Search results for: recurrent artificial neural network

Authors: Shi-Yu Xu

Abstract:

The top three risk factors that have contributed to building collapses during past earthquake events in Taiwan are: "irregular floor plans or elevations," "insufficient columns in single-bay buildings," and the "weak-story problem." Fortunately, these unsound structural characteristics can be directly identified from the floor plans. However, due to the vast number of old buildings, conducting manual inspections to identify these compromised structural features in all existing structures would be time-consuming and prone to human errors. This study aims to develop an algorithm that utilizes artificial intelligence techniques to automatically pinpoint the structural components within a building's floor plans. The obtained spatial information will be utilized to construct a digital structural model of the building. This information, particularly regarding the distribution of columns in the floor plan, can then be used to conduct preliminary seismic assessments of the building. The study employs various image processing and pattern recognition techniques to enhance detection efficiency and accuracy. The study enables a large-scale evaluation of structural vulnerability for numerous old buildings, providing ample time to arrange for structural retrofitting in those buildings that are at risk of significant damage or collapse during earthquakes.

Keywords: structural vulnerability detection, object recognition, seismic capacity assessment, old buildings, artificial intelligence

Procedia PDF Downloads 91

Authors: Simon Grossemy, Peggy P. Y. Chan, Pauline M. Doran

Abstract:

Nerve tissue engineering is the main field of research aimed at finding an alternative to autografts as a treatment for nerve injuries. Scaffolds are used as a support to enhance nerve regeneration. In order to successfully design novel scaffolds and in vitro cell culture systems, a deep understanding of the factors affecting nerve regeneration processes is needed. Physical and biological parameters associated with the culture environment have been identified as potentially influential in nerve cell differentiation, including electrical stimulation, exposure to extracellular-matrix (ECM) proteins, dynamic medium conditions and co-culture with glial cells. The mechanisms involved in driving the cell to differentiation in the presence of these factors are poorly understood; the complexity of each of them raises the possibility that they may strongly influence each other. Some questions that arise in investigating nerve regeneration include: What are the best protein coatings to promote neural cell attachment? Is the scaffold design suitable for providing all the required factors combined? What is the influence of dynamic stimulation on cell viability and differentiation? In order to study these effects, scaffolds adaptable to bioreactor culture conditions were designed to allow electrical stimulation of cells exposed to ECM proteins, all within a dynamic medium environment. Gold coatings were used to make the surface of viscose rayon microfiber scaffolds (VRMS) conductive, and poly-L-lysine (PLL) and laminin (LN) surface coatings were used to mimic the ECM environment and allow the attachment of rat PC12 neural cells. The robustness of the coatings was analyzed by surface resistivity measurements, scanning electron microscope (SEM) observation and immunocytochemistry. Cell attachment to protein coatings of PLL, LN and PLL+LN was studied using DNA quantification with Hoechst. The double coating of PLL+LN was selected based on high levels of PC12 cell attachment and the reported advantages of laminin for neural differentiation. The underlying gold coatings were shown to be biocompatible using cell proliferation and live/dead staining assays. Coatings exhibiting stable properties over time under dynamic fluid conditions were developed; indeed, cell attachment and the conductive power of the scaffolds were maintained over 2 weeks of bioreactor operation. These scaffolds are promising research tools for understanding complex neural cell behavior. They have been used to investigate major factors in the physical culture environment that affect nerve cell viability and differentiation, including electrical stimulation, bioreactor hydrodynamic conditions, and combinations of these parameters. The cell and tissue differentiation response was evaluated using DNA quantification, immunocytochemistry, RT-qPCR and functional analyses.

