Search results for: time delay neural network

Authors: Sina Saadati

Abstract:

Multiprocessors Systems-On-Chips (MPSOCs) are used widely on modern computers to execute sophisticated software and applications. These systems include different processors for distinct aims. Most of the proposed task schedulers attempt to improve energy consumption. In some schedulers, the processor's temperature is considered to increase the system's reliability and performance. In this research, we have proposed a new method for thermal-aware task scheduling which is based on an artificial neural network (ANN). This method enables us to consider a variety of factors in the scheduling process. Some factors like ambient temperature, season (which is important for some embedded systems), speed of the processor, computing type of tasks and have a complex relationship with the final temperature of the system. This Issue can be solved using a machine learning algorithm. Another point is that our solution makes the system intelligent So that It can be adaptive. We have also shown that the computational complexity of the proposed method is cheap. As a consequence, It is also suitable for battery-powered systems.

Keywords: task scheduling, MOSOC, artificial neural network, machine learning, architecture of computers, artificial intelligence

Procedia PDF Downloads 103

Authors: Said Benkaciali, Mourad Haddadi, Abdallah Khellaf, Kacem Gairaa, Mawloud Guermoui

Abstract:

In this study, many experiments were carried out to assess the influence of the input parameters on the performance of multilayer perceptron which is one the configuration of the artificial neural networks. To estimate the daily global solar radiation on the horizontal surface, we have developed some models by using seven combinations of twelve meteorological and geographical input parameters collected from a radiometric station installed at Ghardaïa city (southern of Algeria). For selecting of best combination which provides a good accuracy, six statistical formulas (or statistical indicators) have been evaluated, such as the root mean square errors, mean absolute errors, correlation coefficient, and determination coefficient. We noted that multilayer perceptron techniques have the best performance, except when the sunshine duration parameter is not included in the input variables. The maximum of determination coefficient and correlation coefficient are equal to 98.20 and 99.11%. On the other hand, some empirical models were developed to compare their performances with those of multilayer perceptron neural networks. Results obtained show that the neural networks techniques give the best performance compared to the empirical models.

Keywords: empirical models, multilayer perceptron neural network, solar radiation, statistical formulas

Procedia PDF Downloads 345

Authors: Stephen L. Green, Alexander N. Gorban, Ivan Y. Tyukin

Abstract:

Within the past decade, using Convolutional Neural Networks (CNN)’s to create Deep Learning systems capable of translating Sign Language into text has been a breakthrough in breaking the communication barrier for deaf-mute people. Conventional research on this subject has been concerned with training the network to recognize the fingerspelling gestures of a given language and produce their corresponding alphanumerics. One of the problems with the current developing technology is that images are scarce, with little variations in the gestures being presented to the recognition program, often skewed towards single skin tones and hand sizes that makes a percentage of the population’s fingerspelling harder to detect. Along with this, current gesture detection programs are only trained on one finger spelling language despite there being one hundred and forty-two known variants so far. All of this presents a limitation for traditional exploitation for the state of current technologies such as CNN’s, due to their large number of required parameters. This work aims to present a technology that aims to resolve this issue by combining a pretrained legacy AI system for a generic object recognition task with a corrector method to uptrain the legacy network. This is a computationally efficient procedure that does not require large volumes of data even when covering a broad range of sign languages such as American Sign Language, British Sign Language and Chinese Sign Language (Pinyin). Implementing recent results on method concentration, namely the stochastic separation theorem, an AI system is supposed as an operate mapping an input present in the set of images u ∈ U to an output that exists in a set of predicted class labels q ∈ Q of the alphanumeric that q represents and the language it comes from. These inputs and outputs, along with the interval variables z ∈ Z represent the system’s current state which implies a mapping that assigns an element x ∈ ℝⁿ to the triple (u, z, q). As all xi are i.i.d vectors drawn from a product mean distribution, over a period of time the AI generates a large set of measurements xi called S that are grouped into two categories: the correct predictions M and the incorrect predictions Y. Once the network has made its predictions, a corrector can then be applied through centering S and Y by subtracting their means. The data is then regularized by applying the Kaiser rule to the resulting eigenmatrix and then whitened before being split into pairwise, positively correlated clusters. Each of these clusters produces a unique hyperplane and if any element x falls outside the region bounded by these lines then it is reported as an error. As a result of this methodology, a self-correcting recognition process is created that can identify fingerspelling from a variety of sign language and successfully identify the corresponding alphanumeric and what language the gesture originates from which no other neural network has been able to replicate.

