Search results for: deep residual networks

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: convolutional neural network, discrete wavelet transform, deep learning, heart sound classification

Procedia PDF Downloads 338

Authors: José Neves, M. Rosário Martins, Fátima Candeias, Diana Ferreira, Sílvia Arantes, Júlio Cruz-Morais, Guida Gomes, Joaquim Macedo, António Abelha, Henrique Vicente

Abstract:

Some plants of genus Schinus have been used in the folk medicine as topical antiseptic, digestive, purgative, diuretic, analgesic or antidepressant, and also for respiratory and urinary infections. Chemical composition of essential oils of S. molle and S. terebinthifolius had been evaluated and presented high variability according with the part of the plant studied and with the geographic and climatic regions. The pharmacological properties, namely antimicrobial, anti-tumoural and anti-inflammatory activities are conditioned by chemical composition of essential oils. Taking into account the difficulty to infer the pharmacological properties of Schinus essential oils without hard experimental approach, this work will focus on the development of a decision support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks and the respective Degree-of-Confidence that one has on such an occurrence.

Keywords: artificial neuronal networks, essential oils, knowledge representation and reasoning, logic programming, Schinus molle L., Schinus terebinthifolius Raddi

Procedia PDF Downloads 536

Authors: Vijaya Yuvaram Singh V M, Kameshwar Rao J V

Abstract:

The challenge with development of neural network based methods for medical is the availability of data. Anatomical landmark detection in the medical domain is a process to find points on the x-ray scan report of the patient. Most of the time this task is done manually by trained professionals as it requires precision and domain knowledge. Traditionally object detection based methods are used for landmark detection. Here, we utilize reinforcement learning and query based method to train a single agent capable of detecting multiple landmarks. A deep Q network agent is trained to detect single and multiple landmarks present on hip and shoulder from x-ray scan of a patient. Here a single agent is trained to find multiple landmark making it superior to having individual agents per landmark. For the initial study, five images of different patients are used as the environment and tested the agents performance on two unseen images.

Keywords: reinforcement learning, medical landmark detection, multi target detection, deep neural network

Procedia PDF Downloads 137

Authors: Morgan Johansson, Joosef Leppanen, Mathias Flansbjer, Fabio Lozano, Josef Makdesi

Abstract:

Concrete is commonly used for protective structures and how impact loading affects different types of concrete structures is an important issue. Often the knowledge gained from static loading is also used in the design of impulse loaded structures. A large plastic deformation capacity is essential to obtain a large energy absorption in an impulse loaded structure. However, the structural response of an impact loaded concrete beam may be very different compared to a statically loaded beam. Consequently, the plastic deformation capacity and failure modes of the concrete structure can be different when subjected to dynamic loads; and hence it is not sure that the observations obtained from static loading are also valid for dynamic loading. The aim of this paper is to investigate the residual plastic deformation capacity in reinforced concrete beams subjected to drop weight impact tests. A test-series consisting of 18 simply supported beams (0.1 x 0.1 x 1.18 m, ρs = 0.7%) with a span length of 1.0 m and subjected to a point load in the beam mid-point, was carried out. 2x6 beams were first subjected to drop weight impact tests, and thereafter statically tested until failure. The drop in weight had a mass of 10 kg and was dropped from 2.5 m or 5.0 m. During the impact tests, a high-speed camera was used with 5 000 fps and for the static tests, a camera was used with 0.5 fps. Digital image correlation (DIC) analyses were conducted and from these the velocities of the beam and the drop weight, as well as the deformations and crack propagation of the beam, were effectively measured. Additionally, for the static tests, the applied load and midspan deformation were measured. The load-deformation relations for the beams subjected to an impact load were compared with 6 reference beams that were subjected to static loading only. The crack pattern obtained were compared using DIC, and it was concluded that the resulting crack formation depended much on the test method used. For the static tests, only bending cracks occurred. For the impact loaded beams, though, distinctive diagonal shear cracks also formed below the zone of impact and less wide shear cracks were observed in the region half-way to the support. Furthermore, due to wave propagation effects, bending cracks developed in the upper part of the beam during initial loading. The results showed that the plastic deformation capacity increased for beams subjected to drop weight impact tests from a high drop height of 5.0 m. For beams subjected to an impact from a low drop height of 2.5 m, though, the plastic deformation capacity was in the same order of magnitude as for the statically loaded reference beams. The beams tested were designed to fail due to bending when subjected to a static load. However, for the impact tested beams, one beam exhibited a shear failure at a significantly reduced load level when it was tested statically; indicating that there might be a risk of reduced residual load capacity for impact loaded structures.

