Search results for: Wireless Sensor Networks

Authors: Daniel Martinez, Tim de Leeuw, Stefan Haefliger

Abstract:

The challenges of managing a large and geographically dispersed R&D organization have been further increasing during the past years, concentrating on the leverage of a geo-graphically dispersed body of knowledge in an efficient and effective manner. In order to reduce complexity and improve performance, firms introduce product modularity as one key element for global R&D network teams to develop their products and projects in collaboration. However, empirical studies on the effects of product modularity on innovation performance are really scant. Furthermore, some researchers have suggested that product modularity promotes innovation performance, while others argue that it inhibits innovation performance. This research fills this gap by investigating the impact of product modularity on various dimensions of innovation performance, i.e. effectiveness and efficiency. By constructing the theoretical framework, this study suggests that that there is an inverted U-shaped relationship between product modularity and innovation performance. Moreover, this research work suggests that the optimum of innovation performance efficiency will be at a higher level than innovation performance effectiveness at a given product modularity level.

Keywords: modularity, innovation performance, networks, R&D, collaboration

Procedia PDF Downloads 518

Authors: Shreyas Srinivas Rangan, Jurgis Porins

Abstract:

The internet traffic has increased exponentially due to the high demand for data rates by the users, and the constantly increasing metro networks and access networks are focused on improving the maximum transmit distance of the long-reach optical networks. One of the common methods to improve the maximum transmit distance of the long-reach optical networks at the component level is to use broadband optical amplifiers. The Erbium Doped Fiber Amplifier (EDFA) provides high amplification with low noise figure but due to the characteristics of EDFA, its operation is limited to C-band and L-band. In contrast, the Raman amplifier exhibits a wide amplification spectrum, and negative noise figure values can be achieved. To obtain such results, high powered pumping sources are required. Operating Raman amplifiers with such high-powered optical sources may cause fire hazards and it may damage the optical system. In this paper, we implement a hybrid optical amplifier configuration. EDFA and Raman amplifiers are used in this hybrid setup to combine the advantages of both EDFA and Raman amplifiers to improve the reach of the system. Using this setup, we analyze the maximum transmit distance of the network by obtaining a correlation diagram between the length of the single-mode fiber (SMF) and the Bit Error Rate (BER). This hybrid amplifier configuration is implemented in a Wavelength Division Multiplexing (WDM) system with a BER of 10⁻⁹ by using NRZ modulation format, and the gain uniformity noise ratio (signal-to-noise ratio (SNR)), the efficiency of the pumping source, and the optical signal gain efficiency of the amplifier are studied experimentally in a mathematical modelling environment. Numerical simulations were implemented in RSoft OptSim simulation software based on the nonlinear Schrödinger equation using the Split-Step method, the Fourier transform, and the Monte Carlo method for estimating BER.

Keywords: Raman amplifier, erbium doped fibre amplifier, bit error rate, hybrid optical amplifiers

Procedia PDF Downloads 67

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 394

Authors: Ousmane Youme, Jean Marie Dembele, Eugene Ezin, Christophe Cambier

Abstract:

In recent years, the convolutional neural networks (CNN) architectures designed by evolution algorithms have proven to be competitive with handcrafted architectures designed by experts. However, these algorithms need a lot of computational power, which is beyond the capabilities of most researchers and engineers. To overcome this problem, we propose an evolution architecture under length constraints. It consists of two algorithms: a search length strategy to find an optimal space and a search architecture strategy based on a genetic algorithm to find the best individual in the optimal space. Our algorithms drastically reduce resource costs and also keep good performance. On the Cifar-10 dataset, our framework presents outstanding performance with an error rate of 5.12% and only 4.6 GPU a day to converge to the optimal individual -22 GPU a day less than the lowest cost automatic evolutionary algorithm in the peer competition.

