Vehicle Recognition Via Sensor Data From Smart Devices

Pias, Tanmoy Sarkar; Eisenberg, David; Islam, Muhammad Aminul

doi:10.1109/ecice47484.2019.8942799

Cited by 13 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a distinctly non-visual, low-cost, and mobile branch of vehicle recognition research, the smart sensor vehicle recognition system has the potential of contributing to the integration of intelligent transportation systems with human activity recognition, such that a person's travel activities may be tracked in and out of their vehicle, and subsequently has the potential to contribute to and integrate with all other mobile-based activity systems. Expanding on the findings from Pias et al [4], this paper contributes to vehicle recognition research based in smart sensors.…”

Section: Introductionmentioning

confidence: 86%

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors

Pias

Eisenberg

Fresneda

2022

Sensors

Self Cite

View full text Add to dashboard Cite

This paper explores the utilization of smart device sensors for the purpose of vehicle recognition. Currently a ubiquitous aspect of people’s lives, smart devices can conveniently record details about walking, biking, jogging, and stepping, including physiological data, via often built-in phone activity recognition processes. This paper examines research on intelligent transportation systems to uncover how smart device sensor data may be used for vehicle recognition research, and fit within its growing body of literature. Here, we use the accelerometer and gyroscope, which can be commonly found in a smart phone, to detect the class of a vehicle. We collected data from cars, buses, trains, and bikes using a smartphone, and we designed a 1D CNN model leveraging the residual connection for vehicle recognition. The model achieved more than 98% accuracy in prediction. Moreover, we also provide future research directions based on our study.

show abstract

Section: Introductionmentioning

confidence: 86%

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors

Pias

Eisenberg

Fresneda

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…CNN has proven to be very effective in different fields of pattern recognition from images [ 83 , 84 ]. Importantly, several studies utilized the pattern recognition power of 1D CNN, including smartphone sensor signal recognition [ 85 , 86 , 87 ], and ECG signal recognition [ 88 ]. Therefore, the current study continues to test its performance with CNN models as well.…”

Section: Methodsmentioning

confidence: 99%

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Akter

Prodhan

Pias

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Emotion recognition, or the ability of computers to interpret people’s emotional states, is a very active research area with vast applications to improve people’s lives. However, most image-based emotion recognition techniques are flawed, as humans can intentionally hide their emotions by changing facial expressions. Consequently, brain signals are being used to detect human emotions with improved accuracy, but most proposed systems demonstrate poor performance as EEG signals are difficult to classify using standard machine learning and deep learning techniques. This paper proposes two convolutional neural network (CNN) models (M1: heavily parameterized CNN model and M2: lightly parameterized CNN model) coupled with elegant feature extraction methods for effective recognition. In this study, the most popular EEG benchmark dataset, the DEAP, is utilized with two of its labels, valence, and arousal, for binary classification. We use Fast Fourier Transformation to extract the frequency domain features, convolutional layers for deep features, and complementary features to represent the dataset. The M1 and M2 CNN models achieve nearly perfect accuracy of 99.89% and 99.22%, respectively, which outperform every previous state-of-the-art model. We empirically demonstrate that the M2 model requires only 2 seconds of EEG signal for 99.22% accuracy, and it can achieve over 96% accuracy with only 125 milliseconds of EEG data for valence classification. Moreover, the proposed M2 model achieves 96.8% accuracy on valence using only 10% of the training dataset, demonstrating our proposed system’s effectiveness. Documented implementation codes for every experiment are published for reproducibility.

show abstract

“…After FFT,data shape becomes (1437,396) and saves in 1 1 1 FFT.npy file. The corresponding eye movement and DE file's (1 1 1 EYE.npy), (1 1 1 DE.npy) shape is (18,33) and (18,310). So, we do padding using repeat and insert function from the python numpy library to (1 1 1 EYE.npy) and (1 1 1 DE.npy) for increasing row numbers like 1 1 1 FFT.npy file.…”

Section: Data Preparationmentioning

confidence: 99%

“…In the Literature review section, we have elaborately discussed various deep learning algorithms for signal recognition that are used by many researchers. Among those, ANN [33], [34], CNN [35]- [37], hybrid CNN-LSTM, LSTM, BDAE, and DCCA are frequently applied to the SEED-V dataset. However, in this study, we utilize a 1D-CNN model with two convolution layers.…”

Section: E Model Architecturementioning

confidence: 99%

Exploring Emotions in EEG: Deep Learning Approach with Feature Fusion

Tasaouf Mridula,

Ferdaus,

Pias

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Emotion is an intricate physiological response that plays a crucial role in how we respond and cooperate with others in our daily affairs. Numerous experiments have been evolved to recognize emotion, however still require exploration to intensify the performance. To enhance the performance of effective emotion recognition, this study proposes a subject-dependent robust end-to-end emotion recognition system based on a 1D convolutional neural network (1D-CNN). We evaluate the SJTU1Emotion EEG Dataset SEED-V with five emotions (happy, sad, neural, fear, and disgust). To begin with, we utilize the Fast Fourier Transform (FFT) to decompose the raw EEG signals into six frequency bands and extract the power spectrum feature from the frequency bands. After that, we combine the extracted power spectrum feature with eye movement and differential entropy (DE) features. Finally, for classification, we apply the combined data to our proposed system. Consequently, it attains 99.80% accuracy which surpasses each prior state-of-the-art system.

show abstract

Vehicle Recognition Via Sensor Data From Smart Devices

Cited by 13 publications

References 4 publications

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Exploring Emotions in EEG: Deep Learning Approach with Feature Fusion

Contact Info

Product

Resources

About