Search results for: computer assisted classification

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 268

Authors: Afaf Alharbi, Qianni Zhang

Abstract:

The identification of malignant tissue in histopathological slides holds significant importance in both clinical settings and pathology research. This paper introduces a methodology aimed at automatically categorizing cancerous tissue through the utilization of a multiple-instance learning framework. This framework is specifically developed to acquire knowledge of the Bernoulli distribution of the bag label probability by employing neural networks. Furthermore, we put forward a neural network based permutation-invariant aggregation operator, equivalent to attention mechanisms, which is applied to the multi-instance learning network. Through empirical evaluation of an openly available colon cancer histopathology dataset, we provide evidence that our approach surpasses various conventional deep learning methods.

Keywords: attention multiple instance learning, MIL and transfer learning, histopathological slides, cancer tissue classification

Procedia PDF Downloads 110

Authors: Yasser F. Hassan

Abstract:

Deep learning structure is a branch of machine learning science and greet achievement in research and applications. Cellular neural networks are regarded as array of nonlinear analog processors called cells connected in a way allowing parallel computations. The paper discusses how to use deep learning structure for representing neural cellular automata model. The proposed learning technique in cellular automata model will be examined from structure of deep learning. A deep automata neural cellular system modifies each neuron based on the behavior of the individual and its decision as a result of multi-level deep structure learning. The paper will present the architecture of the model and the results of simulation of approach are given. Results from the implementation enrich deep neural cellular automata system and shed a light on concept formulation of the model and the learning in it.

Keywords: cellular automata, neural cellular automata, deep learning, classification

Procedia PDF Downloads 198

Authors: Nguyen The Hoang Anh, Tran Huy Hoang, Vu Tat Thang, T. T. Quyen Bui

Abstract:

Mental state classification is an important step for realizing a control system based on electroencephalography (EEG) signals which could benefit a lot of paralyzed people including the locked-in or Amyotrophic Lateral Sclerosis. Considering that EEG signals are nonstationary and often contaminated by various types of artifacts, classifying thoughts into correct mental states is not a trivial problem. In this work, our contribution is that we present and realize a novel model which integrates different techniques: Independent component analysis (ICA), relative wavelet energy, and support vector machine (SVM) for the same task. We applied our model to classify thoughts in two types of experiment whether with two or three mental states. The experimental results show that the presented model outperforms other models using Artificial Neural Network, K-Nearest Neighbors, etc.

Keywords: EEG, ICA, SVM, wavelet

Procedia PDF Downloads 384

Authors: Rakkrit Duangsoithong, Jermphiphut Jaruenpunyasak, Alba Garcia

Abstract:

The use of foot recognition can be applied in many medical fields such as the gait pattern analysis and the knee exercises of patients in rehabilitation. Generally, a camera-based foot recognition system is intended to capture a patient image in a controlled room and background to recognize the foot in the limited views. However, this system can be inconvenient to monitor the knee exercises at home. In order to overcome these problems, this paper proposes to use the deep learning method using Convolutional Neural Networks (CNNs) for foot recognition. The results are compared with the traditional classification method using LBP and HOG features with kNN and SVM classifiers. According to the results, deep learning method provides better accuracy but with higher complexity to recognize the foot images from online databases than the traditional classification method.

Keywords: foot recognition, deep learning, knee rehabilitation, convolutional neural network

Procedia PDF Downloads 161

Authors: Somorjeet Sharma Shamurailatpam, Rabindra Das, A. Suchitra Devi

Abstract:

Computer and video display users might complain about Asthenopia, burning, dry eyes etc. The management of dry eyes is often not in the lines of severity. Following systematic evaluation and grading, dry eye disease is one condition that can be practiced at all levels of ophthalmic care. In the present study, different spectrum causing dry eye and prevalence of dry eye disease in computer users of Manipur, India are determined with 600 individuals (300 cases and 300 control). Individuals between 15 and 50 years who used computers for more than 3 hrs a day for 1 year or more were included. Tear break up time (TBUT) and Schirmer’s test were conducted. It shows that 33 (20.4%) out of 164 males and 47 (30.3%) out of 136 females have dry eye. Possible explanation for the observed result is discussed.

