and practices have led to developments in the form of prototypes, designs and tools to enable rapid information flow to the user.
The book is divided into two chapters: Next Generation Soft Computing and Evolutionary Networking and Communications.
Next Generation Soft Computing provides a miracle solution for solving more complex problems by adapting to changing scenarios. The recent developments of soft-computation techniques in various fields of application related to data and image processing paves the way for handling huge volumes of data, thereby bringing about a significant change in technological advancements. It also provides a premier platform for scientists, researchers, practitioners and academicians to present and discuss the most recent innovations, trends and concerns, as well as the practical challenges encountered in this field.
Evolutionary Networking and Communications focuses on various aspects of 5G communications systems and networking, including cloud and virtualisation solutions, management technologies, and vertical application areas. It brings together cutting- edge researchers from all over the world to present the latest upcoming technologies, and also provides an excellent international forum for the sharing of knowledge and results from theory, methodology and applications in networking and communications. Furthermore, the newer and more innovative ideas are well grounded, with adequate technical support and the core competent technical domains in communication to improve their intellectual aspects. The conference attracted significant contributions about wired and wireless networks in theoretical and practical aspects; authors were asked to contribute experiences that describe significant advances in, but not limited to, the following areas: computing, communication, control systems and knowledge engineering, and the above chapters bring together the ideas, innovations and experimental results of academicians, researchers and scientists in their domain of interest in these areas.
Prof. D. Jude Hemanth
Department of Electronics and Communication Engineering, Karunya Institute of Science and Technology, Tamil Nadu, India
Prof. V.D. Ambeth Kumar & Prof. Dr. S. Malathi
Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, Tamil Nadu, India
The main objective of Perceptual Image Super Resolution is to obtain a high resoluted image from a normal low resolution image. The task is very simple that we just want to make a Low firmness appearance into a extraordinary resolution image. To perform this task we have various methods like Classical Approach in which we try to maximize the mean squared error, evaluate by PSNR(Peak-Signal-to-Noise-Ratio). The first method used to perform this operation was SRCNN (Super Resolution Convolution Neural Network) and these days many of them use DRCN and VDSR which are slightly upgraded methods. Another technique used for the purpose of upscaling to get a high resoluted image from normal little resolution image is the state of art by PSNR. This method was a quite simple one in which we take a low determination image as input and place in a convolution neural network(CNN) and produce a high resolution image as the output. In this technique the edges will be clearly defined, but the whole image will be blurred. This method is unable to produce good-looking textures.
In the digital era, more and more information is shared through the internet. This may lead to editing, transmitting, misusing detection and usage of information by unauthorized persons. To avoid such a problem we use the digital right management (DRM) with blockchain. In our daily life, blockchain is a powerful utensil to share the data in decentralized and distributed technology. The DRM process provides security and authentication for the content and owner of the data. In our proposed system, the following steps have been implemented Watermark Embedding with Discrete Wavelet Transform (DWT), Arnold Transform (AT), Perceptual Hash, Hash Code generation (md5), Watermark Extraction and Blockchain Creation. Discrete Wavelet Transform provides better image quality and robustness. Arnold Transform provides the best watermark encryption. The hash code generation gives a numeric value which helps in the recognizable proof of a ediget during equality testing. Blockchain is used to store the information in a secured manner and also provide timestamp authentication. Watermark extraction is achieved with the inverse of Arnold transform, inverse Discrete Wavelet Transform with the matching of hash code. This system provides secure transactions with copyright-protected data and safe transparent management.