Keywords: CNN architecture, genetic algorithm, evolution algorithm, length constraints

Procedia PDF Downloads 127

Authors: Mary Anne Roa

Abstract:

Congestion in network occurs due to exceed in aggregate demand as compared to the accessible capacity of the resources. Network congestion will increase as network speed increases and new effective congestion control methods are needed, especially for today’s very high speed networks. To address this undeniably global issue, the study focuses on the development of a fuzzy-based congestion control model concerned with allocating the resources of a computer network such that the system can operate at an adequate performance level when the demand exceeds or is near the capacity of the resources. Fuzzy logic based models have proven capable of accurately representing a wide variety of processes. The model built is based on bandwidth, the aggregate incoming traffic and the waiting time. The theoretical analysis and simulation results show that the proposed algorithm provides not only good utilization but also low packet loss.

Keywords: congestion control, queue management, computer networks, fuzzy logic

Procedia PDF Downloads 395

Authors: Harold Mauricio Díaz-Vargas, Cristian Alfonso Jimenez-Castaño, David Augusto Cárdenas-Peña, Guillermo Alberto Ortiz-Gómez, Alvaro Angel Orozco-Gutierrez

Abstract:

Precise identification of the nerves is a crucial task performed by anesthesiologists for an effective Peripheral Nerve Blocking (PNB). Now, anesthesiologists use ultrasound imaging equipment to guide the PNB and detect nervous structures. However, visual identification of the nerves from ultrasound images is difficult, even for trained specialists, due to artifacts and low contrast. The recent advances in deep learning make neural networks a potential tool for accurate nerve segmentation systems, so addressing the above issues from raw data. The most widely spread U-Net network yields pixel-by-pixel segmentation by encoding the input image and decoding the attained feature vector into a semantic image. This work proposes a conditioning approach and encoder pre-training to enhance the nerve segmentation of traditional U-Nets. Conditioning is achieved by the one-hot encoding of the kind of target nerve a the network input, while the pre-training considers five well-known deep networks for image classification. The proposed approach is tested in a collection of 619 US images, where the best C-UNet architecture yields an 81% Dice coefficient, outperforming the 74% of the best traditional U-Net. Results prove that pre-trained models with the conditional approach outperform their equivalent baseline by supporting learning new features and enriching the discriminant capability of the tested networks.

Keywords: nerve segmentation, U-Net, deep learning, ultrasound imaging, peripheral nerve blocking

Procedia PDF Downloads 105

Authors: Vishnu Pratap Singh Kirar

Abstract:

Artificial Neural Network (ANN) can be trained using backpropagation (BP). It is the most widely used algorithm for supervised learning with multi-layered feed-forward networks. Efficient learning by the BP algorithm is required for many practical applications. The BP algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a two-term algorithm consisting of a learning rate (LR) and a momentum factor (MF). The major drawbacks of the two-term BP learning algorithm are the problems of local minima and slow convergence speeds, which limit the scope for real-time applications. Recently the addition of an extra term, called a proportional factor (PF), to the two-term BP algorithm was proposed. The third increases the speed of the BP algorithm. However, the PF term also reduces the convergence of the BP algorithm, and criteria for evaluating convergence are required to facilitate the application of the three terms BP algorithm. Although these two seem to be closely related, as described later, we summarize various improvements to overcome the drawbacks. Here we compare the different methods of convergence of the new three-term BP algorithm.

Keywords: neural network, backpropagation, local minima, fast convergence rate

Procedia PDF Downloads 498

Authors: Suha Alawadhi, Malak Alrasheed

Abstract:

In the recent past, public participation in governments has been declined to a great extent, as citizens have been isolated from community life and their ability to articulate demands for good government has been noticeably decreased. However, the Internet has introduced new forms of interaction that could enhance different types of relationships, including government-public relationship. In fact, technology-enabled government has become a catalyst for enabling social inclusion. This exploratory study seeks to investigate public perceptions in Kuwait regarding the use of social media networks in government where social capital is built to achieve social inclusion. Social capital has been defined as social networks and connections amongst individuals, that are based on shared trust, ideas and norms, enable participants of a network to act effectively to pursue a shared objective. The quantitative method was used to generate empirical evidence. A questionnaire was designed to address the research objective and reflect the identified constructs: social capital dimensions (bridging, bonding and maintaining social capital), social inclusion, and social equality. In this pilot study, data was collected from a random sample of 61 subjects. The results indicate that all participants have a positive attitude towards the dimensions of social capital (bridging, bonding and maintaining), social inclusion and social equality constructs. Tests of identified constructs against demographic characteristics indicate that there are significant differences between male and female as they perceived bonding and maintaining social capital, social inclusion and social equality whereas no difference was identified in their perceptions of bridging social capital. Also, those who are aged 26-30 perceived bonding and maintaining social capital, social inclusion and social equality negatively compared to those aged 20-25, 31-35, and 40-above whose perceptions were positive. With regard to education, the results also show that those holding high school, university degree and diploma perceived maintaining social capital positively higher than with those who hold graduate degrees. Moreover, a regression model is proposed to study the effect of bridging, bonding, and maintaining social capital on social inclusion via social equality as a mediator. This exploratory study is necessary for testing the validity and reliability of the questionnaire which will be used in the main study that aims to investigate the perceptions of individuals towards building social capital to achieve social inclusion.

