Search

Decentralized Model Reference Adaptive Control problems are investigated for a class of linear time-invariant two time-scale model, having fast and slow dynamics and unmatched interconnections. Design of full state feedback controller is a critical task to the system having interrelated dynamics and nonlinear interconnections of time varying lags, however, can be addressed by singular perturbation procedures and time scale modeling. In this research, full order observer-based state feedback control is designed to two-time scale system to ensure the stability of the closed loop system. Then, decentralized model reference adaptive controller with the novel reference model is designed to individual subsystems. It is found that the proposed design enforces the system states to track the reference state asymptotically. To investigate the proposed design, an example of drying process is considered. Simulation results are analyzed to confirm the efficacy of the proposed control scheme.

Spine canal segmentation is an emerging zone in research proposed to help interpretation and processing of advanced MRI and CT images. For instance, high resolution three-dimensional volumes can be divided to provide an estimation of spine canal atrophy. Spine canal segmentation is complex because of assortment of MRI contrasts and variation in human life structures. This investigation illustrates the details of spine canal segmentation techniques and gives a few measurements that can be utilized to contrast with other segmentation strategies. The details of background and foreground subtraction techniques, spine canal segmentation approach and optimization approach which are utilized in the different applications have been considered. In this paper, spine canal segmentation on probabilistic booting tree (PBT) with fuzzy support vector machine performance measures and metrics are analysed in state-of-the art technologies. Proposed approach is performed on the base of the automatic spine canal segmentation with the group of data MR. This proposed segmentation continue with fuzzy support vector machine (FSVM) technique to make fully automatic stream pipeline. The declaration in an automatic segmentation of stream pipeline was implemented with flexible voxel wise classification accompanying dimensions analogous with 3D Haar and labelled machine learning algorithms i.e. probabilistic boosting tree combined fuzzy support vector machine (PBT-FSVM). The novel segmentation technique correlated with MR data sets provides better accuracy than the exiting techniques and it is shown in experimental outcomes. To still improve performance of the results, online learning classification method can be in the proposed work.

Cloud computing has been employed for supporting storage and handling of Internet of Things (IoT) data. There is an increasing demand for IoT framework to provide services with fast processing time and less delay to offer latency sensitivity real-time applications like disaster management in smart homes. IoT process is mostly comprised of scheduling techniques that makes it hard to self-adapt, self-configure to respond with performance aware on environment changes. Existing scheduling techniques of IoT applications are not based on allocating tasks through sleep modes, which unavoidably lead to more power consumption and longer time delays. Consenting sensor devices and applying separate queueing to a sensor device that varies differently in their capabilities are increasingly significant. In this work, a dynamic management framework for IoT devices in cloud (DMFIC) algorithm is proposed to evaluate and schedule requests and sensor data, which allow coordinating huge data with high time-based resolution in a cost-effectual manner through anticipating various queues for sending an appropriate notification to users. A smart home application was used to demonstrate the proposed framework. The experimental result shows that the DMFIC algorithm gives an average of 5% higher processing time and 0.2% less delay compared to other IoT services and can efficiently manage sensor data in cloud.

In this globalized scenario, the overall performance of the manufacturing industries is the backbone of the development of the countries’ economies. In this research, the authors’ main objective of the study is to segment the manufacturing industries by using the triangular interval-valued fuzzy TOPSIS Method and find out the factors determining its performance. The researchers have collected the data from 350 manufacturing industries located in Puducherry, India. They applied a Simple Random sampling method by using a structured questionnaire from manufacturing industries. To analyze the data, the researchers used software packages like Excel, SPSS and LISREL 8.72. The researchers applied Confirmatory Factor Analysis, Triangular Interval-Valued Fuzzy TOPSIS Method, Chi square and Correspondent Analysis to conclude the result. Based on the factors loadings of the items, the contribution made by the items in respect of Performance may be ranked as Sales growth, Market share, Profit margin and Return on investment. With the help of Triangular Interval-Valued Fuzzy TOPSIS Method researchers segmented the manufacturing industries into three groups and by using the Chi square analysis the researchers found that the five demographics characteristics like Number of years in Business (Company), Scale of industry, Kind of manufacturing, Number of employees and location of the production plant of the respondents and these are significantly associated with segmenting the manufacturing industries and determine the performance of manufacturing industries.