Keywords: asthenopia, computer vision syndrome, dry eyes, Schirmer's test, TBUT

Procedia PDF Downloads 374

Authors: Lae-Jeong Park, Kyusoo Chung, Jungho Moon

Abstract:

This paper introduces an effective method of segmenting Korean text (place names in Korean) from a Korean road sign image. A Korean advanced directional road sign is composed of several types of visual information such as arrows, place names in Korean and English, and route numbers. Automatic classification of the visual information and extraction of Korean place names from the road sign images make it possible to avoid a lot of manual inputs to a database system for management of road signs nationwide. We propose a series of problem-specific heuristics that correctly segments Korean place names, which is the most crucial information, from the other information by leaving out non-text information effectively. The experimental results with a dataset of 368 road sign images show 96% of the detection rate per Korean place name and 84% per road sign image.

Keywords: segmentation, road signs, characters, classification

Procedia PDF Downloads 444

Authors: Kellen Sharp

Abstract:

This study explores the phenomenon of ‘Passport Bros’, a subset within the manosphere responding to perceived crises in masculinity amidst changing gender dynamics. Focusing on a computational analysis of the passport bro community, the research addresses normative beliefs, deviations from MGTOW ideology, and discussions on nationality, race, and gender. Originating from the MGTOW movement, passport bros engage in a neocolonial approach by seeking traditional, non-Western women, attributing this pursuit to dissatisfaction with modern Western women. The paper examines how hetero pessimism within MGTOW shapes the emergence of passport bros, leading to the adoption of red pill ideologies and ultimately manifesting in the form of sex tourism. Analyzing data collected from passport bro forums through computer-assisted content analysis, the study identifies key discourses such as questions and answers, money, attitudes towards Western and traditional women, and discussions about the movement itself. The findings highlight the nuanced intersection of gender, race, and global power dynamics within the passport bro community, shedding light on their motivations and impact on neocolonial legacies.

Keywords: toxic online community, manosphere, gender and media, neocolonialism

Procedia PDF Downloads 74

Authors: Sherrene Bogle, Verlia Bogle, Tyrone Anderson

Abstract:

In recent years, organizations have become increasingly interested in the possibility of analyzing social media as a means of gaining meaningful feedback about their products and services. The aspect based sentiment analysis approach is used to predict the sentiment for Twitter datasets for Digicel and Lime, the main mobile companies in Jamaica, using supervised learning classification techniques. The results indicate an average of 82.2 percent accuracy in classifying tweets when comparing three separate classification algorithms against the purported baseline of 70 percent and an average root mean squared error of 0.31. These results indicate that the analysis of sentiment on social media in order to gain customer feedback can be a viable solution for mobile companies looking to improve business performance.

Keywords: machine learning, sentiment analysis, social media, supervised learning

Procedia PDF Downloads 444

Authors: Hasan Frookh Jamal

Abstract:

This is a case of a 36-year-old Bahraini gentleman diagnosed to have Cushing's Syndrome with a large anterior mediastinal mass. He was sent abroad to the Speciality hospital in Jordan, where he underwent diagnostic video-assisted thoracoscopy, partial thymectomy and pericardial fat excision. Histopathology of the mass was reported to be an Atypical carcinoid tumor with a low Ki67 proliferation index of 5%, the mitotic activity of 4 MF/10HPF and pathological stage classification(pTNM): pT1aN1. MRI of the pituitary gland showed an ill-defined non-enhancing focus of about 3mm on the Rt side of the pituitary on coronal images, with a similar but smaller one on the left side, which could be due to enhancing pattern rather than a real lesion as reported. The patient underwent Ga68 Dotate PET/CT scan post-operatively, which showed multiple somatostatin receptor-positive lesions seen within the tail, body and head of the pancreas and positive somatostatin receptor lymph nodes located between the pancreatic head and IVC. There was no uptake detected at the anterior mediastinum nor at the site of thymic mass resection. There was no evidence of any positive somatostatin uptake at the soft tissue or lymph nodes. The patient underwent IPSS, which proved that the source is, in fact, an ectopic source of ACTH secretion. Unfortunately, the patient's serum cortisol remained elevated after surgery and failed to be suppressed by 1 mg ODST and by 2 days LLDST with a high ACTH value. The patient was started on Osilodrostat for treatment of hypercortisolism for the time being and his future treatment plan with Lutetium-177 Dotate therapy vs. bilateral adrenalectomy is to be considered in an MDT meeting.