Nowadays computer vision systems are widely used for identification, classification and grading of different kind of fruits. Existing research concentrates on features like size of the fruit, colour, shape and texture for classification and maturity detection of mango fruits. Colour of the fruit is one of the prominent feature, though a lot of effort is focused towards identification, maturity and defect detection of mango using colour features,less attempts are made in the direction of the identification of artificially ripening of mango fruits.From another perspective very few attempts are concentrated towards deeper analysis of colour features of the fruits. In order to solve these issues this research paper proposes a new framework for detection of artificial ripening of mango fruit based on MPEG-7 colour descriptors. The proposed scheme includes three stages: first, a pre-processing stage consisting of masking, filtering, segmenting and cropping of an image followed by dominant colour extraction using dominant colour descriptors which are finally mapped with the help of clustering to identify the artificial ripening of mango fruit. The results of experimentsis carried out on two different datasets involving four types of mangoes which demonstrates robustness and efficiency of the proposed method against various other methods.
With the discovery of paperless expensive means of internet access, network communication via social media is on the rise, which often comprises threats and distortions. Un authenticates identification may sometimes lead to ambiguities in end-user identification and misunderstandings. Therefore, proper identification of a person is a must in network communication. Image private watermarking is one solution when the owner of the digital images are identified properly by embedding additional information such as a private watermark in the digital images like fingerprint and retina imperceptibly concealed inside another image. On the other hand, communication also leads to a serious surge in decompress technique on the images. This work introduces three techniques: digital watermarking, steganography, ICA. Using a private watermark using the visible  and non-blind technique on the photo image. Then two original fingerprints and retina images to achieve stego analysis technique to convert as a stego image. Then the stego image concealed by a watermarked photo image. Then mixing the two techniques to achieve the ICA (Independent Component Analysis) for protecting data transmission. To providing compression using the IDCT (Inverse Discrete Cosine Transform) technique with the key using AES (Advanced Encryption Standard) 64-bit algorithm. Implementation and to determine the utilize the JAVA platform.
Extensive study over Z-source inverter (ZSI) has been pursued for years to compensate the drawbacks of the conventional converters. Single stage (one-step) conversion with buck-boost characteristics was the primary features for its wide usage. But presence of passive elements may prove to be a disadvantage as the size of the converter increases along with its ratings. Modifications on such converters leading to different topologies have been discussed briefly in this paper. The comparative study based on reduced passive elements and better gain is done to obtain an optimal converter structure.
The illegal movement of valuable trees such as sandal wood trees in forests poses a severe risk to natural reserves and it instigates a great loss to our country’s wealth. Almost 24,000 square miles has been lost due to deforestation in the past decade. This paper proposes an antipoaching system using NodeMCU based wireless system that uses 3- axis MEMS accelerometer (GY-61) and tilt sensor for detecting the falling of trees due to cutting of trees or natural calamities and Flame sensor, fire retardant for detecting and controlling the fire. In this project we use NodeMCU which has an inbuilt Wi-Fi module which covers a distance of around 300m range, is used in this project for cost efficiency and also NodeMCU enables the communication with neighbor nodes like client and server nodes. This protocol is used to monitor the trees even using a single node from the server system. The solenoid valve is used to spray the fire retardant to control the fire. Some IOT modules can also be used in this system to provide accurate information and remote monitoring of trees.
This paper presents an overview of quantum errors and noise channels, their mathematical modeling and its implementation in quantum one time password (QOTP) based user authentication. Quantum noise plays a pivotal role in understanding quantum information theory which is important to build up quantum communication theory. The Kraus operators provide a powerful mathematical tool in understanding and modeling various quantum channels. Use of QOTP provides an impressive method of carrying out user authentication involving quantum operations based on user biometrics. However, the efficiency of this method can be better envisaged by incorporating noise models during qubit transmission.
In the current trend, Internet of Things (IoT) technology is more useful in healthcare in terms of mobile health and remote patient monitoring. IoT produces enormous data to be processed in cloud. In practice, the latency caused by cloud for processing the data leads to unacceptable losses. As an alternative method, we have proposed a system to reduce the latency caused. The health care IoT devices start emitting the data relevant to a patient. The data are then uploaded as current status of a patient from smart home or hospital to the cloud continuously. The mobile of each patient will be acting as Fog-node in which it collects the data and computes the received data and generates events for abnormal cases. When an event is triggered the cloud sends alert to doctor, ambulance and relatives based on the threshold of event occurred. All data transmission occurring in-between Cloud Server and Mobile of each patient is encrypted using One Time Pad security mechanism. The proposed encryption mechanism is a lightweight encryption compatible with IoT based system. Since it has an encryption that is yet to be cracked, we can ensure secure transmission of patient records with a higher performance than which was achieved by cloud computing.
