CNN Research Papers - Academia.edu (original) (raw)

In this era of automation, deep learning has a vital role in computer vision for objects detection. Deep learning provides powerful tools that are able to learn semantics, and high-level deep features to address the problems that exist in traditional architectures of hand-crafted feature extraction techniques like HOG and SIFT. In this paper we proposed an automatic surveillance and auditing system for detecting eight categories of automobiles i.e. bus, car, truck, bike, horse buggy, rickshaws, and van that can help vehicle tracking systems for commercialized parking areas. A transfer learning technique has been used in this research to quickly learn the features by recording a small number of training images. A convolution neural network is used, to fine-tune the accuracy of classification for a given set of images. The network extracts the feature maps from all the data set and generate a label for each object (vehicle) in the image that can help in vehicle-type detection and classification. The experimental results showed that the proposed system is working accurately and efficiently by giving 91.09% accuracy.

- by and +2
- •
- Image Classification, CNN, Vehicle Types, Vehicle Identification

In this digital world, artificial intelligence has provided solutions to many problems, likewise to encounter problems related to digital images and operations related to the extensive set of images. We should learn how to analyze an image, and for that, we need feature extraction of the content of that image. Image description methods involve natural language processing and concepts of computer vision. The purpose of this work is to provide an efficient and accurate image description of an unknown image by using deep learning methods. We propose a novel generative robust model that trains a Deep Neural Network to learn about image features after extracting information about the content of images, for that we used the novel combination of CNN and LSTM. We trained our model on MSCOCO dataset, which provides set of annotations for a particular image, and after the model is fully automated, we tested it by providing raw images. And also several experiments are performed to check effici...

- by Shivam Gupta
- •
- Computer Science, Computer Vision, Image Processing, Natural Language Processing

Muscles can cause injury by training to improve physical performance. However, there are few ways to assess muscle fatigue currently. Therefore, in this paper, muscle fatigue is evaluated using surface EMG(ElectroMyoGram). The proposed method in this research consists of 4 parts: Measurement, Pre-processing, Feature extraction, and Learning identification parts. The effectiveness of the proposed method is demonstrated in two ways, classification and regression analysis, and comparative verification is conducted.

- by SDIWC Organization
- •
- Biometrics, CNN, Deep Learning, Regression Analysis

American media offer predictably efficient servings of propagandized news information for audiences eager to confirm their personal biases (Giroux, 2017, Scollon, 2014). Exemplary reports delivered by CNN and Fox News feature young people and a Native Americans on the steps of the Lincoln Memorial in Washington, D.C., U.S.A. on January 18 th , 2019. The headlines and accompanying photos of this story are presented as meme-like ensembles, designed for flash-consumption by audiences expecting certain ideological perspectives. This study proposes that each news source presents meme-tic constructs of McDonaldized-media discourse (McMD) and attempts to delineate them as such by asking: 1) What power relationships and ideologies emerge from the multimodal discourse of each headline and their accompanying photo? 2) What do the findings tell us about the differences between them? 3) Do any of the findings appear to qualify as McMD? A multimodal critical discourse analysis (Machin & Mayr, 2012) of the data revealed predictably efficient kernels of 'news' suggestive of McDonaldization (Montgomery, 2007; Ritzer, 1993). The findings not only yield the ideological positionings of CNN and Fox News but suggest an underlying hazard that McMD diminishes democratic process by deoxygenating a free-press, rather than replenishing it with objective reporting.

In a factory production line, different industry parts need to be quickly differentiated and sorted for further
process. Parts can be of different colors and shapes. It is tedious for humans to differentiate and sort these
objects in appropriate categories. Automating this process would save more time and cost. In the
automation process, choosing an appropriate model to detect and classify different objects based on
specific features is more challenging. In this paper, three different neural network models are compared to
the object sorting system. They are namely CNN, Fast R-CNN, and Faster R-CNN. These models are
tested, and their performance is analyzed. Moreover, for the object sorting system, an Arduino-controlled 5
DoF (degree of freedom) robot arm is programmed to grab and drop symmetrical objects to the targeted
zone. Objects are categorized into classes based on color, defective and non-defective objects.

- by Ahmet Çinar
- •
- Image Processing, Machine Learning, Medical Image Processing, Transfer Learning

Currently, the whole world is fighting a very dangerous and infectious disease caused by the novel coronavirus, called COVID-19. The COVID-19 is rapidly spreading around the world due to its high infection rate. Therefore, early discovery of COVID-19 is crucial to better treat the infected person as well as to slow down the spread of this virus. However, the current solution for detecting COVID-19 cases including the PCR test, CT images, epidemiologically history, and clinical symptoms suffer from high false positive. To overcome this problem, we have developed a novel transfer deep learning approach for detecting COVID-19 based on x-ray images. Our approach helps medical staff in determining if a patient is normal, has COVID-19, or other pneumonia. Our approach relies on pre-trained models including Inception-V3, Xception, and MobileNet to perform two tasks: i) binary classification to determine if a person infected with COVID-19 or not and ii) a multi-task classification problem t...

