Search results for: brain tumor classification

Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li

Abstract:

Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.

Keywords: machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation

Procedia PDF Downloads 231

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 111

Authors: Ng Liang Shen, Hau Yuan Wen

Abstract:

Arrhythmia analysis of ECG signal plays a major role in diagnosing most of the cardiac diseases. Therefore, a single arrhythmia detection of an electrocardiographic (ECG) record can determine multiple pattern of various algorithms and match accordingly each ECG beats based on Machine Learning supervised learning. These researchers used different features and classification methods to classify different arrhythmia types. A major problem in these studies is the fact that the symptoms of the disease do not show all the time in the ECG record. Hence, a successful diagnosis might require the manual investigation of several hours of ECG records. The point of this paper presents investigations cardiovascular ailment in Electrocardiogram (ECG) Signals for Cardiac Arrhythmia utilizing examination of ECG irregular wave frames via heart beat as correspond arrhythmia which with Machine Learning Pattern Recognition.

Keywords: electrocardiogram, ECG, classification, machine learning, pattern recognition, detection, QRS

Procedia PDF Downloads 370

Authors: Moschos Vogiatzis, K. Perakis

Abstract:

Spatial-explicit and up-to-date land use/land cover information is fundamental for spatial planning, land management, sustainable development, and sound decision-making. In the last decade, many satellite-derived land cover products at different spatial, spectral, and temporal resolutions have been developed, such as the European Copernicus Land Cover product. However, more efficient and detailed information for land use/land cover is required at the regional or local scale. A typical Mediterranean basin with a complex landscape comprised of various forest types, crops, artificial surfaces, and wetlands was selected to test and develop our approach. In this study, we investigate the improvement of Copernicus Land Cover product (CLC2018) using Landsat 8 and Sentinel-2 pixel-based classification based on all available existing geospatial data (Forest Maps, LPIS, Natura2000 habitats, cadastral parcels, etc.). We examined and compared the performance of the Random Forest classifier for land use/land cover mapping. In total, 10 land use/land cover categories were recognized in Landsat 8 and 11 in Sentinel-2A. A comparison of the overall classification accuracies for 2018 shows that Landsat 8 classification accuracy was slightly higher than Sentinel-2A (82,99% vs. 80,30%). We concluded that the main land use/land cover types of CLC2018, even within a heterogeneous area, can be successfully mapped and updated according to CLC nomenclature. Future research should be oriented toward integrating spatiotemporal information from seasonal bands and spectral indexes in the classification process.

Keywords: classification, land use/land cover, mapping, random forest

Procedia PDF Downloads 117

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Eileen E. Birch, Brooke A. Koritala, Reed M. Jost, Becky Luu, David Stager, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. We developed a two-stage method for strabismus detection and classification based on photographs of the face. The first stage detects the presence or absence of strabismus, and the second stage classifies the type of strabismus. The first stage comprises face detection using Haar cascade, facial landmark estimation, face alignment, aligned face landmark detection, segmentation of the eye region, and detection of strabismus using VGG 16 convolution neural networks. Face alignment transforms the face to a canonical pose to ensure consistency in subsequent analysis. Using facial landmarks, the eye region is segmented from the aligned face and fed into a VGG 16 CNN model, which has been trained to classify strabismus. The CNN determines whether strabismus is present and classifies the type of strabismus (exotropia, esotropia, and vertical deviation). If stage 1 detects strabismus, the eye region image is fed into stage 2, which starts with the estimation of pupil center coordinates using mask R-CNN deep neural networks. Then, the distance between the pupil coordinates and eye landmarks is calculated along with the angle that the pupil coordinates make with the horizontal and vertical axis. The distance and angle information is used to characterize the degree and direction of the strabismic eye misalignment. This model was tested on 100 clinically labeled images of children with (n = 50) and without (n = 50) strabismus. The True Positive Rate (TPR) and False Positive Rate (FPR) of the first stage were 94% and 6% respectively. The classification stage has produced a TPR of 94.73%, 94.44%, and 100% for esotropia, exotropia, and vertical deviations, respectively. This method also had an FPR of 5.26%, 5.55%, and 0% for esotropia, exotropia, and vertical deviation, respectively. The addition of one more feature related to the location of corneal light reflections may reduce the FPR, which was primarily due to children with pseudo-strabismus (the appearance of strabismus due to a wide nasal bridge or skin folds on the nasal side of the eyes).

