Abstract: During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.
Abstract: The built-up area is a significant proxy to measure regional economic growth and reflects the Gross Provincial Product (GPP). However, an up-to-date and reliable database of built-up areas is not always available, especially in developing countries. The cloud-based geospatial analysis platform such as Google Earth Engine (GEE) provides an opportunity with accessibility and computational power for those countries to generate the built-up data. Therefore, this study aims to extract the built-up areas in Eastern Economic Corridor (EEC), Thailand using day and nighttime satellite imagery based on GEE facilities. The normalized indices were generated from Landsat 8 surface reflectance dataset, including Normalized Difference Built-up Index (NDBI), Built-up Index (BUI), and Modified Built-up Index (MBUI). These indices were applied to identify built-up areas in EEC. The result shows that MBUI performs better than BUI and NDBI, with the highest accuracy of 0.85 and Kappa of 0.82. Moreover, the overall accuracy of classification was improved from 79% to 90%, and error of total built-up area was decreased from 29% to 0.7%, after night-time light data from the Visible and Infrared Imaging Suite (VIIRS) Day Night Band (DNB). The results suggest that MBUI with night-time light imagery is appropriate for built-up area extraction and be utilize for further study of socioeconomic impacts of regional development policy over the EEC region.
Abstract: Clustering is an unsupervised learning technique for aggregating data objects into meaningful classes so that intra cluster similarity is maximized and inter cluster similarity is minimized in data mining. However, no single clustering algorithm proves to be the most effective in producing the best result. As a result, a new challenging technique known as the cluster ensemble approach has blossomed in order to determine the solution to this problem. For the cluster analysis issue, this new technique is a successful approach. The cluster ensemble's main goal is to combine similar clustering solutions in a way that achieves the precision while also improving the quality of individual data clustering. Because of the massive and rapid creation of new approaches in the field of data mining, the ongoing interest in inventing novel algorithms necessitates a thorough examination of current techniques and future innovation. This paper presents a comparative analysis of various cluster ensemble approaches, including their methodologies, formal working process, and standard accuracy and error rates. As a result, the society of clustering practitioners will benefit from this exploratory and clear research, which will aid in determining the most appropriate solution to the problem at hand.
Abstract: Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.
Abstract: As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.
Abstract: In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.
Abstract: Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.
Abstract: The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses wherein a set of assumptions and methods for a given data set will be made. It is therefore important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR were presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of Law. The estimate of LR is fundamentally a Bayesian concept and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE) for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR has different confidence intervals which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the LoR performed better than the KDE when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.
Abstract: The requirement for maintaining data integrity in laboratory operations is critical for regulatory compliance. Automation of procedures reduces incidence of human errors. Quality control laboratories located in low-income economies may face some barriers in attempts to automate their processes. Since data from quality control tests on pharmaceutical products are used in making regulatory decisions, it is important that laboratory reports are accurate and reliable. Zinc Sulphate (ZnSO4) tablets is used in treatment of diarrhea in pediatric population, and as an adjunct therapy for COVID-19 regimen. Unfortunately, zinc content in these formulations is determined titrimetrically; a manual analytical procedure. The assay for ZnSO4 tablets involves time-consuming steps that contain mathematical formulae prone to calculation errors. To achieve consistency, save costs, and improve data integrity, validated spreadsheets were developed to simplify the two critical steps in the analysis of ZnSO4 tablets: standardization of 0.1M Sodium Edetate (EDTA) solution, and the complexometric titration assay procedure. The assay method in the United States Pharmacopoeia was used to create a process flow for ZnSO4 tablets. For each step in the process, different formulae were input into two spreadsheets to automate calculations. Further checks were created within the automated system to ensure validity of replicate analysis in titrimetric procedures. Validations were conducted using five data sets of manually computed assay results. The acceptance criteria set for the protocol were met. Significant p-values (p < 0.05, α = 0.05, at 95% Confidence Interval) were obtained from students’ t-test evaluation of the mean values for manual-calculated and spreadsheet results at all levels of the analysis flow. Right-first-time analysis and principles of data integrity were enhanced by use of the validated spreadsheet calculators in titrimetric evaluations of ZnSO4 tablets. Human errors were minimized in calculations when procedures were automated in quality control laboratories. The assay procedure for the formulation was achieved in a time-efficient manner with greater level of accuracy. This project is expected to promote cost savings for laboratory business models.
