JOURNAL OF ADVANCEMENTS IN ROBOTICS

Visionary Fusion: Empowering Robot Sight with Model-driven Multi-band Enhancement

Ushaa Eswaran, C. Pushpalatha, Shaik Beebi, B. Mallesh — Thu, 21 Dec 2023 00:00:00 +0000

Single image enhancement is crucial for improving visual quality in applications like robot vision. This study proposes a novel topic-model assisted multi-band image fusion method to enhance a single input image while preserving semantic information. The key innovation is using topic models for adaptive band fusion based on image content. Comparative experiments on benchmark datasets demonstrate that the proposed technique outperforms state-of-the-art methods in quantitative and qualitative evaluation. This study also provides real-time demonstrations and case studies in robot navigation, highlighting the efficacy of the proposed fusion strategy. The fused images exhibit finer details and color consistency leading to improved navigation and obstacle avoidance. This technique has wide-ranging applications for computer vision related tasks in autonomous systems.

Accounting and Finance with Robotic Process Automation (RPA)

Vipul Chovatiya — Wed, 31 Jan 2024 00:00:00 +0000

This study explores the potential of robotic process automation (RPA) to transform finance and accounting (F&A) operations. RPA involves utilizing software robots to mimic human interactions with applications, specifically targeting rule-based and repetitive tasks across various financial processes. Key findings: Boosted productivity and efficiency: RPA may result in considerable efficiency improvements by streamlining repetitive operations and freeing up F&A employees to concentrate on more strategic, higher-value work. Enhanced accuracy and compliance: RPA improves reporting accuracy and compliance by ensuring consistency and conformity to complicated financial laws by removing human error in data entry and computations. Reduced costs: Streamlining processes through the automation of time-consuming tasks may result in reduced resource consumption and operating expenses. Improved employee morale: Staff members are more engaged and satisfied at work when they are freed from boring duties, which enables them to work on more rewarding projects. Examples of RPA applications in F&A: Accounts payable/receivable: Creating client statements, initiating payments, processing invoices, and entering data automatically. Bank reconciliation: Simplifying account reconciliation and cutting down on mistake rates and human labour. Financial reporting: Executing duties related to regulatory compliance, report creation, and data aggregation automatically. Payroll processing: Automating timesheet processing, tax preparation, and payroll computations. Tax preparation: Automating the filing of tax returns, data collecting, and tax computations. Challenges and considerations: Initial investment: Software development and licensing expenses are required for RPA implementation. Successful implementation of change management requires meticulous planning, support for staff, and comprehensive training. Process standardization: Automation can only be successful if processes are well-defined and standardised. Security and integration: Important things to consider are security protocols and smooth system integration.

Intrusion Detection System with Machine Learning Algorithms

Seyfali Mahini — Thu, 11 Jan 2024 00:00:00 +0000

Machine learning has become increasingly relevant in recent years, including in IT security. Algorithms are used to train intrusion detection systems to be able to react to new attack vectors. In this work, the basics of machine learning are explained and the results of two research projects are presented in order to investigate which algorithms are suitable for training a machine-learning intrusion detection system. In addition, the software library Scikit-Learn and the software Weka, with which the implementations take place, are presented.

Application of AI Driven Robots and Their Future Direction

Regala Supriya, Manas Kumar Yogi — Wed, 06 Dec 2023 00:00:00 +0000

AI-driven robots have found applications in various domains, including manufacturing, healthcare, logistics, agriculture, and more. Robots with computer vision and machine learning skills are improving accuracy, productivity, and quality control in manufacturing. In healthcare, robotic surgery and patient care assistance are becoming increasingly common. Logistics and warehousing benefit from AI-driven robots for tasks such as autonomous navigation and inventory management. Within the field of agriculture, robots find application in activities such as seeding, gathering crops, and overseeing crop conditions. These applications illustrate the versatility of AI-driven robots across industries.

Comparative Analysis of Supervised Learning Algorithms for the Traffic Accident Prediction Under Rural and Urban Areas

Vinay Bhatt — Thu, 11 Jan 2024 00:00:00 +0000

The features of different mechanisms for safety to traffic accidents are the biggest challenge for the automobile manufacturing industry in rural and urban areas. The objective of this work is to address the challenge of safety in traffic accidents by developing an accurate prediction model for identifying patterns in the different scenarios for preventing traffic accidents using accurate prediction. The machine learning algorithm is used to easily predict the traffic accident scenario and automatically identify data and patterns. By using an ML-based model, a cost-effective approach for safety measures was built. The aim of this prediction model is to improve the accurate prediction for preventing traffic accidents in security measures. In this prediction model, three ML-based algorithms namely random forest, decision tree and SVM were used to predict the data of traffic accidents with low-budget scientific measures for reduction of maximum possible accidents. The focus of this study is to achieve accurate data on traffic congestion. The random forest algorithm is a category of supervised learning algorithms in which part of the machine learning algorithm is best for the prediction of traffic accidents due to a higher accuracy rate when compared to other proposed algorithms such as SVM and decision tree, as concluded in this research work. In this work, large amounts of data related to traffic accidents on behalf of the time accident location, road features and weather conditions were collected. The target of this study is reducing traffic congestion and preventing traffic accidents.