The outbreak of chronic diseases such as COVID-19 has made a renewed call for providing urgent healthcare facilities to the citizens across the globe. The recent pandemic exposes the shortcomings of traditional healthcare system, i.e., hospitals and clinics alone are not capable to cope with this situation. One of the major technology that aids contemporary healthcare solutions is the smart and connected wearables. The advancement in Internet of Things (IoT) has enabled these wearables to collect data on an unprecedented scale. These wearables gather context-oriented information related to our physical, behavioural and psychological health. The big data generated by wearables and other healthcare devices of IoT is a challenging task to manage that can negatively affect the inference process at the decision centres. Applying big data analytics for mining information, extracting knowledge and making predictions/inferences has recently attracted significant attention. Machine learning is another area of research that has successfully been applied to solve various networking problems such as routing, traffic engineering, resource allocation, and security. Recently, we have seen a surge in the application of ML-based techniques for the improvement of various IoT applications. Although, big data analytics and machine learning are extensively researched, there is a lack of study that exclusively focus on the evolution of ML-based techniques for big data analysis in the IoT healthcare sector. In this paper, we have presented a comprehensive review on the application of machine learning techniques for big data analysis in the healthcare sector. Furthermore, strength and weaknesses of existing techniques along with various research challenges are highlighted. Our study will provide an insight for healthcare practitioners and government agencies to keep themselves well-equipped with the latest trends in ML-based big data analytics for smart healthcare.

/pdf/a-comprehensive-survey-on-machine-learning-based-big-data-15umb5se5n.pdf

A Comprehensive Survey on Machine Learning-Based Big Data Analytics for IoT-Enabled Smart Healthcare System

There is a growing research interest in studying microgrids as a way to overcome the lack of access to energy. These microgrids could be the key to global energy access because of their many advantages related to flexibility, efficiency, and reliability. Despite all these qualities, microgrids remain challenging to implement in a sustainable and resilient way without a clear consensus on what causes these failures. To this end, this work proposes a new paradigm to make a multidisciplinary and comprehensive review of the operation of microgrids. By reconciling the different fields inherent to microgrids, this review enables the study of microgrids within a unified framework. Microgrids will be presented through energy, information, financial, and social fields to provide the necessary elements for their systemic understanding. Each field will be presented with its internal elements, architecture, and significant issues. By elaborating on this new vision of microgrids, this article hopes to open the way to a deeper understanding of their systemic operation and diagnose their long-term sustainability.

/pdf/understanding-microgrid-sustainability-a-systemic-and-1wllyd4q.pdf

Understanding Microgrid Sustainability: A Systemic and Comprehensive Review

This study presents a new deep learning approach based on capsule networks and ensemble learning for the detection of plant diseases. The developed method is called as multi-channel capsule network ensemble. The main innovation behind the proposed method is the use of multi-channel capsule networks, individually trained on images applied different preprocessing techniques and then combined together. In this way, the final ensemble can better detect plant diseases by making use of different attributes of the data. Our experiments carried out using a well-known data set and various state-of-the-art classification methods demonstrate that our classification approach can provide competitive advantages in terms of classification accuracy.

/pdf/multi-channel-capsule-network-ensemble-for-plant-disease-4141mnp7l5.pdf

Multi-channel capsule network ensemble for plant disease detection

Nowadays, there is a significant need for maintenance free modern Internet of things (IoT) devices which can monitor an environment. IoT devices such as these are mobile embedded devices which provide data to the internet via Low Power Wide Area Network (LPWAN). LPWAN is a promising communications technology which allows machine to machine (M2M) communication and is suitable for small mobile embedded devices. The paper presents a novel data-driven self-learning (DDSL) controller algorithm which is dedicated to controlling small mobile maintenance-free embedded IoT devices. The DDSL algorithm is based on a modified Q-learning algorithm which allows energy efficient data-driven behavior of mobile embedded IoT devices. The aim of the DDSL algorithm is to dynamically set operation duty cycles according to the estimation of future collected data values, leading to effective operation of power-aware systems. The presented novel solution was tested on a historical data set and compared with a fixed duty cycle reference algorithm. The root mean square error (RMSE) and measurements parameters considered for the DDSL algorithm were compared to a reference algorithm and two independent criteria (the performance score parameter and normalized geometric distance) were used for overall evaluation and comparison. The experiments showed that the novel DDSL method reaches significantly lower RMSE while the number of transmitted data count is less than or equal to the fixed duty cycle algorithm. The overall criteria performance score is 40% higher than the reference algorithm base on static confirmation settings. 

