Search

In order to prevent the overloading, the routing algorithm aids in building productive paths both within and between clusters. When sending information from the source IoT device to a base station, not all IoT devices are utilized in the path. We introduced an energy aware cluster-based routing in this paper, in which Improved Fuzzy C-means model plays a major role in clustering initially. Meanwhile, the clustering procedure considers the factors like energy and distance. Subsequent to the clustering process, optimal routing will be takes place by a new hybrid optimization algorithm named Custom Honey Badger and Coot Optimization (CHBCO) that combines the models like Honey badger optimization and Coot optimization model, respectively. For routing, the model considers the constraints like Energy as well as link quality. Also, this model establishes the fault tolerance method, which ensures that the network will continue to operate normally even in the situation of a CH failure. During this, the cluster members switch to another CH. The performance of proposed CHBCO based routing model is compared over existing models with respect to convergence rate, distance evaluation, energy, alive nodes, distance, normalized energy and link quality under five scenarios such as 100, 500, 1000, 1500, and 2000. Moreover, the proposed model obtained 56 alive nodes in the round 1500 for scenario 1(i.e node 100). Also in the round 1500, the CHBCO model obtain a minimum distance as 25 however the existing models achieve higher distance like EHO as 50, HHO as 70, COOT as 40, HBA as 60, MFO as 75, DCPSO as 150, and HGS as 85 for the node setup 1000. The proposed method achieve a better normalized energy as 0.29 in the 2000 round along with node setup 100, while the conventional models reach the lowest normalized energy. Moreover, the CHBCO method fine link quality values such as 0.96, 0.96, 0.95, 0.97, and 0.97 at the node setups of 100, 500, 1000, 1500, 2000 respectively.

Internet of Things (IoT) is a networking paradigm shift that aims to link almost everything on the world. Due to the limited form of smart devices, energy-efficient routing would be critical to their effective implementation. Clustering techniques divide a network's nodes into groups or clusters, each of which is led by a specified node known as the cluster head. Clustering methods have been presented in the area of Wireless Sensor Networks (WSN), while their application in IoT might solve comparable problems. By transferring a major portion of communication overhead to the cluster head, clustering would promote topology maintenance and energy efficient routing. Therefore, this article aims to establish a novel clustering model in IoT, in which the cluster head selection is performed via a proposed Sandpiper Optimization with Cycle Crossover Process (SOCCP) model. Moreover, this cluster head selection includes certain constraints including (i) Distance (ii) Energy (iii) security (based on the risk levels), and (iv) Cluster Radius, respectively. At first, the clustering is done by the Optimized Fuzzy C-Means (FCM) algorithm. Here, the determination of the cluster head and cluster radius is tuned optimally via an adopted SOCCP model. At the end, the results of the adopted technique are computed to extant based on various metrics including alive node analysis, risk analysis, distance analysis, cluster radius analysis, as well as normalized energy analysis, respectively.

In the past decades, AI was not playing a pivotal role in technology. But now, artificial intelligence is a key part of the revolution of technology. AI has become a powerful tool in recent years, enabling machines to think and act like humans. AI helps in developing a better approach to teaching students (i.e., adaptive learning where a computer algorithm identifies the rate of learning of a student and adapts itself so that the student learns efficiently). The aim of implementing AI in education is not to replace tutors, but to assist them in understanding the potential and limitations of each student individually. This chapter will cover the introduction, existing applications, and new applications of artificial intelligence in higher education. The prime focus of the chapter will be on the approaches to different product developments and their implementation using artificial intelligence in the education sector. It provides a brief idea of how the existing applications solve the problems in higher education and new approaches to make higher education more efficient.

With the speeding up of social activities, rapid changes in lifestyles, and an increase in the pressure in professional fields, people are suffering from several types of sleep‐related disorders. It is a very tedious task for clinicians to monitor the entire sleep durations of the subjects and analyse the sleep staging in traditional and manual laboratory environmental methods. For the purpose of accurate diagnosis of different sleep disorders, we have considered the automated analysis of sleep epochs, which were collected from the subjects during sleep time. The complete process of an automated approach of sleep stages’ classification is majorly executed through four steps: pre‐processing the raw signals, feature extraction, feature selection, and classification. In this study, we have extracted 12 statistical properties from input signals. The proposed models are tested in three different combinations of features sets. In the first experiment, the feature set contained all the 12 features. The second and third experiments were conducted with the nine and five best features. The patient records come from the ISRUC‐Sleep database. The highest classification accuracy was achieved for sleep staging through combinations with the five feature set. From the categories of the subjects, the reported accuracy results were found to exceed above 90%. As per the outcome from the proposed system the random forest classification techniques achieved best accuracy incomparable to that of the other two classifiers.