- by saja tawalbeh
- •
- Computer Science, CNN, Deep Learning, Epidemic

broadcast a report about the custom of clitoridectomy in Egypt. The televised report included footage of such a ceremony performed on a ten-year-old Egyptian girl in Cairo a few days earlier. This broadcast revived the public polemics on clitoridectomy in Egypt. Secular newspapers such as al-Wafd and al-Ahali opposed this practice while religious circles used the al-Sha’b newspaper to justify it. The religious argument is based on Islamic tradition although the origin of the practice is admittedly pre-Islamic. This position maintains that the type of clitoridectomy performed involves minimal excision, but in practice it is much more radical. There are voices from within the Islamic camp, mainly those of women, that call for the abolition of this practice, basing this demand on the fact that this act is a minor rather than major principle of Islamic Law. Although the secular educated classes in Egypt tend to avoid this practice, they are a minority. The public argument continues in a...

- by Mordechai Kedar
- •
- Female Circumcision, Media, Islam, Tradition

The use of deep learning models to identify lesions on cotton leaves on the premise of images of the crop within the field is proposed in this article. Its cultivation in tropical regions has made it the target of a large spectrum of agricultural pests and diseases, and efficient economical solutions are needed. Moreover, the symptoms of the main pests and diseases cannot be differentiated within the initial stages, and also the correct identification of a lesion can be troublesome for the producer. To help resolve the problem, the present research provides a solution based on deep learning in the screening of cotton leaves that builds it attainable to watch the health of the cotton crop and make higher choices for its management. For this approach, Automatic classifier CNN will be used for classification based on learning with some training samples of that two categories. Finally the simulated result shows that used network classifier provides minimum error during training and better accuracy in classification.

- by IJRASET Publication
- •
- CNN, Deep Learning
- by Varun Magotra
- •
- CNN, Deep Learning, Plant Disease, Tensorflow

The face mask is an essential sanitaryware in daily lives growing during the pandemic period and is a big threat to current face recognition systems. The masks destroy a lot of details in a large area of face, and it makes it difficult to recognize them even for humans. The evaluation report shows the difficulty well when recognizing masked faces. Rapid development and breakthrough of deep learning in the recent past have witnessed most promising results from face recognition algorithms. But they fail to perform far from satisfactory levels in the unconstrained environment during the challenges such as varying lighting conditions, low resolution, facial expressions, pose variation and occlusions. Facial occlusions are considered one of the most intractable problems. Especially when the occlusion occupies a large region of the face because it destroys lots of official features.

The proposed method aids in the diagnosis of plant diseases as well as the provision of medicines that may be employed as a defensive machine against them. The file collected from the web is correctly separated, and the various plant types are recognized and named again to produce a suitable record. A test file including several plant ailments is then obtained, which is used to assess the project's accuracy and confidence level. We'll next train our classifier with training data, and the result will be expected with maximum accuracy. We employ a Deep Convolutional Neuronic network (CNN), which consists of many layers for an estimate. A newly designed drone prototypical is also being developed that can be used to provide live updates of huge farming lands. The drone will be equipped with a highresolution photographic camera that will capture the image of the plants, which will be used as a contribution to the software, which will determine whether the plant is healthy or not. We reached a 78 percent accuracy level with our programming and training model. Our programmer provides us with the identity of the plant species, as well as the confidence level of the species and the medicine that may be used to treat it.

- by IJRASET Publication
- •
- Image Processing, Machine Learning, CNN, Remedy
- by Sarah Madi
- •
- Machine Learning, CNN, Supervised Learning, K- nearest neighbour (KNN)

Bot spammer merupakan penyalahgunaan user dalam menggunakan Twitter untuk menyebarkan pesan spam sesuai dengan keinginan user. Tujuan spam mencapai trending topik yang ingin dibuatnya. Penelitian ini mengusulkan deteksi bot spammer pada Twitter berbasis Time Interval Entropy dan global vectors for word representations (Glove). Time Interval Entropy digunakan untuk mengklasifikasi akun bot berdasarkan deret waktu pembuatan tweet. Glove digunakan untuk melihat co-occurrence kata tweet yang disertai Hashtag untuk proses klasifikasi menggunakan Convolutional Neural Network (CNN). Penelitian ini menggunakan data API Twitter dari 18 akun bot dan 14 akun legitimasi dengan 1.000 tweet per akunnya. Hasil terbaik recall, precision, dan f-measure yang didapatkan yaitu 100%; 100%, dan 100%. Hal ini membuktikan bahwa Glove dan Time Interval Entropy sukses mendeteksi bot spammer dengan sangat baik. Hashtag memiliki pengaruh untuk meningkatkan deteksi bot spammer.