Abstract: To improve the registration accuracy of a source point cloud and template point cloud when the initial relative deflection angle is too large, a PointNetLK algorithm combined with an oriented bounding box (PointNetLK-OBB) is proposed. In this algorithm, the OBB of a 3D point cloud is used to represent the macro feature of source and template point clouds. Under the guidance of the iterative closest point algorithm, the OBB of the source and template point clouds is aligned, and a mirror symmetry effect is produced between them. According to the fitting degree of the source and template point clouds, the mirror symmetry plane is detected, and the optimal rotation and translation of the source point cloud is obtained to complete the 3D point cloud registration task. To verify the effectiveness of the proposed algorithm, a comparative experiment was performed using the publicly available ModelNet40 dataset. The experimental results demonstrate that, compared with PointNetLK, PointNetLK-OBB improves the registration accuracy of the source and template point clouds when the initial relative deflection angle is too large, and the sensitivity of the initial relative position between the source point cloud and template point cloud is reduced. The primary contribution of this paper is the use of PointNetLK to avoid the non-convex problem of traditional point cloud registration and leveraging the regularity of the OBB to avoid the local optimization problem in the PointNetLK context.
Abstract: It is necessary to test to see if optical devices such as camera, night vision devices are working properly. Therefore, a precision biaxial rotary system (gimbal) is required for mounting Unit Under Test, UUT. The Gimbal systems can be utilized for precise positioning of the UUT; hence, optical test can be performed with high accuracy. The weight of UUT, which is placed outside the axis of rotation, causes an off-axis moment to the mounting armature. The off-axis moment can act against the direction of movement for some orientation, thus the electrical motor, which rotates the gimbal axis, has to apply higher level of torque to guide and stabilize the system. Moreover, UUT and its mounting fixture to the gimbal can be changed, which causes change in applied resistance moment to the gimbals electrical motor. In this study, a preloaded spring is added to the gimbal system for minimizing applied off axis moment with the help of four bar mechanism. Two different possible methods for preloading spring are introduced and system optimization is performed to eliminate all moment which is created by off axis weight.
Abstract: Nowadays, the use of drones has been extended to practically any human activity. One of the main applications is focused on the surveying field. In this regard, software programs that process the images captured by the sensor from the drone in an almost automatic way have been developed and commercialized, but they only allow contrasting the results through control points. This work proposes the contrast of a 3D model obtained from a flight developed by a drone and a non-metric camera (due to its low cost), with a second model that is obtained by means of the historically-endorsed classical methods. In addition to this, the contrast is developed over a certain territory with a significant unevenness, so as to test the model generated with photogrammetry, and considering that photogrammetry with drones finds more difficulties in terms of accuracy in this kind of situations. Distances, heights, surfaces and volumes are measured on the basis of the 3D models generated, and the results are contrasted. The differences are about 0.2% for the measurement of distances and heights, 0.3% for surfaces and 0.6% when measuring volumes. Although they are not important, they do not meet the order of magnitude that is presented by salespeople.
Abstract: In this research, a method is developed to obtain high-dimensional configuration space for path planning problems. In typical cases, the path planning problems are solved directly in the 3-dimensional (D) workspace. However, this method is inefficient in handling the robots with various geometrical and mechanical restrictions. To overcome these difficulties, path planning may be formalized and solved in a new space which is called configuration space. The number of dimensions of the configuration space comes from the degree of freedoms of the system of interest. The method can be applied in two ways. In the first way, the point clouds of all the bodies of the system and interaction of them are used. The second way is performed via using the clearance function of simulation software where the minimum distances between surfaces of bodies are simultaneously measured. A double-turret system is held in the scope of this study. The 4-D configuration space of a double-turret system is obtained in these two ways. As a result, the difference between these two methods is around 1%, depending on the density of the point cloud. The disparity between the two forms steadily decreases as the point cloud density increases. At the end of the study, in order to verify 4-D configuration space obtained, 4-D path planning problem was realized as 2-D + 2-D and a sample path planning is carried out with using A* algorithm. Then, the accuracy of the configuration space is proved using the obtained paths on the simulation model of the double-turret system.
Abstract: We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.
Abstract: Biosensors play a significant role in the healthcare
sectors, scientific and technological progress. Developing electrodes
that are easy to manufacture and deliver better electrochemical
performance is advantageous for diagnostics and biosensing. They
can be implemented extensively in various analytical tasks such as
drug discovery, food safety, medical diagnostics, process controls,
security and defence, in addition to environmental monitoring.