Keywords: bioreactor, electrical stimulation, nerve differentiation, PC12 cells, scaffold

Procedia PDF Downloads 248

Authors: Shivendra Pratap Singh, Rishabh Sharma

Abstract:

The widespread adoption of mobile technology in recent years has revolutionized the way we communicate and access information. The evolution of mobile systems has been rapid and impactful, shaping our lives and changing the way we live and work. However, despite its significant influence, the history and development of mobile technology are not well understood by the general public. This research paper aims to examine the history, technology and future of mobile systems, exploring their evolution from early mobile phones to the latest smartphones and beyond. The study will analyze the technological advancements and innovations that have shaped the mobile industry, from the introduction of mobile internet and multimedia capabilities to the integration of artificial intelligence and 5G networks. Additionally, the paper will also address the challenges and opportunities facing the future of mobile technology, such as privacy concerns, battery life, and the increasing demand for high-speed internet. Finally, the paper will also provide insights into potential future developments and innovations in the mobile sector, such as foldable phones, wearable technology, and the Internet of Things (IoT). The purpose of this research paper is to provide a comprehensive overview of the history, technology, and future of mobile systems, shedding light on their impact on society and the challenges and opportunities that lie ahead.

Keywords: mobile technology, artificial intelligence, networking, iot, technological advancements, smartphones

Procedia PDF Downloads 94

Authors: Bashir Abdu Muzakkari, Mohamad Afendee Mohamad, Mohd Fadzil Abdul Kadir

Abstract:

Wireless Sensor Networks (WSNs) is an aggregation of several tiny, low-cost sensor nodes, spatially distributed to monitor physical or environmental status. WSN is constantly changing because of the rapid technological advancements in sensor elements such as radio, battery and operating systems. The Medium Access Control (MAC) protocols remain very vital in the WSN because of its role in coordinating communication amongst the sensors. Other than battery consumption, packet collision, network lifetime and latency are factors that largely depend on WSN MAC protocol and these factors have been widely treated in recent days. In this paper, we survey some latest proposed WSN Contention-based, Scheduling-based and Hybrid MAC protocols while presenting an examination, correlation of advantages and limitations of each protocol. Concentration is directed towards investigating the treatment of Quality of Service (QoS) performance metrics within these particular protocols. The result shows that majority of the protocols leaned towards energy conservation. We, therefore, believe that other performance metrics of guaranteed QoS such as latency, throughput, packet loss, network and bandwidth availability may play a critical role in the design of future MAC protocols for WSNs.

Keywords: WSN, QoS, energy consumption, MAC protocol

Procedia PDF Downloads 402

Authors: Mehrnaz Aminifar

Abstract:

The relation between textural parameters and casein network on release of aromatic compounds was investigated over 90-days of ripening. Low DE maltodextrin and WPI were used to modify the textural properties of low fat brined cheese. Hardness, brittleness and compaction of casein network were affected by addition of maltodextrin and WPI. Textural properties and aroma release from cheese texture were affected by interaction of WPI protein-cheese protein and maltodexterin-cheese protein.

Keywords: aroma release, brined cheese, maltodexterin, WPI

Procedia PDF Downloads 356

Authors: Harris Niavis, Dimitra Politaki

Abstract:

The manufacturing industry was collecting vast amounts of data for monitoring product quality thanks to the advances in the ICT sector and dedicated IoT infrastructure is deployed to track and trace the production line. However, industries have not yet managed to unleash the full potential of these data due to defective data collection methods and untrusted data storage and sharing. Blockchain is gaining increasing ground as a key technology enabler for Industry 4.0 and the smart manufacturing domain, as it enables the secure storage and exchange of data between stakeholders. On the other hand, AI techniques are more and more used to detect anomalies in batch and time-series data that enable the identification of unusual behaviors. The proposed scheme is based on smart contracts to enable automation and transparency in the data exchange, coupled with anomaly detection algorithms to enable reliable data ingestion in the system. Before sensor measurements are fed to the blockchain component and the smart contracts, the anomaly detection mechanism uniquely combines artificial intelligence models to effectively detect unusual values such as outliers and extreme deviations in data coming from them. Specifically, Autoregressive integrated moving average, Long short-term memory (LSTM) and Dense-based autoencoders, as well as Generative adversarial networks (GAN) models, are used to detect both point and collective anomalies. Towards the goal of preserving the privacy of industries' information, the smart contracts employ techniques to ensure that only anonymized pointers to the actual data are stored on the ledger while sensitive information remains off-chain. In the same spirit, blockchain technology guarantees the security of the data storage through strong cryptography as well as the integrity of the data through the decentralization of the network and the execution of the smart contracts by the majority of the blockchain network actors. The blockchain component of the Data Traceability Software is based on the Hyperledger Fabric framework, which lays the ground for the deployment of smart contracts and APIs to expose the functionality to the end-users. The results of this work demonstrate that such a system can increase the quality of the end-products and the trustworthiness of the monitoring process in the smart manufacturing domain. The proposed AI-enabled data traceability software can be employed by industries to accurately trace and verify records about quality through the entire production chain and take advantage of the multitude of monitoring records in their databases.

