Search

Hierarchical clustering is one of effective methods in creating a phylogenetic tree based on the distance matrix between DNA (deoxyribonucleic acid) sequences. One of the well-known methods to calculate the distance matrix is k-mer method. Generally, k-mer is more efficient than some distance matrix calculation techniques. The steps of k-mer method are started from creating k-mer sparse matrix, and followed by creating k-mer singular value vectors. The last step is computing the distance amongst vectors. In this paper, we analyze the sequences of MERS-CoV (Middle East Respiratory Syndrome - Coronavirus) DNA by implementing hierarchical clustering using k-mer sparse matrix in order to perform the phylogenetic analysis. Our results show that the ancestor of our MERS-CoV is coming from Egypt. Moreover, we found that the MERS-CoV infection that occurs in one country may not necessarily come from the same country of origin. This suggests that the process of MERS-CoV mutation might not only be influenced by geo...

Internet of things (IoT) becomes the backbone of the advanced countries and it has a real contribute to exchange the traditional style or way of practical life, even personal life into smart style, with (IoT) technology the life become more and more easy and professional. internet of things achieves various applications coordinate with sensors and standard protocols to apply what is called machine -to- machine connection (M2M), in this paper we will talk more about the concept of (M2M), the main component of internet of things and finally the common protocols that is used in network, in addition to that this work present an IOT operation with processing system using camera for capturing image and Xilinx system generator(XSG)models for designing image processing algorithms and the result of the processing is an image with black and white for edge detection and Thresholding models and gray color image for gray enhancement model.

Electroencephalogram (EEG) is one of the most practical device to record the brain’s electrical activity, and often been used in the diagnosis of brain diseases over the years. Recently, the biometric authentication and identication by using EEG has become a great way to confirm a user’s identity. This paper investigated the biometric authentication information in brain lobes such as frontal lobe, parietal lobe, temporal lobe and occipital lobe based on frequency bands approach. The power spectrum density (PSD) features were extracted from 32 EEG channels recorded signals during typing task. At that point, signal processing techniques such as such as pre-processing, feature extraction and classification have been carried out. The obtained results proved that the frontal lobe is related to the thinking whereas the parietal lobe is related to the spelling process when the users type their own names (Task 1) and random names given (Task 2). The users are more familiar to typing task 1 rather than typing task 2.

This paper discusses stereoscopic images gain using library in OpenCV on Python platform. The simple stereo camera system that can provide stereoscopic images in both as a picture (PNG) or as a video (AVI) is developed. The system comprises a stereo camera, a USB connector, a tripod, and a notebook with programming language of Python 3.7, along with the free library of OpenCV 4.0 installed inside the notebook. The system has successfully provided both images and videos. However, the spatial resolution and the frame rate depend to the specifications of the stereo camera being used. The camera resolution of 1280 × 360 with a frame rate of 5 fps is obtained based on the stereo camera specifications in this study. The disparity of the stereo camera as a function of distance of the camera to the object of interest is measured. From the experimental results, the p constant is 1059.4, q constant is -0.527 over a distance of 10–100 cm. It shows that farther the object from the camera, the disparity decreases. This system will be used for performing physical measurement in the future.

Biometric authentication is a recognition of individual according to their unique physiological and behavioural characteristics. Recently, the application of biometric is the most trending in cyber security technology such as fingerprint, facial recognition, and voice recognition. However, these biometrics have their own drawbacks which allow the unauthorized party to cybercrime and the number of cases is also increased. To encounter this kind of problem, the previous researchers proposed brain signal or electroencephalogram (EEG) as biometric trait. EEG is an electrical activity recorded via non-invasive method using electrode placed on the scalps and measured as voltages. EEG is chosen by the researchers as biometric module because EEG hold its own unique characteristics and more robust against the cybercriminals. This paper presents a review of the EEG-based biometric studies and research. The previous research was reviewed based on their signal acquisition, pre-processing, feature extraction and classification. The general knowledge of EEG and the basic operation of biometric authentication also discussed in this paper. The recent studied and research is chosen with various proposed method respect to the better performance rate. In addition, the deep learning in biometric authentication is found to be the popular among the researchers for classification step because more robust and automatically extracted feature within the network.

Obstacle avoidance is a task in robotics which includes detection of obstacles and therefore avoiding the collision path of such obstacles. Obstacle avoidance robotics has application in various fields such as autonomous vehicle sector, military applications include unmanned aerial vehicle etc. The paper presents the prototype type design of real time line tracking and obstacle avoiding robot. The robot is designed around Raspberry pi microcontroller and python is used for coding.