- by Arif Mudi Priyatno
- •
- Computer Science, Informatics, Twitter, CNN
- by Jaydip Sen
- •
- Computer Science, Artificial Intelligence, Image Processing, Machine Learning

The use of deep learning models to identify lessions on cotton leaves on the basis of images of the crop in the field is proposed in this article. Its cultivation in tropical regions has made it the target of a wide spectrum of agricultural pests and diseases, and efficient solutions are required. Moreover, the symptoms of the main pests and diseases cannot be differentiated in the initial stages, and the correct identification of a lesion can be difficult for the producer. To help resolve the problem, the present research provides a solution based on deep learning in the screening of cotton leaves which makes it possible to monitor the health of the cotton crop and make better decisions for its management. For this approach, Automatic classifier CNN will be used for classification based on learning with some training samples of that two categories. Finally the simulated result shows that used network classifier provides minimum error during training and better accuracy in classification.

- by IJRASET Publication
- •
- CNN, Deep Learning, Plant Disease

The concept of Object recognition is the most recent and the evolving topic in the field of Artificial Intelligence, which helps the machine to identify the objects which is present in the surrounding environment and recognising that object from the dataset. For identifying the objects from the dataset there is a lot of classification so that the object to be identified can be identified accurately. This will help the visually impaired person to know their surroundings better, which can guide them in every step they take. This will be the helping hand for the person to avoid obstacles which is on their way.

- by IJRASET Publication
- •
- Neural Networks, CNN, Yolo

Automated reading of handwritten Kannada documents is highly challenging due to the presence of vowels, consonants and its modifiers. The variable nature of handwriting styles aggravates the complexity of machine based reading of handwritten vowels and consonants. In this paper, our investigation is inclined towards design of a deep convolution network with capsule and routing layers to efficiently recognize Kannada handwritten characters. Capsule network architecture is built of an input layer, two convolution layers, primary capsule, routing capsule layers followed by trilevel dense convolution layer and an output layer. For experimentation, datasets are collected from more than 100 users for creation of training data samples of about 7769 comprising of 49 classes. Test samples of all the 49 classes are again collected separately from 3 to 5 users creating a total of 245 samples for novel patterns. It is inferred from performance evaluation; a loss of 0.66% is obtained in the classification process and for 43 classes precision of 100% is achieved with an accuracy of 99%. An average accuracy of 95% is achieved for all remaining 6 classes with an average precision of 89%.

Swarm intelligence (SI), an important aspect of artificial intelligence, is increasingly gaining popularity as more and more high-complexity challenges necessitate solutions that are sub-optimal but still feasible in a fair amount of time. Artificial intelligence that mimics the collective behavior of a group of animals is known as swarm intelligence. Attempting to survive. Optimization contributes to optimal resource management by way of efficient and effective problem-solving. Engineers' attention has been driven to more effective and scalable metaheuristic algorithms as a result of the complicated optimization issues. It is primarily influenced by biological systems. The main aim of our article is to find out more about the guiding principle, classify possible implementation areas, and include a thorough analysis of several SI algorithms. Swarms can be observed in ant colonies, fish schools, bird flocks, among other fields. During this article, we will look at some Swarm instances and their behavior. The authors see many Swarm Intelligence systems, like Ant colony Optimization, which explains ant activity, nature, and how they conquer challenges; in birds, we see Particle Swarm Optimization is a swarm intelligence-based optimization technique, and how the locations must be positioned based on the three concepts. The Bee Colony Optimization follows, and explores the behavior of bees, their relationships, as well as movement and how they work in a swarm. This paper explores several algorithms such as ACO, PSO, GA, and FA.

- by Shahab Karim
- •
- Swarm Intelligence, CNN

Automatic identity recognition of ear images represents an active area of interest within the biometric community. The human ear is a perfect source of data for passive person identification. Ear images can be captured from a distance and in a covert manner; this makes ear recognition technology an attractive choice for security applications and surveillance in addition to related application domains. Differing from other biometric modalities, the human ear is neither affected by expressions like faces are nor do need closer touching like fingerprints do. In this paper, a deep learning object detector called faster region based convolutional neural networks (Faster R-CNN) is used for ear detection. A convolutional neural network (CNN) is used as feature extraction. principal component analysis (PCA) and genetic algorithm are used for feature reduction and selection respectively and a fully connected artificial neural network as a matcher. The testing proved the accuracy of 97.8% percentage of success with acceptable speed and it confirmed the accuracy and robustness of the proposed system.