Recently, several abnormal functioning identifiers in the plants and animals to demolish the agricultural production in the field of the agricultural department. Particularly, in the effect of bacteria, fungi, micro-organisms, and viruses are heavily affect the fruits and their leaf. To achieve fantabulous functioning in leaf disease identification is a vital role in the efficient plant’s disease management and its demonstration to the continuous monitoring of bacteria, fungi and micro-organisms viruses persists a vital work that is undertaken or attempted by the agricultural department. To point out the leaf disease in an efficient manner, this article proposed an Advanced Segmented Dimension Extraction (ASDE) with Heterogeneous Internet of things procedural (HIoT) aspects. IoT procedural aspects identified as a repetitive and persistent space in the leaf image. This is also used to find the impact gesture of a leaf image, that insignificant to the identification time to a feasible extent. This paper suggests a Signs based plant disease identification for real-time resembling of leaf diseases namely bacteria, fungi, micro-organisms, and viruses. Diagnosis and Isolation techniques are maintained by Signs based plant disease identification, namely heterogeneous IoT detection. The relying on experiment show that the aimed framework distinguishes a detection of doing plant disease identification successfully accomplishing of 97.35% with a high-detection quotient. In addition to this proposed paper shows the relevance of algorithms for automatic recognition of fine-tuned disease nodes in the isolated leaf image. On the automatic recognition carried out by parsing, localization, normalization and segmentation procedures.

In this article, a simple controller design with the fractional order calculations applies to unstable cascade processes with a significant time delay. Series cascade control system consists of two loops in which the inner loop is designed using the IMC principle based on the synthesis method. The primary controller is designed with the FOPI-FOPD controller to ensure stable and satisfactory closed-loop performances for the unstable processes. For the primary controller, five tuning parameters are involved, which tuned using the centroid of the convex stability region method. Different examples are given to illustrate the superiority of the proposed design over some existing designs. Results obtained from simulation reveals that with the proposed control design, enhanced closed-loop control performances are obtained for nominal and perturbed conditions.

In the past few decades, chronic hepatitis B caused by hepatitis B virus (HBV) has been one of the most serious diseases to human health. The development of innovative systems is essential for preventing the complex pathogenesis of hepatitis B and reducing side effects caused by drugs. HBV inhibitory drugs have been developed through various compounds, and they are often limited by routine experimental screening and delay drug development. More recently, virtual screening of compounds has gradually been used in drug research with strong computational capability and is further applied in anti-HBV drug screening, thus facilitating a reliable drug screening process. However, the lack of structural information in traditional compound analysis is an important hurdle for unsatisfactory efficiency in drug screening. Here, a natural language processing technique was adopted to analyze compound simplified molecular input line entry system strings. By using the targeted optimized word2vec model for pretraining, we can accurately represent the relationship between the compound and its substructure. The machine learning model based on training results can effectively predict the inhibitory effect of compounds on HBV and liver toxicity. The reliability of the model is verified by the results of wet-lab experiments. In addition, a tool has been published to predict potential compounds. Hence, this article provides a new perspective on the prediction of compound properties for anti-HBV drugs that can help improve hepatitis B diagnosis and further develop human health in the future.

Through the revolutionization of artificial intelligence (AI) technologies in clinical research, significant improvement is observed in diagnosis of cancer. Utilization of these AI technologies, such as machine and deep learning, is imperative for the discovery of novel anticancer drugs and improves existing/ongoing cancer therapeutics. However, building a model for complicated cancers and their types remains a challenge due to lack of effective therapeutics that hinder the establishment of effective computational tools. In this review, we exploit recent approaches and state-of-the-art in implementing AI methods for anticancer drug discovery, and discussed how advances in these applications need to be considered in the current cancer therapeutics. Considering the immense potential of AI, we explore molecular docking and their interactions to recognize metabolic activities that support drug design. Finally, we highlight corresponding strategies in applying machine and deep learning methods to various types of cancer with their pros and cons.

Drought is the primary and dominant natural cause of stress on vegetation, and thus, it needs our full attention. Current understanding of drought across extensive spatial measures, around the world, is considerably limited. As case studies to evaluate the feasibility of utilizing space-based solar-induced chlorophyll fluorescence (SIF) across extensive spatial measures, here, we have used data from 2007 to 2017 in Heilongjiang and Jiangsu provinces of China. The onset of the 2015 drought was accompanied by a substantial response of SIF from vegetation in both the provinces; these data were associated with changes in soil moisture, standardized precipitation evapotranspiration index, and emissivity. Our findings suggest that SIF can effectively provide the spatial and temporal progress of drought, as inferred through substantial associations with SIF normalized by absorbed photosynthetically active radiation (related to Φ

This paper concentrates on the modeling and control of the sugar industry's nonlinear clarifier process. Since the sugar industry's clarification mechanism is complex and nonlinear, it is therefore important to obtain the exact model with identification methods. Using the normal modeling technique, the basic model of the complex process is obtained and further improved to make the model act like the actual system. The most accurate model from the algorithms is analysed using metaheuristic algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and State Transition Algorithm (STA). The proposed STA design to the clarifier model provides the maximum fitness. The clarifier model derived from State Transition Algorithm (STA) behaves more similar to the actual clarifier process by capturing the principle dynamic qualities of the process. Simulations have demonstrated that STA is an optimum algorithm for the clarifier process than the other algorithms. From the results, it is inferred that the controllers introduced in this study, can be utilized to accomplish a better performance than the standard controller design, and during the control of any nonlinear procedure and STA is extremely helpful in modeling a nonlinear process.