Keywords: convolutional neural networks, deep learning, shallow correctors, sign language

Procedia PDF Downloads 100

Authors: Hani Baek, Gwang Min Sun, Chansun Shin, Sung Ho Ahn

Abstract:

Fast neutron irradiation using nuclear reactors is an effective method to improve switching loss and short circuit durability of power semiconductor (insulated gate bipolar transistors (IGBT) and insulated gate transistors (IGT), etc.). However, not only fast neutrons but also thermal neutrons, epithermal neutrons and gamma exist in the nuclear reactor. And the electrical properties of the IGBT may be deteriorated by the irradiation of gamma. Gamma irradiation damages are known to be caused by Total Ionizing Dose (TID) effect and Single Event Effect (SEE), Displacement Damage. Especially, the TID effect deteriorated the electrical properties such as leakage current and threshold voltage of a power semiconductor. This work can confirm the effect of the gamma irradiation on the electrical properties of 600 V NPT-IGBT. Irradiation of gamma forms lattice defects in the gate oxide and Si-SiO₂ interface of the IGBT. It was confirmed that this lattice defect acts on the center of the trap and affects the threshold voltage, thereby negatively shifted the threshold voltage according to TID. In addition to the change in the carrier mobility, the conductivity modulation decreases in the n-drift region, indicating a negative influence that the forward voltage drop decreases. The turn-off delay time of the device before irradiation was 212 ns. Those of 2.5, 10, 30, 70 and 100 kRad(Si) were 225, 258, 311, 328, and 350 ns, respectively. The gamma irradiation increased the turn-off delay time of the IGBT by approximately 65%, and the switching characteristics deteriorated.

Keywords: NPT-IGBT, gamma irradiation, switching, turn-off delay time, recombination, trap center

Procedia PDF Downloads 155

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long short-term memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: dialogue management, response generation, deep learning, evaluation

Procedia PDF Downloads 167

Authors: C. S. Subhashini, H. L. Premaratne

Abstract:

Landslides are the most recurrent and prominent disaster in Sri Lanka. Sri Lanka has been subjected to a number of extreme landslide disasters that resulted in a significant loss of life, material damage, and distress. It is required to explore a solution towards preparedness and mitigation to reduce recurrent losses associated with landslides. Artificial Neural Networks (ANNs) and Hidden Markov Model (HMMs) are now widely used in many computer applications spanning multiple domains. This research examines the effectiveness of using Artificial Neural Networks and Hidden Markov Model in landslides predictions and the possibility of applying the modern technology to predict landslides in a prominent geographical area in Sri Lanka. A thorough survey was conducted with the participation of resource persons from several national universities in Sri Lanka to identify and rank the influencing factors for landslides. A landslide database was created using existing topographic; soil, drainage, land cover maps and historical data. The landslide related factors which include external factors (Rainfall and Number of Previous Occurrences) and internal factors (Soil Material, Geology, Land Use, Curvature, Soil Texture, Slope, Aspect, Soil Drainage, and Soil Effective Thickness) are extracted from the landslide database. These factors are used to recognize the possibility to occur landslides by using an ANN and HMM. The model acquires the relationship between the factors of landslide and its hazard index during the training session. These models with landslide related factors as the inputs will be trained to predict three classes namely, ‘landslide occurs’, ‘landslide does not occur’ and ‘landslide likely to occur’. Once trained, the models will be able to predict the most likely class for the prevailing data. Finally compared two models with regards to prediction accuracy, False Acceptance Rates and False Rejection rates and This research indicates that the Artificial Neural Network could be used as a strong decision support system to predict landslides efficiently and effectively than Hidden Markov Model.

Keywords: landslides, influencing factors, neural network model, hidden markov model

Procedia PDF Downloads 384

Authors: Shaik Jilani Basha, Inavolu Avinash, Alla Venu Sai Reddy, Bitragunta Taraka Ramu

Abstract:

We can use the neural style transfer technique to build a picture with the same "content" as the beginning image but the "style" of the picture we've chosen. Neural style transfer is a technique for merging the style of one image into another while retaining its original information. The only change is how the image is formatted to give it an additional artistic sense. The content image depicts the plan or drawing, as well as the colors of the drawing or paintings used to portray the style. It is a computer vision programme that learns and processes images through deep convolutional neural networks. To implement software, we used to train deep learning models with the train data, and whenever a user takes an image and a styled image, the output will be as the style gets transferred to the original image, and it will be shown as the output.