- by TELKOMNIKA JOURNAL and +1
- •
- CNN, Pca, Real Time, Ear Recognition

In the agriculture field, plant disease diagnosis is one of the leading factors. Therefore, to create an automated system that may identify plant disease diagnosis as simple as possible. The exact identification of crop diseases is exceptionally wanted in the field of agriculture. In this project, to propose a convolution neural network architecture for corn leaf disease identification. The analysis is implemented using corn leaf images from the plant village dataset. The proposed CNNs are trained to identify three different classes, that is two diseases and one healthy class. The trained model achieves an accuracy of 96.04%. The trained program specimens are embedded in the raspberry pi, and it fitted on the drone. Recently, Unmanned Aerial Vehicle (UAVs) has increased a lot of consideration. Specifically, there is a developing in utilizing UAVs for agricultural application such as crop monitoring and management. Proposing a computerized framework that is capable of detecting corn leaf diseases with high accuracy. The framework embraces computer vision and deep learning to process the images captured by UAVs at low altitudes and to identify the infected corn leaf.

This Project is focused on credit card fraud detection in real-world scenarios. Fraud is one of the major ethical issues in the credit card industry. In this era we can see many innovative financial services like ATMs, online banking, etc. Besides, along with the rapid advances of e-commerce, the use of credit cards has become a convenient and necessary part of financial life. A credit card is a payment card supplied to customers as a system of payment. Using a third-person credit card or its information without the knowledge of that person is referred to as credit card fraud. Application and Behavioral fraud are major types of fraud where people are easily tricked and lose their money. The same user may submit multiple applications which may lead to identical fraud. Application fraud takes place when fraudsters apply for new cards from a bank or issuing companies using false or others' information. In this project, we will be applying some supervised and unsupervised algorithms and will classify the credit card dataset. We will use CNN and correlate the data train and get the model's accuracy.

- by IJRASET Publication
- •
- Logistic Regression, CNN, Feature Extraction

Safety is of predominant value for employees who are working in an industrial and construction environment. Real time Object detection is an important technique to detect violations of safety compliance in an industrial setup. The negligence in wearing safety helmets could be hazardous to workers, hence the requirement of the automatic surveillance system to detect persons not wearing helmets is of utmost importance and this would reduce the labor-intensive work to monitor the violations. In this paper, we deployed an advanced Convolutional Neural Network (CNN) algorithm called Single Shot Multibox Detector (SSD) to monitor violations of safety helmets. Various image processing techniques are applied to all the video data collected from the industrial plant. The practical and novel safety detection framework is proposed in which the CNN first detects persons from the video data and in the second step it detects whether the person is wearing the safety helmet. Using the proposed mode...

- by Nilesh Powar
- •
- Computer Science, Image Processing, CNN, Deep Learning

Eczema is the most common among all types of skin diseases. A solution for this disease is very crucial for patients to have better treatment. Eczema is usually detected manually by doctors or dermatologists. It is tough to distinguish between different types of Eczema because of the similarities in symptoms. In recent years, several attempts have been taken to automate the detection of skin diseases with much accuracy. Many methods such as Image Processing Techniques, Machine Learning algorithms are getting used to execute segmentation and classification of skin diseases. It is found that among all those skin disease detection systems, particularly detection work on eczema disease is rare. There is also insufficiency in eczema disease dataset. In this paper, we propose a novel deep CNN-based approach for classifying five different classes of Eczema with our collected dataset. Data augmentation is used to transform images for better performance. Regularization techniques such as batch normalization and dropout helped to reduce overfitting. Our proposed model achieved an accuracy of 96.2%, which exceeded the performance of the state of the arts.

- by Joyece Jane
- •
- CNN

Theft is one of the most common criminal behaviors and it is increasing day by day. It has become one of the never-ending problems of the world. In the USA alone, about 7000 cases of baggage theft are reported to Transportation Security Administration (TSA) for theft on airports. Most of the screening takes place before the passengers and their luggage can get on the plane. In order to stop these increasing theft on the airports, a robust system is required which would detect if there is any robbery taking place and would inform the respective authorities. So to solve this problem, we will be creating a system which would accurately track the people and their baggage's and would detect if there is any theft and would inform the authorities.

- by Ijariit Journal
- •
- Computer Vision, CNN, Theft

Oral cancer is one of the most dangerous cancers which affects and originates from the oral cavity and neck. Overuse of tobacco and smoking cigarettes are the primary risk factor for developing oral cancer. This technique derives a group of features that would help the classifiers to identify the image state automatically. Various machine learning methods are applied on the datasets and their performance are analyzed. The derived features were classified using CNN, which are compared against various standard classification approaches such as SVM, Naive bayes. From the results, it is observed that the different stage classification of oral cancer can be classified effectively. Hence, the classification of various oral cancers can be achieved more efficiently by means of CNN.

