Time Series Forecasting Using Various Deep Learning Models

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Development of a Basic Robot System for Medical and Nursing Care for Patients with Glaucoma

Medical methods to completely treat glaucoma are yet to be developed. Therefore, ophthalmologists manage patients mainly to delay disease progression. Patients with glaucoma are mainly elderly individuals. In elderly people's houses, having an equipment that can provide medical treatment and care can release their family from their care. For elderly people with the glaucoma to live by themselves as much as possible, we developed a support robot having five functions: elderly people care, ophthalmological examination, trip assistance to the neighborhood, medical treatment, and data referral to a hospital. The medical and nursing care robot should approach the visual field that the patients can see at a speed suitable for their eyesight. This is because the robot will be dangerous if it approaches the patients from the visual field that they cannot see. We experimentally developed a robot that brings a white cane to elderly people with glaucoma. The base part of the robot is a carriage, which is a Megarover 1.1, and it has two infrared sensors. The robot moves along a white line on the floor using the infrared sensors and has a special arm, which does not use electricity. The arm can scoop the block attached to the white cane. Next, we also developed a direction detector comprised of a charge-coupled device camera (SVR41ResucueHD; Sun Mechatronics), goggles (MG-277MLF; Midori Anzen Co. Ltd.), and biconvex lenses with a focal length of 25 mm (Edmund Co.). Some young people were photographed using the direction detector, which was put on their faces. Image processing was performed using Scilab 6.1.0 and Image Processing and Computer Vision Toolbox 4.1.2. To measure the people's line of vision, we calculated the iris's center of gravity using five processes: reduction, trimming, binarization or gray scale, edge extraction, and Hough transform. We compared the binarization and gray scale processes in image processing. The binarization process was better than the gray scale process. For edge extraction, we compared five methods: Sobel, Prewitt, Laplacian of Gaussian, fast Fourier transform, and Canny. The Canny method was the optimal extraction method. We performed the Hough transform to search for the main coordinates from the iris's edge, and we found that the Hough transform could calculate the center point of the iris.

Wildfires Assessed by Remote Sense Images and Burned Land Monitoring

The tools described in this paper enable the location of burned areas where took place the annihilation of natural habitats and establishes a baseline for major changes in forest ecosystems during recovery. Moreover, the result allows the follow up of the surface fuel loading, allowing the evaluation and guidance of restoration measures to remote areas by phased time planning. This case study implements the evaluation of burned areas that suffered successive wildfires in Portugal mainland during the summer of 2017, killing more than 60 people. The goal is to show that this evaluation can be done with remote sense data free of charges in a simple laptop, with open-source software, describing the not-so-simple methodology step by step, to make it accessible for local workers in the areas attained, where the availability of information is essential for the immediate planning of mitigation measures, such as restoring road access, allocate funds for the recovery of human dwellings and assess further needs for restoration of the ecological system. Wildfires also devastate forest ecosystems having a direct impact on vegetation cover and killing or driving away the animal population, besides loss of all crops in rural areas that are essential as local resources. The economic interests are also attained, as the pinewood burned becomes useless for the noblest applications, so its value decreases, and resin extraction ends for several years.

Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories

In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. To approach this problem, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we use “fading.” We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFN+CNN is the best performing network with an error rate of 39%.

An Image Processing Based Approach for Assessing Wheelchair Cushions

Wheelchair users spend long hours in a sitting position, and selecting the right cushion is highly critical in preventing pressure ulcers in that demographic. Pressure Mapping Systems (PMS) are typically used in clinical settings by therapists to identify the sitting profile and pressure points in the sitting area to select the cushion that fits the best for the users. A PMS is a flexible mat composed of arrays of distributed networks of pressure sensors. The output of the PMS systems is a color-coded image that shows the intensity of the pressure concentration. Therapists use the PMS images to compare different cushions fit for each user. This process is highly subjective and requires good visual memory for the best outcome. This paper aims to develop an image processing technique to analyze the images of PMS and provide an objective measure to assess the cushions based on their pressure distribution mappings. In this paper, we first reviewed the skeletal anatomy of the human sitting area and its relation to the PMS image. This knowledge is then used to identify the important features that must be considered in image processing. We then developed an algorithm based on those features to analyze the images and rank them according to their fit to the user's needs. 

A Convolutional Deep Neural Network Approach for Skin Cancer Detection Using Skin Lesion Images

Malignant Melanoma, known simply as Melanoma, is a type of skin cancer that appears as a mole on the skin. It is critical to detect this cancer at an early stage because it can spread across the body and may lead to the patient death. When detected early, Melanoma is curable. In this paper we propose a deep learning model (Convolutional Neural Networks) in order to automatically classify skin lesion images as Malignant or Benign. Images underwent certain pre-processing steps to diminish the effect of the normal skin region on the model. The result of the proposed model showed a significant improvement over previous work, achieving an accuracy of 97%.