Keywords: neural networks, computer vision, deep learning, convolutional neural networks

Procedia PDF Downloads 95

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 160

Authors: Bhavini Pandya

Abstract:

This paper considers Hη: T2 → T2 the Perturbed Cerbelli-Giona map. That is a family of 2-dimensional nonlinear area-preserving transformations on the torus T2=[0,1]×[0,1]= ℝ2/ ℤ2. A single parameter η varies between 0 and 1, taking the transformation from a hyperbolic toral automorphism to the “Cerbelli-Giona” map, a system known to exhibit multifractal properties. Here we study the multifractal properties of the family of maps. We apply a box-counting method by defining a grid of boxes Bi(δ), where i is the index and δ is the size of the boxes, to quantify the distribution of stable and unstable manifolds of the map. When the parameter is in the range 0.51< η <0.58 and 0.68< η <1 the map is ergodic; i.e., the unstable and stable manifolds eventually cover the whole torus, although not in a uniform distribution. For accurate numerical results we require correspondingly accurate construction of the stable and unstable manifolds. Here we use the piecewise linearity of the map to achieve this, by computing the endpoints of line segments which define the global stable and unstable manifolds. This allows the generalized fractal dimension Dq, and spectrum of dimensions f(α), to be computed with accuracy. Finally, the intersection of the unstable and stable manifold of the map will be investigated, and compared with the distribution of periodic points of the system.

Keywords: feed forward, gradient descent, neural network, integral equation

Procedia PDF Downloads 188

Authors: Syed Mahbubuz Zaman, A. B. M. Abrar Haque, Mehedi Hassan Nayeem, Misbah Uddin Sagor

Abstract:

Everyday e-mails are being used by millions of people as an effective form of communication over the Internet. Although e-mails allow high-speed communication, there is a constant threat known as spam. Spam e-mail is often called junk e-mails which are unsolicited and sent in bulk. These unsolicited emails cause security concerns among internet users because they are being exposed to inappropriate content. There is no guaranteed way to stop spammers who use static filters as they are bypassed very easily. In this paper, a smart system is proposed that will be using neural networks to approach spam in a different way, and meanwhile, this will also detect the most relevant features that will help to design the spam filter. Also, a comparison of different parameters for different neural network models has been shown to determine which model works best within suitable parameters.

Keywords: long short-term memory, bidirectional long short-term memory, gated recurrent unit, natural language processing, natural language processing

Procedia PDF Downloads 205

Authors: Redvan Ghasemlounia, Elham Ansari, Hikmet Kerem Cigizoglu

Abstract:

Hydrological modeling in arid and semi-arid regions is very important. Iran has many regions with these climate conditions such as Chaharmahal and Bakhtiari province that needs lots of attention with an appropriate management. Forecasting of hydrological parameters and estimation of hydrological events of catchments, provide important information that used for design, management and operation of water resources such as river systems, and dams, widely. Discharge in rivers is one of these parameters. This study presents the application and comparison of some estimation methods such as Feed-Forward Back Propagation Neural Network (FFBPNN), Multi Linear Regression (MLR), Gene Expression Programming (GEP) and Bayesian Network (BN) to predict the daily flow discharge of the Soolegan River, located at Chaharmahal and Bakhtiari province, in Iran. In this study, Soolegan, station was considered. This Station is located in Soolegan River at 51° 14՜ Latitude 31° 38՜ longitude at North Karoon basin. The Soolegan station is 2086 meters higher than sea level. The data used in this study are daily discharge and daily precipitation of Soolegan station. Feed Forward Back Propagation Neural Network(FFBPNN), Multi Linear Regression (MLR), Gene Expression Programming (GEP) and Bayesian Network (BN) models were developed using the same input parameters for Soolegan's daily discharge estimation. The results of estimation models were compared with observed discharge values to evaluate performance of the developed models. Results of all methods were compared and shown in tables and charts.

Keywords: ANN, multi linear regression, Bayesian network, forecasting, discharge, gene expression programming

Procedia PDF Downloads 561

Authors: Shibo Wei, Ting Jiang

Abstract:

Convolutional-recurrent neural networks (CRN) have achieved much success recently in the speech enhancement field. The common processing method is to use the convolution layer to compress the feature space by multiple upsampling and then model the compressed features with the LSTM layer. At last, the enhanced speech is obtained by deconvolution operation to integrate the global information of the speech sequence. However, the feature space compression process may cause the loss of information, so we propose to model the upsampling result of each step with the residual LSTM layer, then join it with the output of the deconvolution layer and input them to the next deconvolution layer, by this way, we want to integrate the global information of speech sequence better. The experimental results show the network model (RES-CRN) we introduce can achieve better performance than LSTM without residual and overlaying LSTM simply in the original CRN in terms of scale-invariant signal-to-distortion ratio (SI-SNR), speech quality (PESQ), and intelligibility (STOI).