Natural language processing is generally used to understand the interactions between humans and machine, and it is also a subpart of artificial intelligence. Sentimental analysis is a subpart of AI and used to differentiate the words by the patterns that are given by people like good, bad, or average. Sentiment analysis is used to know about user’s likes and dislikes toward a product. Zomato is an app which is used for ordering foods from different restaurants and allows user to drop their reviews and ratings of respective food that they ordered. These reviews given by the customers will be taken for sentimental analysis. The buying decision of a customer is also depending on the reviews and ratings. So, reviews have a lot more important. It is estimated that 79% of unstructured data is producing every day. A lot of textual data are generating through social media, healthcare, e-commerce applications. We as humans cannot analyze these huge volumes of data. Sentiment analysis will help us to do this task very easily. In this project, we can train with millions of data and predict new data as positive, negative, and neutral. We use artificial neural networks (ANNs) to train the model and to predict the reviews as positive, negative, or neutral. Artificial neural networks use feedforward networks and work as biological neural networks.

The present work mainly focused on automatic classification of the sleep stages classification from the different medical-conditioned subjects under American Academy of Sleep Medicine (AASM). The present research study was used single individual channel for classifying two-state sleep stage classification problem in between wake versus Sleep. During first part, we have conducted experiments such as acquisition of data from participated subjects, preprocessing the raw signal to remove the irrelevant artefacts and muscle movements from recorded sleep data, extract quantitative features obtained from EEG signal and also used feature selection techniques to choose the suitable features which is most useful for characterizing the abnormality pattern. In second step, we have used two machine learning classifiers such as support vector machine (SVM) and K-nearest neighbor (KNN). The proposed scheme was conducted through six different medical conditions subjects with considering both affected sleep diseases subjects and healthy subjects and their one session and two session recordings. The obtained results demonstrated that the proposed methodologies support to sleep experts for accurately measure the irregularities occurred during sleep and also helps the clinicians to evaluate the presence and criticality of sleep related disorders.

Sleep stages including wake (W), non-rapid eye movement (NREM), and rapid eye movement (REM) help to analyze the depth of the sleep patterns. To describe the sleep behavior of the subject is one of the important steps during the diagnosis of the various sleep-related disorders. The best way of analyzing sleep staging is obtaining the polysomnography (PSG) signal recordings from the patients. Therefore, this proposed study develops an automated sleep staging system that uses electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals. In this study, both linear (time and frequency) and non-linear features are extracted from the preprocessed signals. Additionally, we also obtain the feature selection techniques to find out the most suitable features using the ReliefF feature selection algorithm. Finally, the selected features are classified through the Random Forest (RF) classification model. In the proposed study, we evaluated the proposed model using two different subgroups, namely, subgroup-I (SG-I) and subgroup-III (SG-III) data of the ISRUC-Sleep dataset under AASM sleep scoring rules. The proposed research work is evaluated on two subgroups of ISRUC-Sleep datasets. The results of the model provide the highest classification accuracy of 98.40, 98.49, 98.31, and 98.52% with the SG-I dataset, similarly, for the SG-III dataset, the reported accuracy reached 97.96, 98.67, 98.40, and 98.46% by using random forest classification techniques. The proposed machine learning model is ready for the diagnosis of the different types of sleep-related disorders and can be managed with huge polysomnography records. The performance of the proposed sleep staging classification of five-sleep states (CT-5) shows the overall classification accuracy of 98.99%, 98.75%, 98.17%, and 99.14% using single-channel EEG, EMG, EOG, and EEG+EMG+EOG, respectively. It has been seen that the achieved results of the proposed model reveal that the proposed methodology provides better sleep staging analysis incomparable to the existing contributions.

An automatic analysis of sleep stage classification can reduce the use of manual annotating the sleep recordings from subjects during sleep time. This approach can alleviate the overburden of clinicians and this approach is indirectly helpful for sleep experts to take proper diagnosis of sleep-related diseases. For the proper treatment of sleep disorder the most important step is sleep scoring and computer-assisted sleep stage classification. With considering this above, two important steps our proposed research article is based on automated sleep stage classification in between two sleep classes such as wake versus sleep stages with high rates of accuracy and sensitivity. In this proposed study we have considered the EEG signals of one subject with suspected light sleep problem and the EEG signals of one healthy subject with prior no medication in subject to sleep problems. Here we have recorded the EEG signals from dual channels such as F3-A2 and C3-A2 and extracted epochs is 30 s. Eleven statistical features are extracted from each input channels. In this proposed work we have obtained the Online Streaming Feature Selection (OSFS) algorithm to identify the suitable features for classification task. The selected features classified by two conventional machine learning classifier such as DT and KNN. We have obtained tenfold cross-validation techniques to evaluate the system parameters. The result of our proposed experimental study is evaluated for two-state sleep classification sleep problems. The highest overall accuracy achieved for healthy subject through F3-A2 channel as 81.6% with DT classifier, and in same manner, the highest overall accuracy obtained for suspected light sleep problem subject through F3-A2 channel as 91.1% with DT classifier. The system performance toward sleep stage classification compared with the earlier contributed works mentioned in the state-of-the-art systems. The proposed research work can be used for health care application with huge PSG signal recordings for objective to improving in sleep stage classification system.

