Search

In the current era, as there is an abundant expansion of functionally similar web services, it becomes a prodigious issue for the web service discovery process. The service classification plays a significant role to greatly reduce the search space and retrieves the desirable service quickly and accurately. The classification is performed using the functional values. Recent research activities recommend RNN (Recurrent Neural Network) deep learning algorithms for efficient classification process. The state-of-the-art of GRU (Gated Recurrent Unit) one of the RNN model, provides a proficient classification process. However, the ratio of training and testing dataset, and hyperparameters namely neural network size, and batch size etc, affects the classification accuracy. The objective of the paper is to incorporate GRU model for efficient classification process. The novelty of the proposed model lies in implementing the GRU model for semantic web service classification. Furthermore, the genetic algorithm is used to predict the optimal ratio of training and testing dataset and optimal hidden neural Network units of GRU model in order to attain optimal classification. The experimental results exemplifies that the semantic web service classification is efficiently deliberated using the proposed GA-GRU model that outperforms the classification process as compared with the conventional semantic extraction using accuracy, precision, F-measure, recall and FDR (False Date Rate) rate.

As a future leading technology, sixth generation (6G) networks should be capable of dynamic allocation of resources, process signals, and change in traffic flow. AI/ML can bring about such solutions to manage such tasks. AI-empowered techniques can be used in optimizing the performance of the network efficiently together with mobile edge computing. AI/ML techniques provide the possibility of producing automatic-learning models for optimized network for 6G wireless networks, which grants operators/providers the access for optimizing parameters of network and automatic network adjustment. In this chapter, the authors explore the various applications of AI/ML in sixth-generation and next generation networks and provide detailed explanation on how AI/ML may be implemented in 6G network effectively. Moreover, they provide possible issues while implementing AI-empowered 6G networks.

A series of Isatin derivative Schiff Base ligands have been prepared by the nucleophilic addition of 5-Bromo Isatin with various amine derivatives and characterized by CHNS analysis and spectral data. Similarly, two of Salicylaldehyde ligand have been prepared by the nucleophilic addition of Salal with amine derivatives. In order to investigate the coordination behavior of these ligands and their metal complexes of the type M(acac)x, L [M = Cu(II), Ni(II); L = Schiff base ligands; x = 0 or 2] mixed ligand (chelate) have been prepared from the reaction of these ligands with their corresponding metal (Ni, Cu) acetylacetonates. The present paper was an approach to understand the chelating mixed ligand formation in complexes. All the isolated Shiff base ligands and mixed acac metal complexes were characterized by using IR, 1H NMR, UV-VIS, molar conductance and TGA/DTA analysis. The biological activities of all the isolated ligands and their corresponding mixed acac metal complexes have been used to screening against the microorganisms both gram positive and gram negative bacteria such as E.coli and S.sureus respectively, fungi A.niger and C.albicans and the results have been compared with standard and control. The main idea of these types of biological screening is to understand the role of these isolated compounds in pharmaceutical industries for drug development.

Universal interconnection networks are prime performance tailback for high performance SoCs (Systems-on-Chip). Since shrinking the size of the ICs (Integrated Circuits) is the main aim, NoC (Network-on-Chip), being a segmental and mountable design tactic is a propitious substitute to outmoded bus-mode architectures. NoC combined with 3D-Routers and label switching technique can guarantee low power consumption, QoS along with less latency. In the proposed work, 3D NoCs are proven to be more advantageous by achieving 39.9% reduction in Area, 1.7% reduction in Power Consumption, and 11.3% reduction in Memory usage.

In the present study, an effort was made to identify the anti hyperglycemic potential of ethanolic extract of Cadaba fruticosa leaves concentrating the enteric system. The glucose-lowering potential was studied by using the in vitro methods such as α amylase inhibitory activity, inhibition of glucose diffusion, glucose adsorption and uptake by yeast cells. In silico methods comprising of the molecular docking of the selected phyto constituents as antagonistic ligands to the disaccharide digesting enzyme α glucosidase and glucose level maintaining enzyme dipeptidyl peptidase IV. The plant extract inhibited α amylase enzyme and the glucose diffusion considerably, which was found to be concentration-dependent. The uptake of glucose by the yeast cells in the presence of the extract was also found to be increased. In the molecular docking analysis based on the docking score, iso quercetin was found to be a potential antagonistic ligand for both enzymes α glucosidase and dipeptidyl peptidase IV since they exhibited similar amino acid interactions shown by the acarbose and Sitagliptin which are the standard competitive inhibitors of these two enzymes. It can be concluded that the leaves of Cadaba fruticosa may serve as a potential anti hyperglycemic drug in future for the management of diabetes mellitus.