Keywords: government, social capital, social inclusion, social networks

Procedia PDF Downloads 326

Authors: Konstans Ruseva, Kristina Ivanova, Katerina Todorova, Margarita Gabrashanska, Tzanko Tzanov, Elena Vassileva

Abstract:

Zwitterionic polymers (ZP) are well-known with their ultralow biofouling. They are successfully competing with poly(ethylene glycols) (PEG), which are considered as the “golden standard” in this respect. These unique properties are attributed to their strong hydration capacity, defined by the dipole-dipole interactions, arising between the ZP pendant groups as well as to the dipoles interaction with water molecules. Beside, ZP are highly resistant to bacterial adhesion thus ensuring an excellent anti-biofilm formation ability. Moreover, ZP are able to respond upon external stimuli such as temperature, pH, salt concentration changes which in combination with their anti-biofouling effect render this type of polymers as materials with a high potential in biomedical applications. The present work is focused on the development of zwitterionic hydrogels for efficient treatment of highly exudating and hard-to-heal chronic wounds. To this purpose, two types of ZP networks with different crosslinking degree were synthesized - polysulfobetaine (PSB) and polycarboxybetaine (PCB) ones. They were characterized in terms of their physico-mechanical properties, e.g. microhardness, swelling ability, smart behaviour. Furthermore, the potential of ZP networks to resist biofilm formation towards Staphylococcus aureus and Escherichia coli was studied. Their ability to reduce the high levels of myeloperoxidase and metalloproteinase, two enzymes that are part of the chronic wounds enviroenment, was revealed. Moreover, the in vitro cytotoxic assessment of PSB and PCB networks along with their in vivo performance in rats was also studied to reveal their high biocompatibility.

Keywords: absorption properties, biocompatibility, enzymatic inhibition activity, wound healing, zwitterionic polymers

Procedia PDF Downloads 196

Authors: Freddy Rodriguez Saza, Erika Sanabria, Jair Tibana

Abstract:

Currently, the important role of neurosciences in the professional training of the physical educator is known, highlighting in the teaching-learning process aspects such as the nervous structures involved in the adjustment of posture and movement, the neurophysiology of locomotion, the process of nerve impulse transmission, and the relationship between physical activity, learning, and cognition. The teaching-learning process of neurosciences is complex, due to the breadth of the contents, the diversity of teaching contexts required, and the demanding ability to relate concepts from different disciplines, necessary for the correct understanding of the function of the nervous system. This text presents the results of the application of a didactic environment based on the Allosteric Learning Model in morphophysiology students of the Faculty of Military Physical Education, Military School of Cadets of the Colombian Army (Bogotá, Colombia). The research focused then, on analyzing the change in the cognitive structure of the students on neurosciences. Methodology. [1] The predominant learning styles were identified. [2] Students' cognitive structure, core concepts, and threshold concepts were analyzed through the construction of Pathfinder Associative Networks. [3] Didactic Units in Neuroscience were designed to favor metacognition, the development of Executive Functions (working memory, cognitive flexibility, and inhibitory control) that led students to recognize their errors and conceptual distortions and to overcome them. [4] The Teacher's Professional Knowledge and the role of the assessment strategies applied were taken into account, taking into account the perspective of the Dynamizer, Obstacle, and Questioning axes. In conclusion, the study found that physical education students achieved significant learning in neuroscience, favored by the development of executive functions and by didactic environments oriented with the predominant learning styles and focused on increasing cognitive networks and overcoming difficulties, neuromyths and neurophobia.