Keywords: digital image correlation (DIC), drop weight impact, experiments, plastic deformation capacity, reinforced concrete

Procedia PDF Downloads 140

Authors: Shin-Shin Kao, Hsiu-Chunj Pan

Abstract:

Given a graph G. A cycle of G is a sequence of vertices of G such that the first and the last vertices are the same. A hamiltonian cycle of G is a cycle containing all vertices of G. The graph G is k-ordered (resp. k-ordered hamiltonian) if for any sequence of k distinct vertices of G, there exists a cycle (resp. hamiltonian cycle) in G containing these k vertices in the specified order. Obviously, any cycle in a graph is 1-ordered, 2-ordered and 3-ordered. Thus the study of any graph being k-ordered (resp. k-ordered hamiltonian) always starts with k = 4. Most studies about this topic work on graphs with no real applications. To our knowledge, the chordal ring families were the first one utilized as the underlying topology in interconnection networks and shown to be 4-ordered [1]. Furthermore, based on computer experimental results in [1], it was conjectured that some of them are 4-ordered hamiltonian. In this paper, we intend to give some possible directions in proving the conjecture.

Keywords: Hamiltonian cycle, 4-ordered, Chordal rings, 3-regular

Procedia PDF Downloads 427

Authors: Rishabh Sharma

Abstract:

The main design parameter of WSN (wireless sensor network) is the energy consumption. To compensate this parameter, hierarchical clustering is a technique that assists in extending duration of the networks life by efficiently consuming the energy. This paper focuses on dealing with the WSNs and the FIS (fuzzy interface system) which are deployed to enhance the BEENISH protocol. The node energy, mobility, pause time and density are considered for the selection of CH (cluster head). The simulation outcomes exhibited that the projected system outperforms the traditional system with regard to the energy utilization and number of packets transmitted to sink.

Keywords: wireless sensor network, sink, sensor node, routing protocol, fuzzy rule, fuzzy inference system

Procedia PDF Downloads 98

Authors: Yoel Agustheo Rinding

Abstract:

Globalization has made physical borders between countries become more obscure. Due to the free flow of information between countries, issue for instance, environment has become global concern. The concern has grown as the result of endless campaign made by most of the non-governmental organizations (NGOs). By means of this situation, international voluntary initiatives on environmental issues have appeared to be popular among world’s society today especially for youth. AIESEC as international non-governmental organization (INGO) through IGreen Project has initiated environmental international voluntary initiatives concerning in environmental awareness of Bandung’s citizen. Bandung itself is still struggling on solving flood as one of its major problems regardless the fact that Bandung is one of the most developed cities in Indonesia. This paper would like to discuss on how globalization affects AIESEC as an INGO in order to spread its influence and also on how it could build international voluntary initiatives networks. Afterwards, author would like to elaborate how both AIESEC and youth perceive the importance of international voluntary initiatives by using cosmopolitanism approach. In order to get a deep understanding of how this activity works, this paper also would like to explain regarding the management, expected outcomes, and the real impacts of IGreen project towards Bandung. In the end of this paper, author would like to propose solutions on how to utilize international voluntary initiatives as a solution for environmental issues nowadays.

Keywords: AIESEC, cosmopolitanism, environmental issues, globalization, IGreen project, international environmental voluntary initiatives, INGO, youth

Procedia PDF Downloads 219

Authors: N. Sabiyath Fatima, R. K. Shanmugasundaram

Abstract:

In Mobile Ad-hoc Networks (MANETS), every node performs both as transmitter and receiver. The existing backoff models do not exactly forecast the performance of the wireless network. Also, the existing models experience elevated packet collisions. Every time a collision happens, the station’s contention window (CW) is doubled till it arrives at the utmost value. The main objective of this paper is to diminish collision by means of contention window Multiplicative Increase Decrease Backoff (CWMIDB) scheme. The intention of rising CW is to shrink the collision possibility by distributing the traffic into an outsized point in time. Within wireless Ad hoc networks, the CWMIDB algorithm dynamically controls the contention window of the nodes experiencing collisions. During packet communication, the backoff counter is evenly selected from the given choice of [0, CW-1]. At this point, CW is recognized as contention window and its significance lies on the amount of unsuccessful transmission that had happened for the packet. On the initial transmission endeavour, CW is put to least amount value (C min), if transmission effort fails, subsequently the value gets doubled, and once more the value is set to least amount on victorious broadcast. CWMIDB is simulated inside NS2 environment and its performance is compared with Binary Exponential Backoff Algorithm. The simulation results show improvement in transmission probability compared to that of the existing backoff algorithm.

