JournalTOCs

International Journal of Intelligent Machines and Robotics
Number of Followers: 3

Hybrid journal (It can contain Open Access articles)
ISSN (Print) 2398-7510 - ISSN (Online) 2398-7529
Published by Inderscience Publishers

[439 journals]

Deep learning-based approach for recognition of local fish
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Masum Shah Junayed, Afsana Ahsan Jeny, Md. Tarek Habib, Md. Sadekur Rahman
  Pages: 293 - 313
  Abstract: Bangladesh is a riverine country with thousands of rivers and ponds. Bangladesh, being a fish-loving nation, is considered one of the most suitable areas for fish culture. People of this generation in Bangladesh usually fail to recognise the local freshwater fish. Performing a classification of freshwater fish can help people recognise the local fish of Bangladesh. In this way, a vital part of the cultural heritage of Bangladesh can be retained. In this paper, a number of local freshwater fish are classified based on their characteristics. For this reason, we take a purpose for identifying fish. For our experiment, we have used a total of 6,000 images of ten local freshwater fish. We have used four convolutional neural network models, namely Inception-V3, MobileNet, ResNet50, and Xception for classifying the fish. We have obtained good accuracy, i.e., more than 95% with all four models, where MobileNet outperforms all other models by showing an accuracy of 98.41%.
  Keywords: artificial intelligence; convolutional neural networks; deep learning; local fish detection; transfer learning; computer vision; Bangladesh
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 293 - 313
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138950
  Issue No: Vol. 1, No. 4 (2024)
Recognition of handwritten Indic digits using a hybridisation of capsule
network and ANN features through mRMR optimisation
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Mohammad Reduanul Haque, Rubaiya Hafiz, Mohammad Zahidul Islam, Mohammad Shorif Uddin
  Pages: 314 - 324
  Abstract: Handwritten digit recognition through computer vision is a challenging task. Recently, deep learning techniques have shown promising success in solving computer vision problems, especially recognition of handwritten digits. However, most of the existing works focused on only one language, i.e., either Hindi or Bangla, etc. Hence, the development of a language invariant method will be very beneficial as we live in a global village. Indian subcontinent is rich in multi-languages which we called Indic languages. However, a few works have been done on handwritten Indic digits recognition. So, in this work, we developed a hybrid model incorporating a capsule network along with an ANN-based bag of feature (BoF) method. These features are optimised through the minimum redundancy and maximum relevance (mRMR) technique. The method is investigated on five widely-used languages in the Indian subcontinent. Experimental result confirms that the proposed method performs better than the capsule network only.
  Keywords: Indic digits recognition; capsule network; artificial neural network; ANN; bag of feature; BoF
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 314 - 324
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138979
  Issue No: Vol. 1, No. 4 (2024)
Design and implementation of sub-systems of an underwater remotely
operated vehicle
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Priyanka Jadli, Gaurav Kelkar, Saket Yeolekar
  Pages: 325 - 336
  Abstract: This paper aims to discuss the design and systems involved in the working of remotely operated vehicles (ROVs). Its design can be divided into navigation and arms. The navigation includes thrusters, float assembly and a central ballast. The float assembly controlled by a stepper motor and the central ballast for vertical movement are used to controlling the crude motion of the ROV, while the thrusters are used to fine-tune it. The arms are controlled using a hydraulic assembly, with proportional directional control valves (PDCVs) positioned inside the ROV and a power pack above the water surface. A forward kinematics (FK) and comprehensive inverse kinematics (IK) approach is also discussed in the paper.
  Keywords: underwater ROV; remotely operated vehicles; ROVs; navigation; manipulators; FABRIK; kinematics
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 325 - 336
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138951
  Issue No: Vol. 1, No. 4 (2024)
Automation of food delivery service in railways
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Yash Pawse, Anudeepa Kholapure, Sai Karthik Nandigama, Mrinal Malkar, Vaibhavi Amal
  Pages: 337 - 360
  Abstract: In this era of smartphones, one needs maximum facilities readily available with a click of a button. As days pass, technology has improved greatly, shifting many services to the online web and smartphone-based platforms. In this hour of the smartphone revolution, our focus should be on achieving the maximum possible mobile services, or, say, the services which can be available anywhere, anytime, without much hassle. This paper aims towards achieving a freestanding and autonomous delivery service for railways that requires almost no monitoring or direct involvement of humans. This idea is much needed at a time when less human interaction is preferable, and it promotes the idea of 'social distancing' during some widespread epidemics and pandemics. The idea can be abstracted to various other domains including restaurants, hospitals, libraries, etc. Furthermore, it reduces the workload on labour and can help save costs in the long run, considering a one-time investment in the setup costs of the technology. Our approach to this idea covers the crucial aspects of the service, and some minor add-ons can be added later on as per the needs of the domain in which it is deployed.
  Keywords: Android; application; automation; delivery service; smartphones; microcontroller; railways
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 337 - 360
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138952
  Issue No: Vol. 1, No. 4 (2024)
Research and implementation of intelligent robot SLAM based on fusion of
2D LiDAR and depth camera
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Bailin Fan, Hang Zhao, Lingbei Meng
  Pages: 361 - 376
  Abstract: To address the limitations of single-sensor SLAM in the field of intelligent robot SLAM, this paper proposes a low-cost SLAM method based on the fusion of 2D laser radar and depth camera. The method uses Kalman filtering and Bayesian estimation to generate accurate and rich 2D grid maps, effectively improving the accuracy and completeness of SLAM, and providing more reliable map information for intelligent robots. Experiments show that the proposed method constructs maps with rich environmental information compared to other commonly used methods in actual indoor scenes, compensating for the shortcomings of single-sensor mapping and improving the perception ability of intelligent robots to detect surrounding obstacles. The effectiveness and superiority of the proposed method are demonstrated.
  Keywords: 2D LiDAR; depth camera; multi-sensor fusion; ROS; intelligent robot
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 361 - 376
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138980
  Issue No: Vol. 1, No. 4 (2024)
A nouvelle tennis-ball collecting mobile robot
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Mahmoud A. Sharabati, Majdi H. Sultan, Sohaib J. Abu Omar, Karim A. Tahboub
  Pages: 377 - 395
  Abstract: Tennis players need to collect played balls from different points on the court. Players use a lot of balls during training sessions. That makes collection time-consuming and tedious. Some tools and mechanisms are used to facilitate the collection process, such as picking up hoppers and tubes. This article presents a novel mobile robot designed to collect up to 50 tennis balls. The novel collection system consists of a rotating brush that pushes tennis balls into a lightweight basket behind the robot. The mobile robot has onboard intelligence and is equipped with an integrated myRIO device, actuators, sensors, and a rechargeable battery. A point-to-point path planning algorithm with a fifth-order timing law is implemented with three levels of control to achieve the robot's required speed and overcome the change in its tire diameter. A tennis player can command the robot to move it and collect the balls through a mobile phone application.
  Keywords: mobile robot; tennis ball robot; path planning; human-robot interaction; mechatronic design; PID control; differential drive mobile robot; DDMR
  Citation: International Journal of Intelligent Machines and Robotics, Vol. 1, No. 4 (2024) pp. 377 - 395
  PubDate: 2024-06-05T23:20:50-05:00
  DOI: 10.1504/IJIMR.2024.138975
  Issue No: Vol. 1, No. 4 (2024)

HOME > Browse the 73 Subjects covered by JournalTOCs
Subject	Total Journals