The main goal of this paper to evaluate the performance of the proposed long short-term memory (LSTM)- basis relative humidity (RH) prediction model. Computational physics learning theory is a subfield in artificial intelligence. In this paper, we use the real observed weather data of RH from synoptic station location as an important aspect and effect in weather and climate and using machine learning approach basis on the LSTM neural network, which is a type of recurrent neural network (RNN). We use a machine learning approach to compute the relative humidity basis on the LSTM model. The LSTM is trained by using two years of climate data (from January 2008 to December 2009). LSTM is capable of forecasting complex univariate relative humidity time series with strong no-stationarity. The result shows the usefulness of LSTM and out performs traditional forecasting methods in the challenging relative humidity record problem.

The primary objective of this paper is to verify individuals as indicated by their finger surfaces. We propose to remove Finger Texture (FT) highlights of the two finger pictures (center, ring) from a low goal contactless hand picture utilizing LBP strategy. The utilization of Inner-Knuckle-Print (IKP) in biometric recognition is the most broadly proposed validation work. The unique characteristics of the IKP give us the requirement for recognizable proof. During the IKP filtering process, the image created by the scanner might be partially unique. This paper proposes artificial neural networks for effectively coordinating procedures to IKP validation. By utilizing the Back-Propagation method, the algorithm coordinates IKP and relates them to a novel accomplished client. After grouping, the procedure restores to the best counterpart for the given finger impression variables.

In order to construct and control walking robots similar to humans, i.e., in anthropomorphic robotics, as well as the corresponding exoskeletons, it is necessary to know the physical human properties such as the corresponding geometry, mass, and inertial characteristics of the segments of the human body. In addition, the study of human locomotion is on the basis of the development and design of all possible devices aimed to help people, after some incident, say in traumatology, orthopedics, orthotics and prosthetics design. For that aim one often uses computer simulation and computer design approach. In the present work, we present a 16 segmental biomechanical geometrical model of the body of the averaged Bulgarian women and study the changes in vertical position in its mass center, as well as the inertial parameters of the body during walking. We do that using proper 3D CAD software. We have considered, in accordance with the literature, 8 distinct phases of the gait cycle. The study could be beneficial for disabled people who need orthopedic and prosthetic devices for rehabilitation. The model and the mass-inertial characteristics obtained may be used in studies of injuries, ergonomics, and sports. Furthermore, the results of this paper will be in the basis of further study of the gait dynamics of the average Bulgarian female. Despite the current computer realization and the specific data obtained are for the average Bulgarian women, the presented approach can be easily applied to a specific individual provided a set of relatively easily measurable anthropometric data for that individual are known.

This paper presents a Fuzzy Decision Making (FDM) problem with the fuzzy Decision Making Trial and Evaluation Laboratory (DEMATEL) method based on the new concept of the relationship between influenced and influencing factors to analyze the ranking by using the problems of transgender when the collected data’s are expressed in terms of trapezoidal fuzzy numbers. A numerical example is given from this proposed method.

Myoelectric pattern recognition has shown promise in the control of the prosthetic arm. But interfering noise and motion artifacts have hindered this kind of method to be used outside a controlled environment. This paper has designed an optimized circuit to process the Electromyography (EMG) signal. EMG signal is acquired from surface skin using sEMG (Surface Electromyography) electrode. EMG can be defined as an electrical potential produced due to contraction of the muscle. EMG signal requires to the undergo process of amplification and noise reduction before it can be converted to digital signal by the analog-digital converter (ADC) and processed to drive the motors or actuators of the prosthetic arm. The proposed denoising algorithm will improve the signal to noise ratio in real life uses. But the improved signal to noise ratio is expected to be insignificant as machine learning algorithm integrate noise as part of the signal. However, the variation of noise in real life uses is expected to occur where the proposed algorithm would potentially have a positive impact and further enhance the feasibility of using prosthetic for daily life