- by IAEME Publication
- •
- CNN, Segmentation, Classification, Svm

This Accurate Real-time object detection needs faster computation power to identify the object at that specific time. The accuracy of object detection has increased drastically with the advancement of deep learning techniques. We incorporate a stateof-the-art method for object detection to achieve high accuracy with real-time performance. The state-of-the-art methods are subdivided into two types. The first is one-stage methods that prioritize inference speed, and example models include YOLO, SSD, and RetinaNet. The second is two-stage methods that prioritize detection accuracy, and its example models include Faster R-CNN, Mask R-CNN, and Cascade R-CNN. Among all these, Faster-RCNN and SSD have better accuracy, while YOLO performs better when speed is given preference over accuracy. A major challenge in many of the object detection systems is that it is dependent on the other computer vision techniques for helping the deep learning-based approach, which results in slow and non-optimal performance. In this paper, we have used a deep learning-based approach to solve the matter of object detection in an end-to-end fashion. Deep learning combines SSD and Mobile Nets to perform the efficient implementation of detection and tracking.SSD eliminates the feature resampling stage and combined all calculated results as a single component. MobileNet is a lightweight network model that uses depth-wise separable convolution for the places which lacks computational power like mobile devices (eg: laptop, mobile phones, etc). This algorithm performs efficient object detection while not compromising on the performance The main purpose of our research is to elaborate the accuracy of an object detection method SSD and the importance of the pre-trained deep learning model MobileNet. The resultant system is fast and accurate, thus aiding those applications which require object detection

- by IJRASET Publication
- •
- CNN, Solid State Drive(SSD), Tensorflow

Depth estimation is an important component of understanding geometric relations within a scene. Different depth estimation techniques using a single image are analyzed in this survey paper. Depth estimation from a single image is often described as an ill-posed and inherently ambiguous problem. Recovering depth information in applications like 3D modeling, robotics, autonomous driving, etc. is more important when no other information such as stereo images, optical flow, or point clouds are unavailable. For the task of depth estimation using single images, learning based methods have shown very promising results.

- by Ijariit Journal
- •
- CNN, Higher resolution maps, Depth estimaton

With the growing population, there comes a great need to provide sufficient necessities for everyone. Here comes the question whether we have enough resources to provide necessities for everyone or not. It shows the importance of increasing agricultural production. There are a lot of reasons for the decrease in Agriculture production, one of the main factors is diseases/pests. Pests/diseases can damage the entire crop in a short time if not detected and diagnosed on time. Detection of crop diseases at an initial stage can help farmers diagnose the disease on time, hence increasing the productivity of the crop. This is possible with the implementation of advanced technologies like Deep Learning (DL) in the field of Agriculture. DL is being used in Agriculture for Crop Recommendation, Precision Agriculture, Disease detection, and Smart Irrigation etc. DL approach, precisely Convolution Neural Network (CNN) can be used to detect the leaf disease more precisely and accurately than humans. The proposed work uses various CNN architectures like AlexNet, MobileNet, ResNet50 and some CNN based models that are built from scratch for the detection and identification of leaf diseases of various crops. Once the classification is done, these architectures will then be compared based on their performance and accuracy. The best model will be chosen for deployment using Django framework to create a web application to make the model more readable and user friendly.

- by Kushal H and +1
- •
- Image Processing, CNN, Deep Learning, Plant Disease

This study examines how participatory journalism reshapes the field of journalism in the case of CNN iReport. Participation is conceptualized on a continuum, ranging from participants as providing comments to news stories to participants as constructing news. Using a textual analysis combined with a content analysis of CNN’s broadcast transcripts and articles posted online on CNN.com (N = 668) over a period of six years, this study investigates CNN iReporters’ positions in the organization’s news content as part of its overall news culture. Findings suggest that CNN assigns three major positions to iReporters: commentator, eyewitness, and co-worker. Positions of iReporters vary in story topics and contexts over time. Results show that CNN repositions itself and legitimizes its position as an agenda setter and moderator in relation to citizens’ contributions. In the context of the CNN iReport, participatory journalism as integrated in corporate media content may reinforce the organization’s cultural capital—their independence from external influences—while letting citizens and ultimately free labor be part of news as well as, more recently, sharing with citizens the process of constructing news.

