<?xml version="1.0" encoding="UTF-8"?>



<records>

  <record>
    <language>eng</language>
          <publisher>Oriental Scientific Publishing Company</publisher>
        <journalTitle>Biomedical and Pharmacology Journal</journalTitle>
          <issn>0974-6242</issn>
            <publicationDate>2026-11-09</publicationDate>
    
        <volume>19</volume>
        <issue>4</issue>

 
    <startPage></startPage>
    <endPage></endPage>

	    <publisherRecordId>74173</publisherRecordId>
    <documentType>article</documentType>
    <title language="eng">Intelligent Bio Robotic Prosthetic Arm System Using HCI (Human Computer Interface)</title>

    <authors>
	 


      <author>
       <name>Anuj Singh</name>

 
		
	<affiliationId>1</affiliationId>
      </author>
    

	 


      <author>
       <name>Kamlesh Chandra Purohit</name>


		
	<affiliationId>1</affiliationId>

      </author>
    

	

	


	


	
    </authors>
    
	    <affiliationsList>
	    
		
		<affiliationName affiliationId="1">Department of Computer Science and Engineering, Graphic Era (Deemed to be University), Dehradun, India.</affiliationName>
    

		
		
		
		
		
	  </affiliationsList>






    <abstract language="eng">In this research we study present design and implementation of an intelligent bio-robotic prosthetic arm and hand that integrates electromyography (EMG)- based control model with vision-based object identification and recognition using Machine learning techniques (ML). the basic objective is to enhance the ability, usability and adaptability of prosthetic system by enabling an enhancement   of autonomous grip section for real time-based object detection and user intent. The proposed system utilizes EMG signals acquired from connected muscles, which are processed and fused with visual data captured through a camera module. A lightweight deep learning model (SSD)-MobileNetV2) is employed for object detection, while an Arduino-based control system executes appropriate grasp patterns. Experimental results demonstrate an object recognition and grasping accuracy ranging from 73% to 87% across multiple real-world objects. It can accurately predict the path of the user's hand movement because it knows how the user's muscles work. This is possible due to machine learning and computer vision. The system can better do tasks like manipulating and grasping by watching objects in real time. This method is easier to learn because it is similar to how people naturally use their hands

The system utilizes affordable components such as EMG sensors, Raspberry Pi, Arduino and 3D printed structures. This allows for a cost-effective and scalable solution to be implemented. This study boasts several significant contributions: firstly, the development of a hybrid EMG vision control system; secondly, an adaptive grip mechanism that operates in real-time; thirdly, the creation of an economical prosthetic option. By incorporating these advancements into our approach, we have successfully enhanced user interaction while reducing training complexity. Furthermore, the functional performance surpasses that of existing prosthetic systems. In short – our revolutionary method not only saves money but also elevates overall functionality through improved human-computer interactions."</abstract>

    <fullTextUrl format="html">https://biomedpharmajournal.org/vol19no4/intelligent-bio-robotic-prosthetic-arm-system-using-hci-human-computer-interface/</fullTextUrl>

<keywords language="eng">

      
        <keyword>Arduino</keyword>
      

      
        <keyword> Electromyography (EMG)</keyword>
      

      
        <keyword> Machine Learning (ML)</keyword>
      

      
        <keyword> Motor Control</keyword>
      

      
        <keyword> OpenCV (computer version)</keyword>
      

      
        <keyword> Real-time Object Detection</keyword>
      

      
        <keyword> Raspberry Pi</keyword>
      
</keywords>
  </record>
</records>