Tuberculosis (TB) is one of the most common diseases in developing countries such as Indonesia. TB disease oftenly attacks the human lungs due to its high oxygen pressure. The basic characteristics of TB-infected lungs are in the form of wounds, which change its texture and shape. The common detection method is by comparing the X-ray thoracic image with the tuberculin skin test (TST) and fast acid staining methods. This diagnosis method is often constrained by the availability of radiologists in the health facilities. To overcome such situation, a computer-aided diagnosis (CAD) tool is required to assist the doctor read the X-ray images easily. In this paper, a complementary detection method is proposed by using a chest X-ray (CXR) image to assist the diagnosis process. In current method, the image is segmented to reduce unnecessary parts prior to preprocessing step. We use a texture-based feature approach for detection purpose because most of the common examination methods for abnormality detection on CXRs is by analyzing the change of textural (content) CXR. In our texture approach, we use texture-based statistical properties on the histogram’s intensity. Some features that are used in this approach including Mean, Standard Deviation, Smoothness, Entropy, Root Mean Square (RMS), Variance, Kurtosis, Skewness, and Inverse Difference Moment (IDM). As a result of simulation, it indicates that CXR images can be well segmented to localize the focus area, allowing to the features can be extracted from the CXR image for further detection process. The obtained accuracy is about 93.94% and 92.86%, respectively for Shenzhen-Chest X-ray dataset and Montgomery County-Chest X-ray dataset.

In recent years many of the people are suffering from diabetics which may result damaging the human eye sights by damaging the blood vessels of the retinal by form exudates around the optic disc. In this paper, we intend to build retinal exudates from fundus image to predict the severity of diabetics resulting in blood vessels tissue damages. In order to analysis the blood vessels damage and diabetic severity initially we use appropriate image pre-processing techniques to remove any noise from the retinal funds image, to remove the noise in this paper we use wavelet transform and first order Gaussian derivative and matched filter to segment the fundus image by rotating the original image by certain angle. The filtered data is stored in the matched filter bank, then by applying k-NN clustering technique to identify minimum value in each filter bank and marking such minimum value center of k-nearest neighbor value. Further, Support vector machine a supervised learning algorithm is applied to the identified k-nearest neighbor values thereby predicting the severity of blood vessel tissue damage from the fundus image.

The adoption of robotics has been becoming prominent in computational thinking literature. The modularity characteristics of lego robotics, for example, enables learners to construct their understanding of the abstraction of complex robotics parts. Educational organisations that adopt computing would be likely to introduce computational thinking as an integrated part of the regular curriculum. Organisations in the UK and the United States, for example, conceptualise the delivery of computing curricula in connection with the development of computational thinking skills that all students must learn in the 21st century. This paper is a literature review report aggregating publications from outstanding outlets. Focusing on investigating more deeply about the roles of learning computational thinking using robotics-based media, in hopes of finding new findings that can support the advance of 21st-century skills. The results show that computational thinking using robotics-based media can foster interest in the STEM field, which includes some skills like creative thinking, problem-solving, collaborative learning, algorithmic and critical thinking, abstraction, and debugging. The skills are essential for children to develop themselves in the 21st century, taking into account the learning material and the right learning approach.

In recent years, advances have been made in the field of machine learning and artificial intelligence (AI), primarily through developments in deep learning neural networks (DLNN). Challenges however exist with transitioning emerging DLNN algorithms directly for NDE applications. As a counterpoint to AI, intelligence augmentation (IA) refers to the effective use of information technology to enhance human intelligence. While attempting to replicate the human mind has encountered many obstacles over the years, IA has a much longer history of success. All forms of information technology, from writing cuneiform on clay tables to computers and smartphones today, have essentially been developed to enhance the information processing capabilities of the human mind. This paper introduces a series of best practices for intelligence augmentation in NDE, highlighting how the operator should interface with NDE data and algorithms. Algorithms clearly have a great potential to help alleviate the burden of ’big data’ in NDE; however, it is important that operators are involved in both secondary indication review, and the detection of rare event indications not addressed well by typical algorithms. Several past examples of transitioning algorithms for NDE applications are presented, emphasizing the successful interfacing of operator and software for optimal data review and decision making.

Emotion classification rapidly gains popularity in research world, especially in healthcare field. EEG signal used to classify human emotional state might provide wider range of information rather using other types of signal, yet this data need more complex processes because of its dimensions and noises. ANN is one of many techniques used to classify human emotion, by using DEAP’s EEG dataset this research will provide higher recognition rate of 2-dimensional emotion classification, which is using EEG’s non-linear features, including every frequency bands in EEG signal except delta rhythm which produced when subjects are sleeping. In this research PCA played a big role in computational optimization and provide higher number of recognition rates up to 60,15%. To achieve this recognition rate, the system is given an additional part, which is BPNN as data train’s correction so that training rate will be on its maximum. Through this correlation, we will analyze the correlation of those additions for human emotional classification. And the result of this paper will give possibility of further research in human emotional classification using BPNN as correction factor of recognition rate.Emotion classification rapidly gains popularity in research world, especially in healthcare field. EEG signal used to classify human emotional state might provide wider range of information rather using other types of signal, yet this data need more complex processes because of its dimensions and noises. ANN is one of many techniques used to classify human emotion, by using DEAP’s EEG dataset this research will provide higher recognition rate of 2-dimensional emotion classification, which is using EEG’s non-linear features, including every frequency bands in EEG signal except delta rhythm which produced when subjects are sleeping. In this research PCA played a big role in computational optimization and provide higher number of recognition rates up to 60,15%. To achieve this recognition rate, the system is given an additional part, which is BPNN as data train’s correction so that training rate will be on its maximum. Through this correlation, we will analyze the correlation of those additions for human emo...