- by Lea Hellmueller and +1
- •
- New Media, Journalism, Participatory Media, Robotic Journalism, Online Gatekeeping

In the diagnosis of Brain tumor Magnetic Resonance Imaging has an important role in the identification of tumor. But classification becomes very difficult for the physician due to the complex structure of the brain. A very few features can be extracted from 2D Brain MRI. 3D MRI provides comparable diagnostic performance and gives more features than 2D MRI. In this paper, 3D MRI is employed for the detection and classification of a Brain Tumor. Radiomics uses data-characterization algorithms capable of getting a large number of features from MRI. These radiomics features can uncover the characteristics of the disease. Pyradiomics, a python open-source package is used to extract GLCM features. A Combinational Model that uses the features of GLCM (Grey Level Co-occurrence Matrix) and 3D-CNN (Convolution Neural Network) combined with KNN (K-Nearest Neighbor) is carried out on 3D MRI. 3D-CNN is used to extract a more powerful volumetric representation across all three axes. The last layer of 3D-CNN is supposed to learn a good representation of an image. The features are extracted from that layer and provided to KNN classifier for further prediction. The accuracy is observed to be improved by up to 96.7% using this method.

During pandemic COVID-19, the World Health Organization (WHO) reports suggest that the two main routes of transmission of the COVID-19 virus are respiratory droplets and physical contact. Respiratory droplets are generated when an infected person coughs or sneezes. Any person in close contact (within 1 m) with someone who has respiratory symptoms (coughing, sneezing) is at risk of being exposed to potentially infective respiratory droplets. Droplets may also land on surfaces where the virus could remain viable; thus, the immediate environment of an infected individual can serve as a source of transmission (contact transmission). Wearing a medical mask and social distancing is one of the prevention measures that can limit the spread of certain respiratory viral diseases, including COVID-19. World Health Organization has made wearing masks and also social distancing compulsory to protect against this deadly virus. This paper is about we developed a generic Deep Neural Network-Based model for mask detection, tracking using cameras and also we developed second application for social distancing monitoring application with the help of Python and Computer Vision.

- by IJRASET Publication
- •
- Computer Vision, AI, CNN, Deep Learning

Malaria is a parasitic infection caused in humans by the parasite belonging to the genus Plasmodium. The
traditional approach of diagnosis by the use of microscopy, considered to be the “gold standard method” has at times proved to
be inefficacious and inefficient as it is time consuming, needs more expertise and is erring at times. This raises a need for
better alternatives for the diagnosis of the parasitic infection. This paper highlights the advancement in the field of machine
learning and its beneficial applications in the detection, identification and diagnosis of the malarial infection via the use of
smartphones. It uses a pre trained CNN for the detection of the parasite. The experimental results excelled in the relevant
attributes of accuracy, efficiency and sensitivity of this technique, making this outperform the traditional means of detection.

- by IJRASET Publication
- •
- Image Processing, Machine Learning, CNN

The higher death rate in motorbike accidents is credited to carelessness in wearing a head protector (helmet) by bike riders. Identification of helmetless riders continuously is a necessary task to forestall the event of such accidents. This paper presents an automated framework to distinguish motor bikers without a head protector (helmet) from traffic observation recordings progressively. In this paper, a Single shot multibox detector (SSD) model is applied to the helmet detection problem. This model can utilize just one single CNN system to distinguish the bounding box area of motorbike and rider. When the area is chosen we classify whether the biker is wearing or not wearing a helmet on real-time. Convolutional Neural Network is applied to select motorbikers among the moving objects and recognition of motorbikers without a helmet. Further applying the You only look once (YOLO) model, I recognize the License Plates of motorbikers without a helmet. So I have applied three models in all through the framework, the custom CNN Model, SSD Model and the YOLO model.

- by Publishing India Group and +1
- •
- Computer Science, Machine Learning, CNN, Deep Learning

- by Altaf Hussain
- •
- Image Classification, CNN, Vehicle Types, Vehicle Identification

The concept of Raga and Tala is integral part of Indian Classical music. Raga is the melodic component while Tala is the rhythmic component in the music. Hence, Tala classification and identification is a paramount problem in the area of Music Information Retrieval (MIR) systems. Although there are seven basic Talas in Carnatic Music, a further subdivision of them gives a total of 175 ragas. Statistical and machine learning approaches are proposed in Literature Survey to classify Talas. However, they use complete musical recording for training and testing. As part of this paper, a novel approach is proposed for the first time in Carnatic music to classify Talas using repetitive structure called Thumbnails.

Tumors are now the second major cause of cancer. A huge percentage of patients are in danger as more than just a consequence of cancer. The medical field needs fast, automated, efficient and reliable technique to detect tumor like brain tumor. Detection plays very important role in treatment. If proper detection of tumor is possible then doctors keep a patient out of danger. Various image processing techniques are used in this application. Doctors are able to provide excellent treatment and save a huge number of tumour patients by using this application. A tumour is nothing more than an uncontrolled growth of cells. Brain tumour cells expand to the point where they consume all of the nutrition intended for healthy cells and tissues, resulting in brain failure. Currently, doctors manually locate the position and area of a brain tumour by looking at the patient's MR images of the brain. This leads to inaccuracy in tumour detection and is extremely time intensive. A tumour is an uncontrollably growing clump of tissue. We can utilise CNN (Convolution Neural Network), also known as NN (Neural Network), and VGG 16 Deep Learning architectures (visual geometry group). To diagnose a brain tumour, transfer learning is used. The model's performance predicts whether or not a tumour is present in an image. If a tumour is present, the answer is yes; otherwise, the answer is no.