Keywords: allosteric learning model, military physical education, neurosciences, pathfinder associative networks, teacher professional knowledge

Procedia PDF Downloads 235

Authors: Udayan Patankar, Shashwati Bhagat, Vilas Nitneware, Ants Koel

Abstract:

An ISM band power amplifier is a type of electronic amplifier used to convert a low-power radio-frequency signal into a larger signal of significant power, typically used for driving the antenna of a transmitter. Due to drastic changes in telecommunication generations may lead to the requirements of improvements. Rapid changes in communication lead to the wide implementation of WLAN technology for its excellent characteristics, such as high transmission speed, long communication distance, and high reliability. Many applications such as WLAN, Bluetooth, and ZigBee, etc. were evolved with 2.4GHz to 5 GHz ISM Band, in which the power amplifier (PA) is a key building block of RF transmitters. There are many manufacturing processes available to manufacture a power amplifier for desired power output, but the major problem they have faced is about the power it consumed for its proper working, as many of them are fabricated on the GaN HEMT, Bi COMS process. In this paper we present a CMOS Base two stage cascode design of power amplifier working on 2.4GHz ISM frequency band. To lower the costs and allow full integration of a complete System-on-Chip (SoC) we have chosen 0.13µm low power CMOS technology for design. While designing a power amplifier, it is a real task to achieve higher power efficiency with minimum resources. This design showcase the Multi biased Cascode methodology to implement a two-stage CMOS power amplifier using ADS and LTSpice simulating tool. Main source is maximum of 2.4V which is internally distributed into different biasing point VB driving and VB driven as required for distinct stages of two stage RF power amplifier. It shows maximum power added efficiency near about 70.195% whereas its Power added efficiency calculated at 1 dB compression point is 44.669 %. Biased MOSFET is used to reduce total dc current as this circuit is designed for different wireless applications comes under 2.4GHz ISM Band.

Keywords: RFIC, PAE, RF CMOS, impedance matching

Procedia PDF Downloads 222

Authors: A. Mohammadpour, Ebrahim Najafi Kajabad, Ghazale Ipakchi

Abstract:

Presently, computer networks’ security rise in importance and many studies have also been conducted in this field. By the penetration of the internet networks in different fields, many things need to be done to provide a secure industrial and non-industrial network. Fire walls, appropriate Intrusion Detection Systems (IDS), encryption protocols for information sending and receiving, and use of authentication certificated are among things, which should be considered for system security. The aim of the present study is to use the outcome of several algorithms, which cause decline in IDS errors, in the way that improves system security and prevents additional overload to the system. Finally, regarding the obtained result we can also detect the amount and percentage of more sub attacks. By running the proposed system, which is based on the use of multi-algorithmic outcome and comparing that by the proposed single algorithmic methods, we observed a 78.64% result in attack detection that is improved by 3.14% than the proposed algorithms.

Keywords: intrusion detection systems, clustering, k-means, k-medoids, SV clustering, ensemble

Procedia PDF Downloads 221

Authors: Shweta Singh, Sudaman Katti

Abstract:

The most well-known sequence models make use of complex recurrent neural networks in an encoder-decoder configuration. The model used in this research makes use of a transformer, which is based purely on a self-attention mechanism, without relying on recurrence at all. More specifically, encoders and decoders which make use of self-attention and operate based on a memory, are used. In this research work, results for various 3D visual and non-visual reinforcement learning tasks designed in Unity software were obtained. Convolutional neural networks, more specifically, nature CNN architecture, are used for input processing in visual tasks, and comparison with standard long short-term memory (LSTM) architecture is performed for both visual tasks based on CNNs and non-visual tasks based on coordinate inputs. This research work combines the transformer architecture with the proximal policy optimization technique used popularly in reinforcement learning for stability and better policy updates while training, especially for continuous action spaces, which are used in this research work. Certain tasks in this paper are long horizon tasks that carry on for a longer duration and require extensive use of memory-based functionalities like storage of experiences and choosing appropriate actions based on recall. The transformer, which makes use of memory and self-attention mechanism in an encoder-decoder configuration proved to have better performance when compared to LSTM in terms of exploration and rewards achieved. Such memory based architectures can be used extensively in the field of cognitive robotics and reinforcement learning.