Data-Driven Self-Learning Controller for Power-Aware Mobile Monitoring IoT Devices

Impact of temperature condition in crop disease analyzing using machine learning algorithm

The development of brilliant things associated with the Web is relatively in-wrinkling on the world. The IoT-network is empowering the association between the articles or devices and the backend frameworks by means of the Internet to impart. Existed correspondence advances gathers in-field information and after that transmit it to the data center where analytics are examined are connected to it, however, this is no longer survive capable by the development of IoT in which interchanges are more than the communication of human-to-human (H2H) and machine-to-machine (M2M). Effective correspondence innovation is regularly testing because of ultra-low power utilization, handling and capacity abilities, which have significant sway on the feasible throughput and parcel gathering proportion just as idleness. Therefore, every one of these variables makes it is hard to choose a suitable innovation to streamline correspondence execution, which dominatingly relies upon the given application. New methodologies and new advancements are required to change huge measures of gathered information into significant data and furthermore can meet the necessities for gigantic IoT in the 5G period. This paper provides a picture of the main wired medium, wireless communication technologies, and cellular communication technologies for massive IoT in the 5G era (eMTC and NB-IoT) with its features and technical characteristics that means to enable the user to pick a reasonable and satisfactory IoT correspondence innovation for claim requests in the colossal number of assortment. This review gives an exhaustive perspective on the correspondence technologies for IoT availability.

Comprehensive Survey of IoT Communication Technologies

In many real-world applications, different features can be obtained and how to duly utilize them in reduced dimension is a challenge. Simply concatenating them into a long vector is not appropriate because each view has its specific statistical property and physical interpretation. Many dimensionality reduction methods have been developed to identify this lower-dimensional space and map data to it, reducing the number of predictors in supervised learning problems and allowing for better visualization of data relations and clusters. However, the plethora of dimensionality reduction techniques provides a variety of nonlinear, linear, global, and local methods, and it is likely that each method captures different data features. Ensemble methods have achieved much success in supervised learning, from Random Forest to AdaBoost. Ensembles exploit diversity and balance bias, variance, and covariance to achieve these results is likely that disparate dimensionality reduction methods will enhance diversity within a dimensionality reduction-based ensemble. AdaBoost and Random Forest are popular ensemble methods which are widely used for classification of target variables. Major problem with ensembles like AdaBoost and Random Forest is that they perform worse when dimensionality of data is high. Random Forest is the predictor ensemble with a set of decision trees that grow in randomly selected subspaces of data. The proposed research work aims to improve the performance of classification tasks on diseased plants by exploring t-distributed Stochastic Neighbor Embedding (t-SNE) based Ensemble Models. The infected and healthy plant images are subjected to deep learning model to produce their corresponding image embedding. The high dimensional data with thousands of features is then reduced to a smaller number of features dataset by the state-of-the-art t-SNE algorithm. The significant feature dataset is then given as input to the ensemble models to perform the prediction task.

Improving the Accuracy of Prediction of Plant Diseases Using Dimensionality Reduction-Based Ensemble Models

The trend of cloud computing has started from the beginning of Amazon’s cloud services in 2006 despite its extravagant beginning in its starting years now cloud computing is easily one of the trending concepts in computer science engineering. Cloud computing has shown tremendous amount of results in various sectors. This case study helps to find out the similarities and contrasts between different cloud service providers in terms of their technical aspects and range of services provided by them. This case study was used as a subjective methodology for sampling. Since we all know the boom of cloud services that play a vital role in our lives, we do not know the background process in the cloud world. Cloud services are mostly offering renting access to enormous pool of computational power and accounting capacities to the resources. Generally, these are cloud-based‬ infrastructure which describes on characterizing the accounting arrangements for obtaining resources. Most vitally cost-effective strategy is most useful so that the cloud can be purchased at low price and can be used as proficiently as conceivable as possible. ‬With this case study, the readers can get insight of what cloud computing is, what are the various cloud services considered for this paper and various cloud providing systems so that users can purchase which is best and cheap related to the platform they are using.

Cost Effective Model for Using Different Cloud Services

Random linear network coding gained its importance in recent days with its greater potential to enhance the performance of the IoT systems. But the challenging issue is the matrix multiplications and inversions involved in it. Nowadays, with increase in multimedia streaming formats, IoT devices like smartphones will try to make full use of heterogeneous multicore architectures, which are drawing everyone’s attention. The approach presented in this paper is the improvement of matrix operations through optimized operations on matrix blocks. We can schedule the operations on matrix blocks in the heterogeneous cores through directed acyclic graph (DAG). The utilization of computer technology to complete the task is known as computing. It is the process of using computer to complete a given goal-oriented task. Here, we make use of different types of computing in order to solve the problem of high computation of matrix operations. RLNC encoding and decoding achieved higher throughputs than already available approaches.

Study and Analysis of Matrix Operations in RLNC Using Various Computing

In this research work, we study the ubiquitous IoT-based applications, systems and technology amongst areas like healthcare, personal assistance, social interactions, agriculture, environmental conditions, traffic management and home control. We further explore to seek out the common trends, framework and design methodology followed in these systems in order to propose an omnipresent generic architecture which can be used unanimously across all these domains along with their respective plug-ins to achieve their specific functionalities. We go further and verify our proposed architecture against the functionalities of various IoT applications. Hence, the final output of this research is a Generic Architecture for Ubiquitous IoT Applications, which can be used as a base architecture to build upon by specifying domain-oriented functions.

M. Rajasekhara Babu

Papers

Comprehensive Survey of IoT Communication Technologies

Improving the Accuracy of Prediction of Plant Diseases Using Dimensionality Reduction-Based Ensemble Models

Cost Effective Model for Using Different Cloud Services

Study and Analysis of Matrix Operations in RLNC Using Various Computing

Generic Architecture for Ubiquitous IoT Applications