Search

Rice disease has a substantial impact on agriculture production, and accurate rice disease diagnosis is more significant for farmers' economic development. Deep learning algorithms have made a massive impression in the context of agricultural disease identification in past few years. However, there are a number of detection techniques available, some of which may not be quite as effective as they might be. Timely detection and identification of specific disease help significantly in disease control and management. In this regard, deep learning-based convolution neural network model is developed to equip the diagnosis process for early detection. The proposed prototype is introduced by integrating XGBOOST ensemble learning model with Keras Inception ResNet V2 Framework for solving various tasks like classification of input images, object segmentation and image feature extraction. Initially, rice plant images undergo pre-processing stage for rotating, flipping, cropping and scaling to enhance image quality for the process of training and classification. The Adam optimizer is used to further optimize the proposed framework by making the learning and training process more efficient. The proposed model is applied to the augmented dataset and establishes a benchmark performance in terms of accuracy, precision, and recall. The findings of this investigation will help to increase the practice of deep learning technology in agriculture for earlier plant disease diagnosis and prevention.

Stress is the way that everyone can respond actually, intellectually and sincerely to different conditions, changes and requests in our lives. Stress problems are a typical issue among working experts in the business today. With changing way of life and work societies, there is an expansion in the stress among the representatives. However, numerous ventures and corporate give emotional wellness-related plans and attempt to facilitate the work environment climate, the issue is a long way from control. When it comes to Pregnant Women, the uterus climate assumes a fundamental part in future development and improvement of hatchling. Stress during pregnancy will influence the sensitive climate of the hatchling. These can remember impacts for your unborn child’s development and the length of incubation period. They can likewise expand the danger of issues in your child’s future physical and mental turn of events, just as social issues in youth. By using various machine learning techniques, the proposed model can analyze the stress in a working professional and also in a pregnant woman. We can predict the best way of yoga to reduce their stress and get good work results from working employees and a good growth in fetus of a pregnant women. Yoga can positively affect the parasympathetic sensory system and helps in bringing down heartbeat and circulatory strain. This decreases the interest of the body for oxygen and furthermore increment lung limit. Compelling utilization of yoga can likewise decrease the odds of stress, nervousness and despondency.

GenPop is a web based online cross platform tool developed to help Geneticist and Epidemiologist to deal with association studies in analyzing human population genetic data. The tool features include descriptive analysis such as Hardy-Weinberg equilibrium test, chi-square p-value and analysis of single nucleotide polymorphisms (SNPs) with multiple inheritance models such as dominant, recessive, allelic, genotype, odd's ratio and relative risk at 95% confidence interval and analysis of multiple SNPs including haplotype frequencies and linkage disequilibrium for a pair of biallelic markers. This is a user-driven human population genetic data analysis tool that is easily scalable and acceptable with multiple implementations of different algorithms. GenPop has been developed using PHP, JavaScript and with PHPExcel library to analyse the genetic data for case control studies.

Cardiotocography (CTG) is a biophysical method for assessing fetal condition that primarily relies on the recording and automated analysis of fetal heart activity. The quantitative description of the CTG signals is provided by computerized fetal monitoring systems. Even though effective conclusion generation methods for decision process support are still required to find out the fetal risk such as premature embryo, this proposed method and outcome data can confirm the assessment of the fetal state after birth. Low birth weight is quite possibly the main attribute that significantly depicts an unusual fetal result. These expectations are assessed in a constant experimental decision support system, providing valuable information that can be used to obtain additional information about the fetal state using machine learning techniques. The advancements in modern obstetric practice enabled the use of numerous reliable and robust machine learning approaches in classifying fetal heart rate signals. The Naïve Bayes (NB) classifier, support vector machine (SVM), decision trees (DT), and random forest (RF) are used in the proposed method. To assess these outcomes in the proposed method, some of the metrics such as precision, accuracy, F1 score, recall, sensitivity, logarithmic loss and mean absolute error have been taken. The above mentioned metrics will be helpful to predict the fetal risk.

Data mining is the practice of examining unknown patterns of data according to diverse viewpoints for classification into valuable information, which is composed and gathered in collective areas, such as data warehouses.For effective analysis, data mining algorithms enabling business decision making and other information necessities to eventually cut costs and raise revenue. Sentiment analysis is the method of defining the emotional tone behind a sequence of words, used to gain an accepting of the attitudes, opinions and emotions conveyed within an online mention. Sentiment analysis is tremendously useful in social media observing as it allows us to gain a synopsis of the broader public opinion behind definite topics. The applications of sentiment analysis are extensive and influential. The ability to abstract insights from social data is a practice that is being broadly adopted by organizations across the world. In this paper, we focused on sentiment analysis on the twitter data.

