Abdu Gumaei^{1, 2, *}, Mabrook Al-Rakhami^{1, 2}, Hussain AlSalman², Sk. Md. Mizanur Rahman³, Atif Alamri^{1, 2}

CMC-Computers, Materials & Continua, Vol.65, No.2, pp. 1033-1057, 2020, DOI:10.32604/cmc.2020.011740

Abstract Human activity recognition is commonly used in several Internet of Things applications to recognize different contexts and respond to them. Deep learning has gained momentum for identifying activities through sensors, smartphones or even surveillance cameras. However, it is often difficult to train deep learning models on constrained IoT devices. The focus of this paper is to propose an alternative model by constructing a Deep Learning-based Human Activity Recognition framework for edge computing, which we call DL-HAR. The goal of this framework is to exploit the capabilities of cloud computing to train a deep learning model and deploy it on lesspowerful… More >

Jeong-Sik Park¹, Seok-Hoon Kim^2,*

Intelligent Automation & Soft Computing, Vol.26, No.1, pp. 149-159, 2020, DOI:10.31209/2019.100000136

Abstract Variety types of smart home devices have a main function of a human-machine interaction by speech recognition. Speech recognition system may be vulnerable to rapidly changing noises in home environments. This study proposes an efficient noise cancellation approach to eliminate the noises directly on the devices in real time. Firstly, we propose an advanced voice activity detection (VAD) technique to efficiently detect speech and non-speech regions on the basis of spectral property of speech signals. The VAD is then employed to enhance the conventional spectral subtraction method by steadily estimating noise signals in non-speech regions. On several experiments, our approach… More >

Mahiye Uluyagmur Ozturk^a, Ayse Rodopman Arman^b, Gresa Carkaxhiu Bulut^c, Onur Tugce Poyraz Findik^b, Sultan Seval Yilmaz^d, Herdem Aslan Genc^b, M. Yanki Yazgan^e,f, Umut Teker^a, Zehra Cataltepe^a

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 891-905, 2018, DOI:10.31209/2018.100000058

Abstract Emotion recognition behavior and performance may vary between people with major neurodevelopmental disorders such as Autism Spectrum Disorder (ASD), Attention Deficit Hyperactivity Disorder (ADHD) and control groups. It is crucial to identify these differences for early diagnosis and individual treatment purposes. This study represents a methodology by using statistical data analysis and machine learning to provide help to psychiatrists and therapists on the diagnosis and individualized treatment of participants with ASD and ADHD. In this paper we propose an emotion recognition experiment environment and collect eye tracker fixation data together with the application log data (APL). In order to detect… More >

M. Carmel Sobia¹, A. Abudhahir²

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 869-881, 2018, DOI:10.31209/2018.100000014

Abstract In this paper, an efficient facial expression recognition system using ANFIS-MHS (Adaptive Network-based Fuzzy Inference System with Mosquito Host-Seeking) has been proposed. The features were extracted using MLDA (Modified Linear Discriminant Analysis) and then the optimized parameters are computed by using mGSO (modified Glow-worm Swarm Optimization).The proposed system recognizes the facial expressions using ANFIS-MHS. The experimental results demonstrate that the proposed technique is performed better than existing classification schemes like HAKELM (Hybridization of Adaptive Kernel based Extreme Learning Machine), Support Vector Machine (SVM) and Principal Component Analysis (PCA). The proposed approach is implemented in MATLAB. More >

Juan C. Quiroz^a, Amit Banerjee^b, Sergiu M. Dascalu^c, Sian Lun Lau^a

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 785-793, 2018, DOI:10.1080/10798587.2017.1342400

Abstract We use the public Human Activity Recognition Using Smartphones (HARUS) data-set to investigate and identify the most informative features for determining the physical activity performed by a user based on smartphone accelerometer and gyroscope data. The HARUS data-set includes 561 time domain and frequency domain features extracted from sensor readings collected from a smartphone carried by 30 users while performing specific activities. We compare the performance of a decision tree, support vector machines, Naive Bayes, multilayer perceptron, and bagging. We report the various classification performances of these algorithms for subject independent cases. Our results show that bagging and the multilayer… More >