Keywords: convolutional-recurrent neural networks, speech enhancement, residual LSTM, SI-SNR

Procedia PDF Downloads 200

Authors: Ning Xue, Srinivas Merugu, Ignacio Delgado Martinez, Tao Sun, John Tsang, Shih-Cheng Yen

Abstract:

We have developed a polyimide based neural interface electrode to record nerve signals from the sciatic nerve of a rat. The neural interface electrode has a split-ring shape, with four protruding gold electrodes for recording, and two reference gold electrodes around the split-ring. The split-ring electrode can be opened up to encircle the sciatic nerve. The four electrodes can be bent to sit on top of the nerve and hold the device in position, while the split-ring frame remains flat. In comparison, while traditional cuff electrodes can only fit certain sizes of the nerve, the developed device can fit a variety of rat sciatic nerve dimensions from 0.6 mm to 1.0 mm, and adapt to the chronic changes in the nerve as the electrode tips are bendable. The electrochemical impedance spectroscopy measurement was conducted. The gold electrode impedance is on the order of 10 kΩ, showing excellent charge injection capacity to record neural signals.

Keywords: impedance, neural interface, split-ring electrode, neural signal recording

Procedia PDF Downloads 375

Authors: Mecheri Zeid Belmecheri, Maamar Ahfir, Izzet Kale

Abstract:

Automatic cardiac auscultation is still a subject of research in order to establish an objective diagnosis. Recorded heart sounds as Phonocardiogram signals (PCG) can be used for automatic segmentation into components that have clinical meanings. These are the first sound, S1, the second sound, S2, and the systolic and diastolic components, respectively. In this paper, an automatic method is proposed for the robust segmentation of heart sounds. This method is based on calculating an intermediate sawtooth-shaped signal from the length variation of the recorded Phonocardiogram (PCG) signal in the time domain and, using its positive derivative function that is a binary signal in training a Recurrent Neural Network (RNN). Results obtained in the context of a large database of recorded PCGs with their simultaneously recorded ElectroCardioGrams (ECGs) from different patients in clinical settings, including normal and abnormal subjects, show a segmentation testing performance average of 76 % sensitivity and 94 % specificity.

Keywords: heart sounds, PCG segmentation, event detection, recurrent neural networks, PCG curve length

Procedia PDF Downloads 178

Authors: Mahdi Bazarganigilani

Abstract:

Aortic enlargement, also known as an aortic aneurysm, can occur when the walls of the aorta become weak. This disease can become deadly if overlooked and undiagnosed. In this paper, a computer-aided diagnosis (CAD) system was introduced to accurately diagnose aortic enlargement from chest x-ray images. An enhanced convolutional neural network (CNN) was employed and then trained by transfer learning by using three different main areas from the original images. The areas included the left lung, heart, and right lung. The accuracy of the system was then evaluated on 1001 samples by using 4-fold cross-validation. A promising accuracy of 90% was achieved in terms of the F-measure indicator. The results showed using different areas from the original image in the training phase of CNN could increase the accuracy of predictions. This encouraged the author to evaluate this method on a larger dataset and even on different CAD systems for further enhancement of this methodology.

Keywords: computer-aided diagnosis systems, aortic enlargement, chest X-ray, image processing, convolutional neural networks

Procedia PDF Downloads 162

Authors: S. Curteanu, F. Leon, M. Gavrilescu, S. A. Floria

Abstract:

Optimization algorithms inspired from human behavior were applied in this approach, associated with neural networks models. The algorithms belong to human behaviors of learning and cooperation and human competitive behavior classes. For the first class, the main strategies include: random learning, individual learning, and social learning, and the selected algorithms are: simplified human learning optimization (SHLO), social learning optimization (SLO), and teaching-learning based optimization (TLBO). For the second class, the concept of learning is associated with competitiveness, and the selected algorithms are sports-inspired algorithms (with Football Game Algorithm, FGA and Volleyball Premier League, VPL) and Imperialist Competitive Algorithm (ICA). A real process, the synthesis of polyacrylamide-based multicomponent hydrogels, where some parameters are difficult to obtain experimentally, is considered as a case study. Reaction yield and swelling degree are predicted as a function of reaction conditions (acrylamide concentration, initiator concentration, crosslinking agent concentration, temperature, reaction time, and amount of inclusion polymer, which could be starch, poly(vinyl alcohol) or gelatin). The experimental results contain 175 data. Artificial neural networks are obtained in optimal form with biologically inspired algorithm; the optimization being perform at two level: structural and parametric. Feedforward neural networks with one or two hidden layers and no more than 25 neurons in intermediate layers were obtained with values of correlation coefficient in the validation phase over 0.90. The best results were obtained with TLBO algorithm, correlation coefficient being 0.94 for an MLP(6:9:20:2) – a feedforward neural network with two hidden layers and 9 and 20, respectively, intermediate neurons. Good results obtained prove the efficiency of the optimization algorithms. More than the good results, what is important in this approach is the simulation methodology, including neural networks and optimization biologically inspired algorithms, which provide satisfactory results. In addition, the methodology developed in this approach is general and has flexibility so that it can be easily adapted to other processes in association with different types of models.

