Search results for: deep convolutional features

Authors: Thibaud Berthomier, Ali Mansour, Luc Bressollette, Frédéric Le Roy, Dominique Mottier, Léo Fréchier, Barthélémy Hermenault

Abstract:

Deep Venous Thrombosis (DVT) occurs when a thrombus is formed within a deep vein (most often in the legs). This disease can be deadly if a part or the whole thrombus reaches the lung and causes a Pulmonary Embolism (PE). This disorder, often asymptomatic, has multifactorial causes: immobilization, surgery, pregnancy, age, cancers, and genetic variations. Our project aims to relate the thrombus epidemiology (origins, patient predispositions, PE) to its structure using ultrasound images. Ultrasonography and elastography were collected using Toshiba Aplio 500 at Brest Hospital. This manuscript compares two classification approaches: spectral clustering and scattering operator. The former is based on the graph and matrix theories while the latter cascades wavelet convolutions with nonlinear modulus and averaging operators.

Keywords: deep venous thrombosis, ultrasonography, elastography, scattering operator, wavelet, spectral clustering

Procedia PDF Downloads 479

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. It also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 60

Authors: Issa Qabaja, Fadi Thabtah

Abstract:

Email phishing classification is one of the vital problems in the online security research domain that have attracted several scholars due to its impact on the users payments performed daily online. One aspect to reach a good performance by the detection algorithms in the email phishing problem is to identify the minimal set of features that significantly have an impact on raising the phishing detection rate. This paper investigate three known feature selection methods named Information Gain (IG), Chi-square and Correlation Features Set (CFS) on the email phishing problem to separate high influential features from low influential ones in phishing detection. We measure the degree of influentially by applying four data mining algorithms on a large set of features. We compare the accuracy of these algorithms on the complete features set before feature selection has been applied and after feature selection has been applied. After conducting experiments, the results show 12 common significant features have been chosen among the considered features by the feature selection methods. Further, the average detection accuracy derived by the data mining algorithms on the reduced 12-features set was very slight affected when compared with the one derived from the 47-features set.

Keywords: data mining, email classification, phishing, online security

Procedia PDF Downloads 432

Authors: Mst. Tuhin Akter, Sharun Akter Khushbu, S. M. Shaqib

Abstract:

A real-time system architecture is highly effective for monitoring and detecting various damaged products or fruits that may deteriorate over time or become infected with diseases. Deep learning models have proven to be effective in building such architectures. However, building a deep learning model from scratch is a time-consuming and costly process. A more efficient solution is to utilize deep neural network (DNN) based transfer learning models in the real-time monitoring architecture. This study focuses on using a novel strawberry dataset to develop effective transfer learning models for the proposed real-time monitoring system architecture, specifically for evaluating and detecting strawberry freshness. Several state-of-the-art transfer learning models were employed, and the best performing model was found to be Xception, demonstrating higher performance across evaluation metrics such as accuracy, recall, precision, and F1-score.

Keywords: strawberry freshness evaluation, deep neural network, transfer learning, image augmentation

Procedia PDF Downloads 90

Authors: Davide Fuscà, Kanan Rahimli, Roberto Leuzzi

Abstract:

Preventing abuse and illegal activities in a given area of the sea is a very difficult and expensive task. Artificial intelligence offers the possibility to implement new methods to identify the vessel class type from the kinematic features of the vessel itself. The task strictly depends on the quality of the data. This paper explores the application of a deep, long short-term memory model by using AIS flow only with a relatively low quality. The proposed model reaches high accuracy on detecting nine vessel classes representing the most common vessel types in the Ionian-Adriatic Sea. The model has been applied during the Adriatic-Ionian trial period of the international EU ANDROMEDA H2020 project to identify vessels performing behaviors far from the expected one depending on the declared type.

Keywords: maritime surveillance, artificial intelligence, behavior analysis, LSTM

Procedia PDF Downloads 231

Authors: Jaiden Xuan Schraut, Leon Liu, Yiqiao Yin

Abstract:

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image to-label result provides insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. In order to gain local insight into cancerous regions, separate tasks such as imaging segmentation need to be implemented to aid the doctors in treating patients, which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive AI-first medical solutions further, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional convolutional neural networks (CNN) module for auxiliary classification output. Class activation maps are a method of providing insight into a convolutional neural network’s feature maps that leads to its classification but in the case of lung diseases, the region of interest is enhanced by U-net-assisted Class Activation Map (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and is able to generate classification results simultaneously which builds trust for AI-led diagnosis systems. The proposed U-Net model achieves 97.61% accuracy and a dice coefficient of 0.97 on testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Keywords: multi-output network model, U-net, class activation map, image classification, medical imaging analysis