Unmanned Aerial Vehicle (UAV) is increasingly popular as platforms for inspection, professional mapping, and modeling issues. UAV as a low-cost alternative to the classical manned aerial photogrammetry can survey buildings of various heights to take the necessary angle for a favorable photo. This paper presents results of using 3D reconstruction technique based on 2D pictures of a building taken by UAV. Automation and feasible image orientation create images to be processed in the latest developments of UAV image processing methods for photogrammetric applications, mapping, and 3D modeling issues. Images from a campus building construction in Bandung was taken for a case study using UAV with an attached camera. The images were processed to generate a 3D model of campus building using several integrated software. The integrated software was used to create image processing, mapping, orthophoto, and meshing. By using the proposed setting of altitude, overlapping percentage, direction of flight, the results show good quality of regenerated images which contain information of altitude and position of the building.

Multilayer Feedforward Neural Network is one of the linear or nonlinear mathematical model between the set of input vectors and their corresponding output vectors of the real-world problem. In this paper, MAMFFN has been used as a mathematical model as delimited as mathematical approach that develops the Multilayer Feedforward Neural Network with Backpropagation to overcome from the complexity of the conventional model. Also, the proposed model applied on various real-world problems and obtained results are compared with existing results on those problems.

As the main concept, the Digital Twin (DT) shows its potential not only in industry 4.0 but also in other areas. One of the keys that decide the future of DT been known as its model technology. Through models can integrate features, behaviors, and properties of DT artifacts with efficiency, reusability, and interoperability, in order to build a complete mapping between the physical world and digital world, after that realize the ideal DT. This paper aims at comparing and analyzing the DT models in the scientific literature, retracing them from the initial one to the models in most recent researches. Thus, this study also emphasizes several principles of the DT model technology that is related to future work.

This paper addresses the parameter identification in vibrating nano-beams as a classification or regression problem using machine learning methods. It is assumed that the beams have constant dimensions and are weakened by cracks. The vibration model is based on size-dependent nonlocal elasticity theory developed by Eringen. The cracked nano-beam is modelled by dividing the cracked element into two segments connected by a rotational spring at the crack position. The material parameters as well as the crack severities and positions are identified with the aid of machine learning methods using modal-based characteristics.

In recent years, fall injuries have not only caused serious harm to the health of the elderly in China, but also occupied a large amount of social medical resources. The most important reason for the fall injury is the rescue not timely after the fall. In view of this phenomenon, this paper realizes the fusion of multi-threshold detection algorithm and EML learning machine classification algorithm, and proposes a two-layer fall detection algorithm based on weight discrimination. Experiments show that the algorithm has high accuracy of fall alarm detection and low false alarm rate.

With the extensive development of the Internet, digital image resources are more and more abundant. How to effectively retrieve and utilize a large amount of image information has become a hot issue in the current research. In this paper, a perceptual hash algorithm based on SIFT features is proposed by combining the perceptual hash algorithm with the SIFT feature of the image, which helps to overcome the influence of the perceptual hash algorithm on geometric attacks, image scale changes and other abnormal conditions. Improve the accuracy of the perceptual hash algorithm. By studying the application scene of perceptual hash algorithm, using the image-aware hash algorithm to perceive the target object in the image scene, matching the relevant features of the image, the image retrieval technology based on the hash algorithm is realized.

With the development of society, the proportion of sitting time in people’s daily life and working environment is increasing. However, Most of the sitting posture is improper sitting posture in most of the time. Improper sitting posture for a long time is one of the main causes of a series of skeletal muscle diseases. In this paper, a CNN sitting posture recognition model based on human pressure data is proposed. The model is constructed by collecting a large number of pressure data of human-chair contact surface and using these training to get sitting posture recognition algorithm. Experiments show that the algorithm can accurately identify eight kinds of human sitting posture. Its accuracy rate is as high as 95.6%, and the recall rate is 95.5% at same time. The sitting position recognition system constructed by this algorithm can monitor and distinguish the bad sitting posture of human body in real time, and it has the many advantages such as high accuracy, high robustness, high availability and high security.