Keywords: strabismus, deep neural networks, face detection, facial landmarks, face alignment, segmentation, VGG 16, mask R-CNN, pupil coordinates, angle deviation, horizontal and vertical deviation

Procedia PDF Downloads 82

Authors: Bernd Kiefer, Abraham Gebru Tesfay, Dietrich Klakow

Abstract:

The motivation of our work is to detect different terrain types traversed by a robot based on acoustic data from the robot-terrain interaction. Different acoustic features and classifiers were investigated, such as Mel-frequency cepstral coefficient and Gamma-tone frequency cepstral coefficient for the feature extraction, and Gaussian mixture model and Feed forward neural network for the classification. We analyze the system’s performance by comparing our proposed techniques with some other features surveyed from distinct related works. We achieve precision and recall values between 87% and 100% per class, and an average accuracy at 95.2%. We also study the effect of varying audio chunk size in the application phase of the models and find only a mild impact on performance.

Keywords: acoustic features, autonomous robots, feature extraction, terrain classification

Procedia PDF Downloads 358

Authors: Mohamed R. Mhereeg

Abstract:

The paper discusses the implementation of the MultiAgent classification System (MACS) and utilizing it to provide an automated and accurate classification of end users developing applications in the spreadsheet domain. However, different technologies have been brought together to build MACS. The strength of the system is the integration of the agent technology with the FIPA specifications together with other technologies, which are the .NET widows service based agents, the Windows Communication Foundation (WCF) services, the Service Oriented Architecture (SOA), and Oracle Data Mining (ODM). Microsoft's .NET windows service based agents were utilized to develop the monitoring agents of MACS, the .NET WCF services together with SOA approach allowed the distribution and communication between agents over the WWW. The Monitoring Agents (MAs) were configured to execute automatically to monitor excel spreadsheets development activities by content. Data gathered by the Monitoring Agents from various resources over a period of time was collected and filtered by a Database Updater Agent (DUA) residing in the .NET client application of the system. This agent then transfers and stores the data in Oracle server database via Oracle stored procedures for further processing that leads to the classification of the end user developers.

Keywords: MACS, implementation, multi-agent, SOA, autonomous, WCF

Procedia PDF Downloads 268

Authors: Toshitaka Higashino, Naoki Wakamiya

Abstract:

Human beings perform a task by perceiving information from outside, recognizing them, and responding them. There have been various attempts to analyze and understand internal processes behind the reaction to a given stimulus by conducting psychological experiments and analysis from multiple perspectives. Among these, we focused on Model Human Processor (MHP). However, it was built based on psychological experiments and thus the relation with brain activity was unclear so far. To verify the validity of the MHP and propose our model from a viewpoint of neuroscience, EEG (Electroencephalography) measurements are performed during experiments in this study. More specifically, first, experiments were conducted where Latin alphabet characters were used as visual stimuli. In addition to response time, ERPs (event-related potentials) such as N100 and P300 were measured by using EEG. By comparing cycle time predicted by the MHP and latency of ERPs, it was found that N100, related to perception of stimuli, appeared at the end of the perceptual processor. Furthermore, by conducting an additional experiment, it was revealed that P300, related to decision making, appeared during the response decision process, not at the end. Second, by experiments using Japanese Hiragana characters, i.e. Japan's own phonetic symbols, those findings were confirmed. Finally, Japanese Kanji characters were used as more complicated visual stimuli. A Kanji character usually has several readings and several meanings. Despite the difference, a reading-related task and a meaning-related task exhibited similar results, meaning that they involved similar information processing processes of the brain. Based on those results, our model was proposed which reflects response time and ERP latency. It consists of three processors: the perception processor from an input of a stimulus to appearance of N100, the cognitive processor from N100 to P300, and the decision-action processor from P300 to response. Using our model, an application system which reflects brain activity can be established.

