Highway crash detection and risk estimation using deep learning
تشخیص تصادف بزرگراه و تخمین ریسک با استفاده از یادگیری عمیق-2020
Crash Detection is essential in providing timely information to traffic management centers and the public to reduce its adverse effects. Prediction of crash risk is vital for avoiding secondary crashes and safeguarding highway traffic. For many years, researchers have explored several techniques for early and precise detection of crashes to aid in traffic incident management. With recent advancements in data collection techniques, abundant real-time traffic data is available for use. Big data infrastructure and machine learning algorithms can utilize this data to provide suitable solutions for the highway traffic safety system. This paper explores the feasibility of using deep learning models to detect crash occurrence and predict crash risk. Volume, Speed and Sensor Occupancy data collected from roadside radar sensors along Interstate 235 in Des Moines, IA is used for this study. This real-world traffic data is used to design feature set for the deep learning models for crash detection and crash risk prediction. The results show that a deep model has better crash detection performance and similar crash prediction performance than state of the art shallow models. Additionally, a sensitivity analysis was conducted for crash risk prediction using data 1-minute, 5-minutes and 10-minutes prior to crash occurrence. It was observed that is hard to predict the crash risk of a traffic condition, 10 min prior to a crash.
Keywords: Crash detection | Crash prediction | Deep learning
Identification of animal individuals using deep learning: A case study of giant panda
شناسایی فردی حیوانی با استفاده از یادگیری عمیق: یک مطالعه موردی از پاندا غول پیکر-2020
Giant panda (Ailuropoda melanoleuca) is an iconic species of conservation. However, long-term monitoring of wild giant pandas has been a challenge, largely due to the lack of appropriate method for the identification of target panda individuals. Although there are some traditional methods, such as distance-bamboo stem fragments methods, molecular biological method, and manual visual identification, they all have some limitations that can restrict their application. Therefore, it is urgent to explore a reliable and efficient approach to identify giant panda individuals. Here, we applied the deep learning technology and developed a novel face-identification model based on convolutional neural network to identify giant panda individuals. The model was able to identify 95% of giant panda individuals in the validation dataset. In all simulated field situations where the quality of photo data was degraded, the model still accurately identified more than 90% of panda individuals. The identification accuracy of our model is robust to brightness, small rotation, and cleanness of photos, although large rotation angle (> 20°) of photos has significant influence on the identification accuracy of the model (P < 0.01). Our model can be applied in future studies of giant panda such as long-term monitoring, big data analysis for behavior and be adapted for individual identification of other wildlife species.
Keywords: Deep learning | convolutional neural network | Individual identification | Giant panda
An empirical case study on Indian consumers sentiment towards electric vehicles: A big data analytics approach
یک مطالعه موردی تجربی در مورد احساسات مصرف کنندگان هندی نسبت به وسایل نقلیه برقی: یک رویکرد تحلیل داده های بزرگ-2020
Today, climate change due to global warming is a significant concern to all of us. Indias rate of greenhouse gas emissions is increasing day by day, placing India in the top ten emitters in the world. Air pollution is one of the significant contributors to the greenhouse effect. Transportation contributes about 10% of the air pollution in India. The Indian government is taking steps to reduce air pollution by encouraging the use of electric vehicles. But, success depends on consumers sentiment, perception and understanding towards Electric Vehicles (EV). This case study tried to capture the feeling, attitude, and emotions of Indian consumers towards electric vehicles. The main objective of this study was to extract opinions valuable to prospective buyers (to know what is best for them), marketers (for determining what features should be advertised) and manufacturers (for deciding what features should be improved) using Deep Learning techniques (e.g Doc2Vec Algorithm, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN)). Due to the very nature of social media data, big data platform was chosen to analyze the sentiment towards EV. Deep Learning based techniques were preferred over traditional machine learning algorithms (Support Vector Machine, Logistic regression and Decision tree, etc.) due to its superior text mining capabilities. Two years data (2016 to 2018) were collected from different social media platform for this case study. The results showed the efficiency of deep learning algorithms and found CNN yield better results in-compare to others. The proposed optimal model will help consumers, designers and manufacturers in their decision-making capabilities to choose, design and manufacture EV.