Eye Gaze Tracking is emerging as a popular method to increase the efficiency as well as to increase the accessibility of computing systems. It has been already employed in various applications as well as many researches are going on to incorporate the concept in various other fields. There are various fields where the systems are employed ranging from ease of accessibility of computing systems [1] to performance of computer graphics processing by the method of foveated rendering [2] and as well as digital marketing analysis [3]. The application of eye gaze trackers is still limited due to its lack of availability as well as the cost of the eye gaze trackers which makes them still a scarce resource for majority of the population. This paper proposes an efficient system for Eye Gaze Tracking and draws a sharp contrast between the different open source software available for Eye Gaze Tracking on the market. The study draws the comparison between two of the most popular open source eye gaze tracking software available in the market. ITU Gaze Tracker [4] PyGame based Eye Tracker [5]. The components proposed for the system are easily available in the market.

Fault detection and isolation (FDI) techniques is becoming one of the most phenomena in robotics in order to ensure higher levels of safety and productivity. Research, has been produced a considerable effort in seeking systematic approaches to fault detection for both linear and non-linear dynamical systems. In this paper, we present a high gain based observer to solve fault detection and isolation scheme for a class of affine non-linear systems. In order to test the effectiveness of the proposed approach, a case study is developed, based on simulation for a special robot manipulator named Articulated Nimble Adaptable Trunk ”ANAT” for five-degree-of-freedom in order to detected and isolated sensor fault.

Continuous fibre reinforced plastics (CoFRPs) offer remarkable mechanical properties at low density and have thus drawn increasing attention in weight-sensitive industries over the last decades. Contrasting metals, manufacturing of CoFRPs consists of multiple steps, often comprising a forming process of a textile (draping). However, managing the inherently complex, anisotropic and non-linear material behaviour during textile forming and avoiding forming defects is a great challenge in serial production. To assess formability prior to manufacture, virtual process simulations can be applied. For optimum part quality, component design and applied process parameters must complement each other, which in turn requires a high number of optimisation iterations and quickly exceeds reasonable computation times. Considerable effort has been made with respect to obtaining optimum process parameters, however considering geometry adaptions to achieve manufacturability is rarely addressed. Deep Learning techniques using convolutional neural networks (CNN) are capable of learning complex system dynamics from supplied samples. In the work presented here, CNNs are used to rapidly predict textile forming results of variable component geometries. A large database of highly variant geometries and corresponding draping examples is generated, on which the CNNs are trained. The paper shows, that CNNs are capable of reproducing the underlying forming dynamics and that they generalise well to unknown test geometries. Contrasting traditional meta-model approaches, the presented method estimates not just a scalar part quality attribute, but predicts the complete shear strain field, which facilitates engineering interpretation. The method is demonstrated on different geometries ranging from simple shapes to complex geometries. Being computational inexpensive, CNNs give immediate feedback for real-time geometry iterations during component design. Thus, CNNs are considered a promising and time-efficient tool to reflect manufacturability during part and process design.

Disorders related to the use of new psychoactive drugs (NPS) such as amphetamines account for a considerable share of the hospital admissions and fatalities attributable to drug use disorders, second only to those related to the abuse of opioids. According to the World Drug Report 2017 elaborated by the United Nations Office on Drugs and Crime (UNODC), amphetamine-like stimulants (ATS) such as methamphetamine represent the greatest global health threat. Hallucinogenic amphetamines, such as 3,4-methylenedioxyamphetamine (MDA) and its analogues, account for an even larger number of fatalities. The latter compounds have no medical use and are controlled substances in most countries. However, despite their high toxicity, they are abused during rave parties for their euphoriant effect. Hence, new analytical instruments, allowing a more effective in-situ screening for NPS are highly needed. The most important challenge for such forensic instruments is their capacity to scan not only for the known NPS, but also for any compound having a molecular structure (hence a pharmacological activity) similar to the already known and controlled drugs of abuse. Such a new instrument, built within the DIRAC EU funded project, consists of a hollow fiber infrared spectrometer. In order to maximize its compactivity, the radiation source of this spectrometer is a quantum cascade laser (QCL). On the other hand, the use of a laser source of infrared radiation raises another challenge, i.e. obtaining the same detection efficiency as in the case of spectrometers generating the full infrared spectrum, despite the narrow spectral window in which QCLs are emitting. In this paper we are presenting the results obtained for two experimental setups, which were compared in order to find the most appropriate infrared source. Two QCLs, emitting in the spectral windows of 1550-1330 cm−1 (UT7) and 1405-1150 cm−1 (UT8) respectively, have been evaluated by using Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA). The initial database consisted of normalized spectra of the main ATS, hallucinogenic amphetamines and a similar number of negatives, representing miscellaneous substances of forensic interest. The dataset obtained by preprocessing these spectra with a w2MT feature weight has been used for the training process. The PCA plots have indicated the QCL generating the best clustering and which are the main absorptions that ensure a high quality class identity assignment. The potential cluster overlap has been assessed based on the estimated density distributions calculated with a normal kernel function. The results have been validated by using HCA, the quality of the clustering trees being assessed based on the cophenetic correlation coefficient.

