Paper Title

PATTERN CLASSIFICATION TOOLS FOR ROBUST LOSS FUNCTIONS

Abstract

Image denoising using hierarchical structure facilitates extracting multiple features from noisy images when training a deep convolutional neural network (CNN). However, to further improve the denoising performance, there still has a tricky path to be treaded among increasing receptive fields, reducing information loss, raising feature utilization, and keeping computational complexity down. Besides, the choice of the loss function is mostly empirical without a convincing explanation. Our study proposes a novel method based on deep CNN for image denoising, which combined an adaptive hierarchical concatenated network with a robust loss function (ACRNet). The proposed method uses the hierarchical structure as backbone network architecture. Each level consists of residual learning and densely connective convolution layers with Mish activation function responsible for feature utilization and training process stabilization. Then, we integrate an adaptive sampling algorithm into the network to achieve a better trade-off among the large receptive fields, low computational complexity, and few information losses.
KEYWORDS : hierarchical structure, convolutional neural network (CNN), robust loss function, network architecture.

Paper Title

METHODS FOR IMPROVING MACHINE LEARNING TECHNIQUES

Abstract

In the current age of the Fourth Industrial Revolution (4IR or Industry 4.0), the digital world has a wealth of data, such as Internet of Things (IoT) data, cyber security data, mobile data, business data, social media data, health data, etc. To intelligently analyze these data and develop the corresponding smart and automated applications, the knowledge of artificial intelligence (AI), particularly, machine learning (ML) is the key. Various types of machine learning algorithms such as supervised, unsupervised, semi-supervised, and reinforcement learning exist in the area. Besides, the deep learning, which is part of a broader family of machine learning methods, can intelligently analyze the data on a large scale. In this study, we present a comprehensive view on these machine learning algorithms that can be applied to enhance the intelligence and the capabilities of an application. Thus, this study’s key contribution is explaining the principles of different machine learning techniques and their applicability in various real-world application domains, such as cyber security systems, smart cities, healthcare, e-commerce, agriculture, and many more. We also highlight the challenges and potential research directions based on our study.
KEYWORDS : Internet of Things (IoT) data, machine learning, Artificial Intelligence (AI), healthcare.

Paper Title

APPLICATIONS FOR BIG DATA BY USING OPTIMIZATION TECHNIQUES

Abstract

As the world is getting digitized the speed in which the amount of data is over owing from different sources in different format, it is not possible for the traditional system to compute and analysis this kind of big data for which big data tool like Hadoop is used which is an open-source software. It stores and computes data in a distributed environment. In the last few years developing Big Data Applications has become increasingly important. In fact, many organizations are depending upon knowledge extracted from huge amount of data. However traditional data technique shows a reduced performance, accuracy, slow responsiveness and lack of scalability. It stores and computes data in a divided environment. Since a decade Big Data Application development has become increasingly paramount. Many organizations are relied on getting knowledge essence from a huge amount of data. However classic data technique demonstration includes reduced performance, accuracy, slow responsiveness and lack of scalability. To resolve the complicated Big Data problem, many of the work has been carried out. For that various types of technologies have been developed. This research paper focuses on the survey of recent optimization technologies and their Applications developed for Big Data.
KEYWORDS : Big Data, Hadoop, Optimization

Paper Title

PURIFICATION ABILITY OF POROUS ASPHALT PAVEMENT

Abstract

PAP has widely used in Europe, the U.S, and Japan. As an effective technology for urban storm water management, PAP not only decreases storm water volumes but also improves runoff water quality including heavy metals, suspended solids (SS) and nutrients. In addition, it help protects groundwater and urban environment. In this paper the current trends of investigating the purification ability of PAP are introduced. The characteristics, the pavement structures and materials are analyzed. The recent researches in field studies and laboratory experiments are highlighted. The present applications of and challenges to PAP are discussed. Further research needs are recommended. Grainstone, algal packstone, algal wackestone, and foraminifera wackestone are porous rock types, and echinoderm wackestone and mudstone are nonporous rock types. The types of pore structure in the study area can be divided into four types. Type I has midhigh porosity and medium-high permeability due to its large throat, while type II has a fine throat type with midhigh porosity and midpermeability.
KEYWORDS : Porous asphalt pavement (PAP), purification ability, suspended solids (SS), pavement structures.

Paper Title

TRANSFORMING DATA AND DEVELOPMENT PROCESS IN CLOUD ENVIRONMENT

Abstract

Cloud computing is a subscription-based service, which provides on demand scalable and elastic services to its customers using virtualization technology. In the real-world environment, cloud computing plays a crucial role which provides different kinds of services through the Internet to the cloud users, according to the requirements. A cloud service provider is an organization that offers IT-related resources, infrastructure and network services to other individuals and ensuring the on-going operation of the overall cloud infrastructure. Due to the distributive feature of computing, cloud environment is receiving greater interest in both academic and industry communities. Personal information can be outsourced by the cloud owners to the cloud server and made use of by the cloud user on public clouds with essential authorization. In order to get the specified outcome, users heavily rely upon the cloud information retrieval mode. Several research works have been conducted in the field of data retrieval employing a keyword dictionary and SQL-like encrypted queries. But an effective ranking of complex query creates considerable challenges.
KEYWORDS : Cloud computing, cloud environment, cloud service, IT infrastructure.

Paper Title

A STUDY ON PEDESTRIAN LEVEL OF SERVICE IN JHUNJHUNU DISTRICT

Abstract

This study seeks to improve pedestrian safety and reduce vehicle-pedestrian interaction. This goal requires find the research area\'s LOS. Level of service (LOS) is used to evaluate vehicle, pedestrian, and bicycle compatibility. HCM defines PLOS levels. The region\'s LOS might be inferred from its PLOS score. In order to compute PLOS, a questionnaire was created to collect qualitative feedback from road users in real time. Data was collected to determine PLOS. Many ages and genders took the survey. All questions were rating-based, in which ratings 1 to 5 are given. Logical questions were included. The pedestrian safety level was assessed and it was found that the area under investigation is a great destination for pedestrians since they feel comfortable and find all the amenities that would tempt them to stroll there.
KEYWORDS : Pedestrian, Level of Service.

Paper Title

THE IMPACTS OF OLD INDIAN MATHEMATICIANS TO SCIENCE

Abstract

Over the course of many thousand years, ancient Indian mathematicians made substantial advancements in a variety of mathematical disciplines, including algebra, number theory, calculus, trigonometry, and measurement. This paper\'s goal is to introduce the mathematical achievements of ancient India\'s thinkers and scholars.
KEYWORDS : Number Theory; Algebra; Mathematics; Pythagoras Theorem.