Keywords: blockchain, data quality, industry4.0, product quality

Procedia PDF Downloads 191

Authors: Pitigalage Chamath Chandira Peiris

Abstract:

A widely researched domain in the field of image processing in recent times has been single image super-resolution, which tries to restore a high-resolution image from a single low-resolution image. Many more single image super-resolution efforts have been completed utilizing equally traditional and deep learning methodologies, as well as a variety of other methodologies. Deep learning-based super-resolution methods, in particular, have received significant interest. As of now, the most advanced image restoration approaches are based on convolutional neural networks; nevertheless, only a few efforts have been performed using Transformers, which have demonstrated excellent performance on high-level vision tasks. The effectiveness of CNN-based algorithms in image super-resolution has been impressive. However, these methods cannot completely capture the non-local features of the data. Enhancer is a simple yet powerful Transformer-based approach for enhancing the resolution of images. A method for single image super-resolution was developed in this study, which utilized an efficient and effective transformer design. This proposed architecture makes use of a locally enhanced window transformer block to alleviate the enormous computational load associated with non-overlapping window-based self-attention. Additionally, it incorporates depth-wise convolution in the feed-forward network to enhance its ability to capture local context. This study is assessed by comparing the results obtained for popular datasets to those obtained by other techniques in the domain.

Keywords: single image super resolution, computer vision, vision transformers, image restoration

Procedia PDF Downloads 107

Authors: Shunsuke Saito, Kazuho Yoshimoto, Shunichi Ohmori, Sirawadee Arunyanart

Abstract:

In this paper, we suggest a mechanism of assessment that rater and Ratee (or employees) to convince. There are many problems exist in the personnel assessment. In particular, we were focusing on the three. (1) Raters are not sufficiently recognized assessment point. (2) Ratee are not convinced by the mechanism of assessment. (3) Raters (or Evaluators) and ratees have empathy. We suggest 1: Setting of "understanding of the assessment points." 2: Setting of "relative assessment ability." 3: Proposal of two-way assessment mechanism to solve these problems. As a prerequisite, it is assumed that there are multiple raters. This is because has been a growing importance of multi-faceted assessment. In this model, it determines the weight of each assessment point evaluators by the degree of understanding and assessment ability of raters and ratee. We used the ANP (Analytic Network Process) is a theory that an extension of the decision-making technique AHP (Analytic Hierarchy Process). ANP can be to address the problem of forming a network and assessment of Two-Way is possible. We apply this technique personnel assessment, the weights of rater of each point can be reasonably determined. We suggest absolute assessment for Two-Way assessment by ANP. We have verified that the consent of the two approaches is higher than conventional mechanism. Also, human resources consultant we got a comment about the application of the practice.

Keywords: personnel evaluation, pairwise comparison, analytic network process (ANP), two-ways

Procedia PDF Downloads 384

Authors: Nicola Rubino

Abstract:

This paper presents an analysis of a group of commodity exporting countries' nominal exchange rate movements in relationship to the US dollar. Using a series of Unrestricted Self-exciting Threshold Autoregressive models (SETAR), we model and evaluate sixteen national CPI price differentials relative to the US dollar CPI. Out-of-sample forecast accuracy is evaluated through calculation of mean absolute error measures on the basis of two-hundred and fifty-three months rolling window forecasts and extended to three additional models, namely a logistic smooth transition regression (LSTAR), an additive non linear autoregressive model (AAR) and a simple linear Neural Network model (NNET). Our preliminary results confirm presence of some form of TAR non linearity in the majority of the countries analyzed, with a relatively higher goodness of fit, with respect to the linear AR(1) benchmark, in five countries out of sixteen considered. Although no model appears to statistically prevail over the other, our final out-of-sample forecast exercise shows that SETAR models tend to have quite poor relative forecasting performance, especially when compared to alternative non-linear specifications. Finally, by analyzing the implied half-lives of the > coefficients, our results confirms the presence, in the spirit of arbitrage band adjustment, of band convergence with an inner unit root behaviour in five of the sixteen countries analyzed.