Keywords: cushing syndrome, neuroendocrine tumur, carcinoid tumor, Thymoma

Procedia PDF Downloads 83

Authors: Anurag Gaur Nidhi

Abstract:

Targeted drug delivery is a method of delivering medication to a patient in a manner that increases the concentration of the medication in some parts of the body relative to others. Targeted drug delivery seeks to concentrate the medication in the tissues of interest while reducing the relative concentration of the medication in the remaining tissues. This improves efficacy of the while reducing side effects. In the present work, we investigate the effect of magnetic field, flow rate and particle concentration on the capturing of magnetic particles transported in a stent implanted fluidic channel. Iron oxide magnetic nanoparticles (Fe3O4) nanoparticles were synthesized via co-precipitation method. The synthesized Fe3O4 nanoparticles were added in the de-ionized (DI) water to prepare the Fe3O4 magnetic particle suspended fluid. This fluid is transported in a cylindrical tube of diameter 8 mm with help of a peristaltic pump at different flow rate (25-40 ml/min). A ferromagnetic coil of SS 430 has been implanted inside the cylindrical tube to enhance the capturing of magnetic nanoparticles under magnetic field. The capturing of magnetic nanoparticles was observed at different magnetic magnetic field, flow rate and particle concentration. It is observed that capture efficiency increases from 47-67 % at magnetic field 2-5kG, respectively at particle concentration 0.6 mg/ml and at flow rate 30 ml/min. However, the capture efficiency decreases from 65 to 44 % by increasing the flow rate from 25 to 40 ml/min, respectively. Furthermore, it is observed that capture efficiency increases from 51 to 67 % by increasing the particle concentration from 0.3 to 0.6 mg/ml, respectively.

Keywords: capture efficiency, implant assisted-Magnetic drug targeting (IA-MDT), magnetic nanoparticles, In-vitro study

Procedia PDF Downloads 307

Authors: Xue Ma, Yang Fu, Dangyuan Lei

Abstract:

Passive daytime radiative cooling is an emerging technology which has attracted worldwide attention in recent years due to its huge potential in cooling buildings without the use of electricity. Various coating materials with different optical properties have been developed to improve the daytime radiative cooling performance. However, commercial cooling coatings comprising functional fillers with optical bandgaps within the solar spectral range suffers from severe intrinsic absorption, limiting their cooling performance. Fortunately, it has recently been demonstrated that introducing fluorescent materials into polymeric coatings can covert the absorbed sunlight to fluorescent emissions and hence increase the effective solar reflectance and cooling performance. In this paper, we experimentally investigate the key factors for fluorescence-assisted radiative cooling with TiO2-based white coatings. The surrounding TiO2 nanoparticles, which enable spatial and temporal light confinement through multiple Mie scattering, lead to Purcell enhancement of phosphors in the coating. Photoluminescence lifetimes of two phosphors (BaMgAl10O17:Eu2+ and (Sr, Ba)SiO4:Eu2+) exhibit significant reduction of ~61% and ~23%, indicating Purcell factors of 2.6 and 1.3, respectively. Moreover, smaller Stokes shifts of the phosphors are preferred to further diminish solar absorption. Field test of fluorescent cooling coatings demonstrate an improvement of ~4% solar reflectance for the BaMgAl10O17:Eu2+-based fluorescent cooling coating. However, to maximize solar reflectance, a white appearance is introduced based on multiple Mie scattering by the broad size distribution of fillers, which is visually pressurized and aesthetically bored. Besides, most colored pigments absorb visible light significantly and convert it to non-radiative thermal energy, offsetting the cooling effect. Therefore, current colored cooling coatings are facing the compromise between color saturation and cooling effect. To solve this problem, we introduced colored fluorescent materials into white coating based on SiO2 microspheres as a top layer, covering a white cooling coating based on TiO2. Compared with the colored pigments, fluorescent materials could re-emit the absorbed light, reducing the solar absorption introduced by coloration. Our work investigated the scattering properties of SiO2 dielectric spheres with different diameters and detailly discussed their impact on the PL properties of phosphors, paving the way for colored fluorescent-assisted cooling coting to application and industrialization.