Keywords: Electric vehicles | Deep learning | Big data | Sentiment analysis | India
A hybrid deep learning model for efficient intrusion detection in big data environment
یک مدل یادگیری عمیق ترکیبی برای تشخیص نفوذ موثر در محیط داده های بزرگ-2020
The volume of network and Internet traffic is expanding daily, with data being created at the zettabyte to petabyte scale at an exceptionally high rate. These can be character- ized as big data, because they are large in volume, variety, velocity, and veracity. Security threats to networks, the Internet, websites, and organizations are growing alongside this growth in usage. Detecting intrusions in such a big data environment is difficult. Various intrusion-detection systems (IDSs) using artificial intelligence or machine learning have been proposed for different types of network attacks, but most of these systems either cannot recognize unknown attacks or cannot respond to such attacks in real time. Deep learning models, recently applied to large-scale big data analysis, have shown remarkable performance in general but have not been examined for detection of intrusions in a big data environment. This paper proposes a hybrid deep learning model to efficiently detect network intrusions based on a convolutional neural network (CNN) and a weight-dropped, long short-term memory (WDLSTM) network. We use the deep CNN to extract mean- ingful features from IDS big data and WDLSTM to retain long-term dependencies among extracted features to prevent overfitting on recurrent connections. The proposed hybrid method was compared with traditional approaches in terms of performance on a publicly available dataset, demonstrating its satisfactory performance.
Keywords: Big data | Intrusion | detection Deep learning | Convolution neural network | Weight-dropped long short-term memory | network
Multi-model ensemble with rich spatial information for object detection
اثر گروهی چند مدلی با اطلاعات مکانی غنی برای ردیابی شی-2020
Due to the development of deep learning networks and big data dimensionality, research on ensemble deep learning is receiving an increasing amount of attention. This paper takes the object detection task as the research domain and proposes an object detection framework based on ensemble deep learning. To guarantee the accuracy as well as real-time detection, the detector uses a Single Shot MultiBox Detector (SSD) as the backbone and combines ensemble learning with context modeling and multi-scale feature representation. Two modes were designed in order to achieve ensemble learning: NMS Ensembling and Feature Ensembling. In addition, to obtain contextual information, we used dilated convolution to ex- pand the receptive field of the network. Compared with state-of-the-art detectors, our detector achieves superior performance on the PASCAL VOC set and the MS COCO set.
Keywords: Ensemble learning | Object detection | Dilated convolution | Feature fusion
کمترین از دست دادن حاشیه برای تشخیص چهره عمیق
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 9 - تعداد صفحات فایل doc فارسی: 24
تشخیص چهره موفقیت بزرگی به دست آورده است که دلیل اصلی آن توسعه سریع شبکه های عصبی عمیق (DNN) در سال های اخیر است. کارکردهای مختلف ازدست دادن (اتلاف) در یک شبکه عصبی عمیق قابل استفاده است که منجر به عملکرد متفاوتی می شود. اخیراً برخی از کارکردهای تلفات پیشنهاد داده شده است. با این حال، آن ها نمی توانند مساله جهت گیری حاشیه ای را که در مجموعه داده های غیر متعادل وجود دارد حل کنند. در این مقاله حل مساله تمایل حاشیه ای را با تعیین یک حاشیه حداقلی برای تمامی زوج کلاس ها پیشنهاد می دهیم. ما تابع اتلاف جدیدی به نام حداقل اتلاف حاشیه ای (MML) پیشنهاد می دهیم که هدف آن گسترش محدوده آن هایی است که به زوج های مرکزی دسته بیش از حد نزدیک می شوند تا قابلیت متمایز کننده ویژگی های عمیق را ارتقاء دهد. تابع MML همراه با توابع Softmax Loss و Centre Loss بر فرآیند آموزش نظارت می کنند تا حاشیه های تمامی دسته ها را صرف نظر از توزیع دسته آن ها مورد نظارت قرار دهند. ما تابع MML را در پلتفورم Inception-ResNet-v1 پیاده سازی می کنیم و آزمایش های گسترده ای را بر روی هفت مجموعه داده تشخیص چهره انجام می دهیم که شامل MegaFace، FaceScrub، LFW، SLLFW، YTF، IJB-B و IJB-C است. نتایج تجربی نشان می دهد که تابع از دست دادن MML پیشنهادی منجر به حالت جدیدی در تشخیص چهره می شود و اثر منفی جهت گیری حاشیه ای را کاهش می دهد.