Keywords: artificial neural networks, human behaviors of learning and cooperation, human competitive behavior, optimization algorithms

Procedia PDF Downloads 107

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 18

Authors: Houda Najeh, Stéphane Ploix, Mahendra Pratap Singh, Karim Chabir, Mohamed Naceur Abdelkrim

Abstract:

Building systems are highly vulnerable to different kinds of faults and failures. In fact, various faults, failures and human behaviors could affect the building performance. This paper tackles the detection of unreliable sensors in buildings. Different literature surveys on diagnosis techniques for sensor grids in buildings have been published but all of them treat only bias and outliers. Occurences of data gaps have also not been given an adequate span of attention in the academia. The proposed methodology comprises the automatic thresholding for data gap detection for a set of heterogeneous sensors in instrumented buildings. Sensor measurements are considered to be regular time series. However, in reality, sensor values are not uniformly sampled. So, the issue to solve is from which delay each sensor become faulty? The use of time series is required for detection of abnormalities on the delays. The efficiency of the method is evaluated on measurements obtained from a real power plant: an office at Grenoble Institute of technology equipped by 30 sensors.

Keywords: building system, time series, diagnosis, outliers, delay, data gap

Procedia PDF Downloads 245

Authors: Ahmadu Maidorawa, Kamalrulnizam Abu Bakar

Abstract:

This paper proposed an Enhanced Connectivity Aware Routing (ECAR) protocol for Vehicular Ad hoc Network (VANET). The protocol uses a control broadcast to reduce the number of overhead packets needed in a route discovery process. It is also equipped with an alternative backup route that is used whenever a primary path to destination failed, which highly reduces the frequent launching and re-launching of the route discovery process that waste useful bandwidth and unnecessarily prolonging the average packet delay. NS2 simulation results show that the performance of ECAR protocol outperformed the original connectivity aware routing (CAR) protocol by reducing the average packet delay by 28%, control overheads by 27% and increased the packet delivery ratio by 22%.

Keywords: alternative path, primary path, protocol, routing, VANET, vehicular ad hoc networks

Procedia PDF Downloads 402

Authors: G. Ravindranath, S. Savitha

Abstract:

This paper presents heat transfer analysis of single horizontal bare tube and heat transfer analysis of staggered arrangement of bare tube bundles bare tube bundles in gas-solid (air-solid) fluidized bed and predictions are done by using Artificial Neural Network (ANN) based on experimental data. Fluidized bed provide nearly isothermal environment with high heat transfer rate to submerged objects i.e. due to through mixing and large contact area between the gas and the particle, a fully fluidized bed has little temperature variation and gas leaves at a temperature which is close to that of the bed. Measurement of average heat transfer coefficient was made by local thermal simulation technique in a cold bubbling air-fluidized bed of size 0.305 m. x 0.305 m. Studies were conducted for single horizontal Bare Tube of length 305mm and 28.6mm outer diameter and for bare tube bundles of staggered arrangement using beds of large (average particle diameter greater than 1 mm) particle (raagi and mustard). Within the range of experimental conditions influence of bed particle diameter ( Dp), Fluidizing Velocity (U) were studied, which are significant parameters affecting heat transfer. Artificial Neural Networks (ANNs) have been receiving an increasing attention for simulating engineering systems due to some interesting characteristics such as learning capability, fault tolerance, and non-linearity. Here, feed-forward architecture and trained by back-propagation technique is adopted to predict heat transfer analysis found from experimental results. The ANN is designed to suit the present system which has 3 inputs and 2 out puts. The network predictions are found to be in very good agreement with the experimental observed values of bare heat transfer coefficient (hb) and nusselt number of bare tube (Nub).