Development of biosensors aims to create high-performance
electrochemical electrodes for diagnostics and biosensing. A
biosensor is a device that inspects the biological and chemical
reactions generated by the biological sample. A biosensor carries
out biological detection via a linked transducer and transmits the
biological response into an electrical signal; stability, selectivity,
and sensitivity are the dynamic and static characteristics that affect
and dictate the quality and performance of biosensors. In this
research, a developed experimental study for laser scribing technique
for graphene oxide inside a vacuum chamber for processing of
graphene oxide is presented. The processing of graphene oxide (GO)
was achieved using the laser scribing technique. The effect of the
laser scribing on the reduction of GO was investigated under two
conditions: atmosphere and vacuum. GO solvent was coated onto a
LightScribe DVD. The laser scribing technique was applied to reduce
GO layers to generate rGO. The micro-details for the morphological
structures of rGO and GO were visualised using scanning electron
microscopy (SEM) and Raman spectroscopy so that they could
be examined. The first electrode was a traditional graphene-based
electrode model, made under normal atmospheric conditions, whereas
the second model was a developed graphene electrode fabricated
under a vacuum state using a vacuum chamber. The purpose was
to control the vacuum conditions, such as the air pressure and the
temperature during the fabrication process. The parameters to be
assessed include the layer thickness and the continuous environment.
Results presented show high accuracy and repeatability achieving low
cost productivity.
Abstract: This paper aims to prove the accuracy of an inexpensive smartphone camera as a non-contact vibration sensor to recover the vibration modes of a vibrating structure such as a cantilever beam. A video of a vibrating beam is filmed using a smartphone camera and then processed by the motion magnification technique. Based on this method, the first two natural frequencies and their associated mode shapes are estimated experimentally and compared to the analytical ones. Results show a relative error of less than 4% between the experimental and analytical approaches for the first two natural frequencies of the beam. Also, for the first two-mode shapes, a Modal Assurance Criterion (MAC) value of above 0.9 between the two approaches is obtained. This slight error between the different techniques ensures the viability of a cheap smartphone camera as a non-contact vibration sensor, particularly for structures vibrating at relatively low natural frequencies.
Abstract: Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We present a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.
Abstract: Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.
Abstract: The applications of composite materials within the aviation industry has been increasing at a rapid pace. However, the growing applications of composite materials have also led to growing demand for more tooling to support its manufacturing processes. Tooling and tooling maintenance represents a large portion of the composite manufacturing process and cost. Therefore, the industry’s adaptability to new techniques for fabricating high quality tools quickly and inexpensively will play a crucial role in composite material’s growing popularity in the aviation industry. One popular tool fabrication technique currently being developed involves additive manufacturing such as 3D printing. Although additive manufacturing and 3D printing are not entirely new concepts, the technique has been gaining popularity due to its ability to quickly fabricate components, maintain low material waste, and low cost. In this study, a team of Purdue University School of Aviation and Transportation Technology (SATT) faculty and students investigated the effectiveness of a 3D printed composite compression mold. A 3D printed composite compression mold was fabricated by 3D scanning a steel valve cover of an aircraft reciprocating engine. The 3D printed composite compression mold was used to fabricate carbon fiber versions of the aircraft reciprocating engine valve cover. The 3D printed composite compression mold was evaluated for its performance, durability, and dimensional stability while the fabricated carbon fiber valve covers were evaluated for its accuracy and quality. The results and data gathered from this study will determine the effectiveness of the 3D printed composite compression mold in a mass production environment and provide valuable information for future understanding, improvements, and design considerations of 3D printed composite molds.
Abstract: Network security is role of the ICT environment
because malicious users are continually growing that realm of
education, business, and then related with ICT. The network security
contravention is typically described and examined centrally based
on a security event management system. The firewalls, Intrusion
Detection System (IDS), and Intrusion Prevention System are
becoming essential to monitor or prevent of potential violations,
incidents attack, and imminent threats. In this system, the firewall
rules are set only for where the system policies are needed. Dataset
deployed in this system are derived from the testbed environment. The
traffic as in DoS and PortScan traffics are applied in the testbed with
firewall and IDS implementation. The network traffics are classified
as normal or attacks in the existing testbed environment based on
six machine learning classification methods applied in the system.
It is required to be tested to get datasets and applied for DoS and
PortScan. The dataset is based on CICIDS2017 and some features
have been added. This system tested 26 features from the applied
dataset. The system is to reduce false positive rates and to improve
accuracy in the implemented testbed design. The system also proves
good performance by selecting important features and comparing
existing a dataset by machine learning classifiers.