Keywords: brain activity, EEG, information processing model, model human processor

Procedia PDF Downloads 93

Authors: Rim Messaoudi, Nogaye-Gueye Gning, François Azelart

Abstract:

Automatic text classification applies mostly natural language processing (NLP) and other AI-guided techniques to automatically classify text in a faster and more accurate manner. This paper discusses the subject of using predictive maintenance to manage incident tickets inside the sociality. It focuses on proposing a tool that treats and analyses comments and notes written by administrators after resolving an incident ticket. The goal here is to increase the quality of these comments. Additionally, this tool is based on NLP and machine learning techniques to realize the textual analytics of the extracted data. This approach was tested using real data taken from the French National Railways (SNCF) company and was given a high-quality result.

Keywords: machine learning, text classification, NLP techniques, semantic representation

Procedia PDF Downloads 92

Authors: Mrinal Kanti Bhowmik, Usha Rani Gogoi Jr., Anjan Kumar Ghosh, Debotosh Bhattacharjee

Abstract:

In the last few decades, breast thermography has achieved an average sensitivity and specificity of 90% for breast tumor detection. Breast thermography is a non-invasive, cost-effective, painless and radiation-free breast imaging modality which makes a significant contribution to the evaluation and diagnosis of patients, suspected of having breast cancer. An abnormal breast thermogram may indicate significant biological risk for the existence or the development of breast tumors. Breast thermography can detect a breast tumor, when the tumor is in its early stage or when the tumor is in a dense breast. The infrared breast thermography is very sensitive to environmental changes for which acquisition of breast thermography should be performed under strictly controlled conditions by undergoing some standard protocols. Several factors like air, temperature, humidity, etc. are there to be considered for characterizing thermal images as an imperative tool for detecting breast cancer. A detailed study of various breast thermogram acquisition protocols adopted by different researchers in their research work is provided here in this paper. After going through a rigorous study of different breast thermogram acquisition protocols, a new standard breast thermography acquisition setup is proposed here in this paper for proper and accurate capturing of the breast thermograms. The proposed breast thermogram acquisition setup is being built in the Radiology Department, Agartala Government Medical College (AGMC), Govt. of Tripura, Tripura, India. The breast thermograms are captured using FLIR T650sc thermal camera with the thermal sensitivity of 20 mK at 30 degree C. The paper is an attempt to highlight the importance of different critical parameters of breast thermography like different thermography views, patient preparation protocols, acquisition room requirements, acquisition system requirements, etc. This paper makes an important contribution by providing a detailed survey and a new efficient approach on breast thermogram capturing.

Keywords: acquisition protocol, breast cancer, breast thermography, infrared thermography

Procedia PDF Downloads 394

Authors: Clea Southall

Abstract:

Many children leave primary school having formed preconceptions about their relationship with science. Thus, primary school represents a critical window for stimulating scientific interest in younger children. Engagement relies on the provision of hands-on activities coupled with an ability to capture a child’s innate curiosity. This requires children to perceive science topics as interesting and relevant to their everyday life. Teachers and pupils alike have suggested the school curriculum be tailored to help stimulate scientific interest. Young children are naturally inquisitive about the human body; the brain is one topic which frequently engages pupils, although it is not currently included in the UK primary curriculum. Teaching children about the brain could have wider societal impacts such as increasing knowledge of neurological disorders. However, many primary school teachers do not receive formal neuroscience training and may feel apprehensive about delivering lessons on the nervous system. This is exacerbated by a lack of educational neuroscience resources. One solution is for undergraduates to form partnerships with schools - delivering engaging lessons and supplementing teacher knowledge. The aim of this project was to evaluate the success of a short lesson on the brain delivered by an undergraduate neuroscientist to primary school pupils. Prior to entering schools, semi-structured online interviews were conducted with teachers to gain pedagogical advice and relevant websites were searched for neuroscience resources. Subsequently, a single lesson plan was created comprising of four hands-on activities. The activities were devised in a top-down manner, beginning with learning about the brain as an entity, before focusing on individual neurons. Students were asked to label a ‘brain map’ to assess prior knowledge of brain structure and function. They viewed animal brains and created ‘pipe-cleaner neurons’ which were later used to depict electrical transmission. The same session was delivered by an undergraduate student to 570 key stage 2 (KS2) pupils across five schools in Leeds, UK. Post-session surveys, designed for teachers and pupils respectively, were used to evaluate the session. Children in all year groups had relatively poor knowledge of brain structure and function at the beginning of the session. When asked to label four brain regions with their respective functions, older pupils labeled a mean of 1.5 (± 1.0) brain regions compared to 0.8 (± 0.96) for younger pupils (p=0.002). However, by the end of the session, 95% of pupils felt their knowledge of the brain had increased. Hands-on activities were rated most popular by pupils and were considered the most successful aspect of the session by teachers. Although only half the teachers were aware of neuroscience educational resources, nearly all (95%) felt they would have more confidence in teaching a similar session in the future. All teachers felt the session was engaging and that the content could be linked to the current curriculum. Thus, a short fifty-minute session can successfully enhance pupils’ knowledge of a new topic: the brain. Partnerships with an undergraduate student can provide an alternative method for supplementing teacher knowledge, increasing their confidence in delivering future lessons on the nervous system.