Keywords: convolutional neural networks, reinforcement learning, self-attention, transformers, unity

Procedia PDF Downloads 135

Authors: R. Boudjelthia

Abstract:

The aim of this study is to determine the influence of mix composition of concrete as the content of water and cement, water–binder ratio, and the replacement of fly ash on the durability of self compacting concrete (SCC) by using artificial neural networks (ANNs). To achieve this, an ANNs model is developed to predict the durability of self compacting concrete which is expressed in terms of chloride ions permeability in accordance with ASTM C1202-97 or AASHTO T277. Database gathered from the literature for the training and testing the model. A sensitivity analysis was also conducted using the trained and tested ANN model to investigate the effect of fly ash on the durability of SCC. The results indicate that the developed model is reliable and accurate. the durability of SCC expressed in terms of total charge passed over a 6-h period can be significantly improved by using at least 25% fly ash as replacement of cement. This study show that artificial neural network have strong potentialas a feasible tool for predicting accurately the durability of SCC containing fly ash.

Keywords: artificial neural networks, durability, chloride ions permeability, self compacting concrete

Procedia PDF Downloads 377

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 204

Authors: Eshta Ranyal, Kamal Jain, Vikrant Ranyal

Abstract:

Potholes are a severe threat to road safety and a major contributing factor towards road distress. In the Indian context, they are a major road hazard. Timely detection of potholes and subsequent repair can prevent the roads from deteriorating. To facilitate the roadway authorities in the timely detection and repair of potholes, we propose a pothole detection methodology using convolutional neural networks. The YOLOv3 model is used as it is fast and accurate in comparison to other state-of-the-art models. You only look once v3 (YOLOv3) is a state-of-the-art, real-time object detection system that features multi-scale detection. A mean average precision(mAP) of 73% was obtained on a training dataset of 200 images. The dataset was then increased to 500 images, resulting in an increase in mAP. We further calculated the depth of the potholes using stereoscopic vision by reconstruction of 3D potholes. This enables calculating pothole volume, its extent, which can then be used to evaluate the pothole severity as low, moderate, high.

Keywords: CNN, pothole detection, pothole severity, YOLO, stereovision

Procedia PDF Downloads 135

Authors: Mehrdad Shafiei Dizaji, Hoda Azari

Abstract:

The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction, akin to advancements in medical imaging for tracking tumor progression in the human body. This research presents a detailed development framework for a specialized PINN model proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws governing subsurface structures—or, in medical terms, human tissues—the model effectively embeds the physics of electromagnetic wave propagation into its architecture. This ensures that predictions not only align with fundamental physical principles but also mirror the precision needed in medical diagnostics for detecting and monitoring tumors. The suggested deep learning structure comprises three components: a CNN, a spatial feature channel attention (SFCA) mechanism, and ConvLSTM, along with temporal feature frame attention (TFFA) modules. The attention mechanism computes channel attention and temporal attention weights using self-adaptation, thereby fine-tuning the visual and temporal feature responses to extract the most pertinent and significant visual and temporal features. By integrating physics directly into the neural network, our model has shown enhanced accuracy in forecasting GPR data. This improvement is vital for conducting effective assessments of bridge deck conditions and other evaluations related to civil infrastructure. The use of Physics-Informed Neural Networks (PINNs) has demonstrated the potential to transform the field of Non-Destructive Evaluation (NDE) by enhancing the precision of infrastructure deterioration predictions. Moreover, it offers a deeper insight into the fundamental mechanisms of deterioration, viewed through the prism of physics-based models.