Procedia PDF Downloads 203

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 130

Authors: Selim M. Khan

Abstract:

Indoor air quality is strongly influenced by the presence of radioactive radon (222Rn) gas. Indeed, exposure to high 222Rn concentrations is unequivocally linked to DNA damage and lung cancer and is a worsening issue in North American and European built environments, having increased over time within newer housing stocks as a function of as yet unclear variables. Indoor air radon concentration can be influenced by a wide range of environmental, structural, and behavioral factors. As some of these factors are quantitative while others are qualitative, no single statistical model can determine indoor radon level precisely while simultaneously considering all these variables across a complex and highly diverse dataset. The ability of AI- machine (deep) learning to simultaneously analyze multiple quantitative and qualitative features makes it suitable to predict radon with a high degree of precision. Using Canadian and Swedish long-term indoor air radon exposure data, we are using artificial deep neural network models with random weights and polynomial statistical models in MATLAB to assess and predict radon health risk to human as a function of geospatial, human behavioral, and built environmental metrics. Our initial artificial neural network with random weights model run by sigmoid activation tested different combinations of variables and showed the highest prediction accuracy (>96%) within the reasonable iterations. Here, we present details of these emerging methods and discuss strengths and weaknesses compared to the traditional artificial neural network and statistical methods commonly used to predict indoor air quality in different countries. We propose an artificial deep neural network with random weights as a highly effective method for assessing and predicting indoor radon.

Keywords: radon, radiation protection, lung cancer, aI-machine deep learnng, risk assessment, risk prediction, Europe, North America

Procedia PDF Downloads 96

Authors: Haiyan Wu, Ying Liu, Shaoyun Shi

Abstract:

Authorship attribution is to extract features to identify authors of anonymous documents. Many previous works on authorship attribution focus on statistical style features (e.g., sentence/word length), content features (e.g., frequent words, n-grams). Modeling these features by regression or some transparent machine learning methods gives a portrait of the authors' writing style. But these methods do not capture the syntactic (e.g., dependency relationship) or semantic (e.g., topics) information. In recent years, some researchers model syntactic trees or latent semantic information by neural networks. However, few works take them together. Besides, predictions by neural networks are difficult to explain, which is vital in authorship attribution tasks. In this paper, we not only utilize the statistical style and content features but also take advantage of both syntactic and semantic features. Different from an end-to-end neural model, feature selection and prediction are two steps in our method. An attentive n-gram network is utilized to select useful features, and logistic regression is applied to give prediction and understandable representation of writing style. Experiments show that our extracted features can improve the state-of-the-art methods on three benchmark datasets.

Keywords: authorship attribution, attention mechanism, syntactic feature, feature extraction

Procedia PDF Downloads 136

Authors: Prima Khairunisa, Febriana Tri Kusumawati, Endah Luthfiana

Abstract:

Background: Hypertension in elderly, caused by cardiovascular system cannot work normally, because the valves thickened and inelastic blood vessels. It causes vasoconstriction of the blood vessels. Hypertension exercise, increase cardiovascular function and the elasticity of the blood vessels. While slow deep breathing helps the body and mind feel relax. Combination both of them will decrease the blood pressure. Objective: To know the effect of hypertension exercise and slow deep breathing combination to blood pressure in elderly. Method: The study conducted with one group pre-post test experimental design. The samples were 10 elderly both male and female in a Village in Semarang, Central Java, Indonesia. The tool was manual sphygmomanometer to measure blood pressure. Result: Based on paired t-test between hypertension exercise and slow deep breathing with systole blood pressure showed sig (2-tailed) was 0.045, while paired t-test between hypertension exercise hypertension exercise and slow deep breathing with diastole blood pressure showed sig (2-tailed) was 0,343. The changes of systole blood pressure were 127.5 mmHg, and diastole blood pressure was 80 mmHg. Systole blood pressure decreases significantly because the average of systole blood pressure before implementation was 135-160 mmHg. While diastole blood pressure was not decreased significantly. It was influenced by the average of diastole blood pressure before implementation of hypertension exercise was not too high. It was between 80- 90 mmHg. Conclusion: There was an effect of hypertension exercise and slow deep breathing combination to the blood pressure in elderly after 6 times implementations.

