Human Gait Recognition Using Bag of Words Feature-Representation Method

Bayat, Nasrin; Rastegari, Elham; Li, Qifeng

doi:10.54941/ahfe1001481

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hand-selected features can be applied to the time domain, frequency domain, or time-frequency domain to select signal characteristics involving signal energy or complexity to increase the class separability and robustness of the recorded signal 25 . However, these extracted features are susceptible to including unnecessary or redundant features within and/or between the domains 26 . There is a general redundancy (overlap) of features between time and frequency domains, and it was shown that the time domain features are superior to frequency domain features due to their low complexity 27 .…”

Section: Signal Qualitymentioning

confidence: 99%

Myoelectric Hand Gesture Recognition using Variational Autoencoder and Sensor Fusion

Currier,

FU,

Bayat

et al. 2024

Preprint

View full text Add to dashboard Cite

Pattern recognition-based myoelectric control schemes aim to classify surface electromyographic (sEMG) signals generated by skeletal muscles for use in prosthetics or wearable robots. Many factors impact the EMG signal quality and reliability, such as motion artifacts, electrode shift, and reduced conductivity over time, which calls for robust pattern recognition-based myoelectric control schemes. The manifold hypothesis – a breakdown of high-dimensional space to a lower-dimensional representation to explain how the higher-dimensional space operates – provides a framework to discover the representation or manifold of multimodal biological signals. This paper presents a pattern recognition-based myoelectric control scheme that creates compressed latent space representations using a contrastive variational autoencoder (VAE) with an integrated classifier. The VAE model was designed, trained with a secondary dataset of hand gestures, and validated subjectwise as well as for the group. The individual subject data yielded distinct and separable latent spaces with high classification accuracy ranging from 75.1\% to 91.7\%. Further, the model was optimized to improve classification accuracy, reaching 87.45\% to 97.49\%. The model architecture was generalizable across the subjects, and the compressed latent space achieved high performance when the representation was separable and distinct. The proposed VAE model and latent space representation demonstrate its feasibility and utility for use in myoelectric controls.

show abstract

Section: Signal Qualitymentioning

confidence: 99%

Myoelectric Hand Gesture Recognition using Variational Autoencoder and Sensor Fusion

Currier,

FU,

Bayat

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In other words, the average precision is the area under the precisionrecall curve for each categories of objects. The mean average precision is computed by taking the mean of the average precision for all category of objects [13], [33]. Figure 3 shows the Faster-RCNN results of detection when tested on the PASCAL VOC2007 test data in various levels of resolution (R 1 , ..., R 20 ) as explained in the previous section.…”

Section: A Performance Evaluation Of the Faster-rcnn On Different Res...mentioning

confidence: 99%

Improving Performance of Object Detection using the Mechanisms of Visual Recognition in Humans

Ghasemi¹,

Mottaghian²,

Bayat³

2023

Preprint

View full text Add to dashboard Cite

Object recognition systems are usually trained and evaluated on high resolution images. However, in real world applications, it is common that the images have low resolutions or have small sizes. In this study, we first track the performance of the state-of-the-art deep object recognition network, Faster-RCNN, as a function of image resolution. The results reveals negative effects of low resolution images on recognition performance. They also show that different spatial frequencies convey different information about the objects in recognition process. It means multi-resolution recognition system can provides better insight into optimal selection of features that results in better recognition of objects. This is similar to the mechanisms of the human visual systems that are able to implement multi-scale representation of a visual scene simultaneously. Then, we propose a multi-resolution object recognition framework rather than a single-resolution network. The proposed framework is evaluated on the PASCAL VOC2007 database. The experimental results show the performance of our adapted multi-resolution Faster-RCNN framework outperforms the single-resolution Faster-RCNN on input images with various resolutions with an increase in the mean Average Precision (mAP) of 9.14% across all resolutions and 1.2% on the full-spectrum images. Furthermore, the proposed model yields robustness of the performance over a wide range of spatial frequencies.

show abstract

“…Pada penelitian ini peneliti menggunakan dua model ekstraksi fitur antara lain adalah Bag of Words Model dan Term Frequency-Inverse Dokumen Frequecy (TF-IDF). Bag of Words merupakan suatu cara sederhana dalam menghitung frekuensi kemunculan kata dalam dokumen [10]. Adapun TF-IDF merupakan sebuah proses mengubah token (term) menjadi nilai numerik yang dapat dibaca oleh komputer, tujuannya agar sistem dapat mengevaluasi seberapa pentingnya sebuah term pada suatu dokumen [11].…”

Section: Ekstraksi Fiturunclassified

Analisis Sentimen Program Merdeka Belajar Kampus Merdeka Menggunakan Algoritma Naïve Bayes Classifier

Pandunata,

Ali,

Nurdiansyah

2023

sibc

View full text Add to dashboard Cite

Program Merdeka Belajar – Kampus Merdeka (MBKM) adalah program yang dicanangkan oleh pihak Menteri Pendidikan dan Kebudayaan (Mendikbud) yang bertujuan untuk meningkatkan kualitas mahasiswa serta diharapkan dapat membantu mahasiswa dalam menguasai berbagai bidang keilmuan sehingga siap untuk memasuki dunia kerja. Program MBKM sendiri secara resmi digelar untuk pertama kali pada tahun 2020 silam, tentu seiring berjalannya waktu masyarakat telah merasakan dampak dari program MBKM ini sehingga tak jarang banyak menuai pro dan kontra. Topik penelitian analisis sentimen terhadap program MBKM ini bertujuan untuk menggali informasi sentimen yang terkandung dalam setiap komentar yang diperoleh dari penghimpunan data komentar masyarakat pada media sosial twitter, dari hasil penghimpunan data tersebut tentunya tujuan utama yang ingin dicapai adalah untuk melihat respons masyarakat serta berharap dapat menjadi bahan evaluasi dari pihak pemangku kepentingan khususnya pihak mendikbud. Algoritma Naïve Bayes Classifier difungsikan sebagai sebuah metode yang digunakan dalam proses pengklasifikasian dataset yang berjumlah 2000 data twit. Pengklasifikasian data dilakukan menggunakan tiga skema pengujian dengan perbandingan data training dan data testing sebesar 70%:30%, 80%:20% dan 90%:10%. Adapun nilai akurasi terbaik yang diperoleh dalam pengujian klasifikasi pada penelitian ini menunjukkan nilai sebesar 70% di mana nilai tersebut diperoleh dari pengujian menggunakan perbandingan data sebesar 90%:10%.

show abstract

Human Gait Recognition Using Bag of Words Feature-Representation Method

Cited by 6 publications

References 0 publications

Myoelectric Hand Gesture Recognition using Variational Autoencoder and Sensor Fusion

Myoelectric Hand Gesture Recognition using Variational Autoencoder and Sensor Fusion

Improving Performance of Object Detection using the Mechanisms of Visual Recognition in Humans

Analisis Sentimen Program Merdeka Belajar Kampus Merdeka Menggunakan Algoritma Naïve Bayes Classifier

Contact Info

Product

Resources

About