- by IJRASET Publication
- •
- Image Processing, Transfer Learning, Brain Tumor, CNN

Some infrastructure can be provided for the blind people so that they can feel safe while travelling. A smart stick can be proposed as an additional aid for the blind to improve mobility. The stick helps to sense obstacles and provide assistance to return to home safely. The stick helps to detect the vehicle coming towards the user by means of strong sensors employed in it. This enables the blinds user to cross roads without assistance. The Assistor works based on the technology of object recognition, image processing and human recognition and a navigation system. This model implements a camera on the hand of the stick. It captures the images of person approaching the user. Using convolutional neural network algorithm(CNN), the stick recognize the image and it returns the identity of that person. Ultrasonic sensors are used for obstacle detection. Three of them together helps to detect the vehicles passing by. Atmega328 microcontroller controls the activities taking place in the system. Feedback is given to the user through an audio earpiece using Bluetooth technology. The system employs GPS module for location tracking and navigation. GSM module installed in the stick sends emergency messages to the stored mobile numbers (Usually the numbers of people closer to the user) along with his current location. Index Terms: GPS, GSM, CNN, image recognition, vehicle detection , ultrasonic sensors, bluetooth module, emergency button. I. INTRODUCTION As stated by the WHO, the estimated number of people visually impaired in the world is 285 million, 39 million blind and 246 million having low vision; 65 all blind are 50 years and older. There is a large group of people facing difficulties in carrying out their daily routine work due to eyesight lose. Their most dominant problems are in transportation, such as crossing roads, traveling in trains, or other public places, and also the inability to recognize people approaching them. They always require human assistance to do so. Visually impaired people needs assistance from others in an outdoor environment. They may not know the presence of objects or vehicles in front of them or how close they are from an obstacle. This makes them vulnerable to accidents and other physical damages. The proposed stick detects the obstacles and vehicles with the help of ultrasonic sensors. Three ultrasonic sensors are employed in the stick to get a wider coverage and also the relative position of the obstacle. The blinds cannot recognize people approaching him. It leads to exploitation threat to his safety. This stick helps the user to recognize people approaching him. The stick has a camera module that capture the front view of the user. The system will be trained to recognize the faces of people, those who are related with the user. Others are considered as strangers and an alert is provided whenever the stick finds a stranger in its way. Another functionality of the system is the provision of navigation instructions so that the person will be able to go home with the help of the navigation instructions provided. Blind people can use this walking stick for safe navigation. The stick is embedded with microcontroller, GSM module, GPS module, vibrator, switches and a camera module. GSM module helps to send emergency messages and calls to the phone numbers of people who are related with the user. Microcontroller stores emergency contact numbers. The message includes current location of the user which can be retrieved using GPS module. The stick gives a fair idea about the obstacles, vehicles and humans with the help of audio signal provided through the ear piece. The user will be provided with details about the distance and location of any object in the surrounding/infront of it. The wireless connection between the stick and user's headphone has been established using Bluetooth technology. Once bluetooth pairing is done, the stick can provide voice instructions to the user.

- by IJRASET Publication
- •
- GPS Applications, CNN, GSM network, Image recognition

With the availability of enormous amounts of data and the need to computerize visual-based systems, research on object detection has been the focus for the past decade. This need has been accelerated with the increasing computational power and Convolutional Neural Network (CNN) advancements since 2012. With various CNN network architectures available, the You Only Look Once (YOLO) network is popular due to its many reasons, mainly its speed of identification applicable in real-time object identification. Followed by a general introduction of the background and CNN, this paper wishes to review the innovative, yet comparatively simple approach YOLO takes at object detection.

One of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cancer is the early stage. However, the early stage of lung cancer often does not have any clinical symptoms and is difficult to be found. In this paper, lung nodule classification has been performed; the data have used of CT image is SPIE AAPM-Lung. In recent years, deep learning (DL) was a popular approach to the classification process. One of the DL approaches that have used is Transfer Learning (TL) to eliminate training costs from scratch and to train for deep learning with small training data. Nowadays, researchers have been trying various deep learning techniques to improve the efficiency of CAD (computer-aided system) with computed tomography in lung cancer screening. In this work, we i...