Keywords: education, neuroscience, primary school, undergraduate

Procedia PDF Downloads 205

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 108

Authors: Nitin Shravan, Sudarsun Santhiappan, B. Sivaselvan

Abstract:

Subsection identification, in the context of Electronic Health Records (EHRs), is identifying the important sections for down-stream tasks like auto-coding. In this work, we classify the text present in EHRs according to their information, using machine learning and deep learning techniques. We initially describe briefly about the problem and formulate it as a text classification problem. Then, we discuss upon the methods from the literature. We try two approaches - traditional feature extraction based machine learning methods and deep learning methods. Through experiments on a private dataset, we establish that the deep learning methods perform better than the feature extraction based Machine Learning Models.

Keywords: deep learning, machine learning, semantic clinical classification, subsection identification, text classification

Procedia PDF Downloads 209

Authors: David Edgar

Abstract:

To understand how the brain’s subconscious and conscious functions, we must conquer the physics of Unity, which leads to duality’s algorithm. Where the subconscious (bottom-up) and conscious (top-down) processes function together to produce and consume intelligence, we use terms like ‘time is relative,’ but we really do understand the meaning. In the brain, there are different processes and, therefore, different observers. These different processes experience time at different rates. A sensory system such as the eyes cycles measurement around 33 milliseconds, the conscious process of the frontal lobe cycles at 300 milliseconds, and the subconscious process of the thalamus cycle at 5 milliseconds. Three different observers experience time differently. To bridge observers, the thalamus, which is the fastest of the processes, maintains a synchronous state and entangles the different components of the brain’s physical process. The entanglements form a synchronous cohesion between the brain components allowing them to share the same state and execute in the same measurement cycle. The thalamus uses the shared state to control the firing sequence of the brain’s linear subconscious process. Sharing state also allows the brain to cheat on the amount of sensory data that must be exchanged between components. Only unpredictable motion is transferred through the synchronous state because predictable motion already exists in the shared framework. The brain’s synchronous subconscious process is entirely based on energy conservation, where prediction regulates energy usage. So, the eyes every 33 milliseconds dump their sensory data into the thalamus every day. The thalamus is going to perform a motion measurement to identify the unpredictable motion in the sensory data. Here is the trick. The thalamus conducts its measurement based on the original observation time of the sensory system (33 ms), not its own process time (5 ms). This creates a data payload of synchronous motion that preserves the original sensory observation. Basically, a frozen moment in time (Flat 4D). The single moment in time can then be processed through the single state maintained by the synchronous process. Other processes, such as consciousness (300 ms), can interface with the synchronous state to generate awareness of that moment. Now, synchronous data traveling through a separate faster synchronous process creates a theoretical time tunnel where observation time is tunneled through the synchronous process and is reproduced on the other side in the original time-relativity. The synchronous process eliminates time dilation by simply removing itself from the equation so that its own process time does not alter the experience. To the original observer, the measurement appears to be instantaneous, but in the thalamus, a linear subconscious process generating sensory perception and thought production is being executed. It is all just occurring in the time available because other observation times are slower than thalamic measurement time. For life to exist in the physical universe requires a linear measurement process, it just hides by operating at a faster time relativity. What’s interesting is time dilation is not the problem; it’s the solution. Einstein said there was no universal time.