Keywords: fluidized bed, large particles, particle diameter, ANN

Procedia PDF Downloads 364

Authors: Babak Bahri, Fatemeh Yassaee Meybodi, Changiz Eslahchi

Abstract:

In the pursuit of effective cancer therapies, the exploration of combinatorial drug regimens is crucial to leverage synergistic interactions between drugs, thereby improving treatment efficacy and overcoming drug resistance. However, identifying synergistic drug pairs poses challenges due to the vast combinatorial space and limitations of experimental approaches. This study introduces ClusterSyn, a machine learning (ML)-powered framework for classifying anti-cancer drug synergy scores. ClusterSyn employs a two-step approach involving drug clustering and synergy score prediction using a fully connected deep neural network. For each cell line in the training dataset, a drug graph is constructed, with nodes representing drugs and edge weights denoting synergy scores between drug pairs. Drugs are clustered using the Markov clustering (MCL) algorithm, and vectors representing the similarity of drug pairs to each cluster are input into the deep neural network for synergy score prediction (synergy or antagonism). Clustering results demonstrate effective grouping of drugs based on synergy scores, aligning similar synergy profiles. Subsequently, neural network predictions and synergy scores of the two drugs on others within their clusters are used to predict the synergy score of the considered drug pair. This approach facilitates comparative analysis with clustering and regression-based methods, revealing the superior performance of ClusterSyn over state-of-the-art methods like DeepSynergy and DeepDDS on diverse datasets such as Oniel and Almanac. The results highlight the remarkable potential of ClusterSyn as a versatile tool for predicting anti-cancer drug synergy scores.

Keywords: drug synergy, clustering, prediction, machine learning., deep learning

Procedia PDF Downloads 79

Authors: Deepika Christopher, Garima Anand

Abstract:

To determine the best model for churn prediction in the telecom industry, this paper compares 11 machine learning algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, XGBoost, LightGBM, Cat Boost, AdaBoost, Extra Trees, Deep Neural Network, and Hybrid Model (MLPClassifier). It also aims to pinpoint the top three factors that lead to customer churn and conducts customer segmentation to identify vulnerable groups. According to the data, the Logistic Regression model performs the best, with an F1 score of 0.6215, 81.76% accuracy, 68.95% precision, and 56.57% recall. The top three attributes that cause churn are found to be tenure, Internet Service Fiber optic, and Internet Service DSL; conversely, the top three models in this article that perform the best are Logistic Regression, Deep Neural Network, and AdaBoost. The K means algorithm is applied to establish and analyze four different customer clusters. This study has effectively identified customers that are at risk of churn and may be utilized to develop and execute strategies that lower customer attrition.

Keywords: attrition, retention, predictive modeling, customer segmentation, telecommunications

Procedia PDF Downloads 57

Authors: Stuti Modi, Aditi Kambli

Abstract:

This paper addresses the need for intelligent water management and distribution system in smart cities to ensure optimal consumption and distribution of water for drinking and sanitation purposes. Water being a limited resource in cities require an effective system for collection, storage and distribution. In this paper, applications of two mostly widely used particular types of data-driven models, namely artificial neural networks (ANN) and fuzzy logic-based models, to modelling in the water resources management field are considered. The objective of this paper is to review the principles of various types and architectures of neural network and fuzzy adaptive systems and their applications to integrated water resources management. Final goal of the review is to expose and formulate progressive direction of their applicability and further research of the AI-related and data-driven techniques application and to demonstrate applicability of the neural networks, fuzzy systems and other machine learning techniques in the practical issues of the regional water management. Apart from this the paper will deal with water storage, using ANN to find optimum reservoir level and predicting peak daily demands.

Keywords: artificial neural networks, fuzzy systems, peak daily demand prediction, water management and distribution

Procedia PDF Downloads 186

Authors: Alexander Hudson, Shaogang Gong

Abstract:

Structure determination is key to understanding protein function at a molecular level. Whilst significant advances have been made in predicting structure and function from amino acid sequence, researchers must still rely on expensive, time-consuming analytical methods to visualise detailed protein conformation. In this study, we demonstrate that it is possible to make accurate (≥80%) predictions of protein class and architecture from structures determined at low (>3A) resolution, using a deep convolutional neural network trained on high-resolution (≤3A) structures represented as 2D matrices. Thus, we provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function. We investigate the impact of the input representation on classification performance, showing that side-chain information may not be necessary for fine-grained structure predictions. Finally, we confirm that high resolution, low-resolution and NMR-determined structures inhabit a common feature space, and thus provide a theoretical foundation for boosting with single-image super-resolution.

