Search results for: deep convolution networks

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 196

Authors: Tomas Premoli, Sareh Rowlands

Abstract:

In this study, we investigate the impact of various convolutional neural network (CNN) architectures on the accuracy of diagnosing Alzheimer’s disease (AD) using patient MRI scans. Alzheimer’s disease is a debilitating neurodegenerative disorder that affects millions worldwide. Early, accurate, and non-invasive diagnostic methods are required for providing optimal care and symptom management. Deep learning techniques, particularly CNNs, have shown great promise in enhancing this diagnostic process. We aim to contribute to the ongoing research in this field by comparing the effectiveness of different CNN architectures and providing insights for future studies. Our methodology involved preprocessing MRI data, implementing multiple CNN architectures, and evaluating the performance of each model. We employed intensity normalization, linear registration, and skull stripping for our preprocessing. The selected architectures included VGG, ResNet, and DenseNet models, all implemented using the Keras library. We employed transfer learning and trained models from scratch to compare their effectiveness. Our findings demonstrated significant differences in performance among the tested architectures, with DenseNet201 achieving the highest accuracy of 86.4%. Transfer learning proved to be helpful in improving model performance. We also identified potential areas for future research, such as experimenting with other architectures, optimizing hyperparameters, and employing fine-tuning strategies. By providing a comprehensive analysis of the selected CNN architectures, we offer a solid foundation for future research in Alzheimer’s disease diagnosis using deep learning techniques. Our study highlights the potential of CNNs as a valuable diagnostic tool and emphasizes the importance of ongoing research to develop more accurate and effective models.

Keywords: Alzheimer’s disease, convolutional neural networks, deep learning, medical imaging, MRI

Procedia PDF Downloads 74

Authors: Tolga Yazıcı

Abstract:

As a matter of the fact that online social networks like Twitter, Facebook and MySpace have experienced an extensive growth in recent years. Social media offers individuals with a tool for communicating and interacting with one another. These social networks enable people to stay in touch with other people and express themselves. This process makes the users of online social networks active creators of content rather than being only consumers of traditional media. That’s why millions of people show strong desire to learn the methods and tools of digital content production and necessary communication skills. However, the booming interest in communication and interaction through online social networks and high level of eagerness to invent and implement the ways to participate in content production raise some privacy and security concerns. This presentation aims to open the assumed revolutionary, democratic and liberating nature of the online social media up for discussion by reviewing some recent political developments in Turkey. Firstly, the role of Internet and online social networks in mobilizing collective movements through social interactions and communications will be questioned. Secondly, some cases from Gezi and Okmeydanı Protests and also December 17-25 period will be presented in order to illustrate misinformation and manipulation in social media and violation of individual privacy through online social networks in order to damage social unity and stability contradictory to democratic nature of online social networking.

Keywords: online social media networks, democratic participation, social movements, social polarization, privacy of individuals, Turkey

Procedia PDF Downloads 343

Authors: Jun Ming Moey, Zhiyaun Chen, David Nicholson

Abstract:

Bad actors are often hard to detect in data that imprints their behaviour patterns because they are comparatively rare events embedded in non-bad actor data. An unsupervised machine learning framework is applied here to detect bad actors in financial crime datasets that record millions of transactions undertaken by hundreds of actors (<0.01% bad). Specifically, the framework combines ‘shallow’ (PCA, Isolation Forest) and ‘deep’ (Autoencoder) methods to detect outlier patterns. Detection performance analysis for both the individual methods and their combination is reported.

Keywords: detection, machine learning, deep learning, unsupervised, outlier analysis, data science, fraud, financial crime

Procedia PDF Downloads 96

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 75

Authors: Li Qingjian, Li Ke, He Chun, Huang Yong

Abstract:

In this paper, the method of combining the Pohl Seidman's deep belief network with the self-organizing neural network is proposed to classify the target. This method is mainly aimed at the high nonlinearity of the hyperspectral image, the high sample dimension and the difficulty in designing the classifier. The main feature of original data is extracted by deep belief network. In the process of extracting features, adding known labels samples to fine tune the network, enriching the main characteristics. Then, the extracted feature vectors are classified into the self-organizing neural network. This method can effectively reduce the dimensions of data in the spectrum dimension in the preservation of large amounts of raw data information, to solve the traditional clustering and the long training time when labeled samples less deep learning algorithm for training problems, improve the classification accuracy and robustness. Through the data simulation, the results show that the proposed network structure can get a higher classification precision in the case of a small number of known label samples.