Keywords: physics-informed neural networks, deep learning, ground-penetrating radar (GPR), NDE, ConvLSTM, physics, data driven

Procedia PDF Downloads 37

Authors: Somayeh Komeylian

Abstract:

The antenna arrays for the entire 3D spherical coverage have been developed for their potential use in variety of applications such as radars and body-worn devices of the body area networks. In this study, we have rigorously revamped the hybrid antenna array using the optimum geometry of bowtie elements for achieving a significant improvement in the angular discrimination capability as well as in separating two adjacent targets. In this scenario, we have analogously investigated the effectiveness of increasing the virtual array length in fostering and enhancing the directivity and angular resolution in the 10 GHz frequency. The simulation results have extensively verified that the proposed antenna array represents a drastic enhancement in terms of size, directivity, side lobe level (SLL) and, especially resolution compared with the other available geometries. We have also verified that the maximum directivities of the proposed hybrid antenna array represent the robustness to the all  variations, which is accompanied by the uniform 3D scanning characteristic.

Keywords: bowtie antenna, hybrid antenna array, array signal processing, body area networks

Procedia PDF Downloads 152

Authors: Yasser F. Hassan

Abstract:

Social networking involves use of an online platform or website that enables people to communicate, usually for a social purpose, through a variety of services, most of which are web-based and offer opportunities for people to interact over the internet, e.g. via e-mail and ‘instant messaging’, by analyzing the voting behavior and ratings of judges in a popular comments in social networks. While most of the party literature omits the electorate, this paper presents a model where elites and parties are emergent consequences of the behavior and preferences of voters. The research in artificial intelligence and psychology has provided powerful illustrations of the way in which the emergence of intelligent behavior depends on the development of representational structure. As opposed to the classical voting system (one person – one decision – one vote) a new voting system is designed where agents with opposed preferences are endowed with a given number of votes to freely distribute them among some issues. The paper uses ideas from machine learning, artificial intelligence and soft computing to provide a model of the development of voting system response in a simulated agent. The modeled development process involves (simulated) processes of evolution, learning and representation development. The main value of the model is that it provides an illustration of how simple learning processes may lead to the formation of structure. We employ agent-based computer simulation to demonstrate the formation and interaction of coalitions that arise from individual voter preferences. We are interested in coordinating the local behavior of individual agents to provide an appropriate system-level behavior.

Keywords: voting system, rough sets, multi-agent, social networks, emergence, power indices

Procedia PDF Downloads 392

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 160

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 186

Authors: Johannes Günther

Abstract:

Time Sensitive Networking (TSN), standardized in the IEEE 802.1 standard, has been lent increasing attention in the context of mission critical systems. Such mission critical systems, e.g., in the automotive domain, aviation, industrial, and smart factory domain, are responsible for coordinating complex functionalities in real time. In many of these contexts, a reliable data exchange fulfilling hard time constraints and quality of service (QoS) conditions is of critical importance. TSN standards are able to provide guarantees for deterministic communication behaviour, which is in contrast to common best-effort approaches. Therefore, the superior QoS guarantees of TSN may aid in the development of new technologies, which rely on low latencies and specific bandwidth demands being fulfilled. TSN extends existing Ethernet protocols with numerous standards, providing means for synchronization, management, and overall real-time focussed capabilities. These additional QoS guarantees, as well as management mechanisms, lead to an increased attack surface for potential malicious attackers. As TSN guarantees certain deadlines for priority traffic, an attacker may degrade the QoS by delaying a packet beyond its deadline or even execute a denial of service (DoS) attack if the delays lead to packets being dropped. However, thus far, security concerns have not played a major role in the design of such standards. Thus, while TSN does provide valuable additional characteristics to existing common Ethernet protocols, it leads to new attack vectors on networks and allows for a range of potential attacks. One answer to these security risks is to deploy defense mechanisms according to a moving target defense (MTD) strategy. The core idea relies on the reduction of the attackers' knowledge about the network. Typically, mission-critical systems suffer from an asymmetric disadvantage. DoS or QoS-degradation attacks may be preceded by long periods of reconnaissance, during which the attacker may learn about the network topology, its characteristics, traffic patterns, priorities, bandwidth demands, periodic characteristics on links and switches, and so on. Here, we implemented and tested several MTD-like defense strategies against different attacker models of varying capabilities and budgets, as well as collaborative attacks of multiple attackers within a network, all within the context of TSN networks. We modelled the networks and tested our defense strategies on an OMNET++ testbench, with networks of different sizes and topologies, ranging from a couple dozen hosts and switches to significantly larger set-ups.