Keywords: hypertension exercise, slow deep breathing, elderly, blood pressure

Procedia PDF Downloads 339

Authors: Sangita Pokhrel, Nalinda Somasiri, Rebecca Jeyavadhanam, Swathi Ganesan

Abstract:

Tourism is a booming industry with huge future potential for global wealth and employment. There are countless data generated over social media sites every day, creating numerous opportunities to bring more insights to decision-makers. The integration of Big Data Technology into the tourism industry will allow companies to conclude where their customers have been and what they like. This information can then be used by businesses, such as those in charge of managing visitor centers or hotels, etc., and the tourist can get a clear idea of places before visiting. The technical perspective of natural language is processed by analysing the sentiment features of online reviews from tourists, and we then supply an enhanced long short-term memory (LSTM) framework for sentiment feature extraction of travel reviews. We have constructed a web review database using a crawler and web scraping technique for experimental validation to evaluate the effectiveness of our methodology. The text form of sentences was first classified through Vader and Roberta model to get the polarity of the reviews. In this paper, we have conducted study methods for feature extraction, such as Count Vectorization and TFIDF Vectorization, and implemented Convolutional Neural Network (CNN) classifier algorithm for the sentiment analysis to decide the tourist’s attitude towards the destinations is positive, negative, or simply neutral based on the review text that they posted online. The results demonstrated that from the CNN algorithm, after pre-processing and cleaning the dataset, we received an accuracy of 96.12% for the positive and negative sentiment analysis.

Keywords: counter vectorization, convolutional neural network, crawler, data technology, long short-term memory, web scraping, sentiment analysis

Procedia PDF Downloads 88

Authors: Chen Xi, Liu Xuebing, Lao Xueru, Kuan Sinman, Jiang Yike, Wang Hanwei, Yang Xiaolang, Zhou Junjie, Xie Jinpeng

Abstract:

To further promote the development of smart cities, the microscopic "nerve endings" of the City Intelligent Model (CIM) are extended to be more sensitive. In this paper, we develop a pedestrian trajectory twin terminal based on the CIM and CNN technology. It also uses 5G networks, architectural and geoinformatics technologies, convolutional neural networks, combined with deep learning networks for human behavior recognition models, to provide empirical data such as 'pedestrian flow data and human behavioral characteristics data', and ultimately form spatial performance evaluation criteria and spatial performance warning systems, to make the empirical data accurate and intelligent for prediction and decision making.

Keywords: urban planning, urban governance, CIM, artificial intelligence, sustainable development

Procedia PDF Downloads 419

Authors: Edward K. Boahen, Brunel E. Bouya-Moko, Changda Wang

Abstract:

The major threat to online social network (OSN) users is account compromisation. Spammers now spread malicious messages by exploiting the trust relationship established between account owners and their friends. The challenge in detecting a compromised account by service providers is validating the trusted relationship established between the account owners, their friends, and the spammers. Another challenge is the increase in required human interaction with the feature selection. Research available on supervised learning (machine learning) has limitations with the feature selection and accounts that cannot be profiled, like application programming interface (API). Therefore, this paper discusses the various behaviours of the OSN users and the current approaches in detecting a compromised OSN account, emphasizing its limitations and challenges. We propose a deep learning approach that addresses and resolve the constraints faced by the previous schemes. We detailed our proposed optimized nonsymmetric deep auto-encoder (OPT_NDAE) for unsupervised feature learning, which reduces the required human interaction levels in the selection and extraction of features. We evaluated our proposed classifier using the NSL-KDD and KDDCUP'99 datasets in a graphical user interface enabled Weka application. The results obtained indicate that our proposed approach outperformed most of the traditional schemes in OSN compromised account detection with an accuracy rate of 99.86%.

Keywords: computer security, network security, online social network, account compromisation

Procedia PDF Downloads 119

Authors: Sait Ozsoy, Asude Gokmen, Mehtap Yondem, Hanife A. Alkan, Gulnaz T. Javan

Abstract:

Deep neck infection often develops due to upper respiratory tract and odontogenic infections. Gastrointestinal System perforation can occur for many reasons and is in need of the early diagnosis and prompt surgical treatment. In both cases late or incorrect diagnosis may lead to increase morbidity and high mortality. A patient with a diagnosis of deep neck abscess died while under treatment due to sepsis and multiple organ failure. Autopsy finding showed duodenal ulcer and this is reported in the literature.

