Online Classification of Human Gestures Through Event Camera Data Using a 3DCNN [PDF]
In environments where humans and robots interact and collaborate, the robot needs awareness of human actions and intentions to guarantee operational effectiveness and agent safety.
Polito, Michele +5 more
core +1 more source
Detection of Risky Situations for Frail Adults With Hybrid Neural Networks on Multimodal Health Data
, 2022 In healthcare applications, the multimedia methodology is applied to multimodal signals and visual data. This article focuses on the detection of risk situations of frail people from lifelog multimodal signals and video recorded with wearable sensors. We
MALLICK, Rupayan +12 more
core +1 more source
Deep Learning-Based Detection of Shoplifting Behavior: using 3DCNN and LRCN [PDF]
This research explores the effectiveness of deep learning models in detecting pre-crime behavior in surveillance footage, specifically targeting shoplifting scenarios.
Chinthulla, Anish
core +3 more sources
Deep Learning for Brain MRI Confirms Patterned Pathological Progression in Alzheimer's Disease
Advanced Science, 2023 Deep learning (DL) on brain magnetic resonance imaging (MRI) data has shown excellent performance in differentiating individuals with Alzheimer's disease (AD).
Dan Pan +7 more
doaj +1 more source
Multi‐Tier Spatiotemporal Network for Violence Recognition in Urban Surveillance Systems
Human Behavior and Emerging Technologies, Volume 2026, Issue 1, 2026.In the context of smart cities, the use of intelligent surveillance systems has grown significantly, raising both opportunities for enhanced public safety and challenges related to ethical digital practices. Anomalous activity recognition (AAR) is critical for preventing violent incidents and ensuring rapid emergency response.
Samee Ullah Khan +6 more
wiley +1 more source
Perbandingan Klasifikasi HSI Menggunakan 3DCNN dan Pra-Pemrosesan pada Kondisi Sampel Pelatihan Terbatas [PDF]
Klasifikasi citra hiperspektral menghadapi tantangan utama berupa dimensi data yang sangat tinggi, ketidakseimbangan kelas, serta keterbatasan sampel berlabel.
Purwita Sari +5 more
core +1 more source
, 2022 (a) shows the composition of a Conv2DLSTM network. The receptive field is adjusted using sub-sampling and strides (convLSTM is a Conv2DLSTM layer, fc is fully connected and SM is softmax layer). (b) shows the composition of a 3DCNN.
Faheem Khaskheli (12101998) +4 more
core +1 more source
An Approach to Classify Human Finger Gestures Based on UWB Antenna Parameters
International Journal of RF and Microwave Computer-Aided Engineering, Volume 2026, Issue 1, 2026.The recognition and classification of human finger gestures hold significant interest due to their wide‐ranging applications in human–computer interaction, human–machine communications, virtual control, interactive gaming, and the management of handheld devices.
Bhawna Tiwari +4 more
wiley +1 more source
Decrypting cancer's spatial code: from single cells to tissue niches
Molecular Oncology, Volume 19, Issue 12, Page 3465-3485, December 2025.Spatial transcriptomics maps gene activity across tissues, offering powerful insights into how cancer cells are organised, switch states and interact with their surroundings. This review outlines emerging computational, artificial intelligence (AI) and geospatial approaches to define cell states, uncover tumour niches and integrate spatial data with ...
Cenk Celik +4 more
wiley +1 more source
3D deep convolutional neural networks for amino acid environment similarity analysis
BMC Bioinformatics, 2017 Background Central to protein biology is the understanding of how structural elements give rise to observed function. The surfeit of protein structural data enables development of computational methods to systematically derive rules governing structural ...
Wen Torng, Russ B. Altman
doaj +1 more source