A method to create mammography phantoms with radiopaque ink and an inkjet printer was developed. A mammography image was printed on several sheets of bond paper, modulated by a calibration function, creating a phantom image that can emulate the original object in a clinical image. The radiopaque ink on paper was stable, at least, over a month. The representation of the mammography image was visually equivalent, and the limitations of the method come from noise, alignment difficulties, and dynamic range compression.

There are many medical equipments being used by human as assistance to check some organs inside the body. The medical modalities are developed to obtain the most effective and efficient in terms of quality and cost. Research about infrared spectrum as the medical equipment is a highlight among scientists since it can be captured the blood vessel of humans. Infrared penetrates the human skin and be captured by camera. Vein has a pattern and it can be used as human identification system. However, the images need enhancement because of low contrast. Wavelet transforms such as Haar and Daubechies can enhance the quality of vein images. Hence the identification process can be conducted by using deep learning method. In this paper, we use one of convolutional neural networks (CNN) method called AlexNet structure as the deep learning method due to its high performance. As for the wavelet transforms, the Haar wavelet, Daubechies 2, Daubechies 4, and Daubechies 10 are selected for evaluation on palm vein images in the image preprocessing step. As a result, we found that the accuracy of the wavelet transforms and enhanced palm vein images are more than 92%. The highest accuracy can be achieved by applying Daubechies 10 wavelet transform with an accuracy of 93.92%±0.98334.

Computational Thinking is introduced as a problem-solving ability that is important for future generations to master. The mastery of computational thinking skills from an early age prepares children to anticipate competition and pursue success in the future. Robotics devices are widely advocated as interactive learning media to facilitate Computational Thinking development. Educational robotics have grown from ideas that represent critical stages of Computational Thinking. The application of robotics in teaching computational thinking skills is increasingly used and is evident in the literature. The paper reviews the development of an innovative robotics device in facilitating understanding of computational thinking in young children in terms of several aspects of computational thinking indicators. A review was also conducted to see the advantages and disadvantages of commercially available robotics devices. This paper was prepared by applying critical analysis methods to the literature published from 1952 to 2017 in international journals and proceedings. As a recommendation for future research, this paper proposes for an educational robotic development that facilitates the of computational thinking skills, especially for early childhood education.

EMG is a medical technique that measures muscle response or electrical activity in response to a nerve’s stimulation of the muscle [10]. In this paper we have classified multiple hand gestures using small number of electrodes. This report aims to review current use of EMG based control system and explain the existing challenges. The stages involved includes data acquisition, feature extraction, classification and controller. Some of the application includes Arm rehabilitation, game controller, wheel chair controllers, etc.

Hypertensive Retinopathy (HTR) is a disease caused by high blood pressure flowing into the retinal blood vessels, resulting in thickening of blood vessel walls and reducing blood flow in the retina. Complications arising from this disease are diverse and dangerous, ranging from retinal vein occlusion, eye nerve damage, even blindness. This paper proposed a system for hypertensive retinopathy detection by using Principal Component Analysis (PCA) dan Backpropagation Neural Network (BNN). Retinal image was taken from STARE database which separated into learning and testing data with a ratio 7 to 3. PCA as fundus-image-dimension-reduction method has successfully reduced fundus image raw data by 99.9% reduction, thus cutting computation load for neural network training. This paper presented Backpropagation Neural Network (BNN) as main classification algorithm which done by setting its parameters, learning and testing the data. So the model could classify retinal image into one of two classes, namely the normal retina and retina with high blood pressure, based on the BNN output result. The proposed model result showed that testing accuracy up to 86.36%.