Keywords: transition regression model, real exchange rate, nonlinearities, price differentials, PPP, commodity points

Procedia PDF Downloads 282

Authors: Chia-Chi Chang, Chuan-Bi Lin, Chia-Min Chan

Abstract:

Most ZigBee sensor networks to date make use of nodes with limited processing, communication, and energy capabilities. Energy consumption is of great importance in wireless sensor applications as their nodes are commonly battery-driven. Once ZigBee nodes are deployed outdoors, limited power may make a sensor network useless before its purpose is complete. At present, there are two strategies for long node and network lifetime. The first strategy is saving energy as much as possible. The energy consumption will be minimized through switching the node from active mode to sleep mode and routing protocol with ultra-low energy consumption. The second strategy is to evaluate the energy consumption of sensor applications as accurately as possible. Erroneous energy model may render a ZigBee sensor network useless before changing batteries. In this paper, we present a ZigBee wireless sensor node with four key modules: a processing and radio unit, an energy harvesting unit, an energy storage unit, and a sensor unit. The processing unit uses CC2530 for controlling the sensor, carrying out routing protocol, and performing wireless communication with other nodes. The harvesting unit uses a 2W solar panel to provide lasting energy for the node. The storage unit consists of a rechargeable 1200 mAh Li-ion battery and a battery charger using a constant-current/constant-voltage algorithm. Our solution to extend node lifetime is implemented. Finally, a long-term sensor network test is used to exhibit the functionality of the solar powered system.

Keywords: ZigBee, Li-ion battery, solar panel, CC2530

Procedia PDF Downloads 376

Authors: P. G. Kaviya, B. Muthupandian, R. Ganesan

Abstract:

On-chip routers typically have buffers are used input or output ports for temporarily storing packets. The buffers are consuming some router area and power. The multiple queues in parallel as in VC router. While running a traffic trace, not all input ports have incoming packets needed to be transferred. Therefore large numbers of queues are empty and others are busy in the network. So the time consumption should be high for the high traffic. Therefore using a RoShaQ, minimize the buffer area and time The RoShaQ architecture was send the input packets are travel through the shared queues at low traffic. At high load traffic the input packets are bypasses the shared queues. So the power and area consumption was reduced. A parallel cross bar architecture is proposed in this project in order to reduce the power consumption. Also a new adaptive weighted routing algorithm for 8-port router architecture is proposed in order to decrease the delay of the network on chip router. The proposed system is simulated using Modelsim and synthesized using Xilinx Project Navigator.

Keywords: buffer, RoShaQ architecture, shared queue, VC router, weighted routing algorithm

Procedia PDF Downloads 543

Authors: Jun-Ho Park, Kwang-Woo Nam, Seung-Mo Hong, Tae-Heon Moon, Sang-Ho Lee, Youn-Taik Leem

Abstract:

The aim of this study was to build ‘Ubi-Net’, a decision-making support system for systematic establishment in U-City planning. We have experienced various urban problems caused by high-density development and population concentrations in established urban areas. To address these problems, a U-Service contributes to the alleviation of urban problems by providing real-time information to citizens through network connections and related information. However, technology, devices, and information for consumers are required for systematic U-Service planning in towns and cities where there are many difficulties in this regard, and a lack of reference systems. Thus, this study suggests methods to support the establishment of sustainable planning by providing comprehensive information including IT technology, devices, news, and social networking services(SNS) to U-City planners through intelligent searches. In this study, we targeted Smart U-Parking Planning to solve parking problems in an ‘old’ city. Through this study, we sought to contribute to supporting advances in U-Space and the alleviation of urban problems.