Keywords: transfer learning, protein distance maps, protein structure classification, neural networks

Procedia PDF Downloads 136

Authors: E. Steen, B. Dewulf, N. Müller, C. Vandycke, Y. Vandekerckhove

Abstract:

Introduction: The care for a ST-elevation myocardial infarction (STEMI) patient is time-critical. Reperfusion therapy within 90 minutes of initial medical contact is mandatory in the improvement of the outcome. Primary percutaneous coronary intervention (PCI) without previous fibrinolytic treatment, is the preferred reperfusion strategy in patients with STEMI, provided it can be performed within guideline-mandated times. Aim of the study: During a one year period (January 2013 to December 2013) the files of all consecutive STEMI patients with urgent referral from non-PCI facilities for primary PCI were reviewed. Special attention was given to a subgroup of patients with prior out-of-hospital medical contact generated by the 112-system. In an effort to reduce out-of-hospital system delay to definitive care a change in pre-hospital 112 dispatch strategies is proposed for these time-critical patients. Actual time recordings were compared with travel time simulations for two suggested scenarios. A first scenario (SC1) involves the decision by the on scene ground EMS (GEMS) team to transport the out-of-hospital diagnosed STEMI patient straight forward to a PCI centre bypassing the nearest non-PCI hospital. Another strategy (SC2) explored the potential role of helicopter EMS (HEMS) where the on scene GEMS team requests a PCI-centre based HEMS team for immediate medical transfer to the PCI centre. Methods and Results: 49 (29,1% of all) STEMI patients were referred to our hospital for emergency PCI by a non-PCI facility. 1 file was excluded because of insufficient data collection. Within this analysed group of 48 secondary referrals 21 patients had an out-of-hospital medical contact generated by the 112-system. The other 27 patients presented at the referring emergency department without prior contact with the 112-system. The table below shows the actual time data from first medical contact to definitive care as well as the simulated possible gain of time for both suggested strategies. The PCI-team was always alarmed upon departure from the referring centre excluding further in-hospital delay. Time simulation tools were similar to those used by the 112-dispatch centre. Conclusion: Our data analysis confirms prolonged reperfusion times in case of secondary emergency referrals for STEMI patients even with the use of HEMS. In our setting there was no statistical difference in gain of time between the two suggested strategies, both reducing the secondary referral generated delay with about one hour and by this offering all patients PCI within the guidelines mandated time. However, immediate HEMS activation by the on scene ground EMS team for transport purposes is preferred. This ensures a faster availability of the local GEMS-team for its community. In case these options are not available and the guideline-mandated times for primary PCI are expected to be exceeded, primary fibrinolysis should be considered in a non-PCI centre.

Keywords: STEMI, system delay, HEMS, emergency medicine

Procedia PDF Downloads 319

Authors: Nihal Murali, Kunal Gupta, Surekha Bhanot

Abstract:

Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without any hand-engineered features or domain heuristics. In this paper, the standard control problem of line following robot was used as a test-bed, and an ANN controller for the robot was trained on images from a live video feed using Q-learning. A virtual agent was first trained in simulation environment and then deployed onto a robot’s hardware. The robot successfully learns to traverse a wide range of curves and displays excellent generalization ability. Qualitative analysis of the evolution of policies, performance and weights of the network provide insights into the nature and convergence of the learning algorithm.

Keywords: artificial neural networks, q-learning, reinforcement learning, robot learning

Procedia PDF Downloads 372

Authors: Jesus D. Cortes Gil, Fernanda Ewerling, Leonardo Ferreira, Aluisio J. D. Barros

Abstract:

Background: The sustainable development goals call for inclusive, equitable, and quality learning opportunities for all. This is especially important for children, to ensure they all develop to their full potential. We studied the prevalence and inequalities of suspected delay in child development in 63 low- and middle-income countries. Methods and Findings: We used the early child development module from national health surveys, which covers four developmental domains (physical, social-emotional, learning, literacy-numeracy) and provides a combined indicator (early child development index, ECDI) of whether children are on track. We calculated the age-adjusted prevalence of suspected delay at the country level and stratifying by wealth, urban/rural residence, sex of the child, and maternal education. We also calculated measures of absolute and relative inequality. We studied 330.613 children from 63 countries. The prevalence of suspected delay for the ECDI ranged from 3% in Barbados to 67% in Chad. For all countries together, 25% of the children were suspected of developmental delay. At regional level, the prevalence of delay ranged from 10% in Europe and Central Asia to 42% in West and Central Africa. The literacy-numeracy domain was by far the most challenging, with the highest proportions of delay. We observed very large inequalities, and most markedly for the literacy-numeracy domain. Conclusions: To date, our study presents the most comprehensive analysis of child development using an instrument especially developed for national health surveys. With a quarter of the children globally suspected of developmental delay, we face an immense challenge. The multifactorial aspect of early child development and the large gaps we found only add to the challenge of not leaving these children behind.

