Search results for: neural nets
195 Loss Function Optimization for CNN-Based Fingerprint Anti-Spoofing
Authors: Yehjune Heo
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.Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer
Procedia PDF Downloads 132194 Design of a Standard Weather Data Acquisition Device for the Federal University of Technology, Akure Nigeria
Authors: Isaac Kayode Ogunlade
Abstract:
Data acquisition (DAQ) is the process by which physical phenomena from the real world are transformed into an electrical signal(s) that are measured and converted into a digital format for processing, analysis, and storage by a computer. The DAQ is designed using PIC18F4550 microcontroller, communicating with Personal Computer (PC) through USB (Universal Serial Bus). The research deployed initial knowledge of data acquisition system and embedded system to develop a weather data acquisition device using LM35 sensor to measure weather parameters and the use of Artificial Intelligence(Artificial Neural Network - ANN)and statistical approach(Autoregressive Integrated Moving Average – ARIMA) to predict precipitation (rainfall). The device is placed by a standard device in the Department of Meteorology, Federal University of Technology, Akure (FUTA) to know the performance evaluation of the device. Both devices (standard and designed) were subjected to 180 days with the same atmospheric condition for data mining (temperature, relative humidity, and pressure). The acquired data is trained in MATLAB R2012b environment using ANN, and ARIMAto predict precipitation (rainfall). Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Correction Square (R2), and Mean Percentage Error (MPE) was deplored as standardize evaluation to know the performance of the models in the prediction of precipitation. The results from the working of the developed device show that the device has an efficiency of 96% and is also compatible with Personal Computer (PC) and laptops. The simulation result for acquired data shows that ANN models precipitation (rainfall) prediction for two months (May and June 2017) revealed a disparity error of 1.59%; while ARIMA is 2.63%, respectively. The device will be useful in research, practical laboratories, and industrial environments.Keywords: data acquisition system, design device, weather development, predict precipitation and (FUTA) standard device
Procedia PDF Downloads 84193 An Automated Stock Investment System Using Machine Learning Techniques: An Application in Australia
Authors: Carol Anne Hargreaves
Abstract:
A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system
Procedia PDF Downloads 150192 AI Peer Review Challenge: Standard Model of Physics vs 4D GEM EOS
Authors: David A. Harness
Abstract:
Natural evolution of ATP cognitive systems is to meet AI peer review standards. ATP process of axiom selection from Mizar to prove a conjecture would be further refined, as in all human and machine learning, by solving the real world problem of the proposed AI peer review challenge: Determine which conjecture forms the higher confidence level constructive proof between Standard Model of Physics SU(n) lattice gauge group operation vs. present non-standard 4D GEM EOS SU(n) lattice gauge group spatially extended operation in which the photon and electron are the first two trace angular momentum invariants of a gravitoelectromagnetic (GEM) energy momentum density tensor wavetrain integration spin-stress pressure-volume equation of state (EOS), initiated via 32 lines of Mathematica code. Resulting gravitoelectromagnetic spectrum ranges from compressive through rarefactive of the central cosmological constant vacuum energy density in units of pascals. Said self-adjoint group operation exclusively operates on the stress energy momentum tensor of the Einstein field equations, introducing quantization directly on the 4D spacetime level, essentially reformulating the Yang-Mills virtual superpositioned particle compounded lattice gauge groups quantization of the vacuum—into a single hyper-complex multi-valued GEM U(1) × SU(1,3) lattice gauge group Planck spacetime mesh quantization of the vacuum. Thus the Mizar corpus already contains all of the axioms required for relevant DeepMath premise selection and unambiguous formal natural language parsing in context deep learning.Keywords: automated theorem proving, constructive quantum field theory, information theory, neural networks
Procedia PDF Downloads 173191 Characterization and Correlation of Neurodegeneration and Biological Markers of Model Mice with Traumatic Brain Injury and Alzheimer's Disease
Authors: J. DeBoard, R. Dietrich, J. Hughes, K. Yurko, G. Harms
Abstract:
Alzheimer’s disease (AD) is a predominant type of dementia and is likely a major cause of neural network impairment. The pathogenesis of this neurodegenerative disorder has yet to be fully elucidated. There are currently no known cures for the disease, and the best hope is to be able to detect it early enough to impede its progress. Beyond age and genetics, another prevalent risk factor for AD might be traumatic brain injury (TBI), which has similar neurodegenerative hallmarks. Our research focuses on obtaining information and methods to be able to predict when neurodegenerative effects might occur at a clinical level by observation of events at a cellular and molecular level in model mice. First, we wish to introduce our evidence that brain damage can be observed via brain imaging prior to the noticeable loss of neuromuscular control in model mice of AD. We then show our evidence that some blood biomarkers might be able to be early predictors of AD in the same model mice. Thus, we were interested to see if we might be able to predict which mice might show long-term neurodegenerative effects due to differing degrees of TBI and what level of TBI causes further damage