Keywords: peptic ulcer perforation, peritonitis, retropharyngeal abscess, sepsis

Procedia PDF Downloads 498

Authors: Linyu Wang, Liguo Qiao, Jianhong Xiang, Hao Xu

Abstract:

In semantic communication, the existing joint Source Channel coding (JSCC) wireless communication system without pilot has unstable transmission performance and can not effectively capture the global information and location information of images. In this paper, a pilot-free image transmission system of joint source channel based on multi-level semantic information (Multi-level JSCC) is proposed. The transmitter of the system is composed of two networks. The feature extraction network is used to extract the high-level semantic features of the image, compress the information transmitted by the image, and improve the bandwidth utilization. Feature retention network is used to preserve low-level semantic features and image details to improve communication quality. The receiver also is composed of two networks. The received high-level semantic features are fused with the low-level semantic features after feature enhancement network in the same dimension, and then the image dimension is restored through feature recovery network, and the image location information is effectively used for image reconstruction. This paper verifies that the proposed multi-level JSCC algorithm can effectively transmit and recover image information in both AWGN channel and Rayleigh fading channel, and the peak signal-to-noise ratio (PSNR) is improved by 1~2dB compared with other algorithms under the same simulation conditions.

Keywords: deep learning, JSCC, pilot-free picture transmission, multilevel semantic information, robustness

Procedia PDF Downloads 120

Authors: Seyed Abolhasan Naeini, Saeideh Mohammadi

Abstract:

Time dependent settlement due to loading on soft saturated soils produces many problems such as high consolidation settlements and low consolidation rates. Also, long term consolidation settlement of soft soil underlying the embankment leads to unpredicted settlements and cracks on soil surface. Preloading method is an effective improvement method to solve this problem. Using vertical drains in preloading method is an effective method for improving soft soils. Applying deep soil mixing method on soft soils is another effective method for improving soft soils. There are little studies on using two methods of preloading and deep soil mixing simultaneously. In this paper, the concurrent effect of preloading with deep soil mixing by vertical drains is investigated through a finite element code, Plaxis2D. The influence of parameters such as deep soil mixing columns spacing, existence of vertical drains and distance between them, on settlement and stability factor of safety of embankment embedded on soft soil is investigated in this research.

Keywords: preloading, soft soil, vertical drains, deep soil mixing, consolidation settlement

Procedia PDF Downloads 216

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 162

Authors: Komeil Valipourian

Abstract:

Urban advances and the growing need for developing infrastructures has increased the importance of deep excavations. In this study, after the introducing probability analysis as an important issue, an attempt has been made to apply it for the deep excavation project of Bangkok’s Metro as a case study. For this, the numerical probability model has been developed based on the Finite Difference Method and Monte Carlo sampling approach. The results indicate that disregarding the issue of probability in this project will result in an inappropriate design of the retaining structure. Therefore, probabilistic redesign of the support is proposed and carried out as one of the applications of probability analysis. A 50% reduction in the flexural strength of the structure increases the failure probability just by 8% in the allowable range and helps improve economic conditions, while maintaining mechanical efficiency. With regard to the lack of efficient design in most deep excavations, by considering geometrical and geotechnical variability, an attempt was made to develop an optimum practical design standard for deep excavations based on failure probability. On this basis, a practical relationship is presented for estimating the maximum allowable horizontal displacement, which can help improve design conditions without developing the probability analysis.

Keywords: numerical probability modeling, deep excavation, allowable maximum displacement, finite difference method (FDM)

Procedia PDF Downloads 127

Authors: Meysam Mousakhani, Reza Ziaie Moayed

Abstract:

Considering the population growth and the needs of society, the improvement of problematic soils and the study of the application of different improvement methods have been considered. One of these methods is deep soil mixing, which has been developed in the past decade, especially in soft soils due to economic efficiency, simple implementation, and other benefits. The use of cement is criticized for its cost and the damaging environmental effects, so these factors lead us to use other additives along with cement in the deep soil mixing. Additives that are used today include fly ash, blast-furnace slag, glass powder, and potassium hydroxide. The present study provides a literature review on the application of different additives in deep soil mixing so that the best additives can be introduced from strength, economic, environmental and other perspectives. The results show that by replacing fly ash and slag with about 40 to 50% of cement, not only economic and environmental benefits but also a long-term strength comparable to cement would be achieved. The use of glass powder, especially in 3% mixing, results in desirable strength. In addition to the other benefits of these additives, potassium hydroxide can also be transported over longer distances, leading to wider soil improvement. Finally, this paper suggests further studies in terms of using other additives such as nanomaterials and zeolite, with different ratios, in different conditions and soils (silty sand, clayey sand, carbonate sand, sandy clay and etc.) in the deep mixing method.