Keywords: backoff, contention window, CWMIDB, MANET

Procedia PDF Downloads 272

Authors: Jamileh Vasheghani Farahani

Abstract:

The main purpose of this research is to show the current active faults and active tectonic of the area by three seismic networks in Tehran region: 1-Tehran Disaster Mitigation and Management Organization (TDMMO), 2-Broadband Iranian National Seismic Network Center (BIN), 3-Iranian Seismological Center (IRSC). In this study, we analyzed microearthquakes happened in Tehran city and its surroundings using the Tehran networks from 1996 to 2015. We found some active faults and trends in the region. There is a 200-year history of historical earthquakes in Tehran. Historical and instrumental seismicity show that the east of Tehran is more active than the west. The Mosha fault in the North of Tehran is one of the active faults of the central Alborz. Moreover, other major faults in the region are Kahrizak, Eyvanakey, Parchin and North Tehran faults. An important seismicity region is an intersection of the Mosha and North Tehran fault systems (Kalan village in Lavasan). This region shows a cluster of microearthquakes. According to the historical and microseismic events analyzed in this research, there is a seismic gap in SE of Tehran. The empirical relationship is used to assess the Mmax based on the rupture length. There is a probability of occurrence of a strong motion of 7.0 to 7.5 magnitudes in the region (based on the assessed capability of the major faults such as Parchin and Eyvanekey faults and historical earthquakes).

Keywords: Iran, major faults, microseismicity, Tehran

Procedia PDF Downloads 362

Authors: Sumaya Ismail, Aijaz Ahmad Reshi

Abstract:

The advances in sensor and embedded technologies have led to rapid developments in Wireless Sensor Networks (WSNs). Presently researchers focus on the integration of WSNs to the Internet for their pervasive availability to access these network resources as the interoperable subsystems. The recent computing technologies like cloud computing has made resource sharing as a converged infrastructure with required service interfaces for the shared resources over the Internet. This paper presents application architecture for wireless Sensor and Actuator Networks (WSANS) following web of things, which allows easy integration of each node to the Internet in order to provide them with web accessibility. The architecture enables the sensors and actuator nodes accessed and controlled using cloud interface on WWW. The application architecture was implemented using existing web and its emerging technologies. In particular, the Representational State Transfer protocol (REST) was extended for the specific requirements of the application. The Cloud computing environment has been used as a development platform for the application to assess the possibility of integrating the WSAN nodes to Cloud services. The mushroom farm environment monitoring and control using WSANs has been taken as a research use case.

Keywords: WSAN, REST, web of things, ZigBee, cloud interface, PaaS, sensor gateway

Procedia PDF Downloads 94

Authors: Jin Hwa Yang, Hwang Bae, Sung Uk Ryu, Byong Guk Jeon, Sung Jae Yi, Hyun Sik Park

Abstract:

Experimental studies using a large-scale thermal-hydraulic integral test facility, System–integrated Modular Advanced Reactor Integral Test Loop (SMART-ITL), have been carried out to validate the performance of the prototype, SMART. After Fukushima accident, the passive safety systems have been dealt as important designs for retaining of nuclear safety. One of the concerned scenarios for evaluating the passive safety system is a Complete Loss of Coolant Flow (CLOF). The flowrate of coolant in the primary system is maintained by Reactor Coolant Pump (RCP). When the supply of electric power of RCP is shut off, the flowrate of coolant decreases sharply, and the temperature of the coolant increases rapidly. Therefore, the reactor trip signal is activated to prevent the over-heating of the core. In this situation, Passive Residual Heat Removal System (PRHRS) plays a significant role to assure the soundness of the SMART. The PRHRS using a two-phase natural circulation is a passive safety system in the SMART to eliminate the heat of steam generator in the secondary system with heat exchanger submarined in the Emergency Cooling Tank (ECT). As the RCPs continue to coast down, inherent natural circulation in the primary system transfers heat to the secondary system. The transferred heat is removed by PRHRS in the secondary system. In this paper, the progress of the CLOF accident is described with experimental data of transient condition performed by SMART-ITL. Finally, the capability of passive safety system and inherent natural circulation will be evaluated.

Keywords: CLOF, natural circulation, PRHRS, SMART-ITL

Procedia PDF Downloads 435

Authors: S. Fominow, C. Dobert

Abstract:

The present article describes the research that deals with the development of equivalent geometric imperfections for the stability design of steel members considering lateral-torsional buckling. The application of these equivalent imperfections takes into account the stiffness-reducing effects due to inelasticity and residual stresses, which lead to a reduction of the load carrying capacity of slender members and structures. This allows the application of a simplified design method, that is performed in three steps. Application of equivalent geometric imperfections, determination of internal forces using geometrical non-linear analysis (GNIA) and verification of the cross-section resistance at the most unfavourable location. All three verification steps are closely related and influence the results. The derivation of the equivalent imperfections was carried out in several steps. First, reference lateral-torsional buckling resistances for various rolled I-sections, slenderness grades, load shapes and steel grades were determined. This was done either with geometric and material non-linear analysis with geometrical imperfections and residual stresses (GMNIA) or for standard cases based on the equivalent member method. With the aim of obtaining identical lateral-torsional buckling resistances as the reference resistances from the application of the design method, the required sizes for equivalent imperfections were derived. For this purpose, a program based on the FEM method has been developed. Based on these results, several proposals for the specification of equivalent geometric imperfections have been developed. These differ in the shape of the applied equivalent geometric imperfection, the model of the cross-sectional resistance and the steel grade. The proposed design methods allow a wide range of applications and a reliable calculation of the lateral-torsional buckling resistances, as comparisons between the calculated resistances and the reference resistances have shown.

