Vishal Prajapati

Mr. Vishal Prajapati

Departement of Computer Engineering, University of Mumbai, Mumbai, India
orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 September 2026 in ScienceOpen Preprints
Verified
Preprint
Open access
Vishal PrajapatiVishal Prajapati
Vishal Prajapati
SNSaish Nair
Saish Nair
Industrial robotics has become a foundational element of modern factory automation, enabling higher productivity, improved quality, and safer working environments. This review synthesizes the evolution of advanced and industrial robotics, outlines major robot types, surveys core factory applications, and examines the technical and organizational constraints that shape adoption. It highlights how industrial robots, designed for repetitive, precise, or hazardous tasks, have progressed from early programmable manipulators to connected, sensor-rich systems that increasingly integrate artificial intelligence and machine learning. The review discusses trends such as collaborative robots, autonomous mobile robots, improved sensing and manipulation, and the convergence of robotics with Industry 4.0. Challenges such as system complexity, safety, cost, reliability, adaptability, integration hurdles, skills shortages, and data security are examined alongside opportunities for smarter production and resilient supply chains. Drawing on overview literature, the paper provides a consolidated and structured perspective intended for researchers and practitioners seeking a comprehensive understanding of industrial robotics and its future trajectory. It concludes that industrial robotics will continue to expand its role in manufacturing, but sustainable progress requires careful attention to human factors, governance, and responsible deployment.

19 May 2026 in Research Square
Verified
Preprint
Open access
NDNilesh Deotale
Nilesh Deotale
Vishal PrajapatiVishal Prajapati
Vishal Prajapati
HPHarsh Patil
Harsh Patil
RNRajendra Nahak
Rajendra Nahak
RPRamsaheb Prasad
Ramsaheb Prasad
Manual classroom attendance monitoring is in-herently time-consuming, prone to human error, and fails to capture objective metrics regarding student engagement. This paper proposes ClassVision, a comprehensive edge-deployable computer vision framework designed for simultaneous atten-dance tracking and real-time behavioral analysis in educational environments. The proposed architecture introduces a multi-detector fusion pipeline—integrating YOLOv8-face, MTCNN, and MediaPipe—to ensure robust facial detection across diverse lighting conditions and partial occlusions inherent to dynamic classrooms. Identity verification is achieved utilizing FaceNet-based embeddings coupled with strict cosine similarity threshold-ing ( τ ≥ 0 . 65) to effectively eliminate false positive identifications. Furthermore, we develop a multi-modal attentiveness module that quantifies head pose kinematics, gaze direction, facial aspect ratios (EAR/MAR), and hand gestures. These modalities are fused to dynamically classify student states into four distinct categories: attentive, distracted, drowsy, and sleeping. Experi-mental evaluation on a custom classroom dataset demonstrates that the proposed fusion pipeline yields 4,923 true positive face detections with zero geometric false rejections. The system achieves an 85.7% recognition accuracy for enrolled subjects while maintaining a processing throughput of 5-6 Frames Per Second (FPS) on standard CPU hardware, ensuring complete data privacy via on-device computation. By generating granular, per-student engagement analytics exported via a WebSocket-enabled dashboard, this work bridges the gap between passive attendance tracking and active learning analytics.

21 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Vishal PrajapatiVishal Prajapati
Vishal Prajapati
HPHarsh Patil
Harsh Patil
SNSaish Nair
Saish Nair
JNJenifa Nadar
Jenifa Nadar
HPHitesh Prajapati
Hitesh Prajapati
Quantum image encryption (QIE) loads a digital image into qubits and ciphers it with unitary circuits, usually keyed by chaotic maps, quantum walks or quantum random numbers. This review follows the field from an early geometric-transformation scheme (2013) to designs executed on 127-qubit IBM processors (2025). We organise the literature by image representation (FRQI, NEQR, amplitude encoding), confusion and diffusion mechanism, key source and validation level, and we compare recent schemes on entropy, NPCR, UACI, correlation and key space. Reported statistics sit close to their ideals almost everywhere; recent quantum-walk and chaos-based designs report NPCR of 99.6 to 99.97% and UACI of 33.5 to 33.9%, so these metrics no longer separate strong schemes from weak ones. Three gaps stand out. Most evidence comes from classical simulation. The secret usually sits in a classical key generator rather than in the quantum circuit. And loading an image into qubits, then reading it back, remains the main hardware bottleneck. Hybrid designs that distribute keys with BB84 and cipher the image classically offer the most deployable route today. We close with a research agenda: attack-based benchmarks, error-aware hardware validation, cheaper state preparation and explicit security definitions.

13 October 2026 in ScienceOpen Preprints
Verified
Preprint
Open access
Vishal PrajapatiVishal Prajapati
Vishal Prajapati
HPHarsh Patil
Harsh Patil
SNSaish Nair
Saish Nair
JNJenifa Nadar
Jenifa Nadar
HPHitesh Prajapati
Hitesh Prajapati
Quantum image encryption (QIE) loads a digital image into qubits and ciphers it with unitary circuits, usually keyed by chaotic maps, quantum walks or quantum random numbers. This review follows the field from an early geometric-transformation scheme (2013) to designs executed on 127-qubit IBM processors (2025). We organise the literature by image representation (FRQI, NEQR, amplitude encoding), confusion and diffusion mechanism, key source and validation level, and we compare recent schemes on entropy, NPCR, UACI, correlation and key space. Reported statistics sit close to their ideals almost everywhere; recent quantum-walk and chaos-based designs report NPCR of 99.6 to 99.97% and UACI of 33.5 to 33.9%, so these metrics no longer separate strong schemes from weak ones. Three gaps stand out. Most evidence comes from classical simulation. The secret usually sits in a classical key generator rather than in the quantum circuit. And loading an image into qubits, then reading it back, remains the main hardware bottleneck. Hybrid designs that distribute keys with BB84 and cipher the image classically offer the most deployable route today. We close with a research agenda: attack-based benchmarks, error-aware hardware validation, cheaper state preparation and explicit security definitions.