The key focus of this venture is to evaluate the calibration of classifiers built on rules, trees, and functions by exploring the uncertain information that exists in the Cardiotocography (CTG) dataset. Classification is imperative in diagnosing the health of the foetus and new born specifically in critical cases. It facilitates the obstetricians in acquiring the information of foetal well-being in pregnancy, substantially for the woman with complications. The research aims to classify the CTG data points into normal, suspicious and pathologic. Rules, trees, and function-based classifiers are applied in machine learning for predicting the health of the new born. Particle Swarm Optimization (PSO) is used in pre-processing for selecting the relevant features. Rough set approximations are exploited in extracting the uncertain information from the data set. The result reveals the importance of useful information present in the uncertain data during classification. In this paper, the overall highest accuracy is displayed by Random Forest classifier with 99.57% and a tree-based approach has shown its supremacy over other approaches.

The electronic patient record (EPR) data sharing is a critical and major challenging issue in cloud environment. The processing chain of EPR mainly includes record collection, record storage, record sharing, etc. Conventional healthcare system often requires the delivery of EPR to the cloud which involves user-sensitive information and causes correspondence vitality utilization. Practically, EPR data sharing is a critical and challenging issue. In this work, we proposed a novel technique healthcare system by effectively handling the EPR data in cloud storage. The management of keys has consistently been a security threat of healthcare system; anyway, its belonging has been intensified after presentation of the cloud; that is why key management needs to be performed effectively. Our novel approach can only be done by securing the process of key management. This is the best way to guarantee that touchy data is not weak when it is setting off to the cloud. Furthermore, keys should be mutually made sure about, and the recovery cycle ought to be troublesome and tedious to ensure that information can never be gotten to without authorization. Finally, in order to protect the healthcare data from criminal attackers by our approach, our experiments are demonstrated.

In a bacterial population, the cell-to-cell communication using chemical molecule as a signal in order to perform a collective task is called as quorum sensing. This communicating mechanism regulates the gene expression depending on the population density and dictates the fate of a cell. Quorum sensing regulates gene expression of important traits such as the production of extracellular polysaccharides, enzymes, antibiotics, siderophores, and pigments, virulence, motility, biofilm formation, bio-luminescence, competence, conjugation, sporulation and symbiosis. In order to control these physiological activities that are harmful to the host like humans, animals and plants, understanding of how the quorum sensing phenomenon regulates the gene expression is essential. In this review paper, we have discussed about the mathematical modelling framework used to capture quorum sensing phenomenon. These frameworks are based on the consideration of various factors such as spatial constrains, production of common good and population dynamics. These framework can be simulated using either deterministic modelling approach when average behavior of the population is sufficient to study quorum sensing or stochastic modelling approach when variation in quorum sensing among the individuals in a population occurs.

The operating temperature of electronic devices plays a vital role in its durability of operation. When the electronic chip surface temperature increases beyond threshold limit, it undergoes breakd...

As there is a larger need for drinking water, expensive methodologies are employed in order to get portable drinking water. This work aims at improving the yield of freshwater from a conventional solar still using the different low-cost energy storage material. Theoretical and experimental studies are carried out to analyze the performance of a single slope solar still. From this study, it is observed that the yield of freshwater from the solar still with spherical ball salt storage achieves the maximum yield of 3.7 kg/m2 as compared to a conventional single slope solar still with sponge and without any storage material as 2.7 and 2.2 kg/m2 respectively. The deviations between theoretical and experimental values for with spherical ball salt storage, with sponge and conventional solar still are found as 16.1%, 9.7% and 4.0% respectively. Payback period of the present solar still is found as 4.3 months as it is quicker than other conventional single slope solar still. Finally, single slope solar still with spherical ball heat storage gives low cost of water.

Having understood the strategic significance of the flourishing cloud idea, enterprises across the globe are keenly strategizing and executing to embark on the cloud journey with all the clarity and confidence. There are product vendors bringing forth additional capabilities to easily and quickly setup and sustain competent cloud environments, which are being positioned as the one-stop IT solution for worldwide business organizations. The business domains such as governments, retail stores, healthcare providers, telecommunication service providers, supply chain and logistics, utilities, homeland security, etc. are keenly embracing the cloud idea to be ahead of their competitors in their operations, outputs, and offerings. However, there are some critical challenges and concerns being associated with the cloud paradigm. The widely quoted non-functional requirements (NFRs) and the quality of service (QoS) attributes such as security, performance, reliability, modifiability, and availability have to be fulfilled by cloud software, platform and infrastructures in order to boost the confidence level of business executives and institutions. There are mission-critical and emergency services, which are finding their residence in cloud environments (private, public, and hybrid). Their requirements are quite unique and hence researchers across the globe are striving hard and stretching further to bring forth innovative, disruptive, and transformation technology solutions to fulfill the various needs. This chapter proposes a cloud-based network architecture that contributes a consistent and ubiquitous internet connection. The mesh topology is recommended here to ensure that the connectivity is available all the time without any fail and slowdown. The security of data when it gets transmitted over channels, persisted in data stores, and used by applications, has to be ensured in order to boost the confidence of data owners and users. Hence, this chapter proposes a secure cloud-based heterogeneous network using a novel routing protocol.