Keywords: child development, inequalities, global health, equity

Procedia PDF Downloads 119

Authors: Felipa De Mello-Sampayo

Abstract:

Background: The aim of this study is to undertake, from a patient perspective, an economic analysis of presurgical teledermatology, comparing it with a conventional referral system. Store-and-forward teledermatology allows surgical planning, saving both time and number of visits involving travel, thereby reducing patients’ out-of-pocket expenses, i.e., costs that patients incur when traveling to and from health providers for treatment, visits’ fees, and the opportunity cost of time spent in visits. Method: Patients’ out-of-pocket expenses-effectiveness of presurgical teledermatology were analyzed in the setting of a public hospital during two years. The mean delay in surgery was used to measure effectiveness. The teledermatology network covering the area served by the Hospital Garcia da Horta (HGO), Portugal, linked the primary care centers of 24 health districts with the hospital’s dermatology department. The patients’ opportunity cost of visits, travel costs, and visits’ fee of each presurgical modality (teledermatology and conventional referral), the cost ratio between the most and least expensive alternative, and the incremental cost-effectiveness ratio were calculated from initial primary care visit until surgical intervention. Two groups of patients: those with squamous cell carcinoma and those with basal cell carcinoma were distinguished in order to compare the effectiveness according to the dermatoses. Results: From a patient perspective, the conventional system was 2.15 times more expensive than presurgical teledermatology. Teledermatology had an incremental out-of-pocket expenses-effectiveness ratio of €1.22 per patient and per day of delay avoided. This saving was greater in patients with squamous cell carcinoma than in patients with basal cell carcinoma. Conclusion: From a patient economic perspective, teledermatology used for presurgical planning and preparation is the dominant strategy in terms of out-of-pocket expenses-effectiveness than the conventional referral system, especially for patients with severe dermatoses.

Keywords: economic analysis, out-of-pocket expenses, opportunity cost, teledermatology, waiting time

Procedia PDF Downloads 140

Authors: Sisay Tiroro Salato

Abstract:

Background: Ethiopia has been implementing the maternal death surveillance and response system to provide real-time actionable information, including causes of death and contributing factors. Analysis of maternal mortality surveillance data was conducted to identify the causes and underlying factors in Addis Ababa, Ethiopia. Methods: We carried out a retrospective surveillance data analysis of 324 maternal deaths reported in Addis Ababa, Ethiopia, from 2017 to 2021. The data were extracted from the national maternal death surveillance and response database, including information from case investigation, verbal autopsy, and facility extraction forms. The data were analyzed by computing frequency and presented in numbers, proportions, and ratios. Results: Of 324 maternal deaths, 92% died in the health facilities, 6.2% in transit, and 1.5% at home. The mean age at death was 28 years, ranging from 17 to 45. The maternal mortality ratio per 100,000 live births was 77for the five years, ranging from 126 in 2017 to 21 in 2021. The direct and indirect causes of death were responsible for 87% and 13%, respectively. The direct causes included obstetric haemorrhage, hypertensive disorders in pregnancy, puerperal sepsis, embolism, obstructed labour, and abortion. The third delay (delay in receiving care after reaching health facilities) accounted for 57% of deaths, while the first delay (delay in deciding to seek health care) and the second delay (delay in reaching health facilities) and accounted for 34% and 24%, respectively. Late arrival to the referral facility, delayed management after admission, andnon-recognition of danger signs were underlying factors. Conclusion: Over 86% of maternal deaths were attributed by avoidable direct causes. The majority of women do try to reach health services when an emergency occurs, but the third delays present a major problem. Improving the quality of care at the healthcare facility level will help to reduce maternal death.

Keywords: maternal death, surveillance, delays, factors

Procedia PDF Downloads 113

Authors: Dongkwon Han, Sangho Kim, Sunil Kwon

Abstract:

Unconventional gas resources have dramatically changed the future energy landscape. Unlike conventional gas resources, the key challenges in unconventional gas have been the requirement that applies to advanced approaches for production forecasting due to uncertainty and complexity of fluid flow. In this study, artificial neural network (ANN) model which integrates machine learning and data-driven approach was developed to predict productivity in shale gas. The database of 129 wells of Eagle Ford shale basin used for testing and training of the ANN model. The Input data related to hydraulic fracturing, well completion and productivity of shale gas were selected and the output data is a cumulative production. The performance of the ANN using all data sets, clustering and variables importance (VI) models were compared in the mean absolute percentage error (MAPE). ANN model using all data sets, clustering, and VI were obtained as 44.22%, 10.08% (cluster 1), 5.26% (cluster 2), 6.35%(cluster 3), and 32.23% (ANN VI), 23.19% (SVM VI), respectively. The results showed that the pre-trained ANN model provides more accurate results than the ANN model using all data sets.

Keywords: unconventional gas, artificial neural network, machine learning, clustering, variables importance

Procedia PDF Downloads 196