Cardiac arrhythmia is an abnormal heartbeat or rhythm. The heartbeat rate becomes too fast or when the heartbeat rate is irregular, the ability of the heart to pump blood will be affected. This will eventually reduce the blood flow through the brain which may result in loss of consciousness, dizziness, or even death if the required procedures are not carried out in time. The main aim of the proposed work is to alert some person or people nearby when a patient has an irregular heartbeat. The proposed work implemented Electrocardiogram integrated with micro-controller that monitor the heartbeat of a person and detects the type of arrhythmia, bradycardia or tachycardia based on the heart rate. The threshold set for bradycardia is 60bpm and for tachycardia is 100bpm. The system detects for the irregularity in heartbeat, which could later lead to an unanticipated event. Since the patient experiencing the attack is powerless during his/her sleep, an alarm is provided which is triggered and SMS is sent to registered mobile number with temperature, pulse rate and SpO2 values with type of arrhythmia in case of abnormality. This would alert people around the patient and then necessary immediate would be taken. The vital values are displayed on LCD.

This paper proposes a cheap and effective method to interface the concept of FUZZY LOGIC and (Antilock Braking System) ABS system used in cars and bikes for preventing the condition of wheel locking and wheel slipping and if wheel slipping occurs then how much of intensity of brake should be applied to keep the vehicle in control of the user. This decision is taken by Fuzzy System which makes decision based on user inputs namely Obstacle, Brake force and Slip ratio. The Fuzzy system gives an Pulse Width Modulation output based on three intensity levels of brake will be applied such as High Brake , Medium Brake and No Brake. Hardware Implementation consists of an MCU which is interfaced with an LCD and DC Series motor which displays intensity of brake applied and motor represents the motion of the actual wheel of a vehicle respectively.

Interfaced embedded technology is evolving in current world. Hospitals and diagnostic centers emerge day by day as people have less awareness of their health issues. For Patients with Specific health issues and old age, monitoring the patients for optimal care and keeping track of the health status at anywhere is extremely tedious. Monitoring should be periodically done and their health status need to be informed to their loved ones from time to time while they are not around. This work propose an innovative system that automated the check system for Pulmonary Fibrosis. The heart and lung can be sources of breathing problems as they work together to bring out the Oxygen rich blood to the body. An ECG sensor trace various physiological and abnormal conditions of the heart. Respiration sensor measures person’s breath/minute. This heart beat sensor measures the heart beat rate. The system also helps to inform the person whether he/she has ILD or not. ILD ends up with heart disease. Whether to check the range of all parameters, AVR controller is used. If the values are not in range, the alert will be sent to the concerned persons using Arduino platform with programming c. The system Speed Rate is very high., the Error rate is less and the Duration is absolutely less. Hence the proposed system has high significance in real time medical applications.

Heart disease has turned into the most critical human disease and Heart failure rate has been increased. Accurate diagnosis and timely treatment is needed to prevent deaths. In this work, the heart disease is effectively predicted by a Machine Learning (ML) model, which is trained with the UCI datasets. Univariate and Multivariate analysis of the dataset is performed using statistical methods and checked for data - imbalanced, skewness/kurtosis in the distribution of data, and the correlation between the features. As distributions of few features show skewness and are not normally distributed, Power transformation technique is used to transform the dataset into normal distribution. Before performing the transformation, outliers are detected in the dataset and removed using the Turkey Fence algorithm. The best features among all features of the dataset are selected based on the correlation matrix and several Feature selection approaches, including Extra Trees Classifier. Random Search and Grid Search techniques are used in tuning Hyperparameters of Logistic Regression algorithms. Performance is evaluated using metrics such as confusion matrix, Accuracy score, precision-recall curve (PRC), and Receiver operating curve (ROC). Seven models are developed with various combinations, among which the model for which power transform, Kernel Principal Component Analysis (PCA) performed on the dataset and finally Gridsearch method used to tune hyperparameters gives the 100% accuracy.

This paper mainly focuses on the function of echo-cardiogram to monitor Heart remotely or in a diagnostic centre.The proposed method enables us to fetch the ECG data from the patient in a non-invasive manner by the use of ECG electrodes and predicting their cardiac load and condition from derived parameters like BPM & QRS complex remotely.BPM/Heart rate is calculated through the Continues Wavelet Transform method. The QRS complex is depicted through the QRS wave interval of heart data. which is then compared with the typical interval to produce a conclusion on heart function. To use and assess accurately the information obtained the data is presented in a collaborative report format so that any cardiac-risk analysis is viable for the doctor and the patient to have a complete idea about the patient's present condition which can help diagnosis prior to the disease taking effect.