Keywords: neural synchronization, natural intelligence, 99.95% IoT data transmission savings, artificial subconscious intelligence (ASI)

Procedia PDF Downloads 119

Authors: Argyris Karapetsas, Maria Bampou, Andriani Mitropoulou

Abstract:

The aim of the present work is to study the role of brain function in social awareness processing. Mind controls all the psychosomatic functions. Mind’s functioning enables individual not only to recognize one's own self and propositional attitudes, but also to assign such attitudes to other individuals, and to consider such observed mental states in the elucidation of behavior. Participants and Methods: Twenty (n=20) undergraduate students (mean age 18 years old) were involved in this study. Students participated in a clinical assessment, being conducted in Laboratory of Neuropsychology, at University of Thessaly, in Volos, Greece. Assessment included both electrophysiological (i.e.Event Related Potentials (ERPs) esp.P300 waveform) and neuropsychological tests (Raven's Progressive Matrices (RPM) and Sally-Anne test). Results: Initial assessment’s results confirmed statistically significant differences between the males and females, as well as in score performance to the tests applied. Strong correlations emerged between prefrontal lobe functioning, RPM, Sally-Anne test and P300 latencies. Also, significant dysfunction of mind has been found, regarding its three dimensions (straight, circular and helical). At the end of the assessment, students received consultation and appropriate guidelines in order to improve their intrapersonal and interpersonal skills. Conclusions: Mind and social awareness phenomena play a vital role in human development and may act as determinants of the quality of one’s own life. Meanwhile, brain function is highly correlated with social awareness and it seems that different set of brain structures are involved in social behavior.

Keywords: brain activity, emotions, ERP's, social awareness

Procedia PDF Downloads 187

Authors: Chodidjah, Edi Dharmana, Hardhono, Sarjadi

Abstract:

Breast cancer treatment options including surgery, radiation therapy, chemotherapy, and immunotherapy have not been effective. Besides, they have side effects. Keladi Tikus (Typhonium flagelliforme) has been shown to improve immune system, suppress tumor growth and induce apoptosis. One of the parameters for immune system, tumor growth and apoptosis is IFNγ (Interferon γ), VEGF (Vascular Endothelial Growth Factor) and Caspase 3 respectively. The aim of this study was to examine the effect of the administration of Keladi Tikus tuber extract at the dose of 200 mg/kgBW, 400 mg/KgBW, and 800 mg/kgBW on the level of IFNγ, VEGF and caspase 3 expression. In this experimental study using post test randomized control group design, 24 CH3 mice with tumor were randomly divided into 4 groups including control group and treated groups: Treated with 0.2 cc extract of Keladi Tikus at the dose of 200 mg/kgBW, 400 mg/kgBW, 800 mg/kgBW, respectively for 30 days. On day 31 the lymphatic tissue was taken and evaluated for its level of IFNγ, using ELISA. The tumor tissue was taken and subjected to immunohistochemistry staining for VEGF and caspase 3 expression evaluation. The data on IFNγ, VEGF and Caspase 3 expression were analyzed using One Way Anova with significant level of 0.05. One Way Anova resulted in p<0.05. LSD test showed that the level of IFNγ and Caspase 3 for control group was different from that of treated groups. There was no significant different between the treated group of 400 mg/KgBW and 800mg/KgBW. VEGF expressions for all the treated groups were significant. In conclusion, the oral administration of ethanolic extract of Keladi Tikus (Typhonium flagelliforme) at the dose of 200mg/kgBW, 400 mg/kgBW,800 mg/kgBW increases IFNγ, Caspase 3 and decreases VEGF expression in C3H mice with adenocarsinoma mamma.