Keywords: equivalent geometric imperfections, GMNIA, lateral-torsional buckling, non-linear finite element analysis

Procedia PDF Downloads 151

Authors: Arámbula-Villa Gerónimo, García-Lara Kenia Y., Figueroa-Cárdenas J. D., Pérez-Robles J. F., Jiménez-Sandoval S., Salazar-López R., Herrera-Corredor J. A.

Abstract:

The nixtamalization process (thermal-alkaline method) improves the nutritional part of the corn grain. In this process, the using of Ca(OH)₂ is basic, although the chemical mechanisms between this alkali and the carbohydrates (starch), proteins, lipids, and fiber have not been fully identified. In this study, the native corn starch was taken as a model, and it was subjected to cooking with different concentrations of lime (nixtamalization process) and specific studies of FTIR and XRD were carried out to identify the formation of chemical compounds, and the physical, physicochemical, rheological (paste) and structural properties of material obtained were determined. The FTIR spectra showed the formation of calcium-starch complexes. The treatments with Ca(OH)₂ showed a band shift towards 1675 cm⁻¹ and a band in 1436 cm⁻¹ (COO⁻), indicating the oxidation of starch. Three bands were identified (1575, 1550, and 1540 cm⁻¹) characteristics of carboxylic acid salts for three types of coordinated structures: monodentate, pseudo-bridged, and bidentate. The XRD spectra of starch treated with Ca(OH)₂ showed a peak corresponding to CaCO₃ (29.40°). The oxidation of starch was favored with low concentrations of Ca(OH)₂, producing carboxyl and carbonyl groups and increasing the residual CaCO₃. The increased concentration of Ca(OH)₂ showed the formation of calcium carboxylates, with a decrease in relative crystallinity and residual CaCO₃. Samples with low concentrations of Ca(OH)₂ slowed the onset of gelatinization and increased the swelling of the granules and the peak viscosity. The higher concentrations of Ca(OH)₂ difficulted the water absorption and decreased the viscosity rate and peak viscosity. These results can be used to improve the quality characteristics of the dough and tortillas and to get better acceptance by consumers.

Keywords: maize starch, nixtamalization, gelatinization, calcium carboxylates

Procedia PDF Downloads 87

Authors: Sulemana Ibrahim

Abstract:

Food security remains a paramount global challenge, with vulnerable regions grappling with issues of hunger and malnutrition. This study embarks on a comprehensive exploration of data-driven strategies aimed at ameliorating food security in such regions. Our research employs a multifaceted approach, integrating data analytics to predict crop yields, optimizing supply chains, and enhancing food distribution networks. The study unfolds as a multi-dimensional analysis, commencing with the development of robust machine learning models harnessing remote sensing data, historical crop yield records, and meteorological data to foresee crop yields. These predictive models, underpinned by convolutional and recurrent neural networks, furnish critical insights into anticipated harvests, empowering proactive measures to confront food insecurity. Subsequently, the research scrutinizes supply chain optimization to address food security challenges, capitalizing on linear programming and network optimization techniques. These strategies intend to mitigate loss and wastage while streamlining the distribution of agricultural produce from field to fork. In conjunction, the study investigates food distribution networks with a particular focus on network efficiency, accessibility, and equitable food resource allocation. Network analysis tools, complemented by data-driven simulation methodologies, unveil opportunities for augmenting the efficacy of these critical lifelines. This study also considers the ethical implications and privacy concerns associated with the extensive use of data in the realm of food security. The proposed methodology outlines guidelines for responsible data acquisition, storage, and usage. The ultimate aspiration of this research is to forge a nexus between data science and food security policy, bestowing actionable insights to mitigate the ordeal of food insecurity. The holistic approach converging data-driven crop yield forecasts, optimized supply chains, and improved distribution networks aspire to revitalize food security in the most vulnerable regions, elevating the quality of life for millions worldwide.

Keywords: data-driven strategies, crop yield prediction, supply chain optimization, food distribution networks

Procedia PDF Downloads 55

Authors: Babar Sultan, Kiran Sultan, Waseem Khan, Ijaz Mansoor Qureshi

Abstract:

In this paper, a novel idea for the performance enhancement of secondary network is proposed for Underlay Cognitive Radio Networks (CRNs). In Underlay CRNs, primary users (PUs) impose strict interference constraints on the secondary users (SUs). The proposed scheme is based on Artificial Bee Colony (ABC) optimization for relay selection and power allocation to handle the highlighted primary challenge of Underlay CRNs. ABC is a simple, population-based optimization algorithm which attains global optimum solution by combining local search methods (Employed and Onlooker Bees) and global search methods (Scout Bees). The proposed two-phase relay selection and power allocation algorithm aims to maximize the signal-to-noise ratio (SNR) at the destination while operating in an underlying mode. The proposed algorithm has less computational complexity and its performance is verified through simulation results for a different number of potential relays, different interference threshold levels and different transmit power thresholds for the selected relays.