Healthcare falls under the basic amenities to be provided to the society. In the current world, Non-invasive diagnostic tests are of prime requirement in the medical field to avoid the painful process of collecting samples. This work aims to develop a portable and affordable diagnostic system to measure basic health parameters such as Body mass index (BMI), temperature, pulse rate, blood oxygen saturation level, blood pressure, and blood glucose content and use the machine learning (ML) models to predict the future health complications that could be used to take preventive measures. In this work, we demonstrated that using only core health parameters many diseases can be predicted with good accuracy. Diabetes is taken as a case study and predicted using the Pima Indian Diabetes Dataset (PIDD) of UCI Machine learning Repository. Diabetes is predicted by extracting only core parameter data and compared with the prediction using the complete data set and resulted in comparatively similar accuracy. Decision tree, Naive Bayes, and K-neighbors classifiers (KNN) are used. KNN outperforms the other two algorithms in prediction in both data sets.

The mechanism of resource allocation plays a vital role in maximizing the network utilization and serving the requesting nodes. This idea can be effectively demonstrated using the concept of network virtualization. Through Network virtualization an environment conducive to perform tests using similar network conditions , applications and dependencies can be created to ease and enhance implementation of network elements in a topology. One important challenge on network virtualization is the efficient use of the physical resources. To accomplish such efficient use the management of the physical resources should be transparent to the applications running within the virtual networks. In this paper we use directed graph to simulate the network and to reallocate virtual network resources along different physical nodes in order to understand the dynamics of resource allocation.The system generates analytical results through graph plotting and statistical analysis of network parameters.

Surface epithelial tumors are the most common neoplasms of the ovary. Among these , mucinous tumors accounts for 14% of ovarian tumors. Coexistence of mucinous tumor with other surface epithelial tumors is rare. We report here a rare case of mucinous cystadenoma of the ovary , with Brenner component in a 52 - year - old post - menopausal woman who presented with chief complaint of mass per abdomen since one month and retention of urine since one week. Coexistence of these two tumors supports the theory of a common origin of surface epithelial tumors from coelo mic or germinal epithelium , and therefore , it undergoes metaplastic change to transitional or urothelial - l ike morphology .

The spur of Grid computing is to aggregate the power of widely dispersed resources, and provide non-trivial services to users. In attempts to utilize a diverse set of resources in grids proficiently, scheduling has been made. The primary intention of scheduling is the minimization of application completion time; however, they may lead to the usage of excess and redundant resources. Our algorithm performs the scheduling b y accounting for both completion time and resource usage. Since the performance of grid resources changes dynamically and the accurate estimation of their performance is very difficult, our algorithm incorporates rescheduling to deal with unforeseen performance fluctuations effectively. Also, fault tolerance is an essential part of the grid. In Grid environments, execution failures can occur for various reasons such as network breakdown, failure or non-availability of required resources. Fault tolerance can be achieved in grids by Over provisioning and Check pointing techniques. Since, over provisioning violates the resource usage control, check pointing strategy is implemented in our proposed method.

Product guarantees or warranties have been around for generations, but formal approaches for establishing and examining warranties have been considered only during the past 20 years. A review of the literature on warranty models and analysis methods is provided, along with some suggestions for further research.

Consumers' perceptions of service quality are highly qualitative as well as subjective. Individual variation exists in the meaning of “low,” “medium,” or “high” levels of service quality. A framework for quantifying the service quality dimension levels for technical support service is presented in the current study. Results are combined with the utility values of the dimension levels obtained through conjoint analysis. Customers' behavioral intentions subsequent to the quality of the technical support they experience are also found empirically. The methodology presented in this research can be used in improving the comprehensibility and quantification of service quality.

Point-process models have been shown to be useful in characterizing neural spiking activity as a function of extrinsic and intrinsic factors. Most point-process models of neural activity are parametric, as they are often efficiently computable. However, if the actual point process does not lie in the assumed parametric class of functions, misleading inferences can arise. Nonparametric methods are attractive due to fewer assumptions, but computation in general grows with the size of the data. We propose a computationally efficient method for nonparametric maximum likelihood estimation when the conditional intensity function, which characterizes the point process in its entirety, is assumed to be a Lipschitz continuous function but otherwise arbitrary. We show that by exploiting much structure, the problem becomes efficiently solvable. We next demonstrate a model selection procedure to estimate the Lipshitz parameter from data, akin to the minimum description length principle and demonstrate consistency of our estimator under appropriate assumptions. Finally, we illustrate the effectiveness of our method with simulated neural spiking data, goldfish retinal ganglion neural data, and activity recorded in CA1 hippocampal neurons from an awake behaving rat. For the simulated data set, our method uncovers a more compact representation of the conditional intensity function when it exists. For the goldfish and rat neural data sets, we show that our nonparametric method gives a superior absolute goodness-of-fit measure used for point processes than the most common parametric and splines-based approaches.