Keywords: solar reflection, infrared emissivity, mie scattering, photoluminescent emission, radiative cooling

Procedia PDF Downloads 86

Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas

Abstract:

This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).

Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems

Procedia PDF Downloads 134

Authors: Aishrith Rao

Abstract:

Human activity recognition is an important aspect of video analytics, and many approaches have been recommended to enable action recognition. In this approach, the model is used to identify the action of the multiple people in the frame and classify them accordingly. A few approaches use RNNs and 3D CNNs, which are computationally expensive and cannot be trained with the small datasets which are currently available. Multi-person action recognition has been performed in order to understand the positions and action of people present in the video frame. The size of the video frame can be adjusted as a hyper-parameter depending on the hardware resources available. OpenPose has been used to calculate pose estimate using CNN to produce heap-maps, one of which provides skeleton features, which are basically joint features. The features are then extracted, and a classification algorithm can be applied to classify the action.

Keywords: human activity recognition, computer vision, pose estimates, convolutional neural networks

Procedia PDF Downloads 141

Authors: Vahid Bairami Rad

Abstract:

Due to the tremendous progress in computer technology in the last decades, the capabilities of computers increased enormously and working with a computer became a normal activity for nearly everybody. With all the possibilities a computer can offer, humans and their interaction with computers are now a limiting factor. This gave rise to a lot of research in the field of HCI (human computer interaction) aiming to make interaction easier, more intuitive, and more efficient. To research eye gaze based interfaces it is necessary to understand both sides of the interaction–the human eye and the eye tracker. The first section gives an overview on the anatomy of the eye. The second section accuracy and calibration issue. The subsequent section presents data from a user study where eye movements have been recorded while watching a video and while surfing the Internet. Statistics on the eye movement during these tasks for several individuals provide typical values and ranges for fixation times and saccade lengths and are the foundation for discussions in later chapters. The data also reveal typical limitations of eye trackers.

Keywords: human computer interaction, gaze tracking, calibration, eye movement

Procedia PDF Downloads 537

Authors: Jiahe Liu, Hongyang Yu, Miao Luo, Feng Qian

Abstract:

The widespread application of 3D human body reconstruction spans various fields. Smplify-X, an algorithm reliant on single-image input, employs three distinct body parameter templates, necessitating gender classification of individuals within the input image. Researchers employed a ResNet18 network to train a gender classifier within the Smplify-X framework, setting the threshold at 0.9, designating images falling below this threshold as having neutral gender. This model achieved 62.38% accurate predictions and 7.54% incorrect predictions. Our improvement involved refining the MobileNet network, resulting in a raised threshold of 0.97. Consequently, we attained 78.89% accurate predictions and a mere 0.2% incorrect predictions, markedly enhancing prediction precision and enabling more precise 3D human body reconstruction.

Keywords: SMPLX, mobileNet, gender classification, 3D human reconstruction

Procedia PDF Downloads 99

Authors: Louise Penzenstadler, Tiphaine Robet, Radu Iuga, Daniele Zullino

Abstract:

