Search

In spite of the insight commonality may have concerning agrarian practice, fact is that nowadays agricultural science diligence is accurate, precise, data-driven, and vigorous than ever. The emanation of the technologies based on Internet of Things (IoT) has reformed nearly each industry like smart city, smart health, smart grid, smart home, including “smart agriculture or precision agriculture”. Applying machine learning using the IoT data analytics in agricultural sector will rise new benefits to increase the quantity and quality of production from the crop fields to meet the increasing food demand. Such world-shattering advancements are rocking the current agrarian approaches and generating novel and best chances besides a number of limitations. This paper climaxes the power and capability of computing techniques including internet of things, wireless sensor networks, data analytics and machine learning in agriculture. The paper proposed the prediction model of Apple disease in the apple orchards of Kashmir valley using data analytics and Machine learning in IoT system. Furthermore, a local survey was conducted to know from the farmers about the trending technologies and their effect in precision agriculture. Finally, the paper discusses the challenges faced when incorporating these technologies in the traditional farming approaches.

Fog computing serves the delay-sensitive applications of the Internet of Things (IoT) in more efficient means than the cloud. The heterogeneity of the tasks and the limited fog resources make task scheduling a complicated job. This paper proposes a clustering based task scheduling algorithm. Specifically, the K-Means++ clustering algorithm is used for clustering the fog nodes. Randomized round robin, a task scheduling algorithm is applied to each cluster. The results show that the proposed algorithm reduces the system's average waiting time.

The recent corona virus disease 2019 outbreak has added to the development of novel methods to study the epidemiological and predictive nature of the pandemic. Mining such data is necessary as this data is full of trends and information. Use of data mining techniques allows us to extract and process such data in order to predict the trends and behaviour of the pandemic. Analysis, evaluation and prediction is performed on Jammu and Kashmir’s data during the period 09th of March 2020 to 10th of February 2021. The work is done on the dataset of patients provided by department of information and public relations, Government of Jammu and kashmir. Various mathematical models and techniques were used to predict the virus spread and occurrence with the help of symptoms. Our aim is to propose a model to predict the virus occurrence based on the symptoms and epidemiological nature of the pandemic. The trends and behaviour of the virus in Jammu and Kashmir was studied. People under observation, number of people tested for the virus, positive, negative, recovered, active and deaths were keenly observed. The prediction to find an infected patient was carried out with the help of symptoms. The results obtained from the prediction model are verified with the actual results.

The combined development of wireless communication, sensing, and Internet has given us many smart things—Internet of things (IoT). These smart things have now changed the lifestyle of humans in many areas. This paper introduces an emerging research area—embedding intelligence (EI) in IoT. The EI in IoT promises a new beginning for the things to react and interact with the humans and environment. The development of EI in IoT has many challenges ahead due to the resource constraints in many smart things. The challenges include human-centric sensing, data collection, complex intelligence modelling, and design. This work has implemented and incorporated EI in IoT at the hardware level and has given design and architecture for the same.

We explore using various machine learning architectures to solve a critical problem of understanding relationship between material stability, the structure of materials, and its properties. Studying the structure of crystals plays a very critical role in understanding the various properties of materials which will in turn help us in determining the stability of the chemical compound. Materials engineers are designing materials for the ever-changing parameters and uses of materials after their initial intended purpose. This topic of material stability is especially important since it could potentially help make reaction stability prediction data driven by developing a method to harness the capability of the density function theory and at the same time use the machine learning to derive the knowledge from existing compounds, and/or from simulations of non-existing ones to not only predict the stability of known alternative materials (crystals, metals, ceramics, polymers, etc.), but also predict the stability of unknown compounds.

Background and objective SARS-CoV-2, a novel strain of coronavirus’ also called coronavirus disease 19 (COVID-19), a highly contagious pathogenic respiratory viral infection emerged in December 2019 in Wuhan, a city in China's Hubei province without an obvious cause. Very rapidly it spread across the globe (over 200 countries and territories) and finally on 11 March 2020 World Health Organisation characterized it as a “pandemic”. Although it has low mortality of around 3% as of 18 May 2021 it has already infected 164,316,270 humans with 3,406,027 unfortunate deaths. Undoubtedly the world was rocked by the COVID-19 pandemic, but researchers rose to all manner of challenges to tackle this pandemic by adopting the shreds of evidence of ML and AI in previous epidemics to develop novel models, methods, and strategies. We aim to provide a deeper insight into the convolutional neural network which is the most notable and extensively adopted technique on radiographic visual imagery to help expert medical practitioners and researchers to design and finetune their state-of-the-art models for their applicability in the arena of COVID-19. Method In this study, a deep convolutional neural network, its layers, activation and loss functions, regularization techniques, tools, methods, variants, and recent developments were explored to find its applications for COVID-19 prognosis. The pipeline of a general architecture for COVID-19 prognosis has also been proposed. Result This paper highlights recent studies of deep CNN and its applications for better prognosis, detection, classification, and screening of COVID-19 to help researchers and expert medical community in multiple directions. It also addresses a few challenges, limitations, and outlooks while using such methods for COVID-19 prognosis. Conclusion The recent and ongoing developments in AI, MI, and deep learning (Deep CNN) has shown promising results and significantly improved performance metrics for screening, prediction, detection, classification, forecasting, medication, treatment, contact tracing, etc. to curtail the manual intervention in medical practice. However, the research community of medical experts is yet to recognize and label the benchmark of the deep learning framework for effective detection of COVID-19 positive cases from radiology imagery.