Tracking the good doctors for treatment in rural area is a very difficult job, to requiring the rural folk to track all the way to nearby towns or cities. Therefore, Anytime Medical Machine (AMM) requires deployment in rural areas using the AMM with the ability of people to get good doctors on track and take the treatment through the AMM. The doctor provides medicines on prescription for the patients through AMM. This collects details relating to the patient’s Body Temperature, Heart Beat, Height and Weight using Pi Kit. The Patient desires to see a language known to both of them and sending the collected information to the doctor through AMM. Interaction between the doctor and the patient follows using video conferencing it attached with AMM. Finally, the Doctor observes the patient’s sickness and then suggests the appropriate medicine through AMM. The patient’s information is uploaded in the cloud server. Admin re-fills the medicines in AMM during the intake timing. This AMM application performance level of the data result proven that the efficiency of 90%. The significance of AMM plays a main role in automation of medicine dispatcher.
The aim of this paper is to study pre and post-transplant health records of kidney transplanted people and to find the importance of various factors in renal transplantation. Once the importance of these factors are quantified it can be used to predict the survival probability of the graft for given time. The possibility of using Artificial Neural Network (ANN) as a tool to predict the survival probability is discussed. Transplantation is the best option available to increase the life expectancy of the people who are suffering from end stage renal disease all over the world. The present system for organ procurement and management by the hospital and other reputed legal organizations are not sufficient to deal with the situation. The need of the hour is Systematic procedures for collection of organs, networking and sharing information about both pre transplantation and post transplantation levels. Application of scientific techniques and well proven methodologies of other domains like manufacturing and production can be utilized to improve the level of efficiency in organ transplants of our country.
This paper presents the design details of its implementation of an IoT-based Real Time Health Monitoring System for the monitoring of a patient and provides. The proposed Design permits the monitoring of health related dangers and deals with economy in health care expenditure through effective interpretation and distribution of patient data. This paper works on the concept of reducing human presence in monitoring a patient’s problems and sending vital details to the Doctors and Caretakers on a real time basis. This proposal helps saving in and alerts the Doctors/Caretakers in an emergency situation to ensure critical moments are not wasted. The outcome of the proposed system is to provide exact collected medical services to patients through records and information through sensors which monitor the patient’s details relating to Pulse, temperature, Body Tilt Angle and Glucose Level. This information is sent to the patient’s Doctor/Caretaker using a cloud based App on a real time basis.
In this paper guides in the fuzzy logic and Neural network variable step size Incremental conductance maximum power point tracking controller were analyzed as well suggested on further work. Firstly, the Fuzzy Logic Control (FLC) controller based hardware system derived paper were discussed followed by Neural Network (NN) based VSS Inc-Cond were discussed in the second half. In the first paper derived simple FLC I.e short, medium and long distance were considered to derive the 25 rules. The input of FLC are current and voltage, the output of FLC is duty cycle or D. The duty cycle apply into variable step Inc-conductance method to find the optimal point of the PV system. Further discussed experimental block diagram of FLC-Inc-Cond system. At the end of the paper authors compared various hardware to show tabulations. In the second half, initially discussed conventional Inc-Cond, followed by general Fuzzy logic controller were discussed. Further author derived VSS Inc-Cond based NN MPPT were developed on Matlab simulink. The output of FLC-Inc Cond as well NN based MPPT is great performance when compare to conventional system.