Keywords: network security, time sensitive networking, moving target defense, cyber security

Procedia PDF Downloads 72

Authors: Chia-Feng Lu, Yuh-Jen Wang, Yu-Te Wu, Sui-Hing Yan

Abstract:

This study aimed at investigating whether the functional brain networks constructed using the initial EEG (obtained when patients first visited hospital) can be correlated with the progression of cognitive decline calculated as the changes of mini-mental state examination (MMSE) scores between the latest and initial examinations. We integrated the time–frequency cross mutual information (TFCMI) method to estimate the EEG functional connectivity between cortical regions, and the network analysis based on graph theory to investigate the organization of functional networks in aMCI. Our finding suggested that higher integrated functional network with sufficient connection strengths, dense connection between local regions, and high network efficiency in processing information at the initial stage may result in a better prognosis of the subsequent cognitive functions for aMCI. In conclusion, the functional connectivity can be a useful biomarker to assist in prediction of cognitive declines in aMCI.

Keywords: cognitive decline, functional connectivity, MCI, MMSE

Procedia PDF Downloads 383

Authors: Wiseborn Manfe Danquah, D. Turgay Altilar

Abstract:

Vehicular Ad-hoc Network (VANET) is an integral component of Intelligent Transport Systems (ITS) that has enjoyed a lot of attention from the research community and the automotive industry. This is mainly due to the opportunities and challenges it presents. Vehicular Ad-hoc Network being a class of Mobile Ad-hoc Networks (MANET) has all the security concerns existing in traditional MANET as well as new security and privacy concerns introduced by the unique vehicular communication environment. This paper provides a survey of the possible attacks in vehicular environment, as well as security and privacy concerns in VANET. It also provides an insight into the development of a comprehensive cloud framework to provide a more robust and secured communication among vehicular nodes and road side units. Our proposal, a Metropolitan Based Public Interconnected Vehicular Cloud (MIVC) infrastructure seeks to provide a more reliable and secured vehicular communication network.

Keywords: mobile Ad-hoc networks, vehicular ad hoc network, cloud, ITS, road side units (RSU), metropolitan interconnected vehicular cloud (MIVC)

Procedia PDF Downloads 354

Authors: M. Heydari Vini

Abstract:

There is a complicated relation between effective input parameters of cold rolling and output rolling force and exit thickness of strips.in many mathematical models, the effect of some rolling parameters have been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips,the width of the strips,rolling speeds,mandrill tensions and the required exit thickness of strips with rolling force and the real exit thickness of the rolled strip. First of all, in this paper the effective parameters of cold rolling process modeled using an artificial neural network according to the optimum network achieved by using a written program in MATLAB,it has been shown that the prediction of rolling stand parameters with different properties and new dimensions attained from prior rolled strips by an artificial neural network is applicable.

Keywords: cold rolling, artificial neural networks, rolling force, real rolled thickness of strips

Procedia PDF Downloads 504

Authors: Prashansa Singh, Rohit Bajaj, Manjot Kaur

Abstract:

In the modern agricultural landscape, precision farming has emerged as a pivotal strategy for enhancing crop yield and optimizing resource utilization. This paper introduces an innovative Crop Recommendation System (CRS) that leverages the Internet of Things (IoT) technology and the Message Queuing Telemetry Transport (MQTT) protocol to collect critical environmental and soil data via sensors deployed across agricultural fields. The system is designed to address the challenges of real-time data acquisition, efficient data transmission, and dynamic crop recommendation through the application of advanced Artificial Intelligence (AI) and Machine Learning (ML) models. The CRS architecture encompasses a network of sensors that continuously monitor environmental parameters such as temperature, humidity, soil moisture, and nutrient levels. This sensor data is then transmitted to a central MQTT server, ensuring reliable and low-latency communication even in bandwidth-constrained scenarios typical of rural agricultural settings. Upon reaching the server, the data is processed and analyzed by AI/ML models trained to correlate specific environmental conditions with optimal crop choices and cultivation practices. These models consider historical crop performance data, current agricultural research, and real-time field conditions to generate tailored crop recommendations. This implementation gets 99% accuracy.