کلید واژه ها :یادگیری عمیق | شبکه های عصبی باز رخدادگر (CNN) | تشخیص چهره| کمترین از دست دادن حاشیه ای (MML)
|مقاله ترجمه شده|
Deep Learning-Driven Particle Swarm Optimisation for Additive Manufacturing Energy Optimisation
بهینه سازی ازدحام ذرات با محوریت یادگیری عمیق برای بهینه سازی انرژی تولید افزودنی-2019
The additive manufacturing (AM) process is characterised as a high energy-consuming process, which has a significant impact on the environment and sustainability. The topic of AM energy consumption modelling, prediction, and optimisation has then become a research focus in both industry and academia. This issue involves many relevant features, such as material condition, process operation, part and process design, working environment, and so on. While existing studies reveal that AM energy consumption modelling largely depends on the design-relevant features in practice, it has not been given sufficient attention. Therefore, in this study, design-relevant features are firstly examined with respect to energy modelling. These features are typically determined by part designers and process operators before production. The AM energy consumption knowledge, hidden in the design-relevant features, is exploited for prediction modelling through a design-relevant data analytics approach. Based on the new modelling approach, a novel deep learning-driven particle swarm optimisation (DLD-PSO) method is proposed to optimise the energy utility. Deep learning is introduced to address several issues, in terms of increasing the search speed and enhancing the global best of PSO. Finally, using the design-relevant data collected from a real-world AM system in production, a case study is presented to validate the proposed modelling approach, and the results reveal its merits. Meanwhile, optimisation has also been carried out to guide part designers and process operators to revise their designs and decisions in order to reduce the energy consumption of the designated AM system under study.
Keywords: Additive Manufacturing | Energy Consumption Modelling | Prediction and Optimisation | Deep Learning | Particle Swarm Optimisation
Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images
Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images-2019
Abstract Background: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25e26% of discordance for classifying a benign nevus versus malignant melanoma. A recent study indicated the potential of deep learning to lower these discordances. However, the performance of deep learning in classifying histopathologic melanoma images was never compared directly to human experts. The aim of this study is to perform such a first direct comparison. Methods: A total of 695 lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi/345 melanoma). Only the haematoxylin & eosin (H&E) slides of these lesions were digitalised via a slide scanner and then randomly cropped. A total of 595 of the resulting images were used to train a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison to 11 histopathologists. Three combined McNemar tests comparing the results of the CNNs test runs in terms of sensitivity, specificity and accuracy were predefined to test for significance (p < 0.05). Findings: The CNN achieved a mean sensitivity/specificity/accuracy of 76%/60%/68% over 11 test runs. In comparison, the 11 pathologists achieved a mean sensitivity/specificity/accuracy of 51.8%/66.5%/59.2%. Thus, the CNN was significantly (p Z 0.016) superior in classifying the cropped images. Interpretation: With limited image information available, a CNN was able to outperform 11 histopathologists in the classification of histopathological melanoma images and thus shows promise to assist human melanoma diagnoses.
KEYWORDS : Melanoma | Pathology | Histopathology | Deep learning | Artificial intelligence
Cryptocurrency forecasting with deep learning chaotic neural networks
پیش بینی cryptocurrency با یادگیری عمیق شبکه های عصبی پر هرج و مرج-2019
We implement deep learning techniques to forecast the price of the three most widely traded digital currencies i.e., Bitcoin, Digital Cash and Ripple. To the best of our knowledge, this is the first work to make use of deep learning in cryptocurrency prediction. The results from testing the existence of non- linearity revealed that the time series of all digital currencies exhibit fractal dynamics, long memory and self-similarity. The predictability of long-short term memory neural network topologies (LSTM) is signif- icantly higher when compared to the generalized regression neural architecture, set forth as our bench- mark system. The latter failed to approximate global nonlinear hidden patterns regardless of the degree of contamination with noise, as they are based on Gaussian kernels suitable only for local approximation of non-stationary signals. Although the computational burden of the LSTM model is higher as opposed to brute force in nonlinear pattern recognition, eventually deep learning was found to be highly efficient in forecasting the inherent chaotic dynamics of cryptocurrency markets.
Keywords: Digital currencies | Deep learning | Fractality | Neural networks | Chaos | Forecasting
Temporal and spatial deep learning network for infrared thermal defect detection
شبکه یادگیری عمیق زمانی و مکانی برای تشخیص نقص حرارتی مادون قرمز-2019
Most common types of defects for composite are debond and delamination. It is difficult to detect the inner defects on a complex shaped specimen by using conventional optical thermography nondestructive testing (NDT) methods. In this paper, a hybrid of spatial and temporal deep learning architecture for automatic thermography defects detection is proposed. The integration of cross network learning strategy has the capability to significantly minimize the uneven illumination and enhance the detection rate. The probability of detection (POD) has been derived to measure the detection results and this is coupled with comparison studies to verify the efficacy of the proposed method. The results show that visual geometry group-Unet (VGG-Unet) cross learning structure can significantly improve the contrast between the defective and non-defective regions. In addition, investigation of different feature extraction methods in which embedded in deep learning is conducted to optimize the learning structure. To investigate the efficacy and robustness of the proposed method, experimental studies have been carried out for inner debond defects on both regular and irregular shaped carbon fiber reinforced polymer (CFRP) specimens.
Keywords: Deep learning | Segmentation | Thermography defect detection | Nondestructive testing