- by Ahmet Çinar
- •
- Image Processing, Machine Learning, Medical Image Processing, Transfer Learning

Sign language is one of the oldest and most natural forms of language for communication , but since most people do not know sign language and interpreters are very difficult to come by, we have come up with a real time method using neural networks for fingerspelling based American sign language. In our method, the hand is first passed through a filter and after the filter is applied the hand is passed through a classifier which predicts the class of the hand gestures. Our method provides 95.7% accuracy for the 26 letters of the alphabet.

- by IJRASET Publication
- •
- Computer Science, Image Processing, Sign Languages, CNN

Object Detection is an emerging technology in the field of Computer Vision and Image Processing that deals with
detecting objects of a particular class in digital images. It has considered being one of the complicated and challenging tasks in
computer vision. Earlier several machine learning-based approaches like SIFT (Scale-invariant feature transform) and HOG
(Histogram of oriented gradients) are widely used to classify objects in an image. These approaches use the Support vector
machine for classification. The biggest challenges with these approaches are that they are computationally intensive for use in
real-time applications, and these methods do not work well with massive datasets. To overcome these challenges, we implemented
a Deep Learning based approach Convolutional Neural Network (CNN) in this paper. The Proposed approach provides accurate
results in detecting objects in an image by the area of object highlighted in a Bounding Box along with its accuracy.

- by IJRASET Publication
- •
- CNN, SIFT, Object Detection

Hayvancılık işletmelerinde hayvanların ihtiyaçlarının karşılanıp karşılanmadığının en önemli göstergesi hayvanların vücut kondisyon skoru (VKS) puanlamasıdır. Süt sığırlarında VKS hayvanların dış görünüşüne göre 1 den 5 e kadar puanlanması esasına dayanmaktadır. VKS, sığırlarda sırt, bel ve kuyruk sokumu bölgelerinde deri altı yağ kalınlığının, pelvik bölgede kemik çıkıntıları ile ilişkisinin görsel olarak veya palpasyon yöntemi ile belirlenmesine dayalı sübjektif bir yöntemdir. Genellikle işletmelerde VKS değerleri uzman bilgisine dayanan ve gözlem yoluyla belirlenen bir yöntem ile belirlenmektedir. Eğer hayvan istenilen VKS'nin üzerinde veya altında ise bu aşamada metabolik problemlerden kaynaklanan hastalıklar, verim düşüklüğü veya ileri zamanlarda hayvan kayıpları gözlemlenebilecektir. Bu durumun düzenli bir şekilde kontrolü ile birlikte daha sağlık hayvanların eldesi ile birlikte işletmenin karlılığı da artabilecektir. Bu amaçla çalışmamızda VKS puanlamasının bireysel hataları azaltabilmek için bilgisayar destekli bir yazılım ile belirlenmesi amaçlanmıştır. Sığırlardan alınan görüntüler belirli formlarda düzenlenmiş ve Evrişimsel Sinir Ağları (ESA) ile sınıflandırılmıştır. 180 adet görüntü içerisinden %75'i eğitim, %25'i test için kullanılmıştır. Çalışmada önceden eğitilmiş ESA mimarileri kullanılarak sistem başarımı artırılmış ve farklı mimarilerin VKS sınıflandırma problemine verdikleri tepkiler test edilmiştir. Sonuç olarak VKS puanlamasının ESA yöntemleri ile belirlenmesinin %60'ın üzerinde başarılı bir şekilde yapılabileceği görülmüştür.

- by Kerim Kürşat Çevik and +1
- •
- CNN, Deep Learning, Animal Feed, Body Condition Score
- by MEHMET YAMAK
- •
- War Journalism, CNN, Medya, Televizyon

An important measurable indicator of urbanization and its environmental implications has been identified as the urban impervious surface. It presents a strategy based on three-dimensional convolutional neural networks (3D CNNs) for extracting urbanization from the LiDAR datasets using deep learning technology. Various 3D CNN parameters are tested to see how they affect impervious surface extraction. For urban impervious surface delineation, this study investigates the synergistic integration of multiple remote sensing datasets of Azad Kashmir, State of Pakistan, to alleviate the restrictions imposed by single sensor data. Overall accuracy was greater than 95% and overall kappa value was greater than 90% in our suggested 3D CNN approach, which shows tremendous promise for impervious surface extraction. Because it uses multiscale convolutional processes to combine spatial and spectral information and texture and feature maps, we discovered that our proposed 3D CNN approach makes better use of urbanization than the commonly utilized pixel-based support vector machine classifier. In the fast-growing big data era, image analysis presents significant obstacles, yet our proposed 3D CNNs will effectively extract more urban impervious surfaces.

- by Mazhar Hameed
- •
- Machine Learning, LiDAR, 3D Computer Graphics Programming, CNN