Keywords: deep soil mix, soil stabilization, fly ash, ground improvement

Procedia PDF Downloads 148

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 209

Authors: Amaladhithyan Krishnamoorthy, Ruvaitha Banu

Abstract:

Vision is considered as the most important sense in humans, without which leading a normal can be often difficult. There are many existing smart canes for visually impaired with obstacle detection using ultrasonic transducer to help them navigate. Though the basic smart cane increases the safety of the users, it does not help in filling the void of visual loss. This paper introduces the concept of Digi-Buddy which is an evolved smart cane for visually impaired. The cane consists for several modules, apart from the basic obstacle detection features; the Digi-Buddy assists the user by capturing video/images and streams them to the server using a wide-angled camera, which then detects the objects using Deep Convolutional Neural Network. In addition to determining what the particular image/object is, the distance of the object is assessed by the ultrasonic transducer. The sound generation application, modelled with the help of Natural Language Processing is used to convert the processed images/object into audio. The object detected is signified by its name which is transmitted to the user with the help of Bluetooth hear phones. The object detection is extended to facial recognition which maps the faces of the person the user meets in the database of face images and alerts the user about the person. One of other crucial function consists of an automatic-intimation-alarm which is triggered when the user is in an emergency. If the user recovers within a set time, a button is provisioned in the cane to stop the alarm. Else an automatic intimation is sent to friends and family about the whereabouts of the user using GPS. In addition to safety and security by the existing smart canes, the proposed concept devices to be implemented as a prototype helping visually-impaired visualize their surroundings through audio more in an amicable way.

Keywords: artificial intelligence, facial recognition, natural language processing, internet of things

Procedia PDF Downloads 355

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 68

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 71

Authors: Lei Zhu, Nan Li

Abstract:

Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.

Keywords: springback, cold stamping, convolutional neural networks, machine learning

Procedia PDF Downloads 149

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 104

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 321

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 95

Authors: S. Sharan Sundar, Nithish B. Moudhgalya, Nidhi Bhandari, Vineeth Vijayaraghavan

Abstract:

Automatic Short Answer Grading is one of the prime applications of artificial intelligence in education. Several approaches involving the utilization of selective handcrafted features, graphical matching techniques, concept identification and mapping, complex deep frameworks, sentence embeddings, etc. have been explored over the years. However, keeping in mind the real-world application of the task, these solutions present a slight overhead in terms of computations and resources in achieving high performances. In this work, a simple and effective solution making use of elemental features based on statistical, linguistic properties, and word-based similarity measures in conjunction with tree-based classifiers and regressors is proposed. The results for classification tasks show improvements ranging from 1%-30%, while the regression task shows a stark improvement of 35%. The authors attribute these improvements to the addition of multiple similarity scores to provide ensemble of scoring criteria to the models. The authors also believe the work could reinstate that classical natural language processing techniques and simple machine learning models can be used to achieve high results for short answer grading.

Keywords: artificial intelligence, intelligent systems, natural language processing, text mining

Procedia PDF Downloads 133

Authors: A. Soualem

Abstract:

The design of multi stage deep drawing processes requires the evaluation of many process parameters such as the intermediate die geometry, the blank shape, the sheet thickness, the blank holder force, friction, lubrication etc..These process parameters have to be determined for the optimum forming conditions before the process design. In general sheet metal forming may involve stretching drawing or various combinations of these basic modes of deformation. It is important to determine the influence of the process variables in the design of sheet metal working process. Especially, the punch and die corner for deep drawing will affect the formability. At the same time the prediction of sheet metals springback after deep drawing is an important issue to solve for the control of manufacturing processes. Nowadays, the importance of this problem increases because of the use of steel sheeting with high stress and also aluminum alloys. The aim of this paper is to give a better understanding of the springback and its effect in various sheet metals forming process such as expansion and restraint deep drawing in the cup drawing process, by varying radius die, lubricant for two commercially available materials e.g. galvanized steel and Aluminum sheet. To achieve these goals experiments were carried out and compared with other results. The original of our purpose consist on tests which are ensured by adapting a U-type stretching-bending device on a tensile testing machine, where we studied and quantified the variation of the springback.

Keywords: springback, deep drawing, expansion, restricted deep drawing

Procedia PDF Downloads 454

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 75