and earlier death to the AD model mice. Upon application of TBIs via an apparatus to effectively induce extremely mild to mild TBIs, wild-type (WT) mice and AD mouse models were tested for cognition, neuromuscular control, olfactory ability, blood biomarkers, and brain imaging. Experiments are currently still in process, and more results are therefore forthcoming. Preliminary data suggest that neuromotor control diminishes as well as olfactory function for both AD and WT mice after the administration of five consecutive mild TBIs. Also, seizure activity increases significantly for both AD and WT after the administration of the five TBI treatment. If future data supports these findings, important implications about the effect of TBI on those at risk for AD might be possible.Keywords: Alzheimer's disease, blood biomarker, neurodegeneration, neuromuscular control, olfaction, traumatic brain injury
Procedia PDF Downloads 139190 Hybridization of Manually Extracted and Convolutional Features for Classification of Chest X-Ray of COVID-19
Authors: M. Bilal Ishfaq, Adnan N. Qureshi
Abstract:
COVID-19 is the most infectious disease these days, it was first reported in Wuhan, the capital city of Hubei in China then it spread rapidly throughout the whole world. Later on 11 March 2020, the World Health Organisation (WHO) declared it a pandemic. Since COVID-19 is highly contagious, it has affected approximately 219M people worldwide and caused 4.55M deaths. It has brought the importance of accurate diagnosis of respiratory diseases such as pneumonia and COVID-19 to the forefront. In this paper, we propose a hybrid approach for the automated detection of COVID-19 using medical imaging. We have presented the hybridization of manually extracted and convolutional features. Our approach combines Haralick texture features and convolutional features extracted from chest X-rays and CT scans. We also employ a minimum redundancy maximum relevance (MRMR) feature selection algorithm to reduce computational complexity and enhance classification performance. The proposed model is evaluated on four publicly available datasets, including Chest X-ray Pneumonia, COVID-19 Pneumonia, COVID-19 CTMaster, and VinBig data. The results demonstrate high accuracy and effectiveness, with 0.9925 on the Chest X-ray pneumonia dataset, 0.9895 on the COVID-19, Pneumonia and Normal Chest X-ray dataset, 0.9806 on the Covid CTMaster dataset, and 0.9398 on the VinBig dataset. We further evaluate the effectiveness of the proposed model using ROC curves, where the AUC for the best-performing model reaches 0.96. Our proposed model provides a promising tool for the early detection and accurate diagnosis of COVID-19, which can assist healthcare professionals in making informed treatment decisions and improving patient outcomes. The results of the proposed model are quite plausible and the system can be deployed in a clinical or research setting to assist in the diagnosis of COVID-19.Keywords: COVID-19, feature engineering, artificial neural networks, radiology images
Procedia PDF Downloads 72189 Applying Multiplicative Weight Update to Skin Cancer Classifiers
Authors: Animish Jain
Abstract:
This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer
Procedia PDF Downloads 72188 Use Cloud-Based Watson Deep Learning Platform to Train Models Faster and More Accurate
Authors: Susan Diamond
Abstract:
Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare.Keywords: deep learning, machine learning, cognitive computing, model training
Procedia PDF Downloads 203187 Using Hyperspectral Sensor and Machine Learning to Predict Water Potentials of Wild Blueberries during Drought Treatment
Authors: Yongjiang Zhang, Kallol Barai, Umesh R. Hodeghatta, Trang Tran, Vikas Dhiman
Abstract:
Detecting water stress on crops early and accurately is crucial to minimize its impact. This study aims to measure water stress in wild blueberry crops non-destructively by analyzing proximal hyperspectral data. The data collection took place in the summer growing season of 2022. A drought experiment was conducted on wild blueberries in the randomized block design in the greenhouse, incorporating various genotypes and irrigation treatments. Hyperspectral data ( spectral range: 400-1000 nm) using a handheld spectroradiometer and leaf water potential data using a pressure chamber were collected from wild blueberry plants. Machine learning techniques, including multiple regression analysis and random forest models, were employed to predict leaf water potential (MPa). We explored the optimal wavelength bands for simple differences (RY1-R Y2), simple ratios (RY1/RY2), and normalized differences (|RY1-R Y2|/ (RY1-R Y2)). NDWI ((R857 - R1241)/(R857 + R1241)), SD (R2188 – R2245), and SR (R1752 / R1756) emerged as top predictors for predicting leaf water potential, significantly contributing to the highest model performance. The base learner models achieved an R-squared value of approximately 0.81, indicating their capacity to explain 81% of the variance. Research is underway to develop a neural vegetation index (NVI) that automates the process of index development by searching for specific wavelengths in the space ratio of linear functions of reflectance. The NVI framework could work across species and predict different physiological parameters.Keywords: hyperspectral reflectance, water potential, spectral indices, machine learning, wild blueberries, optimal bands
Procedia PDF Downloads 61186 Selection of Optimal Reduced Feature Sets of Brain Signal Analysis Using Heuristically Optimized Deep Autoencoder
Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh
Abstract:
In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization
Procedia PDF Downloads 110185 Improving Chest X-Ray Disease Detection with Enhanced Data Augmentation Using Novel Approach of Diverse Conditional Wasserstein Generative Adversarial Networks
Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang
Abstract:
Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.Keywords: CNN, classification, deep learning, GAN, Resnet50
Procedia PDF Downloads 75184 A Deep Learning Approach to Real Time and Robust Vehicular Traffic Prediction
Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage
Abstract:
Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention
Procedia PDF Downloads 66183 DeepLig: A de-novo Computational Drug Design Approach to Generate Multi-Targeted Drugs
Authors: Anika Chebrolu
Abstract:
Mono-targeted drugs can be of limited efficacy against complex diseases. Recently, multi-target drug design has been approached as a promising tool to fight against these challenging diseases. However, the scope of current computational approaches for multi-target drug design is limited. DeepLig presents a de-novo drug discovery platform that uses reinforcement learning to generate and optimize novel, potent, and multitargeted drug candidates against protein targets. DeepLig’s model consists of two networks in interplay: a generative network and a predictive network. The generative network, a Stack- Augmented Recurrent Neural Network, utilizes a stack memory unit to remember and recognize molecular patterns when generating novel ligands from scratch. The generative network passes each newly created ligand to the predictive network, which then uses multiple Graph Attention Networks simultaneously to forecast the average binding affinity of the generated ligand towards multiple target proteins. With each iteration, given feedback from the predictive network, the generative network learns to optimize itself to create molecules with a higher average binding affinity towards multiple proteins. DeepLig was evaluated based on its ability to generate multi-target ligands against two distinct proteins, multi-target ligands against three distinct proteins, and multi-target ligands against two distinct binding pockets on the same protein. With each test case, DeepLig was able to create a library of valid, synthetically accessible, and novel molecules with optimal and equipotent binding energies. We propose that DeepLig provides an effective approach to design multi-targeted drug therapies that can potentially show higher success rates during in-vitro trials.Keywords: drug design, multitargeticity, de-novo, reinforcement learning
Procedia PDF Downloads 88182 Arabic Light Word Analyser: Roles with Deep Learning Approach
Authors: Mohammed Abu Shquier
Abstract:
This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN
Procedia PDF Downloads 34181 Rational Allocation of Resources in Water Infrastructure Development Projects
Authors: M. Macchiaroli, V. Pellecchia, L. Dolores
Abstract:
Within any European and world model of management of the integrated water service (in Italy only since 2012 is regulated by a national Authority, that is ARERA), a significant part is covered by the development of assets in terms of hydraulic networks and wastewater collection networks, including all their relative building works. The process of selecting the investments to be made starts from the preventive analysis of critical issues (water losses, unserved areas, low service standards, etc.) who occur in the managed territory of the Operator. Through the Program of Interventions (Provision by ARERA n. 580/2019/R/idr), the Operator provides to program the projects that can meet the emerged needs to determine the improvement of the water service levels. This phase (analyzed and solved by the author with a work published in 2019) involves the use of evaluation techniques (cost-benefit analysis, multi-criteria, and multi-objective techniques, neural networks, etc.) useful in selecting the most appropriate design answers to the different criticalities. However, at this point, the problem of establishing the time priorities between the various works deemed necessary remains open. That is, it is necessary to hierarchize the investments. In this decision-making moment, the interests of the private Operator are often opposed, which favors investments capable of generating high profitability, compared to those of the public controller (ARERA), which favors investments in greater social impact. In support of the concertation between these two actors, the protocol set out in the research has been developed, based on the AHP and capable of borrowing from the programmatic documents an orientation path for the settlement of the conflict. The protocol is applied to a case study of the Campania Region in Italy and has been professionally applied in the shared decision process between the manager and the local Authority.Keywords: analytic hierarchy process, decision making, economic evaluation of projects, integrated water service
Procedia PDF Downloads 116180 Digi-Buddy: A Smart Cane with Artificial Intelligence and Real-Time Assistance
Authors: Amaladhithyan Krishnamoorthy, Ruvaitha Banu
Abstract:
Vision is considered as the most important sense in humans, without which leading a normal can be often difficult. There are many existing smart canes for visually impaired with obstacle detection using ultrasonic transducer to help them navigate. Though the basic smart cane increases the safety of the users, it does not help in filling the void of visual loss. This paper introduces the concept of Digi-Buddy which is an evolved smart cane for visually impaired. The cane consists for several modules, apart from the basic obstacle detection features; the Digi-Buddy assists the user by capturing video/images and streams them to the server using a wide-angled camera, which then detects the objects using Deep Convolutional Neural Network. In addition to determining what the particular image/object is, the distance of the object is assessed by the ultrasonic transducer. The sound generation application, modelled with the help of Natural Language Processing is used to convert the processed images/object into audio. The object detected is signified by its name which is transmitted to the user with the help of Bluetooth hear phones. The object detection is extended to facial recognition which maps the faces of the person the user meets in the database of face images and alerts the user about the person. One of other crucial function consists of an automatic-intimation-alarm which is triggered when the user is in an emergency. If the user recovers within a set time, a button is provisioned in the cane to stop the alarm. Else an automatic intimation is sent to friends and family about the whereabouts of the user using GPS. In addition to safety and security by the existing smart canes, the proposed concept devices to be implemented as a prototype helping visually-impaired visualize their surroundings through audio more in an amicable way.Keywords: artificial intelligence, facial recognition, natural language processing, internet of things
Procedia PDF Downloads 346179 Impact of Drainage Defect on the Railway Track Surface Deflections; A Numerical Investigation
Authors: Shadi Fathi, Moura Mehravar, Mujib Rahman
Abstract:
The railwaytransportation network in the UK is over 100 years old and is known as one of the oldest mass transit systems in the world. This aged track network requires frequent closure for maintenance. One of the main reasons for closure is inadequate drainage due to the leakage in the buried drainage pipes. The leaking water can cause localised subgrade weakness, which subsequently can lead to major ground/substructure failure.Different condition assessment methods are available to assess the railway substructure. However, the existing condition assessment methods are not able to detect any local ground weakness/damageand provide details of the damage (e.g. size and location). To tackle this issue, a hybrid back-analysis technique based on artificial neural network (ANN) and genetic algorithm (GA) has been developed to predict the substructurelayers’ moduli and identify any soil weaknesses. At first, afinite element (FE) model of a railway track section under Falling Weight Deflection (FWD) testing was developed and validated against field trial. Then a drainage pipe and various scenarios of the local defect/ soil weakness around the buried pipe with various geometriesand physical properties were modelled. The impact of the soil local weaknesson the track surface deflection wasalso studied. The FE simulations results were used to generate a database for ANN training, and then a GA wasemployed as an optimisation tool to optimise and back-calculate layers’ moduli and soil weakness moduli (ANN’s input). The hybrid ANN-GA back-analysis technique is a computationally efficient method with no dependency on seed modulus values. The modelcan estimate substructures’ layer moduli and the presence of any localised foundation weakness.Keywords: finite element (FE) model, drainage defect, falling weight deflectometer (FWD), hybrid ANN-GA
Procedia PDF Downloads 146178 Grid and Market Integration of Large Scale Wind Farms using Advanced Predictive Data Mining Techniques
Authors: Umit Cali
Abstract:
The integration of intermittent energy sources like wind farms into the electricity grid has become an important challenge for the utilization and control of electric power systems, because of the fluctuating behaviour of wind power generation. Wind power predictions improve the economic and technical integration of large amounts of wind energy into the existing electricity grid. Trading, balancing, grid operation, controllability and safety issues increase the importance of predicting power output from wind power operators. Therefore, wind power forecasting systems have to be integrated into the monitoring and control systems of the transmission system operator (TSO) and wind farm operators/traders. The wind forecasts are relatively precise for the time period of only a few hours, and, therefore, relevant with regard to Spot and Intraday markets. In this work predictive data mining techniques are applied to identify a statistical and neural network model or set of models that can be used to predict wind power output of large onshore and offshore wind farms. These advanced data analytic methods helps us to amalgamate the information in very large meteorological, oceanographic and SCADA data sets into useful information and manageable systems. Accurate wind power forecasts are beneficial for wind plant operators, utility operators, and utility customers. An accurate forecast allows grid operators to schedule economically efficient generation to meet the demand of electrical customers. This study is also dedicated to an in-depth consideration of issues such as the comparison of day ahead and the short-term wind power forecasting results, determination of the accuracy of the wind power prediction and the evaluation of the energy economic and technical benefits of wind power forecasting.Keywords: renewable energy sources, wind power, forecasting, data mining, big data, artificial intelligence, energy economics, power trading, power grids
Procedia PDF Downloads 510177 Data Mining Model for Predicting the Status of HIV Patients during Drug Regimen Change
Authors: Ermias A. Tegegn, Million Meshesha
Abstract:
Human Immunodeficiency Virus and Acquired Immunodeficiency Syndrome (HIV/AIDS) is a major cause of death for most African countries. Ethiopia is one of the seriously affected countries in sub Saharan Africa. Previously in Ethiopia, having HIV/AIDS was almost equivalent to a death sentence. With the introduction of Antiretroviral Therapy (ART), HIV/AIDS has become chronic, but manageable disease. The study focused on a data mining technique to predict future living status of HIV/AIDS patients at the time of drug regimen change when the patients become toxic to the currently taking ART drug combination. The data is taken from University of Gondar Hospital ART program database. Hybrid methodology is followed to explore the application of data mining on ART program dataset. Data cleaning, handling missing values and data transformation were used for preprocessing the data. WEKA 3.7.9 data mining tools, classification algorithms, and expertise are utilized as means to address the research problem. By using four different classification algorithms, (i.e., J48 Classifier, PART rule induction, Naïve Bayes and Neural network) and by adjusting their parameters thirty-two models were built on the pre-processed University of Gondar ART program dataset. The performances of the models were evaluated using the standard metrics of accuracy, precision, recall, and F-measure. The most effective model to predict the status of HIV patients with drug regimen substitution is pruned J48 decision tree with a classification accuracy of 98.01%. This study extracts interesting attributes such as Ever taking Cotrim, Ever taking TbRx, CD4 count, Age, Weight, and Gender so as to predict the status of drug regimen substitution. The outcome of this study can be used as an assistant tool for the clinician to help them make more appropriate drug regimen substitution. Future research directions are forwarded to come up with an applicable system in the area of the study.Keywords: HIV drug regimen, data mining, hybrid methodology, predictive model
Procedia PDF Downloads 140176 Investigating Role of Novel Molecular Players in Forebrain Roof-Plate Midline Invagination
Authors: Mohd Ali Abbas Zaidi, Meenu Sachdeva, Jonaki Sen
Abstract:
In the vertebrate embryo, the forebrain anlagen develops from the anterior-most region of the neural tube which is the precursor of the central nervous system (CNS). The roof plate located at the dorsal midline region of the forebrain anlagen, acts as a source of several secreted molecules involved in patterning and morphogenesis of the forebrain. One such key morphogenetic event is the invagination of the forebrain roof plate which results in separation of the single forebrain vesicle into two cerebral hemispheres. Retinoic acid (RA) signaling plays a key role in this process. Blocking RA signaling at the dorsal forebrain midline inhibits dorsal invagination and results in the absence of certain key features of this region, such as thinning of the neuroepithelium and a lowering of cell proliferation. At present we are investigating the possibility of other signaling pathways acting in concert with RA signaling to regulate this process. We have focused on BMP signaling, which we found to be active in a mutually exclusive domain to that of RA signaling within the roof plate. We have also observed that there is a change in BMP signaling activity on modulation of RA signaling indicating an antagonistic relationship between the two. Moreover, constitutive activation of BMP signaling seems to completely inhibit thinning and partially affect invagination, leaving the lowering of cell proliferation in the midline unaffected. We are employing in-silico modeling as well as molecular manipulations to investigate the relative contribution if any, of regional differences in rates of cell proliferation and thinning of the neuroepithelium towards the process of invagination. We have found expression of certain cell adhesion molecules in forebrain roof-plate whose mRNA localization across the thickness of neuroepithelium is influenced by Bmp and RA signaling, giving regional rigidity to roof plate and assisting invagination. We also found expression of certain cytoskeleton modifiers in a localized small domains in invaginating forebrain roof plate suggesting that midline invagination is under control of many factors.Keywords: bone morphogenetic signaling, cytoskeleton, cell adhesion molecules, forebrain roof plate, retinoic acid signaling
Procedia PDF Downloads 151175 Detecting Memory-Related Gene Modules in sc/snRNA-seq Data by Deep-Learning
Authors: Yong Chen
Abstract:
To understand the detailed molecular mechanisms of memory formation in engram cells is one of the most fundamental questions in neuroscience. Recent single-cell RNA-seq (scRNA-seq) and single-nucleus RNA-seq (snRNA-seq) techniques have allowed us to explore the sparsely activated engram ensembles, enabling access to the molecular mechanisms that underlie experience-dependent memory formation and consolidation. However, the absence of specific and powerful computational methods to detect memory-related genes (modules) and their regulatory relationships in the sc/snRNA-seq datasets has strictly limited the analysis of underlying mechanisms and memory coding principles in mammalian brains. Here, we present a deep-learning method named SCENTBOX, to detect memory-related gene modules and causal regulatory relationships among themfromsc/snRNA-seq datasets. SCENTBOX first constructs codifferential expression gene network (CEGN) from case versus control sc/snRNA-seq datasets. It then detects the highly correlated modules of differential expression genes (DEGs) in CEGN. The deep network embedding and attention-based convolutional neural network strategies are employed to precisely detect regulatory relationships among DEG genes in a module. We applied them on scRNA-seq datasets of TRAP; Ai14 mouse neurons with fear memory and detected not only known memory-related genes, but also the modules and potential causal regulations. Our results provided novel regulations within an interesting module, including Arc, Bdnf, Creb, Dusp1, Rgs4, and Btg2. Overall, our methods provide a general computational tool for processing sc/snRNA-seq data from case versus control studie and a systematic investigation of fear-memory-related gene modules.Keywords: sc/snRNA-seq, memory formation, deep learning, gene module, causal inference