Image Processing Approach for Detection of Three-Dimensional Tree-Rings from X-Ray Computed Tomography

Tree-ring analysis is an important part of the quality assessment and the dating of (archaeological) wood samples. It provides quantitative data about the whole anatomical ring structure, which can be used, for example, to measure the impact of the fluctuating environment on the tree growth, for the dendrochronological analysis of archaeological wooden artefacts and to estimate the wood mechanical properties. Despite advances in computer vision and edge recognition algorithms, detection and counting of annual rings are still limited to 2D datasets and performed in most cases manually, which is a time consuming, tedious task and depends strongly on the operator’s experience. This work presents an image processing approach to detect the whole 3D tree-ring structure directly from X-ray computed tomography imaging data. The approach relies on a modified Canny edge detection algorithm, which captures fully connected tree-ring edges throughout the measured image stack and is validated on X-ray computed tomography data taken from six wood species.

Application of Advanced Remote Sensing Data in Mineral Exploration in the Vicinity of Heavy Dense Forest Cover Area of Jharkhand and Odisha State Mining Area

The study has been carried out on the Saranda in Jharkhand and a part of Odisha state. Geospatial data of Hyperion, a remote sensing satellite, have been used. This study has used a wide variety of patterns related to image processing to enhance and extract the mining class of Fe and Mn ores.Landsat-8, OLI sensor data have also been used to correctly explore related minerals. In this way, various processes have been applied to increase the mineralogy class and comparative evaluation with related frequency done. The Hyperion dataset for hyperspectral remote sensing has been specifically verified as an effective tool for mineral or rock information extraction within the band range of shortwave infrared used. The abundant spatial and spectral information contained in hyperspectral images enables the differentiation of different objects of any object into targeted applications for exploration such as exploration detection, mining.

Deep Learning Application for Object Image Recognition and Robot Automatic Grasping

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Normal and Peaberry Coffee Beans Classification from Green Coffee Bean Images Using Convolutional Neural Networks and Support Vector Machine

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Logistic Model Tree and Expectation-Maximization for Pollen Recognition and Grouping

Palynology is a field of interest for many disciplines. It has multiple applications such as chronological dating, climatology, allergy treatment, and even honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time-consuming task that requires the intervention of experts in the field, which is becoming increasingly rare due to economic and social conditions. So, the automation of this task is a necessity. Pollen slides analysis is mainly a visual process as it is carried out with the naked eye. That is the reason why a primary method to automate palynology is the use of digital image processing. This method presents the lowest cost and has relatively good accuracy in pollen retrieval. In this work, we propose a system combining recognition and grouping of pollen. It consists of using a Logistic Model Tree to classify pollen already known by the proposed system while detecting any unknown species. Then, the unknown pollen species are divided using a cluster-based approach. Success rates for the recognition of known species have been achieved, and automated clustering seems to be a promising approach.

Algorithm for Path Recognition in-between Tree Rows for Agricultural Wheeled-Mobile Robots

Machine vision has been widely used in recent years in agriculture, as a tool to promote the automation of processes and increase the levels of productivity. The aim of this work is the development of a path recognition algorithm based on image processing to guide a terrestrial robot in-between tree rows. The proposed algorithm was developed using the software MATLAB, and it uses several image processing operations, such as threshold detection, morphological erosion, histogram equalization and the Hough transform, to find edge lines along tree rows on an image and to create a path to be followed by a mobile robot. To develop the algorithm, a set of images of different types of orchards was used, which made possible the construction of a method capable of identifying paths between trees of different heights and aspects. The algorithm was evaluated using several images with different characteristics of quality and the results showed that the proposed method can successfully detect a path in different types of environments.

Early Recognition and Grading of Cataract Using a Combined Log Gabor/Discrete Wavelet Transform with ANN and SVM

Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy.

An Intelligent Nondestructive Testing System of Ultrasonic Infrared Thermal Imaging Based on Embedded Linux

Ultrasonic infrared nondestructive testing is a kind of testing method with high speed, accuracy and localization. However, there are still some problems, such as the detection requires manual real-time field judgment, the methods of result storage and viewing are still primitive. An intelligent non-destructive detection system based on embedded linux is put forward in this paper. The hardware part of the detection system is based on the ARM (Advanced Reduced Instruction Set Computer Machine) core and an embedded linux system is built to realize image processing and defect detection of thermal images. The CLAHE algorithm and the Butterworth filter are used to process the thermal image, and then the boa server and CGI (Common Gateway Interface) technology are used to transmit the test results to the display terminal through the network for real-time monitoring and remote monitoring. The system also liberates labor and eliminates the obstacle of manual judgment. According to the experiment result, the system provides a convenient and quick solution for industrial non-destructive testing.

Classification of Computer Generated Images from Photographic Images Using Convolutional Neural Networks

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Cost Effective Real-Time Image Processing Based Optical Mark Reader

In this modern era of automation, most of the academic exams and competitive exams are Multiple Choice Questions (MCQ). The responses of these MCQ based exams are recorded in the Optical Mark Reader (OMR) sheet. Evaluation of the OMR sheet requires separate specialized machines for scanning and marking. The sheets used by these machines are special and costs more than a normal sheet. Available process is non-economical and dependent on paper thickness, scanning quality, paper orientation, special hardware and customized software. This study tries to tackle the problem of evaluating the OMR sheet without any special hardware and making the whole process economical. We propose an image processing based algorithm which can be used to read and evaluate the scanned OMR sheets with no special hardware required. It will eliminate the use of special OMR sheet. Responses recorded in normal sheet is enough for evaluation. The proposed system takes care of color, brightness, rotation, little imperfections in the OMR sheet images.