Keywords: artificial bee colony, underlay spectrum sharing, cognitive radio networks, amplify-and-forward

Procedia PDF Downloads 575

Authors: M. Dezyani, R. Ezzati bbelvirdi, M. Shakerian, H. Mirzaei

Abstract:

Sodium Hexametaphosphate (SHMP) is commonly used as an Emulsifying Salt (ES) in process cheese, although rarely as the sole ES. It appears that no published studies exist on the effect of SHMP concentration on the properties of process cheese when pH is kept constant; pH is well known to affect process cheese functionality. The detailed interactions between the added phosphate, Casein (CN), and indigenous Ca phosphate are poorly understood. We studied the effect of the concentration of SHMP (0.25-2.75%) and holding time (0-20 min) on the textural and Rheological properties of pasteurized process Cheddar cheese using a central composite rotatable design. All cheeses were adjusted to pH 5.6. The meltability of process cheese (as indicated by the decrease in loss tangent parameter from small amplitude oscillatory rheology, degree of flow, and melt area from the Schreiber test) decreased with an increase in the concentration of SHMP. Holding time also led to a slight reduction in meltability. Hardness of process cheese increased as the concentration of SHMP increased. Acid-base titration curves indicated that the buffering peak at pH 4.8, which is attributable to residual colloidal Ca phosphate, was shifted to lower pH values with increasing concentration of SHMP. The insoluble Ca and total and insoluble P contents increased as concentration of SHMP increased. The proportion of insoluble P as a percentage of total (indigenous and added) P decreased with an increase in ES concentration because of some of the (added) SHMP formed soluble salts. The results of this study suggest that SHMP chelated the residual colloidal Ca phosphate content and dispersed CN; the newly formed Ca-phosphate complex remained trapped within the process cheese matrix, probably by cross-linking CN. Increasing the concentration of SHMP helped to improve fat emulsification and CN dispersion during cooking, both of which probably helped to reinforce the structure of process cheese.

Keywords: Iranian processed cheese, emulsifying salt, rheology, texture

Procedia PDF Downloads 429

Authors: Hamida Qumber Ali, Waseem Muhammad Arain, Shama Siddiqui, Sayeed Ghani

Abstract:

We present an implementing of RMAC in TinyOS 1.x. RMAC is a cross layer and Duty-cycle MAC protocols that was proposed to provide energy efficient transmission services for wireless sensor networks. The protocol has a unique and efficient packet transmission scheduling mechanism that enables it to overcome delivery latency and overcome traffic congestion. Design details and implementation challenges are divulged. Experiments are conducted to show the correctness of our implementation with numerous assumptions. Simulations are performed to compare the performance of RMAC and SMAC. Our results show that RMAC outperforms SMAC in energy efficiency and delay.

Keywords: MAC protocol, performance, RMAC, wireless sensor networks

Procedia PDF Downloads 316

Authors: Ruchi Makani, B. V. R. Reddy

Abstract:

Mobile Adhoc Networks (MANETs) are gaining popularity due to their potential of providing low-cost mobile connectivity solutions to real-world communication problems. Integrating Intrusion Detection Systems (IDS) in MANETs is a tedious task by reason of its distinctive features such as dynamic topology, de-centralized authority and highly controlled/limited resource environment. IDS primarily use automated soft-computing techniques to monitor the inflow/outflow of traffic packets in a given network to detect intrusion. Use of machine learning techniques in IDS enables system to make decisions on intrusion while continuous keep learning about their dynamic environment. An appropriate IDS model is essential to be selected to expedite this application challenges. Thus, this paper focused on fuzzy-logic based machine learning IDS technique for MANETs and presented their applicability for achieving effectiveness in identifying the intrusions. Further, the selection of appropriate protocol attributes and fuzzy rules generation plays significant role for accuracy of the fuzzy-logic based IDS, have been discussed. This paper also presents the critical attributes of MANET’s routing protocol and its applicability in fuzzy logic based IDS.