In this paper, a damage predicting form is developed using fuzzy logic techniques. An earthquake damages the building severely. In order to avoid and relieve devastation, it is essential to frame a disaster attentiveness plan according to the results of damage prediction. It is more coherent to deal with earthquake-related damage forecasting problems using fuzzy logic, as there be plenty of unclear and fuzzy concepts in damage predicting problem and relations involving concerning factors have confusing nature. The model is formulated by various parts “IF… THEN” approximate reasoning.

Remote satellite imaging provides vital information for observing number of applications such as, land region detection and urban area classification. This paper proposed a novel approach for Classification and extraction of texture features from high resolution satellite images dataset. Preprocessing is done for satellite sensing image using Hilbert matrix filter and Modified Hilbert matrix filter. Then the texture features are extracted from the Hilbert image and Modified Hilbert image using Gray Level Co-occurrence Matrix (GLCM). Finally, obtained features are classified using Decision tree and Random Forest and the accuracy, precision, recall and F-measure is analyzed for performance evaluation.

Pattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificityPattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificity

Blood pressure (BP) can reflect many physiological characteristics, and timely monitoring of it can somehow prevent hypertension, asphyxia and other diseases. With the development of clinical medical technology, the accuracy requirements of the intelligent physiological monitoring equipment for predicting the physiological characteristics of BP are gradually increasing. This paper proposes a BP prediction model based on Long Short Term Memory Networks (LSTM-NN), which makes full use of the efficient processing characteristics of LSTM for time series information and accurately predicts the systolic BP and diastolic BP. The primitive photoplethysmographic pulse wave (PPW) signal and actual BP data in different time periods and different states were collected on 6 adult goats simultaneously. The blood flow changes were stimulated by injection of adrenaline to obtain a wide range of raw data to improve the generalization ability of the model. The clinical features of each PPW cycle were introduced into the LSTM model for training and prediction to resolve actual systolic BP and diastolic BP. Comparing the model with the prediction effect of BP neural network (BP-NN) model, the result shows that the prediction accuracy of LSTM model is high and the robustness is strong. The maximum error values for systolic and diastolic pressure prediction are 1.05mmHg and 1.8mmHg, respectively.

In this paper, a novel hardware-friendly reinforcement learning algorithm based on memristive spiking neural networks (MSNN-RL) is proposed. Neurons for spike coding are designed specifically to complete transformation between analog data and discrete spikes. Then, remote supervised method (ReSuMe) is used to combine SNN with basic reforcement learing (Sarsa). Besides, bionic memristive snynapses are designed to speed up ReSuMe. Furthermore, the circuit scheme of MSNN-RL is designed with modulation of memristor synapses. Finally, the application of MSNN-RL in acrobot system is discussed. Simulation results and analysis verify the effectiveness of the proposed algorithm (MSNN-RL) and show it is superior to traditional apporach.

Newly developed 3D reconstruction technology has many uses ranging from facial recognition, self-driving vehicles, and producing accurate models of samples. To utilize 3D reconstruction, a depth map of the sample must be generated from a series of images. This can be done using stereoscopic 3D, or in the case of a fixed camera (such as the 10ID On-Axis Microscope at NSLS-II used for this paper) through focus stacking. This paper will explain how focus stacking can be used to generate in-focus images at very shallow depth of fields, and merge these images to create depth maps and 3D models.

Breast cancer is one of the five highest in Malaysia and most affected by women. Computer-aided diagram typically used in conjunction with a mammogram to detect breast cancer cells of women. A detection cancerous cell by using image information is a challenge task because of the different intensity distribution in the breast-affected area. This can lead to wrong results and diagnosis. This paper proposes a method to detect cancer cells from a mammogram image. Matrix Laboratory (MATLAB) programming language is used during this entire analysis. Mammogram image is converted to grayscale and then is resized to 600 x 600 pixels. A median filter is used to remove the noises in the image. The thresholds values are investigated from the value-based grayscale histogram. The results clearly demonstrate the feasibility and effectiveness of the proposed approach of the range threshold value used for segmentation of the cancerous cell.

The paper deals with application of the artificial neural network (ANN) to the spatial prediction of soil pollution by Chromium (Cr). In the work, we examined and compared two neural networks: Generalized Regression Neural Network (GRNN) and Multilayer Perceptron (MLP) as classes of neural networks widely used for continuous function interpolation. For comparison, a geostatistical method co-kriging was also used. The case study is based on the survey on surface contamination by Cr at the subarctic Noyabrsk, Russia. The proposed models have been built, implemented and validated using ArcGIS and MATLAB software. The models frameworks have been developed using a computer simulation based on a minimization of the root mean squared error (RMSE). Each network has its own benefits and drawbacks; however both demonstrated fast training and good prediction possibilities. MLP showed the best predictive accuracy comparing to co-kriging and even to GRNN.