Blockchain technology is increasingly used worldwide to enhance the performance and profit of any environment through its defining characteristics, such as security, auditability, immutability, and inconspicuousness. Owing to these characteristics, the blockchain can be used in various non-financial operations of some domains, such as the Internet of Things (IoT) and distributed computing. However, implementing blockchain technology in IoT is not always a feasible solution because blockchain deployment is costly, it has limited extensibility and provides irregular bandwidth and latency. In this regard, a simple size extensible (SSE) blockchain has been proposed to provide an optimal solution for IoT environments by satisfying the needs of the IoT environment as well as ensuring end-to-end security. The implementation of the proposed blockchain develops an overlay network to obtain a distributed environment where the blockchain is handled by the resources present therein. Two novel algorithms were introduced into the proposed system to minimize the irregularity and latency on one hand, and to maximize the throughput of the system on the other. The shared-time depending agreement algorithm (STD) minimizes the irregularity in the extraction operation and latency. The other, the shared throughput administration algorithm (STA) justifies the overall collection of the transmission load in the network and maintains the performance of the blockchain. The proposed system was applied to smart home IoT appliances to test the performance of the proposed system. The experimental results show that the proposed blockchain system minimizes nearly 70% of the data irregularity, latency, and furthermore, 30% of the blockchain extensibility is maximized as compared to the existing systems.

The effectiveness of satellite solar-induced chlorophyll fluorescence (SIF) for drought evaluation was measured in this study. Here we compare the association of SIF with soil moisture (SM), precipitation (PPT), standardized precipitation evapotranspiration index (SPEI), and ratio of evapotranspiration (ET) to monitor the drought stress on crop growth. A severe drought occurrence was observed in 2015 as compared to other years between 2007 and 2017 in Xinjiang of China. In the period of this drought, the changes of SIF and SIF normalized by absorbed photosynthetically active radiation ( Φ F ) were obstinate. SPEI and ET were observed with higher sensitivity and much more constant decline in response to drought than SM and PPT. Moreover, Φ F is highly sensitive to drought than SIF, SIF normalized by photosynthetically active radiation ( SI F PAR ) , enhanced vegetation index (EVI), and normalized difference vegetation index (NDVI). The results demonstrate that satellite SIF provides deep insight for drought detection.

This article has been retracted at the request of the first and corresponding author, Dr. Karthik Chandran. The author has alerted the Editor-in-Chief of IJUFKS the reasons for the retraction: The proposed system was modelled with the incorrect data set. The system response has become incorrect because of this incorrect data set. Two percent of the information (mathematical assumptions) was taken from one paper without proper citation of the source.

The largest organ and the outer covering of the human body is the skin. With seven layers of it covering the other organs inside, skin is one of the important part to take care of. A skin condition is one which affects the integumentary system and that includes a wide variety of diseases including dermatoses. Classifications of these skin conditions are always a challenge for any medical practitioner and they look at the machine learning systems to assist them in predicting and classifying the skin conditions. This in turn will help to cure or at least reduce the effect. If the skin symptoms such as acne, cellulitis, candidiasis, varicella, scleroderma, fungal skin, psoriasis, inflamed skin condition, etc. are left without treatment in its initial stage, then they can effect in different health impediments leading to even death. Image partitioning is a method which supports with the skin disease detection. Any abnormal skin growth is referred to as skin lesion which could either be primary or secondary. Graph cut algorithms are debated and used in the literature for variety of purposes including image smoothing, image segmentation and other problems involving energy minimization as objective. In this work, we intend to use a novel dynamic graph cut algorithm for skin lesion segmentation followed by a probabilistic classifier called as Naive Bayes classifier for skin disease classification purposes. We have used ISIC 2017 dataset for testing our proposed method and found that the results outperform many state of the art methods including FCN and SegNet by 6.5% and 8.7% respectively. This dataset is available at the International Skin Imaging Collaboration (ISIC) website for public study and experimentation. In terms of accuracy, we could achieve 94.3% for benign cases, 91.2% for melanoma and 92.9% for keratosis on this data set.

Web services playing a vital role in the World Wide Web and generates huge amount of information across various domains of internet. Due to this evolution data in the form of articles, reports, digital galleries and web data of companies were increased everyday. To handle the huge volume of data each and every day, automatic query classification based on internet is more significant method. Research and development community has developed various techniques for the web services discovery, where it offers the mandated data for the improvement method. With respect to the literature survey, most of the researchers are concentrating to provide the efficient web service discovery. The amount of data that is available in the web is keeps on increasing and also it is used to differentiate the services, explanation and work of art. In order to achieve this method, machine learning algorithm is applied extensively for domain categorization. Various machine learning algorithm like KNN is applied for web service discovery. The systems are effectively learning the input and evaluate the performance accuracy with the given datasets. This paper, proposes an improved fuzzy with KNN algorithm for effective web service classification. This is used to increase an outcome in the form of accuracy and performance measures.