Context: The outpatient clinic of the psychiatric addiction service of Geneva University Hospital has been providing support to individuals affected by various narcotics for 30 years. However, the increasing consumption of crack cocaine in Geneva has presented a new challenge for the healthcare system. Research Aim: The aim of this research is to evaluate the impact of an outreach intervention on crack cocaine addiction in users with co-occurring opioid use disorder. Methodology: The research utilizes a combination of quantitative and qualitative retrospective data analysis to evaluate the effectiveness of the outreach intervention. Findings: The data collected from October 2023 to December 2023 show that the outreach program successfully made 1,071 contacts with drug users and led to 15 new requests for care and enrollment in treatment. Patients expressed high satisfaction with the intervention, citing easy and rapid access to treatment and social support. Theoretical Importance: This research contributes to the understanding of the challenges and specific needs of a complex group of drug users who face severe health problems. It highlights the importance of outreach interventions in establishing trust, connecting users with care, and facilitating medication-assisted treatment for opioid addiction. Data Collection: Data was collected through the outreach program's interactions with drug users, including street outreach interventions and presence at locations frequented by users. Patient satisfaction surveys were also utilized. Analysis Procedures: The collected data was analyzed using both quantitative and qualitative methods. The quantitative analysis involved examining the number of contacts made, new requests for care, and treatment enrollment. The qualitative analysis focused on patient satisfaction and their perceptions of the intervention. Questions Addressed: The research addresses the following questions: What is the impact of an outreach intervention on crack cocaine addiction in users with co-occurring opioid use disorder? How effective is the outreach program in connecting drug users with care and initiating medication-assisted treatment? Conclusion: The outreach program has proven to be an effective intervention in establishing trust with crack users, connecting them with care, and initiating medication-assisted treatment for opioid addiction. It has also highlighted the importance of addressing the specific challenges faced by this group of drug users.

Keywords: crack addiction, outreach treatment, peer intervention, polydrug use

Procedia PDF Downloads 64

Authors: Waseem Shahzad, Ayesha Tahir Khan, Hamid Hussain Awan

Abstract:

Ant-Miner algorithm that lies under ACO algorithms is used to extract knowledge from data in the form of rules. A variant of Ant-Miner algorithm named as cAnt-MinerPB is used to generate list of rules using pittsburgh approach in order to maintain the rule interaction among the rules that are generated. In this paper, we propose a parallel Ant MinerPB in which Ant colony optimization algorithm runs parallel. In this technique, a data set is divided vertically (i-e attributes) into different subsets. These subsets are created based on the correlation among attributes using Mutual Information (MI). It generates rules in a parallel manner and then merged to form a final list of rules. The results have shown that the proposed technique achieved higher accuracy when compared with original cAnt-MinerPB and also the execution time has also reduced.

Keywords: ant colony optimization, parallel Ant-MinerPB, vertical partitioning, classification rule discovery

Procedia PDF Downloads 295

Authors: Mehwish Asghar

Abstract:

Breast Cancer (BC) is a common type of cancer among women. Its screening is usually performed using different imaging modalities such as magnetic resonance imaging, mammogram, X-ray, CT, etc. Among these modalities’ mammogram is considered a powerful tool for diagnosis and screening of breast cancer. Sophisticated machine learning approaches have shown promising results in complementing human diagnosis. Generally, machine learning methods can be divided into two major classes: one is Radiomics analysis (RA), where image features are extracted manually; and the other one is the concept of convolutional neural networks (CNN), in which the computer learns to recognize image features on its own. This research aims to improve the incidence of early detection, thus reducing the mortality rate caused by breast cancer through the latest advancements in computer science, in general, and machine learning, in particular. It has also been aimed to ease the burden of doctors by improving and automating the process of breast cancer detection. This research is related to a relative analysis of different techniques for the implementation of different models for detecting and classifying breast cancer. The main goal of this research is to provide a detailed view of results and performances between different techniques. The purpose of this paper is to explore the potential of a convolutional neural network (CNN) w.r.t feature extractor and as a classifier. Also, in this research, it has been aimed to add the module of Radiomics for comparison of its results with deep learning techniques.

Keywords: breast cancer (BC), machine learning (ML), convolutional neural network (CNN), radionics, magnetic resonance imaging, artificial intelligence

Procedia PDF Downloads 225

Authors: Lidija R. Jevrić, Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević

Abstract:

This study considers the selection of the most suitable in silico molecular descriptors that could be used for s-triazine pesticides characterization. Suitable descriptors among topological, geometrical and physicochemical are used for quantitative structure-retention relationships (QSRR) model establishment. Established models were obtained using linear regression (LR) and multiple linear regression (MLR) analysis. In this paper, MLR models were established avoiding multicollinearity among the selected molecular descriptors. Statistical quality of established models was evaluated by standard and cross-validation statistical parameters. For detection of similarity or dissimilarity among investigated s-triazine pesticides and their classification, principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used and gave similar grouping. This study is financially supported by COST action TD1305.