Keywords: DBN, SOM, pattern classification, hyperspectral, data compression

Procedia PDF Downloads 341

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 116

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 132

Authors: Danilo López, Johana Hernández, Edwin Rivas

Abstract:

The use of the Multilayer Perceptron Neural Networks (MLPNN) technique is presented to estimate the future state of use of a licensed channel by primary users (PUs); this will be useful at the spectral decision stage in cognitive radio networks (CRN) to determine approximately in which time instants of future may secondary users (SUs) opportunistically use the spectral bandwidth to send data through the primary wireless network. To validate the results, sequences of occupancy data of channel were generated by simulation. The results show that the prediction percentage is greater than 60% in some of the tests carried out.

Keywords: cognitive radio, neural network, prediction, primary user

Procedia PDF Downloads 372

Authors: Agoubi Belgacem, Adel Kharroubi

Abstract:

Geothermal groundwater is the main water source to supply various sectors in El Hamma city, southeastern Tunisia. This region was long the destination of thousands of people from Tunisia and neighboring countries for care and bathing. The main objective of this study is to understand the groundwater mineralization origins and factors that control. The second goal is the appraisal of radon in geothermal groundwater in the study area. For this aim, geothermal groundwater was sampled and collected from different locations (thermal baths and deep wells). Physical parameters were measured and major ions were analyzed. Results reveal three water types. The water first type has Na-Mg-Ca-SO4-Cl facies and T>55°C. The second water type dominated by Na-Ca-Cl-SO4 facies with a temperature < 45 °C. However the third water type is dominated by Ca-SO4-Na-Cl-Mg. The three water types may be controlled by depth and geology. The first represent groundwater from deep aquifer (lower cretaceous), the second type was the shallow aquifer and the first is mixed water from deep and shallow water with a temperature ranging from 45 to 55°C. Measured Radon shows that shallow aquifer has a higher 222Rn concentration (677 to 2903 Bq.m-3) than deep water (203 to 1100 Bq.m-3). R-222 in El Hamma thermal aquifer was controlled by structures, porosity and permeability of aquifers. Geostatistical analyses of hydrogeological data and radon activities confirm the vertical flow and communication between deep and shallow aquifers through vertical faults system.

Keywords: Radon-222, geothermal, water, environment, Tunisia

Procedia PDF Downloads 362

Authors: Manuel Meranza-Castillon, Rolando Diaz-Castillo, Adrian Arellano-Delgado, Cesar Cruz-Hernandez, Rosa Martha Lopez-Gutierrez

Abstract:

In this work, we deal with experimental network synchronization of chaotic nodes with different topologies. Our approach is based on complex system theory, and we use a master-slave configuration to couple the nodes in the networks. In particular, we design and implement electronically complex dynamical networks composed by nine coupled chaotic Chua’s circuits with topologies: in nearest-neighbor, small-world, open ring, star, and global. Also, network synchronization is evaluated according to a particular coupling strength for each topology. This study is important by the possible applications to private transmission of information in a chaotic communication network of multiple users.

Keywords: complex networks, Chua's circuit, experimental synchronization, multiple users

Procedia PDF Downloads 350

Authors: Elaheh Vaezpour

Abstract:

Data sensing in wireless sensor networks is done by query deceleration the network by the users. In many applications of the wireless sensor networks, many users send queries to the network simultaneously. If the queries are processed separately, the network’s energy consumption will increase significantly. Therefore, it is very important to aggregate the queries before sending them to the network. In this paper, we propose a multiple query optimization framework based on sensors physical and temporal correlation. In the proposed method, queries are merged and sent to network by considering correlation among the sensors in order to reduce the communication cost between the sensors and the base station.

Keywords: wireless sensor networks, multiple query optimization, data correlation, reducing energy consumption

Procedia PDF Downloads 336

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 120

Authors: S. Adjiri-Bailiche, S. M. Boudia, H. Daaou, S. Hadouche, A. Benzaoui

Abstract:

In this work the study of changes in the wind speed depending on the altitude is calculated and described by the model of the neural networks, the use of measured data, the speed and direction of wind, temperature and the humidity at 10 m are used as input data and as data targets at 50m above sea level. Comparing predict wind speeds and extrapolated at 50 m above sea level is performed. The results show that the prediction by the method of artificial neural networks is very accurate.

Keywords: MATLAB, neural network, power low, vertical extrapolation, wind energy, wind speed

Procedia PDF Downloads 694

Authors: Shunzuo Wu, Xudong Luo, Yuanxiu Liao

Abstract:

Recently, the rapid development of deep learning makes artificial intelligence (AI) penetrate into many fields, replacing manual work there. In particular, AI systems also become a research focus in the field of automatic office. To meet real needs in automatic officiating, in this paper we develop an automatic form filling system. Specifically, it uses two classical neural network models and several word embedding models to classify various relevant information elicited from the Internet. When training the neural network models, we use less noisy and balanced data for training. We conduct a series of experiments to test my systems and the results show that our system can achieve better classification results.