Procedia PDF Downloads 116174 Improve Student Performance Prediction Using Majority Vote Ensemble Model for Higher Education
Authors: Wade Ghribi, Abdelmoty M. Ahmed, Ahmed Said Badawy, Belgacem Bouallegue
Abstract:
In higher education institutions, the most pressing priority is to improve student performance and retention. Large volumes of student data are used in Educational Data Mining techniques to find new hidden information from students' learning behavior, particularly to uncover the early symptom of at-risk pupils. On the other hand, data with noise, outliers, and irrelevant information may provide incorrect conclusions. By identifying features of students' data that have the potential to improve performance prediction results, comparing and identifying the most appropriate ensemble learning technique after preprocessing the data, and optimizing the hyperparameters, this paper aims to develop a reliable students' performance prediction model for Higher Education Institutions. Data was gathered from two different systems: a student information system and an e-learning system for undergraduate students in the College of Computer Science of a Saudi Arabian State University. The cases of 4413 students were used in this article. The process includes data collection, data integration, data preprocessing (such as cleaning, normalization, and transformation), feature selection, pattern extraction, and, finally, model optimization and assessment. Random Forest, Bagging, Stacking, Majority Vote, and two types of Boosting techniques, AdaBoost and XGBoost, are ensemble learning approaches, whereas Decision Tree, Support Vector Machine, and Artificial Neural Network are supervised learning techniques. Hyperparameters for ensemble learning systems will be fine-tuned to provide enhanced performance and optimal output. The findings imply that combining features of students' behavior from e-learning and students' information systems using Majority Vote produced better outcomes than the other ensemble techniques.Keywords: educational data mining, student performance prediction, e-learning, classification, ensemble learning, higher education
Procedia PDF Downloads 99173 A Hybrid-Evolutionary Optimizer for Modeling the Process of Obtaining Bricks
Authors: Marius Gavrilescu, Sabina-Adriana Floria, Florin Leon, Silvia Curteanu, Costel Anton
Abstract:
Natural sciences provide a wide range of experimental data whose related problems require study and modeling beyond the capabilities of conventional methodologies. Such problems have solution spaces whose complexity and high dimensionality require correspondingly complex regression methods for proper characterization. In this context, we propose an optimization method which consists in a hybrid dual optimizer setup: a global optimizer based on a modified variant of the popular Imperialist Competitive Algorithm (ICA), and a local optimizer based on a gradient descent approach. The ICA is modified such that intermediate solution populations are more quickly and efficiently pruned of low-fitness individuals by appropriately altering the assimilation, revolution and competition phases, which, combined with an initialization strategy based on low-discrepancy sampling, allows for a more effective exploration of the corresponding solution space. Subsequently, gradient-based optimization is used locally to seek the optimal solution in the neighborhoods of the solutions found through the modified ICA. We use this combined approach to find the optimal configuration and weights of a fully-connected neural network, resulting in regression models used to characterize the process of obtained bricks using silicon-based materials. Installations in the raw ceramics industry, i.e., bricks, are characterized by significant energy consumption and large quantities of emissions. Thus, the purpose of our approach is to determine by simulation the working conditions, including the manufacturing mix recipe with the addition of different materials, to minimize the emissions represented by CO and CH4. Our approach determines regression models which perform significantly better than those found using the traditional ICA for the aforementioned problem, resulting in better convergence and a substantially lower error.Keywords: optimization, biologically inspired algorithm, regression models, bricks, emissions
Procedia PDF Downloads 77172 Identification of Blood Biomarkers Unveiling Early Alzheimer's Disease Diagnosis Through Single-Cell RNA Sequencing Data and Autoencoders
Authors: Hediyeh Talebi, Shokoofeh Ghiam, Changiz Eslahchi
Abstract:
Traditionally, Alzheimer’s disease research has focused on genes with significant fold changes, potentially neglecting subtle but biologically important alterations. Our study introduces an integrative approach that highlights genes crucial to underlying biological processes, regardless of their fold change magnitude. Alzheimer's Single-cell RNA-seq data related to the peripheral blood mononuclear cells (PBMC) was extracted from the Gene Expression Omnibus (GEO). After quality control, normalization, scaling, batch effect correction, and clustering, differentially expressed genes (DEGs) were identified with adjusted p-values less than 0.05. These DEGs were categorized based on cell-type, resulting in four datasets, each corresponding to a distinct cell type. To distinguish between cells from healthy individuals and those with Alzheimer's, an adversarial autoencoder with a classifier was employed. This allowed for the separation of healthy and diseased samples. To identify the most influential genes in this classification, the weight matrices in the network, which includes the encoder and classifier components, were multiplied, and focused on the top 20 genes. The analysis revealed that while some of these genes exhibit a high fold change, others do not. These genes, which may be overlooked by previous methods due to their low fold change, were shown to be significant in our study. The findings highlight the critical role of genes with subtle alterations in diagnosing Alzheimer's disease, a facet frequently overlooked by conventional methods. These genes demonstrate remarkable discriminatory power, underscoring the need to integrate biological relevance with statistical measures in gene prioritization. This integrative approach enhances our understanding of the molecular mechanisms in Alzheimer’s disease and provides a promising direction for identifying potential therapeutic targets.Keywords: alzheimer's disease, single-cell RNA-seq, neural networks, blood biomarkers