Keywords: Iot, MQTT protocol, machine learning, sensor, publish, subscriber, agriculture, humidity

Procedia PDF Downloads 65

Authors: Yusuf Seedat

Abstract:

The necessity to understand global financial markets has increased following the unfortunate spread of the recent financial crisis around the world. Financial markets are considered to be complex systems consisting of highly volatile move-ments whose indexes fluctuate without any clear pattern. Analytic methods of stock prices have been proposed in which financial markets are modeled using common network analysis tools and methods. It has been found that two key components of social network analysis are relevant to modeling financial markets, allowing us to forecast accurate predictions of stock prices within the financial market. Financial markets have a number of interacting components, leading to complex behavioral patterns. This paper describes a social network approach to analyzing financial markets as a viable approach to studying the way complex stock markets function. We also look at how social network analysis techniques and metrics are used to gauge an understanding of the evolution of financial markets as well as how community detection can be used to qualify and quantify in-fluence within a network.

Keywords: network analysis, social networks, financial markets, stocks, nodes, edges, complex networks

Procedia PDF Downloads 190

Authors: Gizem Eser Erdek

Abstract:

This study is research on predicting the remaining life of industrial cutting tools used in the industrial production process with deep learning methods. When the life of cutting tools decreases, they cause destruction to the raw material they are processing. This study it is aimed to predict the remaining life of the cutting tool based on the damage caused by the cutting tools to the raw material. For this, hole photos were collected from the hole-drilling machine for 8 months. Photos were labeled in 5 classes according to hole quality. In this way, the problem was transformed into a classification problem. Using the prepared data set, a model was created with convolutional neural networks, which is a deep learning method. In addition, VGGNet and ResNet architectures, which have been successful in the literature, have been tested on the data set. A hybrid model using convolutional neural networks and support vector machines is also used for comparison. When all models are compared, it has been determined that the model in which convolutional neural networks are used gives successful results of a %74 accuracy rate. In the preliminary studies, the data set was arranged to include only the best and worst classes, and the study gave ~93% accuracy when the binary classification model was applied. The results of this study showed that the remaining life of the cutting tools could be predicted by deep learning methods based on the damage to the raw material. Experiments have proven that deep learning methods can be used as an alternative for cutting tool life estimation.

Keywords: classification, convolutional neural network, deep learning, remaining life of industrial cutting tools, ResNet, support vector machine, VggNet

Procedia PDF Downloads 75

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 263

Authors: Sangwoo Oh, Jaewoo Kim, Dongmin Seo, Jaewon Park, Yongha Hwang, Sungkyu Seo

Abstract:

Plasmonics has been regarded one of the most powerful bio-sensing modalities to evaluate bio-molecular interactions in real-time. However, most of the plasmonic sensing methods are based on labeling metallic nanoparticles, e.g. gold or silver, as optical modulation markers, which are non-recyclable and expensive. This plasmonic modulation can be usually achieved through various nano structures, e.g., nano-hole arrays. Among those structures, plasmonic lens has been regarded as a unique plasmonic structure due to its light focusing characteristics. In this study, we introduce a custom designed plasmonic lens array for bio-sensing, which was simulated by finite-difference-time-domain (FDTD) approach and fabricated by top-down approach. In our work, we performed the FDTD simulations of various plasmonic lens designs for bacteria sensor, i.e., Samonella and Hominis. We optimized the design parameters, i.e., radius, shape, and material, of the plasmonic lens. The simulation results showed the change in the peak intensity value with the introduction of each bacteria and antigen i.e., peak intensity 1.8711 a.u. with the introduction of antibody layer of thickness of 15nm. For Salmonella, the peak intensity changed from 1.8711 a.u. to 2.3654 a.u. and for Hominis, the peak intensity changed from 1.8711 a.u. to 3.2355 a.u. This significant shift in the intensity due to the interaction between bacteria and antigen showed a promising sensing capability of the plasmonic lens. With the batch processing and bulk production of this nano scale design, the cost of biological sensing can be significantly reduced, holding great promise in the fields of clinical diagnostics and bio-defense.

Keywords: plasmonic lens, FDTD, fabrication, bacteria sensor, salmonella, hominis

Procedia PDF Downloads 269