A remote mechanism-based new technology called wireless body area network (WBAN) is provided to observe and collect patient health record data with the aid of some wearable sensors. It provides privacy for healthcare professionals and an excellent degree of system security and also plays a major task in storing and ensuring the patient's records. A novel focus for preventing resources of wireless sensor network is implemented to bring a convenient plat form for the healthcare professionals. The adaptable energy efficient MAC protocol is presented in this chapter for the preservations of energy, and its result is discussed for the healthcare analysis.

The student enrollment for higher study kept on decreasing continuously especially for the past five years. This is affecting the higher education institution drastically – threatening the very existence and sustenance leave alone their sustained growth. Why is this capricious global trend? What is the mitigating solution for the revival? The answers to these questions are being attempted to in this paper by making use of Big Data concept. The four phases of big data namely data generation, data acquisition, data storage and data analytics on various parameters of the student data set from Valdosta state university (VSU) are being adopted for the analysis. The main causes for the epidemic are academic stress, demography, co-student behavior and uncertainty about the future. This paper also address the open issues of big data that promotes the cross function of science and technology that triggers the thinking revolution.

Data mining is the process that is used to extract the meaningful information from the large size dataset. The effective dataset utilization depends on the proper classification of outliers. The main objective of the outlier detection is to extract the abnormal data with inconsistency. The information collection from the different mechanisms is uncertain in nature. The data uncertainty causes the knowledge imperfections namely, vagueness and indiscernibility. The proposed research work implements an efficient fuzzy–rough set classifier for an outlier detection with less computational complexity. The fuzzy logic utilization and the fix of abnormal data easily determine the outliers in the large size database. The proposed classifier is compared with the existing classification methods with performance parameters like average running time, average execution time, execution time, false negative, false positive, true negative, true positive, precision, recall, and accuracy. The comparative analysis depicts the effectiveness of classifier in outlier detection.

In cloud computing environment the owners store their data from their local system to the cloud storage. More data owners store large data into the cloud storage. New security challenges are there, when owner store their data in the cloud storage ie the data owner may be bothered that the data could be misplaced or modify in the cloud storage. This is because in any infrastructure the data loss may happen due to hardware and software failure and human error. Sometimes, the cloud service providers itself may remove the data which has not been used or not often used to enlarge the storage space. We recommend a new scheme to validate the availability and integrity of the outsourced files which uses the checksum value and is implemented using Hadoop. The proposed method requires less computation and storage.

Nowadays, the scientific problem becomes very complex; therefore, it requires more computing power and storage space. These requirements are very common in an organization while dealing with current technological data and requirements. Based on these basic requirements, need of higher computational resources is an important issue when dealing with current technological methodology. Hence, cloud computing has become the most important computing paradigm of recent world. The cloud computing is an open source and using Internet as network model. Rapid growth in the field of &#34cloud computing&#34 also increases severe security concerns, because security has a constant issue. This study reviews security models of cloud computing.

In this study, an efficient routing algorithm for WHAN in private cloud was proposed. Pervasive computing based facilities that are genuinely user-friendly to everyone will require technologies that enable communication between people and objects in close proximity. Since to the context of conventional technologies is "intra body" communication in which the whole human body serves as the transmission medium. The human body can transmit up to 10 mbps at a fraction of time. For these environments we need high transmission rate of scheduling the packets, reliability, integrity and security in packet delivery. Hence we proposed a new algorithm called near field coupling algorithm for packet scheduling, Routing and delivery within the Wireless Human Area Network. Our proposed algorithm reduces the energy consumption, packet routing and scheduling time which uses WHAN as basic framework for transmission. Here our communication channel is optimized through the cloud environment. Experimental results demonstrating our proposed methodology was also included.