Ad Hoc wireless sensor network (WSN) is a collection of nodes that do not need to rely on predefined infrastructure to keep the network connected. The level of security and performance are always somehow related to each other, therefore due to limited resources in WSN, cryptographic methods for securing the network against attacks is not feasible. Byzantine attacks disrupt the communication between nodes in the network without regard to its own resource consumption. This paper discusses the performance of cluster based WSN comparing LEACH with Advanced node based clusters under byzantine attacks. This paper also proposes an algorithm for detection and isolation of the compromised nodes to mitigate the attacks by non-cryptographic means. The throughput increases after using the algorithm for isolation of the malicious nodes, 33% in case of Gray Hole attack and 62% in case of Black Hole attack.

As technology is growing at fast rate, things are getting connected with each other through internet thus producing huge amount of data that need processing. Cloud computing provides the processing, storage and analysis of the collected data, but inspite of the fact that cloud usage is increasing rapidly still, there are various limitations such as unreliable latency, lack of mobility support and location awareness. High redundancy, high communication bandwidth and latency adds extra burden to process the data at the cloud. Fog devices located at the edge of the network solves these problems by processing the generated data locally closer to the end devices and hence avoiding the transmission latency and network bandwidth by not sending each and every bit of information to the cloud for processing. In this paper offloading policy at the Fog layer is proposed and it is also discussed how the Fog computing is efficient than Cloud computing in terms of latency.

Since the dawn of Humanity, to communicate both abstract and concrete ideas, visualization through visual imagery has been an effective way. With the advancement of scientific technologies, vision has been imparted to machines like humans do. Computer vision give ability to machines, to receive and analyze visual data on its own, and then make decisions about it, hence computer vision is more than machine learning applied. So, visualization of computer models to learn without being explicitly programmed using machine learning algorithms is called Visual learning. This work aims to review the state-of-the-art in computer vision by highlighting the contributions, challenges and applications. We first provide an overview of important visual learning approaches and their recent developments, and then describes their applications in diverse vision tasks, such as image classification, object detection, object recognition, visual saliency detection, semantic and instance segmentation, human pose estimation and image retrieval. Hardware constraints are also highlighted for better understanding of model selection. Finally, some important challenges, trends and outlooks are also discussed for better design and training of learning modules, along with several directions that may be further explored in the future.

In Underwater Wireless Sensor Network (UWSN) there are many challenges and one of the major challenge is limited battery power. In UWSN it is not possible to recharge or replace the batteries. Also signal attenuation under water is more as compared to the terrestrial WSN. Therefore for the same distance and amount of data we need to use more power to push the signal on the surface of the water as compared to the terrestrial Wireless Sensor Network (WSN). The scenario is further worsen by the fact that in some cases due to water current etc. there is frequent change in the position and location of the nodes with respect to the cluster head or other nodes. Due to the above reasons the routing in UWSN should be energy efficient and adaptive to the changes in the network. This paper proposes an adaptive architecture which is based on the natural algorithms to keep the nodes connected even if they get away from their cluster and a dedicated cluster head named as advanced node is used to overcome the additional power requirements due to the signal attenuation.

Wireless Sensor Networking is a sensor information gathering technology that has a wide range of applications in numerous fields. However due to the fact that sensor nodes have limited battery and are deployed in remote and harsh environments, energy efficient and real time transmission of the information are still open challenges. Since in a wireless sensor network data transmission is the most power consuming task, so far most useful techniques for the purpose of energy efficient and real time transmissions are based on data compression, the majority of them are based on wavelet transform. This paper give performance analysis of different wavelets for energy efficient and real time image data transmission in application like environment monitoring using wireless visual sensor networks. The performance evaluation shows that Haar wavelet is better in terms of energy efficiency and transmission time.

The data analytics using big data is an upcoming field which helps us in getting quick results from structured and unstructured huge amount of data. There are many fields like healthcare, weather forecasting, education etc. where the data analytics can help us in improving the applicability and services provided thereof. In our paper we concentrate on benefits of Big Data in healthcare therein using the global multi-disease data pertaining to different regions. We made analysis using Hadoop. The results show that there is a lot of information hidden within the medical data which can be useful in improving the healthcare in particular region.

Wireless Sensor Networks (WSNs) consist of dense, small, low cost sensors with processing and communication capabilities, provided by a battery source. They have wide variety of applications which include environmental monitoring, structural health monitoring, military surveillance, medical applications, disaster mitigation etc. Sensor nodes have various energy constraints, computational constraints and communicational constraints. Considerable research has been focused to overcome these difficulties. One of the major issues in WSNs is developing energy efficient routing protocols. We have proposed a new protocol. The new protocol show improvement over LEACH protocol in many respects especially in life of a sensor node as presented in the simulation and analysis. (3 pages)