Keywords: artificial intelligence and office, NLP, deep learning, text classification

Procedia PDF Downloads 202

Authors: Brinda Sharma, Saakshi S. Sarpotdar

Abstract:

Deep-fat frying is popular standard method that has been studied basically to clarify the complicated mechanisms of fat decomposition at high temperatures and to assess their effects on human health. The aim of this paper is to point out the application of method engineering that has been recently improved our understanding of the fundamental principles and mechanisms concerned at different scales and different times throughout the process: pretreatment, frying, and cooling. It covers the several aspects of deep-fat drying. New results regarding the understanding of the frying method that are obtained as a results of major breakthroughs in on-line instrumentation (heat, steam flux, and native pressure sensors), within the methodology of microstructural and imaging analysis (NMR, MRI, SEM) and in software system tools for the simulation of coupled transfer and transport phenomena. Such advances have opened the approach for the creation of significant information of the behavior of varied materials and to the event of latest tools to manage frying operations via final product quality in real conditions. Lastly, this paper promotes an integrated approach to the frying method as well as numerous competencies like those of chemists, engineers, toxicologists, nutritionists, and materials scientists also as of the occupation and industrial sectors.

Keywords: frying, cooling, imaging analysis (NMR, MRI, SEM), deep-fat frying

Procedia PDF Downloads 430

Authors: Engin Eyceyurt, Josko Zec

Abstract:

The current and future cellular mobile communication networks generate enormous amounts of data. Networks have become extremely complex with extensive space of parameters, features and counters. These networks are unmanageable with legacy methods and an enhanced design and optimization approach is necessary that is increasingly reliant on machine learning. This paper proposes that machine learning as a viable approach for uplink throughput prediction. LTE radio metric, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Noise Ratio (SNR) are used to train models to estimate expected uplink throughput. The prediction accuracy with high determination coefficient of 91.2% is obtained from measurements collected with a simple smartphone application.

Keywords: drive test, LTE, machine learning, uplink throughput prediction

Procedia PDF Downloads 158

Authors: T. Zaki, Fathi S. Soliman

Abstract:

Desulfurization process is required by most, if not all refineries, to achieve ultra-low sulfur fuel, that contains less than 10 ppm sulfur. A lot of research works and many effective technologies have been studied to achieve deep desulfurization process in moderate reaction environment, such as adsorption desulfurization (ADS), oxidative desulfurization (ODS), biodesulfurization and extraction desulfurization (EDS). Extraction desulfurization using deep eutectic solvents (DESs) is considered as simple, cheap, highly efficient and environmentally friend process. In this work, four DESs were designed and synthesized. Choline chloride (ChCl) was selected as typical hydrogen bond acceptors (HBA), and ethylene glycol (EG), glycerol (Gl), urea (Ur) and thiourea (Tu) were selected as hydrogen bond donors (HBD), from which a series of deep eutectic solvents were synthesized. The experimental data showed that the synthesized DESs showed desulfurization affinities towards the thiophene species in cyclohexane solvent. Ethylene glycol molecules showed more affinity to create hydrogen bond with thiophene instead of choline chloride. Accordingly, ethylene glycol choline chloride DES has the highest extraction efficiency.

Keywords: DES, desulfurization, green solvent, extraction

Procedia PDF Downloads 289

Authors: Fatma El-Zahraa El-Taher, Ayman Taha, Jane Courtney, Susan Mckeever

Abstract:

Understanding road networks plays an important role in navigation applications such as self-driving vehicles and route planning for individual journeys. Intersections of roads are essential components of road networks. Understanding the features of an intersection, from a simple T-junction to larger multi-road junctions, is critical to decisions such as crossing roads or selecting the safest routes. The identification and profiling of intersections from satellite images is a challenging task. While deep learning approaches offer the state-of-the-art in image classification and detection, the availability of training datasets is a bottleneck in this approach. In this paper, a labelled satellite image dataset for the intersection recognition problem is presented. It consists of 14,692 satellite images of Washington DC, USA. To support other users of the dataset, an automated download and labelling script is provided for dataset replication. The challenges of construction and fine-grained feature labelling of a satellite image dataset is examined, including the issue of how to address features that are spread across multiple images. Finally, the accuracy of the detection of intersections in satellite images is evaluated.