Cloud computing facilitates extremely scalable serv ices that can be consumed over internet. An importa nt aspect of the cloud services is that user data are stored remotely in unknown machines in which users do not posses or manage. Since the data’s are stored remot ely, we have to keep in mind that sensitive cloud d ata have to be encrypted before they are outsourced to the commercial public cloud, which makes efficient data utilization service. Searchable encryption file ret rieval technique allows users to securely search ov er encrypted data through search word. Ranking the fil es based on relevance scores greatly enhances syste m usability by making it possible relevance ranking i nstead of sending unwanted results and further ensu res the file retrieval accuracy. In this study, we are developing an automated system for both named and unnamed documents based on the clustering algorithms. We implement the ranking and searching algorithm to retrieve top k files. We also provides the mapping and encryption algorithm to protect the information . The resulting design is able to provide efficient ranki ng which will reduce the search time drastically an d reduce the communication overhead. The mapping and encryption algorithms protect document against an outside attackers and prevent an untrusted cloud data provi der from learning data.

In real world data mining is emerging in various er a, one of its most outstanding performance is held in various research such as Big data, multimedia minin g, text mining etc. Each of the researcher proves t heir contribution with tremendous improvements in their proposal by means of mathematical representation. Empowering each problem with solutions are classified into mathematical and implementation models. The mathematical model relates to the straight forward rules and formulas that are related to the problem definition of particular field of domain. Whereas t he implementation model derives some sort of knowledge from the real time decision making behaviour such a s artificial intelligence and swarm intelligence an d has a complex set of rules compared with the mathematical model. The implementation model mines and derives knowledge model from the collection of data set and attributes. This knowledge is applied to th e concerned problem definition. The objective of our work is to efficiently mine knowledge from the unstructured text documents. In order to mine textu al documents, text mining is applied. The text mini ng is the sub-domain in data mining. In text mining, the proposed Virtual Mining Model (VMM) is defined for effective text clustering. This VMM involves the le arning of conceptual terms; these terms are grouped in Significant Term List (STL). VMM model is appropriate combination of layer 1 arch with Analysis of Bilateral Intelligence (ABI). The frequent update o f conceptual terms in the STL is more important for effective clustering. The result is shown, Artifial neural network based unsupervised learning algorit hm is used for learning texual pattern in the Virtual Min ing Model. For learning of such terminologies, this paper proposed Artificial Neural Network based learning a lgorithm.

Entertainment in the real world becomes a popular era and it is long lasting for several decades. The major advancement in television as well as in projection leads to highest quality in terms of realistic pictures, images and movies. Various researchers and research forums are under the development of stereoscopic conversion of 2D program material into 3D realistic. Due to less availability of 3D videoscopic displays, we proposed a new methodology to convert 2D array of video sequence into stereoscopic 3D.The proposed methodology focuses on depth array conversion of back grounds from the 2D video and subtracting the active objects in each scenes at every frames, this yields to obtain the depth information from the video which requires heavy computation in real time, which was achieved by Cryengine with AMD QUADCORE A6 CPU, as well with Radeon graphics. Experimental results shows that 3D recognition rate of a single image in the 2D video sequence is up to 78% and display rate of the particular sequence are at 29 frames per second. Experimental results has been included and 3D display rate for the converted sequence is up to 92% accuracy and frame rates be 32 frames per second for FULL HD (1080 p).

A vital issue of routing is how to efficiently stre ngthen energy consumption of the whole network and to avoid the energy-hole which leads to node failure o r node death; this scenario makes the network to wo rk improperly and leads to network death, Here we proves our hypothesis with linearity between routing an d linear principles. Our proposed work effectively ut ilizes the adaption of Optimized particle swarm algorithm (Fast Reactive and fast adaptive algorith m) in order to solve the routing problem in wireles s sensor networks to avoid the energy hole. Our appro ach effectively defines the node leader based on en ergy level and path optimization for node traversing usi ng particle swarm which effectively utilizes the so lution for problem in linearity into routing problem. Our algorithm FFA redefines the particle swarm rules wh ich are reliable in routing strategies and adapts to th e working principle. The optimization in our algori thm is to balance energy level and to withstand for its conte xt. This study proves the accuracy using our algori thm respectively by theoretical survey and analysis wit h simulated results.

Utilizing cloud computing, users can avail a compelling and effective approach for information sharing between collective individuals in the cloud with the facility of less administration cost and little maintenance. Security in cloud computing refers to procedures, standards and processes created to provide assurance for security of information in the cloud environment. In this paper, we project a secure data sharing method in cloud for dynamic members by producing keys for users using Logic Key Hierarchy (LKH) model, i.e., a tree-based key generation technique. We have generated this key using reverse hashing and one way hash-based technique so that no exiled user can predict the new key and new users cannot predict the old keys of the network group. From numerous experiments, this work is proved to be the best in maintaining forward secrecy, backward secrecy and group compromise attacks and consumes less computation cost compared to any other hash-based key generation techniques.