Procedia PDF Downloads 58171 Perinatal Ethanol Exposure Modifies CART System in Rat Brain Anticipated for Development of Anxiety, Depression and Memory Deficits
Authors: M. P. Dandekar, A. P. Bharne, P. T. Borkar, D. M. Kokare, N. K. Subhedar
Abstract:
Ethanol ingestion by the mother ensue adverse consequences for her offspring. Herein, we examine the behavioral phenotype and neural substrate of the offspring of the mother on ethanol. Female rats were fed with ethanol-containing liquid diet from 8 days prior of conception and continued till 25 days post-parturition to coincide with weaning. Behavioral changes associated with anxiety, depression and learning and memory were assessed in the offspring, after they attained adulthood (day 85), using elevated plus maze (EPM), forced swim (FST) and novel object recognition tests (NORT), respectively. The offspring of the alcoholic mother, compared to those of the pair-fed mother, spent significantly more time in closed arms of EPM and showed more immobility time in FST. Offspring at the age of 25 and 85 days failed to discriminate between novel versus familiar object in NORT, thus reflecting anxiogenic, depressive and amnesic phenotypes. Neuropeptide cocaine- and amphetamine-regulated transcript peptide (CART) is known to be involved in central effects of ethanol and hence selected for the current study. Twenty-five days old pups of the alcoholic mother showed significant augmentation in CART-immunoreactivity in the cells of Edinger-Westphal (EW) nucleus and lateral hypothalamus. However, a significant decrease in CART-immunoreactivity was seen in nucleus accumbens shell (AcbSh), lateral part of bed nucleus of the stria terminalis (BNSTl), locus coeruleus (LC), hippocampus (CA1, CA2 and CA3), and arcuate nucleus (ARC) of the pups and/or adults offspring. While no change in the CART-immunoreactive fibers of AcbSh and BNSTl, CA2 and CA3 was noticed in the 25 days old pups, the CART-immunoreactive cells in EW and paraventricular nucleus (PVN), and fibers in the central nucleus of amygdala of 85 days old offspring remained unaffected. We suggest that the endogenous CART system in these discrete areas, among other factors, may be a causal to the abnormalities in the next generation of an alcoholic mother.Keywords: anxiety, depression, CART, ethanol, immunocytochemistry
Procedia PDF Downloads 389170 Radar Track-based Classification of Birds and UAVs
Authors: Altilio Rosa, Chirico Francesco, Foglia Goffredo
Abstract:
In recent years, the number of Unmanned Aerial Vehicles (UAVs) has significantly increased. The rapid development of commercial and recreational drones makes them an important part of our society. Despite the growing list of their applications, these vehicles pose a huge threat to civil and military installations: detection, classification and neutralization of such flying objects become an urgent need. Radar is an effective remote sensing tool for detecting and tracking flying objects, but scenarios characterized by the presence of a high number of tracks related to flying birds make especially challenging the drone detection task: operator PPI is cluttered with a huge number of potential threats and his reaction time can be severely affected. Flying birds compared to UAVs show similar velocity, RADAR cross-section and, in general, similar characteristics. Building from the absence of a single feature that is able to distinguish UAVs and birds, this paper uses a multiple features approach where an original feature selection technique is developed to feed binary classifiers trained to distinguish birds and UAVs. RADAR tracks acquired on the field and related to different UAVs and birds performing various trajectories were used to extract specifically designed target movement-related features based on velocity, trajectory and signal strength. An optimization strategy based on a genetic algorithm is also introduced to select the optimal subset of features and to estimate the performance of several classification algorithms (Neural network, SVM, Logistic regression…) both in terms of the number of selected features and misclassification error. Results show that the proposed methods are able to reduce the dimension of the data space and to remove almost all non-drone false targets with a suitable classification accuracy (higher than 95%).Keywords: birds, classification, machine learning, UAVs
Procedia PDF Downloads 212169 An Artificial Intelligence Framework to Forecast Air Quality
Authors: Richard Ren
Abstract:
Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms
Procedia PDF Downloads 115168 Census and Mapping of Oil Palms Over Satellite Dataset Using Deep Learning Model
Authors: Gholba Niranjan Dilip, Anil Kumar
Abstract:
Conduct of accurate reliable mapping of oil palm plantations and census of individual palm trees is a huge challenge. This study addresses this challenge and developed an optimized solution implemented deep learning techniques on remote sensing data. The oil palm is a very important tropical crop. To improve its productivity and land management, it is imperative to have accurate census over large areas. Since, manual census is costly and prone to approximations, a methodology for automated census using panchromatic images from Cartosat-2, SkySat and World View-3 satellites is demonstrated. It is selected two different study sites in Indonesia. The customized set of training data and ground-truth data are created for this study from Cartosat-2 images. The pre-trained model of Single Shot MultiBox Detector (SSD) Lite MobileNet V2 Convolutional Neural Network (CNN) from the TensorFlow Object Detection API is subjected to transfer learning on this customized dataset. The SSD model is able to generate the bounding boxes for each oil palm and also do the counting of palms with good accuracy on the panchromatic images. The detection yielded an F-Score of 83.16 % on seven different images. The detections are buffered and dissolved to generate polygons demarcating the boundaries of the oil palm plantations. This provided the area under the plantations and also gave maps of their location, thereby completing the automated census, with a fairly high accuracy (≈100%). The trained CNN was found competent enough to detect oil palm crowns from images obtained from multiple satellite sensors and of varying temporal vintage. It helped to estimate the increase in oil palm plantations from 2014 to 2021 in the study area. The study proved that high-resolution panchromatic satellite image can successfully be used to undertake census of oil palm plantations using CNNs.Keywords: object detection, oil palm tree census, panchromatic images, single shot multibox detector
Procedia PDF Downloads 157167 An Approach to Autonomous Drones Using Deep Reinforcement Learning and Object Detection
Authors: K. R. Roopesh Bharatwaj, Avinash Maharana, Favour Tobi Aborisade, Roger Young
Abstract:
Presently, there are few cases of complete automation of drones and its allied intelligence capabilities. In essence, the potential of the drone has not yet been fully utilized. This paper presents feasible methods to build an intelligent drone with smart capabilities such as self-driving, and obstacle avoidance. It does this through advanced Reinforcement Learning Techniques and performs object detection using latest advanced algorithms, which are capable of processing light weight models with fast training in real time instances. For the scope of this paper, after researching on the various algorithms and comparing them, we finally implemented the Deep-Q-Networks (DQN) algorithm in the AirSim Simulator. In future works, we plan to implement further advanced self-driving and object detection algorithms, we also plan to implement voice-based speech recognition for the entire drone operation which would provide an option of speech communication between users (People) and the drone in the time of unavoidable circumstances. Thus, making drones an interactive intelligent Robotic Voice Enabled Service Assistant. This proposed drone has a wide scope of usability and is applicable in scenarios such as Disaster management, Air Transport of essentials, Agriculture, Manufacturing, Monitoring people movements in public area, and Defense. Also discussed, is the entire drone communication based on the satellite broadband Internet technology for faster computation and seamless communication service for uninterrupted network during disasters and remote location operations. This paper will explain the feasible algorithms required to go about achieving this goal and is more of a reference paper for future researchers going down this path.Keywords: convolution neural network, natural language processing, obstacle avoidance, satellite broadband technology, self-driving
Procedia PDF Downloads 242166 Personalizing Human Physical Life Routines Recognition over Cloud-based Sensor Data via AI and Machine Learning
Authors: Kaushik Sathupadi, Sandesh Achar
Abstract:
Pervasive computing is a growing research field that aims to acknowledge human physical life routines (HPLR) based on body-worn sensors such as MEMS sensors-based technologies. The use of these technologies for human activity recognition is progressively increasing. On the other hand, personalizing human life routines using numerous machine-learning techniques has always been an intriguing topic. In contrast, various methods have demonstrated the ability to recognize basic movement patterns. However, it still needs to be improved to anticipate the dynamics of human living patterns. This study introduces state-of-the-art techniques for recognizing static and dy-namic patterns and forecasting those challenging activities from multi-fused sensors. Further-more, numerous MEMS signals are extracted from one self-annotated IM-WSHA dataset and two benchmarked datasets. First, we acquired raw data is filtered with z-normalization and denoiser methods. Then, we adopted statistical, local binary pattern, auto-regressive model, and intrinsic time scale decomposition major features for feature extraction from different domains. Next, the acquired features are optimized using maximum relevance and minimum redundancy (mRMR). Finally, the artificial neural network is applied to analyze the whole system's performance. As a result, we attained a 90.27% recognition rate for the self-annotated dataset, while the HARTH and KU-HAR achieved 83% on nine living activities and 90.94% on 18 static and dynamic routines. Thus, the proposed HPLR system outperformed other state-of-the-art systems when evaluated with other methods in the literature.Keywords: artificial intelligence, machine learning, gait analysis, local binary pattern (LBP), statistical features, micro-electro-mechanical systems (MEMS), maximum relevance and minimum re-dundancy (MRMR)
Procedia PDF Downloads 9