Blockchain uses several cryptographic techniques to validate and store information, thereby making it extremely difficult to hack. Some have even argued that a blockchain is impossible to hack. The blockchain network has gained quite the reputation over the last decade because of its seemingly impenetrable security and owing to this, several organizations have considered or are considering adopting the use of blockchain technology. However, like every other technology, blockchain is also susceptible to attacks. In thischapter, we will take a deep dive into the structure, security attacks, and countermeasures in the blockchain network, with a focus on blockchain vulnerabilities, precautions, and countermeasures.

The Signals in plants are generated by the imbalance in the ion concentrations. Such imbalances are triggered by various external stimuli. Signals can be electrical, mechanical, or chemical form as well. These signals are used by the plants to transmit information. This paper presents a review of various plant signal processing mechanisms. This paper also discusses various issues, challenges involved in plant signal processing. This work will be helpful for the academicians, researchers, biologists and other enthusiasts of plant neurobiologists to have a comprehensive overview of the research progress.

Habit tracker is a mobile application developed in flutter. It is an application which stores our activities regularly. With the habit information it gives scores based on the performance by us in the activity performed. It analysis the information and gives us the scores on daily and monthly basis by which the user can motivate himself to increase the performance. The user is monitored for his/her habits and based on that commanders will set the activities or habits that user has to get habituated. User just need to start performing the activity and the process is monitored regularly. This application is developed to monitor the user activities and give feedback based on it to improve their performance score. The reports generated can be viewed by their parents/caretakers.

It was noticed that numerous vehicles utilizing sensors are working more productively. The majority of the bikes and vehicles which are made of sensors are working effectively in avoiding accidents. Because of this, there are very few street mishaps happening [1]. Considering the above scenario where the number of accidents occurring is very low, if we can execute the idea of the concept of utilizing sensors in the boats, we can diminish boat mishaps. This is the principle thought behind our task. The task was done utilizing the Internet of Things. Task usage can be finished utilizing multiple sensors along with the Arduino.

Unknowingly, artificial intelligence (AI) has become an inevitable part of our lives. In this chapter, the authors discuss how the neural networks, a sub-part of AI, changed the way we analyse things. In this chapter, the advent of neural networks, inspiration from the human brain, simplification models of biological neuron models are discussed. Later, a detailed overview of various neural network models, their strengths, limitations, applications, and challenges are presented in detail.

Deep learning (DL), a part of machine learning (ML), comprises a contemporary technique for processing the images and analyzing the big data with promising outcomes. Deep learning methods are successfully being used in various sectors to gain better results. Agriculture sector is one of the sectors that could be benefitted from the deep learning techniques since the current agriculture techniques cannot keep up with the rapid growth in population. In this chapter, the recent trends in the applications of deep learning techniques in the agricultural sector and the survey of the research efforts that employ deep learning techniques are going to be discussed. Also, the models that are implemented are going to be analyzed and compared with the other existing models.

Forests are essential natural resources which provide us various direct & indirect benefits and play a crucial role in the life existence of human on earth. It is our responsibility to indeed save our earth from the extinction of forests from the major hazard of combustion. In the paper, we proposed an AI-based Flask-driven, Web application framework to support an integrated development, scrutiny, and deployment of forest combustion recognition using deep learning. This project is aimed at the areas where the fire combustion takes place to save the wildlife animals, people situated around and preserve rare species of plants from being extinct. A forest fire has a huge and serious impact on the environment, and it also affects the future for decades. AI and deep learning techniques are used to visualize/recognize whether the forests are with fire or without fire through the images which we give the model to predict. In this paper, training and testing is done using CNN which is analyzing visual imagery by using images to detect the forest with fire and without fire. Eventually, we can avert or put a stop to combustion of forests by providing machines with the suitable algorithms on how we wanted our model to be used and developed by automatic code generation techniques.

Today, Cancer is one of the major lethal diseases in the world. Globally out of every three cancers diagnosed, one is identified as skin cancer. Some reports suggest that one out of every five Americans might fall prey to skin cancer in the course of their life. Early detection of the disease plays a pivotal role in the treatment of skin cancer. Though these skin lesions can be seen without the help of any external clinical device, it is a challenging task to distinguish between malignant and benign skin lesions as they are alike in their physical appearances. This leads to an increased number of unnecessary biopsies where in one study it was revealed that nearly 5,00,000 biopsies are done in children every year to diagnose a mere 400 melanomas. To tackle this problem and help dermatologists in the diagnosis process, we developed an enhanced image classification model which can act as a preliminary check before moving to a costlier biopsy. This model can identify 7 distinct types of skin lesions. An analysis has been carried out on the HAM10000 dataset. We used transfer learning utilizing multiple pre-trained models, combined with class-weighted loss and data augmentation techniques for the classification process. Experimental analysis shows that the modified ResNet50 model is capable of identifying skin lesion images into one of the seven classes with categorical accuracy, weighted average precision, and recall of 90 percent, 0.89, 0.90, respectively. Our model can be used as a clinical decision support system to help dermatologists in the diagnosis process.