Sentimental Analysis or Opinion Mining plays a vital role in the experimentation field that determines the user’s opinions, emotions and sentiments concealing a text. News on the Internet is becoming vast, and it is drawing attention and has reached the point of adequately affecting political and social realities. The popular way of checking online content, i.e. manual knowledge-based on the facts, is practically impossible because of the enormous amount of data that has now generated online. The issue can address by using Machine Learning Algorithms and Artificial Intelligence. One of the Machine Learning techniques used in this is Naive Bayes classifier. In this paper, the polarity of the news article determined whether the given news article is a positive, negative or neutral Naive Bayes Classifier, which works well with NLP (Natural Language problems) used for many purposes. It is a family of probabilistic algorithms that used to identify a word from a given text. In this, we calculate the probability of each word in a given text. Using Bayes theorem, they are getting the probabilities based on the given conditions. Topic Modeling is analytical modelling for finding the abstract of topics from a cluster of documents. Latent Dirichlet Allocation (LDA) is a topic model is used to classify the text in a given document to a specified topic. The news article is classified as positive or negative or neutral using Naive Bayes classifier by calculating the probabilities of each word from a given news article. By using topic modelling (LDA), topics of articles are detected and record data separately. The calculation of the overall sentiment of a chosen topic from different newspapers from previously recorded data done.
Developing cyber-security threats are an industrious test for system managers and security specialists as new malware is persistently cleared. Attackers may search for vulnerabilities in commercial items or execute advanced surveillance crusades to comprehend an objective’s network and assemble data on security items like firewalls and intrusion detection/avoidance systems (network or host-based). Numerous new assaults will in general be changes of existing ones. In such a situation, rule-based systems neglect to detect the assault, despite the fact that there are minor contrasts in conditions/credits between rules to distinguish the new and existing assault. To detect these distinctions the IDS must have the option to disconnect the subset of conditions that are valid and foresee the feasible conditions (not the same as the first) that must be watched. We have given various techniques to detect intrusions (or anomalies) which are dissipated consistently and structure little clusters of irregular data. To improve the clustering results, the dissipated anomalies are detected and expelled before agent clusters are framed utilizing SC (spectral clustering). For assessment, a manufactured and genuine data set are utilized and our outcomes show that the utilization of SC (spectral clustering) is a promising way to deal with the advancement of an Intrusion Detection System.
In the present days’ deaths because of some critical disease has become a significant issue in the medical field. Data mining is one of the significant territories of research that is famous in wellbeing associations. Data mining has a functioning job for finding new patterns and examples in the healthcare association which is valuable for every one of the gatherings related to this field. The medical dataset has heterogeneous data as numbers, content, and pictures that can be mined to convey an assortment of helpful data for the physicians. The examples picked up from the medical data can be helpful for the physicians to find diseases, foresee the survivability of the patients after disease, the seriousness of diseases and so forth. The focal point of this paper is to break down the utilization of data mining in medical space and a portion of the systems utilized in critical disease prediction. We have completely reviewed many research papers of data mining identified with some critical disease prediction.
Security of a data system is a significant property, particularly today when PCs are interconnected by means of the internet. Since no system can be totally secure, the opportune and precise detection of intrusions is essential. Cyber security is the region that manages shielding from cyber terrorism. Cyber-attacks incorporate access control infringement, unapproved intrusions, and disavowal of service just as insider risk. For this reason, IDS were planned. The IDS in the mix with DM can give security to the next level. DM is the way toward presenting inquiries and separating designs, frequently already ambiguous from huge amounts of data utilizing design coordinating or other thinking techniques. This Paper gives the IDDMS (Intrusion Detection with Data Mining system) Framework which is a mix of data mining techniques with the Intrusion detection system, this can be utilized in Cyber-security for accomplishing the next level of service.