Keywords: AODV, mobile adhoc networks, intrusion detection, anomaly detection, fuzzy logic, fuzzy membership function, fuzzy inference system

Procedia PDF Downloads 170

Authors: Khaled M. Ali, Ayman A. Mostafa, Soliman M. Soliman

Abstract:

Objectives: To describe the most common clinical and endoscopic findings associated with complicated corneal ulcers in cats, and to determine the short-term outcomes after surgical treatment of these cats. Animals Eighteen client-owned cats of different breeds (52 females and 28 males), ranging in age from 3 months to 6 years, with corneal ulcers. Procedures: Cats were clinically evaluated to initially determine the concurrent corneal abnormalities. Endoscopic examination was performed to determine the anterior and posterior segments abnormalities. Superficial and deep stromal ulcers were treated using conjunctival flap. Corneal sequestrum was treated by partial keratectomy and conjunctival flap. Anterior synechia was treated via peripheral iridectomy and separation of the adhesion between the iris and the inner cornea. Symblepharon was treated by removal of the adhered conjunctival membrane from the cornea. Incurable endophthalmitis was treated surgically by extirpation. Short-term outcomes after surgical managements of selected corneal abnormalities were then assessed clinically and endoscopically. Results: Deep stromal ulcer with descemetocele, endophthalmitis, symblepharon, corneal sequestration and anterior synechia with secondary glaucoma and corneal scarring were the most common complications of corneal ulcer. FHV-1 was a common etiologic factor of corneal ulceration. Persistent corneal scars of varying shape and size developed in cats with deep stromal ulcer, anterior synechia, and corneal sequestration. Conclusions: Domestic shorthaired and Persian cats were the most predisposed breeds to FHV-1 infection and subsequent corneal ulceration. Immediate management of patients with corneal ulcer would prevent serious complications. No age or sex predisposition to complicated corneal ulceration in cats.

Keywords: cats, complicated corneal ulceration, clinical, endoscopic diagnosis, FHV-1

Procedia PDF Downloads 277

Authors: Shanxiong Chen, Xu Han, Xiaolong Wang, Hui Ma

Abstract:

Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.

Keywords: recognition, CNN, Yi character, divergence

Procedia PDF Downloads 158

Authors: Mansoureh Naderipour, Susan Bastani, Mohammad Fazel Zarandi

Abstract:

Predicting links that may occur in the future and missing links in social networks is an attractive problem in social network analysis. Granular computing can help us to model the relationships between human-based system and social sciences in this field. In this paper, we present a model based on granular computing approach and Type-2 fuzzy logic to predict links regarding nodes’ activity and the relationship between two nodes. Our model is tested on collaboration networks. It is found that the accuracy of prediction is significantly higher than the Type-1 fuzzy and crisp approach.

Keywords: social network, link prediction, granular computing, type-2 fuzzy sets

Procedia PDF Downloads 319

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: convolutional neural networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 113

Authors: Sumaya Iqbal, Aijaz Ahmad Reshi

Abstract:

The advances in sensor and embedded technologies have led to rapid developments in Wireless Sensor Networks (WSNs). Presently researchers focus on the integration of WSNs to Internet for their pervasive availability to access these network resources as the interoperable subsystems. The recent computing technologies like cloud computing has made the resource sharing as a converged infrastructure with required service interfaces for the shared resources over the Internet. This paper presents application architecture for wireless Sensor and Actuator Networks (WSANS) following web of things, which allows easy integration of each node to the Internet in order to provide them web accessibility. The architecture enables the sensors and actuator nodes accessed and controlled using cloud interface on WWW. The application architecture was implemented using existing web and its emerging technologies. In particular Representational State Transfer protocol (REST) was extended for the specific requirements of the application. Cloud computing environment has been used as a development platform for the application to assess the possibility of integrating the WSAN nodes to Cloud services. The mushroom farm environment monitoring and control using WSANs has been taken as a research use case.

Keywords: WSAN, REST, web of things, ZigBee, cloud interface, PaaS, sensor gateway

Procedia PDF Downloads 111

Authors: Mahmoud M. Othman, Y. G. Hegazy, A. Y. Abdelaziz

Abstract:

This paper proposes a novel heuristic algorithm that aims to determine the best size and location of distributed generators in unbalanced distribution networks. The proposed heuristic algorithm can deal with the planning cases where power loss is to be optimized without violating the system practical constraints. The distributed generation units in the proposed algorithm is modeled as voltage controlled node with the flexibility to be converted to constant power factor node in case of reactive power limit violation. The proposed algorithm is implemented in MATLAB and tested on the IEEE 37 -node feeder. The results obtained show the effectiveness of the proposed algorithm.

Keywords: distributed generation, heuristic approach, optimization, planning

Procedia PDF Downloads 514

Authors: Amir Farouk Ahmed Ali Hussin

Abstract:

Social media, such as Facebook, LinkedIn and Ex-Twitter have experienced exponential growth and a remarkable adoption rate in recent years. They give fantastic means of online social interactions and communications with family, friends, and colleagues from around the corner or across the globe, and they have become an important part of daily digital interactions for more than one and a half billion users around the world. The personal information sharing practices that social network providers encourage have led to their success as innovative social interaction platforms. Moreover, these practices have outcome in concerns with respect to privacy and security from different stakeholders. Guiding these privacy and security concerns in social networks is a must for these networks to be sustainable. Real security and privacy tools may not be enough to address existing concerns. Some points should be followed to protect users from the existing risks. In this research, we have checked the various privacy and security issues and concerns pertaining to social media. However, we have classified these privacy and security issues and presented a thorough discussion of the effects of these issues and concerns on the future of the social networks. In addition, we have presented a set of points as precaution measures that users can consider to address these issues.