Keywords: satellite images, remote sensing images, data acquisition, autonomous vehicles

Procedia PDF Downloads 147

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 341

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 145

Authors: Paola Causin, Andrea Aspri, Alessandro Benfenati

Abstract:

Diffuse Optical Tomography (DOT) is an emergent medical imaging technique which employs NIR light to estimate the spatial distribution of optical coefficients in biological tissues for diagnostic purposes, in a noninvasive and non-ionizing manner. DOT reconstruction is a severely ill-conditioned problem due to prevalent scattering of light in the tissue. In this contribution, we present our research in adopting hybrid knowledgedriven/data-driven approaches which exploit the existence of well assessed physical models and build upon them neural networks integrating the availability of data. Namely, since in this context regularization procedures are mandatory to obtain a reasonable reconstruction [1], we explore the use of neural networks as tools to include prior information on the solution. 2. Materials and Methods The idea underlying our approach is to leverage neural networks to solve PDE-constrained inverse problems of the form 𝒒 ∗ = 𝒂𝒓𝒈 𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃), (1) where D is a loss function which typically contains a discrepancy measure (or data fidelity) term plus other possible ad-hoc designed terms enforcing specific constraints. In the context of inverse problems like (1), one seeks the optimal set of physical parameters q, given the set of observations y. Moreover, 𝑦̃ is the computable approximation of y, which may be as well obtained from a neural network but also in a classic way via the resolution of a PDE with given input coefficients (forward problem, Fig.1 box ). Due to the severe ill conditioning of the reconstruction problem, we adopt a two-fold approach: i) we restrict the solutions (optical coefficients) to lie in a lower-dimensional subspace generated by auto-decoder type networks. This procedure forms priors of the solution (Fig.1 box ); ii) we use regularization procedures of type 𝒒̂ ∗ = 𝒂𝒓𝒈𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃)+ 𝑹(𝒒), where 𝑹(𝒒) is a regularization functional depending on regularization parameters which can be fixed a-priori or learned via a neural network in a data-driven modality. To further improve the generalizability of the proposed framework, we also infuse physics knowledge via soft penalty constraints (Fig.1 box ) in the overall optimization procedure (Fig.1 box ). 3. Discussion and Conclusion DOT reconstruction is severely hindered by ill-conditioning. The combined use of data-driven and knowledgedriven elements is beneficial and allows to obtain improved results, especially with a restricted dataset and in presence of variable sources of noise.

Keywords: inverse problem in tomography, deep learning, diffuse optical tomography, regularization

Procedia PDF Downloads 75

Authors: Motahareh Fadaei

Abstract:

Wireless sensor networks that are used to monitor a special environment, are formed from a large number of sensor nodes. The role of these sensors is to sense special parameters from ambient and to make connection. In these networks, the most important challenge is the management of energy usage. Clustering is one of the methods that are broadly used to face this challenge. In this paper, a distributed clustering protocol based on learning automata is proposed for underwater wireless sensor networks. The proposed algorithm that is called LA-Clustering forms clusters in the same energy level, based on the energy level of nodes and the connection radius regardless of size and the structure of sensor network. The proposed approach is simulated and is compared with some other protocols with considering some metrics such as network lifetime, number of alive nodes, and number of transmitted data. The simulation results demonstrate the efficiency of the proposed approach.

Keywords: clustering, energy consumption‎, learning automata, underwater sensor networks

Procedia PDF Downloads 317

Authors: A. S. Issa, S. K. Q. AL-Omari

Abstract:

In this paper, we investigate certain spaces of generalized functions for the Fourier and Fourier type integral transforms. We discuss convolution theorems and establish certain spaces of distributions for the considered integrals. The new Fourier type integral is well-defined, linear, one-to-one and continuous with respect to certain types of convergences. Many properties and an inverse problem are also discussed in some details.

Keywords: Boehmian, Fourier integral, Fourier type integral, generalized quotient

Procedia PDF Downloads 367

Authors: Sara Alshehri, Bayan Alenzi, Atheer Alshehri, Samia Chelloug, Zainab Almry, Hussah Albugmai

Abstract:

This paper concerns body area networks sensor that collect signals around a human body. The black hole attacks are the main security challenging problem because the data traffic can be dropped at any node. The focus of our proposed solution is to efficiently route data packets while detecting black hole nodes.