In the recent past there has been a significant increase in the research on vibration-based energy harvesting. Wherever mechanical movement exists, a lot of heat and vibration energy is wasted which could be used and converted as a supplement to the energy requirements. Towards this objective this project aims to provide a general theory that can be used for generating electricity from vibrating as well as heat body and store the acquired energy using advanced component called the super capacitor. A combination of Cantilever beam and MMA sensor is used for the sensing vibratory motion and the Peltier sensor is used for sensing the temperature of the source. The output obtained from the former source is converted into voltage using MMA technology and the latter is converted directly into the same. Boosted voltage is stored effectively with the help of super capacitor in primary storage device. The acquired voltage from the battery is 12V with respect to this project. For the AC load, the current produced are 300mA. The output would change with respect to the vibrating and the temperature sources like generators or automotive engines
Many industries like pharmaceutics, plastics, food and confectionery, tobacco and cold storage, maintaining the humidity at the desired level is very important. The aim of this paper is to process the model and to design a controller for a dehumidifier to control the humidity at the desired set point. The air is humidified using a humidity chamber. This humid air which is the primary air is mixed with secondary air from the compressor and sent to the dehumidifier. The dehumidifier used here is a centrifugal separator. The humidity of the dehumidified air is measured using a sensor. The output signal of the sensor is compared to the set point. If the output measured exceeds the set point, accordingly the flow rate of the secondary air to the dehumidifier is varied until it reaches the desired set point .The model of the process is identified from the response of the process to the input signals. The controller is designed for the model obtained and the performance of the controller based on the time domain specification is compared.
The healthcare and the management of quality is very essential part to the recent period of medical environment. To enhance these, to make sufferer easy with timely and best remedial care.EEG systems are closely relevant on the performance using wireless system because of its more capabilities. But it has various disadvantages like line frequency interference and signal loss,. Currently there is usage of RF in healthcare environment and medical test centre which have dangerous for the health of the patients. So we are in need of alternative eco-friendly source of communication in health care. So the alternative way is proposed here is the VLC (Visible Light Communication) transmission technology that uses white LED for data transmission which has efficiency, reliability and high precision. The ADC produces data stream of EEG signal which is modulated using OOK .Here LED works as a transmitter and photodiode with sensor works as receiver and uses computer simulation for further evaluation.
In recent days, diagnosis of sepsis involves a wide range of tests. Single test cannot tell that a person has sepsis. Undetected sepsis finally leads to death. The main drawback of sepsis is, there is much delay in predicting the diseases and identifying the various stages. Thus to avoid this delay in detection, we use Machine Learning concept. Thus by using this method prediction of sepsis has been increased and the mortality rate is reduced.
Brain tumor is a growth of abnormal cells in the brain that can be either benign or malignant. It tends to affect people irrespective of age group. Thus earlier detection and treatment of brain tumor is needed for quick recovery. Doctors use Magnetic Resonance Imaging (MRI) to identify the intensity of tumor. The MRI images are pre-processed and then Deep learning neural network and spearman algorithms are used to provide segmentation of images. The segmented images are grouped using Fuzzy clustering technique. The CNN and SVM Classifiers are used to classify and detect the size of tumor cell. On comparison, it was found that CNN classifiers are more accurate, sensitive and yields high performance as compared to SVM classifiers for both 2D and 3D images.
Buoy is a device which floats in the sea water, used to direct the ships in which this paper is preferable to get electricity from salt water/ sea water by using two tongue depressor. Using level sensor has per this paper, where going to sense distance between a ship / a boat and a buoy, regarding the distance between those two objects, alarms or buzzers may indicates. An IOT applications has been implemented on a buoy, so that if any obstacles damage a buoy, the information can be specified to the communication station through SIM900
The humidity sensing behavior and the properties of P3HT based thin film organic field effect transistor (OFET) has been reported. Layers with (Au)/P3HT/SiO2/(Au) are coated and OFET is fabricated. The XRD pattern of thin films are plotted which shows an orientation of (100) indicating its crystalline nature. The morphological studies report the presence of dreg like structures that can absorb water molecules from a humid environment which can be used in humidity sensing applications.