Keywords: international legal, consultation mix, legal research, small and medium-sized enterprises, strategic International law, strategy alignment, house of laws, deployment, production strategy, legal strategy, business strategy

Procedia PDF Downloads 57

Authors: Luther Ollier, Sylvie Thiria, Anastase Charantonis, Carlos E. Mejia, Michel Crépon

Abstract:

Sea Surface Height Anomaly (SLA) is a signature of the sub-mesoscale dynamics of the upper ocean. Sea Surface Temperature (SST) is driven by these dynamics and can be used to improve the spatial interpolation of SLA fields. In this study, we focused on the temporal evolution of SLA fields. We explored the capacity of deep learning (DL) methods to predict short-term SLA fields using SST fields. We used simulated daily SLA and SST data from the Mercator Global Analysis and Forecasting System, with a resolution of (1/12)◦ in the North Atlantic Ocean (26.5-44.42◦N, -64.25–41.83◦E), covering the period from 1993 to 2019. Using a slightly modified image-to-image convolutional DL architecture, we demonstrated that SST is a relevant variable for controlling the SLA prediction. With a learning process inspired by the teaching-forcing method, we managed to improve the SLA forecast at five days by using the SST fields as additional information. We obtained predictions of a 12 cm (20 cm) error of SLA evolution for scales smaller than mesoscales and at time scales of 5 days (20 days), respectively. Moreover, the information provided by the SST allows us to limit the SLA error to 16 cm at 20 days when learning the trajectory.

Keywords: deep-learning, altimetry, sea surface temperature, forecast

Procedia PDF Downloads 81

Authors: Mazarine Roquet, Pierre Dewallef

Abstract:

The building sector, both residential and tertiary, accounts for a significant share of greenhouse gas emissions. In Belgium, partly due to poor insulation of the building stock, but certainly because of the massive use of fossil fuels for heating buildings, this share reaches almost 30%. To reduce carbon emissions from urban building heating, district heating networks emerge as a promising solution as they offer various assets such as improving the load factor, integrating combined heat and power systems, and enabling energy source diversification, including renewable sources and waste heat recovery. However, mainly for sake of simple operation, most existing district heating networks still operate at high or medium temperatures ranging between 120°C and 60°C (the socalled second and third-generations district heating networks). Although these district heating networks offer energy savings in comparison with individual boilers, such temperature levels generally require the use of fossil fuels (mainly natural gas) with combined heat and power. The fourth-generation district heating networks improve the transport and energy conversion efficiency by decreasing the operating temperature between 50°C and 30°C. Yet, to decarbonise the building heating one must increase the waste heat recovery and use mainly wind, solar or geothermal sources for the remaining heat supply. Fifth-generation networks operating between 35°C and 15°C offer the possibility to decrease even more the transport losses, to increase the share of waste heat recovery and to use electricity from renewable resources through the use of heat pumps to generate low temperature heat. The main objective of this contribution is to exhibit on a real-life test case the benefits of replacing an existing third-generation network by a fifth-generation one and to decarbonise the heat supply of the building stock. The second objective of the study is to highlight the difficulties resulting from the use of a fifth-generation, low-temperature, district heating network. To do so, a simulation model of the district heating network including its regulation is implemented in the modelling language Modelica. This model is applied to the test case of the heating network on the University of Liège's Sart Tilman campus, consisting of around sixty buildings. This model is validated with monitoring data and then adapted for low-temperature networks. A comparison of primary energy consumptions as well as CO2 emissions is done between the two cases to underline the benefits in term of energy independency and GHG emissions. To highlight the complexity of operating a lowtemperature network, the difficulty of adapting the mass flow rate to the heat demand is considered. This shows the difficult balance between the thermal comfort and the electrical consumption of the circulation pumps. Several control strategies are considered and compared to the global energy savings. The developed model can be used to assess the potential for energy and CO2 emissions savings retrofitting an existing network or when designing a new one.

Keywords: building simulation, fifth-generation district heating network, low-temperature district heating network, urban building heating

Procedia PDF Downloads 69

Authors: Gennaro Marino

Abstract:

This paper concerns a case of a 10.75 inch diameter buried gas transmission line which was exposed to mine subsidence ground movements. The pipeline was buried about 4ft. below the surface with maximum operating pressure of 1440 psi. The mine subsidence movement was the result of long walling ore at a depth of approximately 1600 ft. As ore extraction progressed, the stress in the monitored pipeline worsened and was approaching unacceptable levels. The excessive pipe compression resulted when it was exposed to the compression zone of subsidence basin created by mining. The pipe stress reached a significant compressive level due to the extensive length of the pipe exposed to frictional ground-pipe slip resistance. The backfill ground movement slip resistance depends on normal stress around the pipe, the rate of slip, and the backfill characteristics. Normal stress depends on the burial depth of the backfill density and the lateral subsidence induced stress. The backfill in this site has a soil dry density of approximately 90 PCF. A suite of direct shear tests was conducted a residual friction angle of 36 was determined for the ambient backfill. These tests showed that the residual shearing resistance was reached within a fraction of an inch. The pipe was coated with fusion-bonded epoxy, so friction reduce factory of 0.6 can be considered. To relieve ground movement induced compressive stress, the line was uncovered. As more of the pipeline was exposed, the pipe abruptly bowed in the excavation. An analysis of this pipe formation which was performed is provided in this paper. Also discussed in this paper are ways to mitigate this pipe deformation or upheaval buckling from occurring. Keywords: Pipe Upheaval, Pipe Buckling, Ground subsidence, Buried Pipeline, Pipe Stress Mitigation.

Keywords: pipe upheaval, pipe buckling, ground subsidence, buried pipeline, pipe stress mitigation

Procedia PDF Downloads 155

Authors: Hai Zhou, Wenzhi Zhao

Abstract:

Water is one of the most important factors limiting plant growth and development in desert ecosystems. In order to understand how desert shrubs cope with variation in water sources over time, it is important to understand plant–water relations in desert-oasis ecotone. We selected the typical desert shrubs: Nitraria sibirica, Calligonum mongolicum and Haloxylon ammodendron of 5-, 10-, 20- and 40-year old as the research species, to study the seasonal variation of plant water sources and response to precipitation in the desert-oasis ecotone of Linze, Northwestern China. We examined stable isotopic ratios of oxygen (δ18O) in stem water of desert shrubs as well as in precipitation, groundwater, and soil water in different soil layers and seasons to determine water sources for the shrubs. We found that the N. sibirica and H. ammodendron of 5-, 10-year old showed significant seasonal variation characteristics of δ18O value of stem water and water sources. However, the C. mongolicum and 20- and 40-year H. ammodendron main water sources were from deep soil water and groundwater, and less response to precipitation pulse. After 22.4 mm precipitation, the contribution of shallow soil water (0-50cm) to the use of N. sibirica increased from 6.7% to 36.5%; the C. mongolicum rarely use precipitation that were about 58.29% and 23.51%, absorbed from the deep soil water and groundwater; the contribution of precipitation to use of H. ammodendron had significantly differences among the four ages. The H. ammodendron of 5- and 10-year old about 86.3% and 42.5% water sources absorbed from the shallow soil water after precipitation. However, the contribution to 20- and 40-year old plant was less than 15%. So, the precipitation was one of the main water sources for desert shrubs, but the species showed different water utilization. We conclude that the main water source of the N. sibirica and H. ammodendron of 5-, 10-year was soil water recharged by precipitation, but the deeply rooted H. ammodendron of 20‐ and 40‐year‐old and the C. mongolicum have the ability to exploit a deep and reliable water source.

Keywords: water use pattern, water resource, stable isotope, seasonal change, precipitation pulse

Procedia PDF Downloads 425

Authors: Jamerson Felipe Pereira Lima, Jeane Cecília Bezerra de Melo

Abstract:

The difficulty and cost related to obtaining of protein tertiary structure information through experimental methods, such as X-ray crystallography or NMR spectroscopy, helped raising the development of computational methods to do so. An approach used in these last is prediction of tridimensional structure based in the residue chain, however, this has been proved an NP-hard problem, due to the complexity of this process, explained by the Levinthal paradox. An alternative solution is the prediction of intermediary structures, such as the secondary structure of the protein. Artificial Intelligence methods, such as Bayesian statistics, artificial neural networks (ANN), support vector machines (SVM), among others, were used to predict protein secondary structure. Due to its good results, artificial neural networks have been used as a standard method to predict protein secondary structure. Recent published methods that use this technique, in general, achieved a Q3 accuracy between 75% and 83%, whereas the theoretical accuracy limit for protein prediction is 88%. Alternatively, to achieve better results, support vector machines prediction methods have been developed. The statistical evaluation of methods that use different AI techniques, such as ANNs and SVMs, for example, is not a trivial problem, since different training sets, validation techniques, as well as other variables can influence the behavior of a prediction method. In this study, we propose a prediction method based on artificial neural networks, which is then compared with a selected SVM method. The chosen SVM protein secondary structure prediction method is the one proposed by Huang in his work Extracting Physico chemical Features to Predict Protein Secondary Structure (2013). The developed ANN method has the same training and testing process that was used by Huang to validate his method, which comprises the use of the CB513 protein data set and three-fold cross-validation, so that the comparative analysis of the results can be made comparing directly the statistical results of each method.

Keywords: artificial neural networks, protein secondary structure, protein structure prediction, support vector machines

Procedia PDF Downloads 612