Keywords: Typhonium flagelliforme, IFNγ, caspase 3, VEGF

Procedia PDF Downloads 419

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 56

Authors: Moohyun Lee, Soojung Hur, Yongwan Park

Abstract:

In this paper is proposed a method uses only LIDAR system to classification an obstacle and determine its type by establishing database for classifying obstacles based on LIDAR. The existing LIDAR system, in determining the recognition of obstruction in an autonomous vehicle, has an advantage in terms of accuracy and shorter recognition time. However, it was difficult to determine the type of obstacle and therefore accurate path planning based on the type of obstacle was not possible. In order to overcome this problem, a method of classifying obstacle type based on existing LIDAR and using the width of obstacle materials was proposed. However, width measurement was not sufficient to improve accuracy. In this research, the width data was used to do the first classification; database for LIDAR intensity data by four major obstacle materials on the road were created; comparison is made to the LIDAR intensity data of actual obstacle materials; and determine the obstacle type by finding the one with highest similarity values. An experiment using an actual autonomous vehicle under real environment shows that data declined in quality in comparison to 3D LIDAR and it was possible to classify obstacle materials using 2D LIDAR.

Keywords: obstacle, classification, database, LIDAR, segmentation, intensity

Procedia PDF Downloads 340

Authors: Shajida M., Sakthiyadharshini N. P., Kamalesh S., Aswitha B.

Abstract:

Natural Language Processing (NLP) continues to play a strategic part in complaint discovery and medicine discovery during the current epidemic. This abstract provides an overview of performance analysis with a combination of visualization and classification techniques of NLP for a medical chatbot. Sentiment analysis is an important aspect of NLP that is used to determine the emotional tone behind a piece of text. This technique has been applied to various domains, including medical chatbots. In this, we have compared the combination of the decision tree with heatmap and Naïve Bayes with Word Cloud. The performance of the chatbot was evaluated using accuracy, and the results indicate that the combination of visualization and classification techniques significantly improves the chatbot's performance.

Keywords: sentimental analysis, NLP, medical chatbot, decision tree, heatmap, naïve bayes, word cloud

Procedia PDF Downloads 68

Authors: Babak Bashari Rad

Abstract:

A metamorphic computer virus uses different code transformation techniques to mutate its body in duplicated instances. Characteristics and function of new instances are mostly similar to their parents, but they cannot be easily detected by the majority of antivirus in market, as they depend on string signature-based detection techniques. The purpose of this research is to propose a Hidden Markov Model for classification of metamorphic viruses in executable files. In the proposed solution, portable executable files are inspected to extract the instructions opcodes needed for the examination of code. A Hidden Markov Model trained on portable executable files is employed to classify the metamorphic viruses of the same family. The proposed model is able to generate and recognize common statistical features of mutated code. The model has been evaluated by examining the model on a test data set. The performance of the model has been practically tested and evaluated based on False Positive Rate, Detection Rate and Overall Accuracy. The result showed an acceptable performance with high average of 99.7% Detection Rate.

Keywords: malware classification, computer virus classification, metamorphic virus, metamorphic malware, Hidden Markov Model

Procedia PDF Downloads 312

Authors: Xiao Chen, Xiaoying Kong, Min Xu

Abstract:

This paper presents a road vehicle detection approach for the intelligent transportation system. This approach mainly uses low-cost magnetic sensor and associated data collection system to collect magnetic signals. This system can measure the magnetic field changing, and it also can detect and count vehicles. We extend Mel Frequency Cepstral Coefficients to analyze vehicle magnetic signals. Vehicle type features are extracted using representation of cepstrum, frame energy, and gap cepstrum of magnetic signals. We design a 2-dimensional map algorithm using Vector Quantization to classify vehicle magnetic features to four typical types of vehicles in Australian suburbs: sedan, VAN, truck, and bus. Experiments results show that our approach achieves a high level of accuracy for vehicle detection and classification.