Segmentation of Gray Scale Images of Dropwise Condensation on Textured Surfaces

In the present work we developed an image processing algorithm to measure water droplets characteristics during dropwise condensation on pillared surfaces. The main problem in this process is the similarity between shape and size of water droplets and the pillars. The developed method divides droplets into four main groups based on their size and applies the corresponding algorithm to segment each group. These algorithms generate binary images of droplets based on both their geometrical and intensity properties. The information related to droplets evolution during time including mean radius and drops number per unit area are then extracted from the binary images. The developed image processing algorithm is verified using manual detection and applied to two different sets of images corresponding to two kinds of pillared surfaces.

Optimized and Secured Digital Watermarking Using Entropy, Chaotic Grid Map and Its Performance Analysis

This paper presents an optimized, robust, and secured watermarking technique. The methodology used in this work is the combination of entropy and chaotic grid map. The proposed methodology incorporates Discrete Cosine Transform (DCT) on the host image. To improve the imperceptibility of the method, the host image DCT blocks, where the watermark is to be embedded, are further optimized by considering the entropy of the blocks. Chaotic grid is used as a key to reorder the DCT blocks so that it will further increase security while selecting the watermark embedding locations and its sequence. Without a key, one cannot reveal the exact watermark from the watermarked image. The proposed method is implemented on four different images. It is concluded that the proposed method is giving better results in terms of imperceptibility measured through PSNR and found to be above 50. In order to prove the effectiveness of the method, the performance analysis is done after implementing different attacks on the watermarked images. It is found that the methodology is very strong against JPEG compression attack even with the quality parameter up to 15. The experimental results are confirming that the combination of entropy and chaotic grid map method is strong and secured to different image processing attacks.

Hand Gesture Detection via EmguCV Canny Pruning

Hand gesture recognition is a technique used to locate, detect, and recognize a hand gesture. Detection and recognition are concepts of Artificial Intelligence (AI). AI concepts are applicable in Human Computer Interaction (HCI), Expert systems (ES), etc. Hand gesture recognition can be used in sign language interpretation. Sign language is a visual communication tool. This tool is used mostly by deaf societies and those with speech disorder. Communication barriers exist when societies with speech disorder interact with others. This research aims to build a hand recognition system for Lesotho’s Sesotho and English language interpretation. The system will help to bridge the communication problems encountered by the mentioned societies. The system has various processing modules. The modules consist of a hand detection engine, image processing engine, feature extraction, and sign recognition. Detection is a process of identifying an object. The proposed system uses Canny pruning Haar and Haarcascade detection algorithms. Canny pruning implements the Canny edge detection. This is an optimal image processing algorithm. It is used to detect edges of an object. The system employs a skin detection algorithm. The skin detection performs background subtraction, computes the convex hull, and the centroid to assist in the detection process. Recognition is a process of gesture classification. Template matching classifies each hand gesture in real-time. The system was tested using various experiments. The results obtained show that time, distance, and light are factors that affect the rate of detection and ultimately recognition. Detection rate is directly proportional to the distance of the hand from the camera. Different lighting conditions were considered. The more the light intensity, the faster the detection rate. Based on the results obtained from this research, the applied methodologies are efficient and provide a plausible solution towards a light-weight, inexpensive system which can be used for sign language interpretation.

CBIR Using Multi-Resolution Transform for Brain Tumour Detection and Stages Identification

Image retrieval is the most interesting technique which is being used today in our digital world. CBIR, commonly expanded as Content Based Image Retrieval is an image processing technique which identifies the relevant images and retrieves them based on the patterns that are extracted from the digital images. In this paper, two research works have been presented using CBIR. The first work provides an automated and interactive approach to the analysis of CBIR techniques. CBIR works on the principle of supervised machine learning which involves feature selection followed by training and testing phase applied on a classifier in order to perform prediction. By using feature extraction, the image transforms such as Contourlet, Ridgelet and Shearlet could be utilized to retrieve the texture features from the images. The features extracted are used to train and build a classifier using the classification algorithms such as Naïve Bayes, K-Nearest Neighbour and Multi-class Support Vector Machine. Further the testing phase involves prediction which predicts the new input image using the trained classifier and label them from one of the four classes namely 1- Normal brain, 2- Benign tumour, 3- Malignant tumour and 4- Severe tumour. The second research work includes developing a tool which is used for tumour stage identification using the best feature extraction and classifier identified from the first work. Finally, the tool will be used to predict tumour stage and provide suggestions based on the stage of tumour identified by the system. This paper presents these two approaches which is a contribution to the medical field for giving better retrieval performance and for tumour stages identification.