Keywords: chemometrics, classification analysis, molecular descriptors, pesticides, regression analysis

Procedia PDF Downloads 393

Authors: S. Zith Dey Babu, S. Kour, S. Verma, C. Verma, V. Pathania, A. Agrawal, V. Chaudhary, A. Manoj Puthur, R. Goyal, A. Pal, T. Danti Dey, A. Kumar, K. Wadhwa, O. Ved

Abstract:

Background: Skin cancer is now is the buzzing button in the field of medical science. The cyst's pandemic is drastically calibrating the body and well-being of the global village. Methods: The extracted image of the skin tumor cannot be used in one way for diagnosis. The stored image contains anarchies like the center. This approach will locate the forepart of an extracted appearance of skin. Partitioning image models has been presented to sort out the disturbance in the picture. Results: After completing partitioning, feature extraction has been formed by using genetic algorithm and finally, classification can be performed between the trained and test data to evaluate a large scale of an image that helps the doctors for the right prediction. To bring the improvisation of the existing system, we have set our objectives with an analysis. The efficiency of the natural selection process and the enriching histogram is essential in that respect. To reduce the false-positive rate or output, GA is performed with its accuracy. Conclusions: The objective of this task is to bring improvisation of effectiveness. GA is accomplishing its task with perfection to bring down the invalid-positive rate or outcome. The paper's mergeable portion conflicts with the composition of deep learning and medical image processing, which provides superior accuracy. Proportional types of handling create the reusability without any errors.

Keywords: computer-aided system, detection, image segmentation, morphology

Procedia PDF Downloads 150

Authors: Vedant Vardhan Rathour, Anant Agrawal

Abstract:

The project aims to provide a touchless, intuitive interface for human-computer interaction, enabling users to control their computer using hand gestures and voice commands. The system leverages advanced computer vision techniques using the MediaPipe framework and OpenCV to detect and interpret real time hand gestures, transforming them into mouse actions such as clicking, dragging, and scrolling. Additionally, the integration of a voice assistant powered by the Speech Recognition library allows for seamless execution of tasks like web searches, location navigation and gesture control on the system through voice commands.

Keywords: gesture recognition, hand tracking, machine learning, convolutional neural networks

Procedia PDF Downloads 12

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 105

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 284

Authors: N. Ghatwary, A. Ahmed, H. Jalab

Abstract:

In this paper, an approach for the liver tumor detection in computed tomography (CT) images is represented. The detection process is based on classifying the features of target liver cell to either tumor or non-tumor. Fractional differential (FD) is applied for enhancement of Liver CT images, with the aim of enhancing texture and edge features. Later on, a fusion method is applied to merge between the various enhanced images and produce a variety of feature improvement, which will increase the accuracy of classification. Each image is divided into NxN non-overlapping blocks, to extract the desired features. Support vector machines (SVM) classifier is trained later on a supplied dataset different from the tested one. Finally, the block cells are identified whether they are classified as tumor or not. Our approach is validated on a group of patients’ CT liver tumor datasets. The experiment results demonstrated the efficiency of detection in the proposed technique.

Keywords: fractional differential (FD), computed tomography (CT), fusion, aplha, texture features.

Procedia PDF Downloads 359

Authors: Jun Gil Ahn, Jong Kang Park, Jong Tae Kim

Abstract:

In this paper, we analyze major components of activity recognition (AR) in wearable device with 9-axis sensors and sensor fusion filters. 9-axis sensors commonly include 3-axis accelerometer, 3-axis gyroscope and 3-axis magnetometer. We chose sensor fusion filters as Kalman filter and Direction Cosine Matrix (DCM) filter. We also construct sensor fusion data from each activity sensor data and perform classification by accuracy of AR using Naïve Bayes and SVM. According to the classification results, we observed that the DCM filter and the specific combination of the sensing axes are more effective for AR in wearable devices while classifying walking, running, ascending and descending.

Keywords: accelerometer, activity recognition, directiona cosine matrix filter, gyroscope, Kalman filter, magnetometer

Procedia PDF Downloads 333

Authors: Livia Eisler, Cristiane C. B. Alves, Cristina L. F. Ortolani, Kurt Faltin Jr.