Keywords: vehicle classification, signal processing, road traffic model, magnetic sensing

Procedia PDF Downloads 313

Authors: Rozhgar A. Khailany, Mehri Igci, Emine Bayraktar, Sakip Erturhan, Metin Karakok, Ahmet Arslan

Abstract:

Kidney cancer is the most lethal urological cancer accounting for 3% of adult malignancies. VHL, a tumor-suppressor gene, is best known to be associated with renal cell carcinoma (RCC). The VHL functions as negative regulator of hypoxia inducible factors. Recent sequencing efforts have identified several novel frequent mutations of histone modifying and chromatin remodeling genes in ccRCC (clear cell RCC) including PBRM1 and SETD2. The PBRM1 gene encodes the BAF180 protein, which involved in transcriptional activation and repression of selected genes. SETD2 encodes a histone methyltransferase, which may play a role in suppressing tumor development. In this study, RNAs of 30 paired tumor and normal samples that were grouped according to the types of kidney cancer and clinical characteristics of patients, including gender and average age were examined by RT-PCR, SSCP and sequencing techniques. VHL, PBRM1 and SETD2 expressions were relatively down-regulated. However, statistically no significance was found (Wilcoxon signed rank test, p > 0.05). Interestingly, no mutation was observed on the contrary of previous studies. Understanding the molecular mechanisms involved in the pathogenesis of RCC has aided the development of molecular-targeted drugs for kidney cancer. Further analysis is required to identify the responsible genes rather than VHL, PBRM1 and SETD2 in kidney cancer.

Keywords: kidney cancer, molecular biomarker, expression analysis, mutation screening

Procedia PDF Downloads 454

Authors: M. C. Paliwal, A. K. Jain, S. K. Katiyar

Abstract:

Classification of satellite imagery is very important for the assessment of its accuracy. In order to determine the accuracy of the classified image, usually the assumed-true data are derived from ground truth data using Global Positioning System. The data collected from satellite imagery and ground truth data is then compared to find out the accuracy of data and error matrices are prepared. Overall and individual accuracies are calculated using different methods. The study illustrates advanced classification and accuracy assessment of land use/land cover mapping using satellite imagery. IRS-1C-LISS IV data were used for classification of satellite imagery. The satellite image was classified using the software in fourteen classes namely water bodies, agricultural fields, forest land, urban settlement, barren land and unclassified area etc. Classification of satellite imagery and calculation of accuracy was done by using ERDAS-Imagine software to find out the best method. This study is based on the data collected for Bhopal city boundaries of Madhya Pradesh State of India.

Keywords: resolution, accuracy assessment, land use mapping, satellite imagery, ground truth data, error matrices

Procedia PDF Downloads 501

Authors: Metee Pigultong

Abstract:

The research aims at 1) composition of meditation music, 2) study of the meditation time reliability. The population is the older adults who meditated practitioners in the Thepnimitra Temple, Don Mueang District, Bangkok. The sample group was the older persons who meditated practitioners from the age of 60 with five volunteers. The research methodology was time-series to conduct the research progression. The research instruments included: 1) meditation music, 2) brain wave recording form. The research results found that 1) the music combines the binaural beats suitable for the meditation of the older persons, consisting of the following features: a) The tempo rate of the meditation music is no more than 60 beats per minute. b) The musical instruments for the meditation music arrangement include only 4-5 pieces. c) The meditation music arrangement needs to consider the nature of the right instrument. d) Digital music instruments are suitable for composition. e) The pure-tone sound combined in music must generate a brain frequency at the level of 10 Hz. 2) After the researcher conducted a 3-weeks brain training procedure, the researcher performed three tests for the reliability level using Cronbach's Alpha method. The result showed that the meditation reliability had the level = .475 as a moderate concentration.

Keywords: binaural beats, music therapy, meditation, older person, the Buddhist meditated practitioners

Procedia PDF Downloads 184

Authors: R. Gautam, P. Sastha Kanagasabai, G. N. Rathna

Abstract:

The proposed healthcare system enables quadriplegic patients, people with severe motor disabilities to send commands to electronic devices and monitor their vitals. The growth of Brain-Computer-Interface (BCI) has led to rapid development in 'assistive systems' for the disabled called 'assistive domotics'. Brain-Computer-Interface is capable of reading the brainwaves of an individual and analyse it to obtain some meaningful data. This processed data can be used to assist people having speech disorders and sometimes people with limited locomotion to communicate. In this Project, Emotiv EPOC Headset is used to obtain the electroencephalogram (EEG). The obtained data is processed to communicate pre-defined commands over the internet to the desired mobile phone user. Other Vital Information like the heartbeat, blood pressure, ECG and body temperature are monitored and uploaded to the server. Data analytics enables physicians to scan databases for a specific illness. The Data is processed in Intel Edison, system on chip (SoC). Patient metrics are displayed via Intel IoT Analytics cloud service.