Keywords: body sensor networks, security, black hole, routing, broadcasting, OMNeT++

Procedia PDF Downloads 647

Authors: C. N. Vanitha, M. Usha

Abstract:

In a real world scenario, the viability of the sensor networks has been proved by standardizing the technologies. Wireless sensor networks are vulnerable to both electronic and physical security breaches because of their deployment in remote, distributed, and inaccessible locations. The compromised sensor nodes send malicious data to the base station, and thus, the total network effectiveness will possibly be compromised. To detect and seclude the Route modifiers, a neural network based Pattern Learning predictor (PLP) is presented. This algorithm senses data at any node on present and previous patterns obtained from the en-route nodes. The eminence of any node is upgraded by their predicted and reported patterns. This paper propounds a solution not only to detect the route modifiers, but also to seclude the malevolent nodes from the network. The simulation result proves the effective performance of the network by the presented methodology in terms of energy level, routing and various network conditions.

Keywords: neural networks, pattern learning, security, wireless sensor networks

Procedia PDF Downloads 405

Authors: Ananya Gangavarapu

Abstract:

Convolutional Neural Networks (CNN) based models are providing diagnostic capabilities on par with the medical specialists in many specialty areas. However, collecting the medical data for training purposes is very challenging because of the increased regulations around data collections and privacy concerns around personal health data. The gathering of the data becomes even more difficult if the capture devices are edge-based mobile devices (like smartphones) with feeble wireless connectivity in rural/remote areas. In this paper, I would like to highlight Federated Learning approach to mitigate data privacy and security issues.

Keywords: deep learning in healthcare, data privacy, federated learning, training in distributed environment

Procedia PDF Downloads 142

Authors: Myriam Ferreira

Abstract:

Websites and social networks allow museums to divulge their works by new and attractive means. Besides, these technologies provide tools to generate a new history of art’s contents and promote visits to their installations. At the same time, museums are proposing more and more activities to families, children and young people. However, these activities usually take place in the museum’s physical installations, while websites and social networks seem to be mainly targeted to adults. The problem is that being children and young people digital natives, they feel apart from museums, so they need a presence of museums in digital means to feel attracted to them. Some institutions are making efforts to fill this vacuum. In this paper, resources designed specifically for children and teenagers have been selected from websites and social networks of five Spanish Museums: Prado Museum, Thyssen Museum, Guggenheim Museum, America Museum and Cerralbo Museum. After that, we have carried out an investigation in a school with children and teenagers between 11 and 15 years old. Those young people have been asked about their valuation of those web pages and social networks, with quantitative-qualitative questions. The results show that the least rated resources were videos and social networks because they were considered ‘too serious’, while the most rated were games and augmented reality. These ratings confirm theoretical papers that affirm that the future of technologies applied to museums is edutainment and interaction.

Keywords: children, museums, social networks, teenagers, websites

Procedia PDF Downloads 153

Authors: Dingyang Hu, Dan Liu

Abstract:

DNN (Deep Neural Network) deep learning models are widely used in classification, prediction, and other task scenarios. To address the difficulties of generic adversarial perturbation generation for deep learning models under black-box conditions, a generic adversarial ingestion generation method based on a saliency map (CJsp) is proposed to obtain salient image regions by counting the factors that influence the input features of an image on the output results. This method can be understood as a saliency map attack algorithm to obtain false classification results by reducing the weights of salient feature points. Experiments also demonstrate that this method can obtain a high success rate of migration attacks and is a batch adversarial sample generation method.

Keywords: adversarial sample, gradient, probability, black box

Procedia PDF Downloads 105

Authors: Chung-Yuan Huang, Yu-Hsiang Fu, Chuen-Tsai Sun

Abstract:

Community detection represents an important data-mining tool for analyzing and understanding real-world complex network structures and functions. We believe that at least four criteria determine the appropriateness of a community detection algorithm: (a) it produces useable normalized mutual information (NMI) and modularity results for social networks, (b) it overcomes resolution limitation problems associated with synthetic networks, (c) it produces good NMI results and performance efficiency for Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks, and (d) it produces good modularity and performance efficiency for large-scale real-world complex networks. To our knowledge, no existing community detection algorithm meets all four criteria. In this paper, we describe a simple hierarchical arc-merging (HAM) algorithm that uses network topologies and rule-based arc-merging strategies to identify community structures that satisfy the criteria. We used five well-studied social network datasets and eight sets of LFR benchmark networks to validate the ground-truth community correctness of HAM, eight large-scale real-world complex networks to measure its performance efficiency, and two synthetic networks to determine its susceptibility to resolution limitation problems. Our results indicate that the proposed HAM algorithm is capable of providing satisfactory performance efficiency and that HAM-identified communities were close to ground-truth communities in social and LFR benchmark networks while overcoming resolution limitation problems.

Keywords: complex network, social network, community detection, network hierarchy

Procedia PDF Downloads 229