The paper addresses the questions of abusive content identification in the Internet. It is presented the solving of the task of toxic online comments classification, which was issued on the site of machine learning Kaggle (www.Kaggle.com) in March of 2018. Based on the analysis of initial data, four models for solving the task are proposed: logistic regression model and three neural networks models - convolutional neural network (Conv), long shortterm memory (LSTM), and Conv + LSTM. All models are realized as a program in Python 3, which has simple structure and can be adapted to solve other tasks. The results of the classification problem solving with help of proposed models are presented. It is concluded that all models provide successful solving of the task, but the combined model Conv + LSTM is the most effective, so as it provides the best accuracy. © 2018 Author(s).

Data analysis is an important issue for companies as it provides deep business insights thus facilitating their performance. Usually enterprise applications and platforms for Big Data processing live in the Java ecosystem. Therefore it is important to investigate how Java-based platforms for data analytics and machine learning work and the functionality they provide. The paper analyzes the most widely used machine learning libraries in the Java world - Deeplearning4j and Spark MLlib. Using data lakes is a common practice for storing large amount of data for data analytic tasks. Hadoop has proved to be the common choice for building data lakes. The paper will review Hadoop ecosystem components, their advantages and potential problems concerning machine learning tasks.

In this paper the stabilization problems of program motion of objects with elastically connected elements are considered. The conditions for stabilizing a program motion ×=0 of the control object are given.

The emergence of various methods in making measurement of similarity of short sentences triggered the development of the development of automatic short scoring system. The measurement of similarity of the automatic short scoring system is a brief description that compares the similarity of meanings between student answer and reference answer. The process of similarity measurement between student answer and reference answer is slightly different from measuring the similarity of meaning between two sentences. This difference lies in the process of justifying the similarity. This is because the measurement of reference answer and student answer is only based on the detection of keywords that appear in both, so that sentences that have additional information are only considered as supplementary information from keywords. This paper proposes a method that can be used to reduce words that are considered less important so that they can be used to improve the measurement of similarity between the reference answer and the student answer. The result shows that the proposed method is able to provide a smaller RMSE value of 1.2 compared with other methods used as a comparison.

Victims of acute cancer and tumor are growing each year and cancer becomes one of the causes of human deaths in the world. Cancers or tumor tissue cells are cells that grow abnormally and turn to take over and damage the surrounding tissues. At the beginning, cancers or tumors do not have definite symptoms in its early stages, and can even attack the tissues inside of the body. This phenomena is not identifiable under visual human observation. Therefore, an early detection system which is cheap, quick, simple, and portable is essensially required to anticipate the further development of cancer or tumor. Among all of the modalities, microwave imaging is considered to be a cheaper, simple, and portable system method. There are at least two simple image reconstruction algorithms i.e. Filtered Back Projection (FBP) and Algebraic Reconstruction Technique (ART), which have been adopted in some common modalities. In this paper, both algorithms will be compared by reconstructing the image from an artificial tissue model (i.e. phantom), which has two different dielectric distributions. We addressed two performance comparisons, namely quantitative and qualitative analysis. Qualitative analysis includes the smoothness of the image and also the success in distinguishing dielectric differences by observing the image with human eyesight. In addition, quantitative analysis includes Histogram, Structural Similarity Index (SSIM), Mean Squared Error (MSE), and Peak Signal-to-Noise Ratio (PSNR) calculation were also performed. As a result, quantitative parameters of FBP might show better values than the ART. However, ART is likely more capable to distinguish two different dielectric value than FBP, due to higher contrast in ART and wide distribution grayscale level.

Structural health monitoring using ultrasonic guided waves relies on accurate interpretation of guided wave propagation to distinguish damage state indicators. However, traditional physics based models do not provide an accurate representation, and classic data driven techniques, such as a support vector machine, are too simplistic to capture the complex nature of ultrasonic guide waves. To address this challenge, this paper uses a deep learning interpretation of ultrasonic guided waves to achieve fast, accurate, and automated structural damaged detection. To achieve this, full wavefield scans of thin metal plates are used, half from the undamaged state and half from the damaged state. This data is used to train our deep network to predict the damage state of a plate with 99.98% accuracy given signals from just 10 spatial locations on the plate, as compared to that of a support vector machine (SVM), which achieved a 62% accuracy.