Emotion Detection became one of the most efficient and challenging activities in human interactions. In general, facial gestures are normal and clear means of expressing their feelings and intentions to human beings. The main features of non-verbal conversations are facial expressions. The study of the techniques of Face Emotion Recognition involves three key phases, like pre-processing, extracting of features and, classification techniques. This paper proposes the comparison of deep learning architectures available in Keras for emotion detection using the Deep Facial Features in images using Transfer Learning from famous pre-trained models like VGG-16, ResNet152V2, InceptionV3, and Xception and generating bottleneck features for our input images. The performance of these models is evaluated based on the dataset which is a combination of the Cohn-Kanade Dataset (CK+) and Japanese female facial emotion (JAFFE). For the above-mentioned architectures, the accuracies obtained are 83.16 %, 82.15 %, 77.1 %, 78.11 % respectively. (Abstract)

The objective of this paper is to conduct a bibliometric study on the use of Raspberry Pi in the medical field. In the past several decades healthcare advancements have played a major role and Raspberry Pi being the charm with its extensive features and low cost, it is of interest to know whether the development in health care technologies with respect to Raspberry Pi has created an impact or not. A platform known as Biblioshiny has been used to collect statistical information and perform the analysis. A total of 154 journal articles have been collected from PubMed, a free full-text archive of biomedical and life sciences journal literature at the U.S. National Institutes of Health's National Library of Medicine (NIH/NLM) and analysis has been made on various parameters such as top authors, countries and affiliations etc. The conclusions drawn help us to understand the usage of Raspberry Pi in the healthcare domain. The Bibliometric Analysis done indicates that there has been an increase in the research over the years and the authors from various countries have been working elaborately indicating that there has been a good amount of usage of Raspberry Pi in the healthcare domain. Overall, our results demonstrate the trending topics the authors currently working on and collaborations amongst authors and countries. Finally, this paper identifies that there are no motor themes but displays the budding keywords (or the ideas where authors have worked on) in the health care domain emerging with the prototyping of Raspberry Pi.

Arduino, an open-source electronics platform, has become the go-to option for anyone working on interactive hardware and software projects. An Arduino board (such as the Uno) connected to a breadboard with plugins such as inputs, sensors, lights, and displays can be controlled by a code written in the Arduino development environment. How to achieve this is by prototyping with Arduino. Prototyping with Arduino has grown in popularity with the increased use of the Arduino platform. Prototyping with Arduino, however, is not an easy task for nonprogrammers with interest in the field. With increased public interest in the field will come a need for accessible information. This paper presents a methodical literature review intended to intensively analyze and compare existing primary studies on prototyping with Arduino. We found about 130 of such studies, all peer-reviewed and published within the last 15 years, including these years (2015–2020). These studies were tediously and carefully chosen through a three-step process. In this paper, a cautious analysis of selected studies was followed by a clear description of the methods applied. The methods were categorized according to the success rate of the studied prototypes. Results obtained can be used in researches on the best technique to adopt while prototyping with Arduino. They can also be used in electronics researches and by individuals who wish to obtain a guide on prototyping with Arduino despite lacking grounded knowledge of the subject matter.

In this chapter, Inverse Synthetic Aperture Radar, a special type of active microwave synthetic aperture radar is introduced and its applications in military surveillance are presented. Then, the basic principles involved in data acquisition and image generation are explained. The issues and challenges involved in processing the ISAR images for autonomous target detection and identification are discussed later. The proposed classification method is explained and its accuracy is evaluated experimentally against the conventional classification method in the rest of the chapter.

In this paper a new classification method is proposed to classify the ISAR images automatically based on Abridged Shape Matrices (ASMs). Initially, a considerate noise removal procedure is used to abate the noise present in the ISAR images and the target is segmented out from the background clutter. ASMs are obtained from the segmented targets by careful interpolation of the shape details of the target by the polar quantization. ASMs are concise and non redundant as the over sampling is avoided in interpolating the inner shape details of the target. The avoidance of superfluous interpolations in polar quantization reduces the generation time of the ASMs, which in turn curtails the over all execution time of the classifier. Experiments were conducted on synthesized ISAR aircraft image dataset and results are presented. The experimental results show that the proposed method is sturdy and more meticulous than existing methods.