Abstract:

Purpose: This paper proposes a technically simple diagnosis method among orthodontists and maxillofacial surgeons in order to evaluate discrete bone alterations. The methodology consists of a protocol to optimize the diagnosis and minimize the possibility for orthodontic and ortho-surgical retreatment. Materials and Methods: A protocol of image processing and analysis, through ImageJ software and its plugins, was applied to 20 pairs of lateral cephalometric images obtained from cone beam computerized tomographies, before and 1 year after undergoing orthognathic surgery. The optical density of the images was analyzed in the condylar region to determine possible bone alteration after surgical correction. Results: Image density was shown to be altered in all image pairs, especially regarding the condyle contours. According to measures, condyle had a gender-related density reduction for p=0.05 and condylar contours had their alterations registered in mm. Conclusion: A simple, viable and cost-effective technique can be applied to achieve the more detailed image-based diagnosis, not depending on the human eye and therefore, offering more reliable, quantitative results.

Keywords: bone resorption, computer-assisted image processing, orthodontics, orthognathic surgery

Procedia PDF Downloads 160

Authors: Meshandren Naidoo, Amy Gooden

Abstract:

Implantable brain-computer interface (BCI) technologies have developed to the point where brain-computer communication is possible. This has great potential in the medical field, as it allows persons who have lost capacities. However, ethicists and regulators call for a strict approach to these technologies due to the impact on personhood. This research demonstrates that the personhood debate is more nuanced and that where an African approach to personhood is used, it may produce results more favorable to the development and use of this technology.

Keywords: artificial intelligence, law, neuroscience, ethics

Procedia PDF Downloads 131

Authors: Rajesha Kumar Alambi, Mansour Ahmed, Garudachari Bhadrachari, Safiyah Al-Muqahwi, Mansour Al-Rughaib, Jibu P. Thomas

Abstract:

Membrane-based pressure assisted osmosis (PAO) for seawater desalination has the potential to overcome the challenges of forward osmosis technology. PAO technology is gaining interest among the research community to ensure the sustainability of freshwater with a significant reduction in energy. The requirements of PAO membranes differ from the FO membrane; as it needs a slightly higher porous with sufficient mechanical strength to overcome the applied hydraulic pressure. The porous metal-organic framework (MOF) as a filler for the membrane synthesis has demonstrated a great potential to generate new channels for water transport, high selectivity, and reduced fouling propensity. Accordingly, this study is aimed at fabricating the UiO-66 MOF-based thin film nanocomposite membranes with specific characteristics for water desalination by PAO. A PAO test unit manufactured by Trevi System, USA, was used to determine the performance of the synthesized membranes. Further, the synthesized membranes were characterized in terms of morphological features, hydrophilicity, surface roughness, and mechanical properties. The 0.05 UiO-66 loaded membrane produced highest flux of 38L/m2h and with low reverse salt leakage of 2.1g/m²h for the DI water as feed solution and 2.0 M NaCl as draw solutions at the inlet feed pressure of 0.6 MPa. The new membranes showed a good tolerance toward the applied hydraulic pressure attributed to the fabric support used during the membrane synthesis.

Keywords: metal organic framework, composite membrane, desalination, salt rejection, flux

Procedia PDF Downloads 135

Authors: Piyush Samant, Ravinder Agarwal

Abstract:

Complementary and Alternative Medicine (CAM) techniques are quite popular and effective for chronic diseases. Iridology is more than 150 years old CAM technique which analyzes the patterns, tissue weakness, color, shape, structure, etc. for disease diagnosis. The objective of this paper is to validate the use of iridology for the diagnosis of the diabetes. The suggested model was applied in a systemic disease with ocular effects. 200 subject data of 100 each diabetic and non-diabetic were evaluated. Complete procedure was kept very simple and free from the involvement of any iridologist. From the normalized iris, the region of interest was cropped. All 63 features were extracted using statistical, texture analysis, and two-dimensional discrete wavelet transformation. A comparison of accuracies of six different classifiers has been presented. The result shows 89.66% accuracy by the random forest classifier.

Keywords: complementary and alternative medicine, classification, iridology, iris, feature extraction, disease prediction

Procedia PDF Downloads 407