Changjiang Liu¹, Xuling Wu², Bing Mo¹, Yi Zhang³

Intelligent Automation & Soft Computing, Vol.24, No.3, pp. 671-678, 2018, DOI:10.31209/2018.100000033

Abstract With continuing commercialization of remote sensing satellites, the high resolution remote sensing image has been increasingly used in various fields of our life. However, processing technology of high resolution remote sensing images is still a tough problem. How to extract useful information from the massive information in high resolution remote sensing images is significant to the subsequent process. A multi-phase oil tank recognition of remote sensing images, namely coarse detection and artificial neural network (ANN) recognition, is proposed. The experimental results of algorithms presented in this paper show that the proposed processing technology is reliable and effective. More >

Amin Alqudah^1,2, Hussein R. Al-Zoubi², Mahmood A. Al-Khassaweneh^2,3, Mohammed Al-Qodah¹

Intelligent Automation & Soft Computing, Vol.24, No.3, pp. 493-505, 2018, DOI:10.31209/2018.100000005

Abstract Handwritten numeral recognition is one of the most popular fields of research in automation because it is used in many applications. Indeed, automation has continually received substantial attention from researchers. Therefore, great efforts have been made to devise accurate recognition methods with high recognition ratios. In this paper, we propose a method for integrating the correlation coefficient with a Self-Organizing Maps (SOM)-based technique to recognize offline handwritten Arabic decimal digits. The simulation results show very high recognition rates compared with the rates achieved by other existing methods. More >

Li-Hong Juang^a, Ming-Ni Wu^b, Shin-An Lin^b

Intelligent Automation & Soft Computing, Vol.24, No.2, pp. 249-256, 2018, DOI:10.1080/10798587.2016.1272777

Abstract Detecting human gender from complex background, illumination variations and objects under computer vision system is very difficult but important for an adaptive information service. In this paper, a preliminary design and some experimental results of gender recognition will be presented from the walking movement that utilizes the gait-energy image (GEI) with denoised energy image (DEI) pre-processing as a machine learning support vector machine (SVM) classifier to train and extract its characteristics. The results show that the proposed method can adopt some characteristic values and the accuracy can reach up to 100% gender recognition rate under combining the horizontal added vertical… More >

M. Humayun Kabir¹, Keshav Thapa², Jae-Young Yang², Sung-HyunYang²

Intelligent Automation & Soft Computing, Vol.25, No.4, pp. 673-681, 2019, DOI:10.31209/2018.100000035

Abstract Recognition of human activity is a key element for building intelligent and pervasive environments. Inhabitants interact with several objects and devices while performing any activity. Interactive objects and devices convey information that can be essential factors for activity recognition. Using embedded sensors with devices or objects, it is possible to get object-use sequencing data. This approach does not create discomfort to the user than wearable sensors and has no impact or issue in terms of user privacy than image sensors. In this paper, we propose a linear model for activity recognition based on the state-space method. The activities and sensor… More >

Ching‐Han Chen^a, Ching‐Yi Chen^b, Nai‐Yuan Liu^a

Intelligent Automation & Soft Computing, Vol.25, No.2, pp. 375-384, 2019, DOI:10.31209/2019.100000099

Abstract This study introduces a dynamic gesture recognition system applicable in IPTV remote control. In this system, we developed a hardware accelerator for realtime moving object detection. It is able to detect the position of hand block in each frame at high speed. After acquiring the information of hand block, the system can capture the robust dynamic gesture feature with the moving trail of hand block in the continuous images, and input to FNN classifier for starting recognition process. The experimental results show that our method has a good recognition performance, and more applicable to real gesture-controlled human-computer interactive environment. More >