Keywords: brain computer interface, Intel Edison, Emotiv EPOC, IoT analytics, electroencephalogram

Procedia PDF Downloads 182

Authors: Chih-Fong Tsai, Ya-Han Hu

Abstract:

The aim of feature selection (or dimensionality reduction) is to filter out unrepresentative features (or variables) making the classifier perform better than the one without feature selection. Since there are many well-known feature selection algorithms, and different classifiers based on different selection results may perform differently, very few studies consider examining the effect of performing different feature selection algorithms on the classification performances by different classifiers over different types of datasets. In this paper, two widely used algorithms, which are the genetic algorithm (GA) and information gain (IG), are used to perform feature selection. On the other hand, three well-known classifiers are constructed, which are the CART decision tree (DT), multi-layer perceptron (MLP) neural network, and support vector machine (SVM). Based on 14 different types of datasets, the experimental results show that in most cases IG is a better feature selection algorithm than GA. In addition, the combinations of IG with DT and IG with SVM perform best and second best for small and large scale datasets.

Keywords: data mining, feature selection, pattern classification, dimensionality reduction

Procedia PDF Downloads 663

Authors: Ana Beatriz C. G. Silva, Luiz Carlos Wrobel, Fernando Luiz B. Ribeiro

Abstract:

This paper presents a thermoregulation model using the finite element method to perform numerical analyses of brain cooling procedures as a contribution to the investigation on the use of therapeutic hypothermia after ischemia in adults. The use of computational methods can aid clinicians to observe body temperature using different cooling methods without the need of invasive techniques, and can thus be a valuable tool to assist clinical trials simulating different cooling options that can be used for treatment. In this work, we developed a FEM package applied to the solution of the continuum bioheat Pennes equation. Blood temperature changes were considered using a blood pool approach and a lumped analysis for intravascular catheter method of blood cooling. Some analyses are performed using a three-dimensional mesh based on a complex geometry obtained from computed tomography medical images, considering a cooling blanket and a intravascular catheter. A comparison is made between the results obtained and the effects of each case in brain temperature reduction in a required time, maintenance of body temperature at moderate hypothermia levels and gradual rewarming.

Keywords: brain cooling, finite element method, hypothermia treatment, thermoregulation

Procedia PDF Downloads 307

Authors: Serdal Pamuk, Irem Cay

Abstract:

Our model is based on the theory of reinforced random walks coupled with Michealis-Menten mechanisms which view endothelial cell receptors as the catalysts for transforming both tumor and macrophage derived tumor angiogenesis factor (TAF) into proteolytic enzyme which in turn degrade the basal lamina. The model consists of two main parts. First part has seven differential equations (DE’s) in one space dimension over the capillary, whereas the second part has the same number of DE’s in two space dimensions in the extra cellular matrix (ECM). We connect these two parts via some boundary conditions to move the cells into the ECM in order to initiate capillary formation. But, when does this movement begin? To address this question we estimate the thresholds that activate the transport equations in the capillary. We do this by using steady-state analysis of TAF equation under some assumptions. Once these equations are activated endothelial, pericyte and macrophage cells begin to move into the ECM for the initiation of angiogenesis. We do believe that our results play an important role for the mechanisms of cell migration which are crucial for tumor angiogenesis. Furthermore, we estimate the long time tendency of these three cells, and find that they tend to the transition probability functions as time evolves. We provide our numerical solutions which are in good agreement with our theoretical results.

Keywords: angiogenesis, capillary formation, mathematical analysis, steady-state, transition probability function

Procedia PDF Downloads 153

Authors: Teklu Urgessa, Wookjae Maeng, Joong Seek Lee

Abstract:

Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.

Keywords: classification algorithms, data mining, knowledge discovery, tourism

Procedia PDF Downloads 291

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.

Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation

Procedia PDF Downloads 87