Keywords: desigin and decision support system, smart u-parking planning, social network analysis, urban engineering

Procedia PDF Downloads 428

Authors: Yasin Tadayonrad

Abstract:

Most of the supply chain networks have many nodes starting from the suppliers’ side up to the customers’ side that each node sends/receives the raw materials/products from/to the other nodes. One of the major concerns in this kind of supply chain network is finding the best schedule for loading /unloading the shipments through the whole network by which all the constraints in the source and destination nodes are met and all the shipments are delivered on time. One of the main constraints in this problem is loading/unloading capacity in each source/ destination node at each time slot (e.g., per week/day/hour). Because of the different characteristics of different products/groups of products, the capacity of each node might differ based on each group of products. In most supply chain networks (especially in the Fast-moving consumer goods industry), there are different planners/planning teams working separately in different nodes to determine the loading/unloading timeslots in source/destination nodes to send/receive the shipments. In this paper, a mathematical problem has been proposed to find the best timeslots for loading/unloading the shipments minimizing the overall delays subject to respecting the capacity of loading/unloading of each node, the required delivery date of each shipment (considering the lead-times), and working-days of each node. This model was implemented on python and solved using Python-MIP on a sample data set. Finally, the idea of a heuristic algorithm has been proposed as a way of improving the solution method that helps to implement the model on larger data sets in real business cases, including more nodes and shipments.

Keywords: supply chain management, transportation, multiple-multiple network, timeslots management, mathematical modeling, mixed integer programming

Procedia PDF Downloads 92

Authors: William Batson, Yunsik Song, Abel Simie

Abstract:

Recent trends in suburban design and planning have centered on economic efficiency in construction and completion. In doing so, developers, builders, and architects have bypassed free and reliable sustainable solutions to minimize the carbon footprint and improve the environment. Often, suburban areas are designed without landscape features, sidewalks, parks, adequate lighting, or walking space. Much of the design concern involves minimizing construction costs and streamlining streets and utilities. A new development in creating retention ponds to mitigate flooding and slow runoff is one step in the positive direction. However, "if you build them (suburbs), they (fauna) will come." The inevitable flora and fauna that soon propagate and take refuge within these artificial retention ponds create an additional dilemma. Architects, planners, and developers know the requirements and current strategies to provide residents and wildlife with a viable and sustainable environment. This includes habitat for hibernating animals and facilitating opportunities, especially for cold-blooded mammals. Many species that migrate to these artificial ponds struggle to survive, especially during flooding and when the water table drains below the artificial rim, preventing aquatic mammals from climbing on land. This flooding often results from large areas of impervious asphalt and concrete. These impervious surfaces retain and dispense large amounts of rainwater and contaminants that carry industrial pollutants, oil, plastics, animal waste, and fertilizers into storm drains and then deposited in these retention ponds. This paper will identify and show how simple and logical solutions are used to create a sustainable suburb and reduce the carbon footprint using landscape architectural strategies and cost-free design solutions. We will also demonstrate simple changes in the present suburban design model to provide a viable and sustainable suburb for the 21st century.

Keywords: sustainavilty, suburban, flora, fauna, carbon footprint

Procedia PDF Downloads 74

Authors: Ismene Ithai Bras-Ruiz

Abstract:

Learning Analytics (LA) is employed by universities not only as a tool but as a specialized ground to enhance students and professors. However, not all the academic programs apply LA with the same goal and use the same tools. In fact, LA is formed by five main fields of study (academic analytics, action research, educational data mining, recommender systems, and personalized systems). These fields can help not just to inform academic authorities about the situation of the program, but also can detect risk students, professors with needs, or general problems. The highest level applies Artificial Intelligence techniques to support learning practices. LA has adopted different techniques: statistics, ethnography, data visualization, machine learning, natural language process, and data mining. Is expected that any academic program decided what field wants to utilize on the basis of his academic interest but also his capacities related to professors, administrators, systems, logistics, data analyst, and the academic goals. The Open and Distance University System (SUAYED in Spanish) of the University National Autonomous of Mexico (UNAM), has been working for forty years as an alternative to traditional programs; one of their main supports has been the employ of new information and communications technologies (ICT). Today, UNAM has one of the largest network higher education programs, twenty-six academic programs in different faculties. This situation means that every faculty works with heterogeneous populations and academic problems. In this sense, every program has developed its own Learning Analytic techniques to improve academic issues. In this context, an investigation was carried out to know the situation of the application of LA in all the academic programs in the different faculties. The premise of the study it was that not all the faculties have utilized advanced LA techniques and it is probable that they do not know what field of study is closer to their program goals. In consequence, not all the programs know about LA but, this does not mean they do not work with LA in a veiled or, less clear sense. It is very important to know the grade of knowledge about LA for two reasons: 1) This allows to appreciate the work of the administration to improve the quality of the teaching and, 2) if it is possible to improve others LA techniques. For this purpose, it was designed three instruments to determinate the experience and knowledge in LA. These were applied to ten faculty coordinators and his personnel; thirty members were consulted (academic secretary, systems manager, or data analyst, and coordinator of the program). The final report allowed to understand that almost all the programs work with basic statistics tools and techniques, this helps the administration only to know what is happening inside de academic program, but they are not ready to move up to the next level, this means applying Artificial Intelligence or Recommender Systems to reach a personalized learning system. This situation is not related to the knowledge of LA, but the clarity of the long-term goals.

Keywords: academic improvements, analytical techniques, learning analytics, personnel expertise

Procedia PDF Downloads 129

Authors: KumarShashvat, ArshpreetKaur, RajeshKumar, Raman Chadha

Abstract:

Wireless sensor networks have principal characteristic of having restricted energy and with limitation that energy of the nodes cannot be replenished. To increase the lifetime in this scenario WSN route for data transmission is opted such that utilization of energy along the selected route is negligible. For this energy efficient network, dandy infrastructure is needed because it impinges the network lifespan. Clustering is a technique in which nodes are grouped into disjoints and non–overlapping sets. In this technique data is collected at the cluster head. In this paper, Adaptive-PSO algorithm is proposed which forms energy aware clusters by minimizing the cost of locating the cluster head. The main concern is of the suitability of the swarms by adjusting the learning parameters of PSO. Particle Swarm Optimization converges quickly at the beginning stage of the search but during the course of time, it becomes stable and may be trapped in local optima. In suggested network model swarms are given the intelligence of the spiders which makes them capable enough to avoid earlier convergence and also help them to escape from the local optima. Comparison analysis with traditional PSO shows that new algorithm considerably enhances the performance where multi-dimensional functions are taken into consideration.

Keywords: Particle Swarm Optimization, adaptive – PSO, comparison between PSO and A-PSO, energy efficient clustering

Procedia PDF Downloads 250

Authors: Smaran Manchala

Abstract:

Homomorphic Encryption (HE) enables computations on encrypted data without requiring decryption, mitigating data vulnerability during processing. Usable Fully Homomorphic Encryption (FHE) could revolutionize secure data operations across cloud computing, AI training, and healthcare, providing both privacy and functionality, however, the computational inefficiency of schemes like Cheon-Kim-Kim-Song (CKKS) hinders their widespread practical use. This study focuses on optimizing CKKS for faster matrix operations through the implementation of vector computation parallelization and GPU acceleration. The variable effects of vector parallelization on GPUs were explored, recognizing that while parallelization typically accelerates operations, it could introduce overhead that results in slower runtimes, especially in smaller, less computationally demanding operations. To assess performance, two neural network models, MLPN and CNN—were tested on the MNIST dataset using both ARM and x86-64 architectures, with CNN chosen for its higher computational demands. Each test was repeated 1,000 times, and outliers were removed via Z-score analysis to measure the effect of vector parallelization on CKKS performance. Model accuracy was also evaluated under CKKS encryption to ensure optimizations did not compromise results. According to the results of the trail runs, applying vector parallelization had a 2.63X efficiency increase overall with a 1.83X performance increase for x86-64 over ARM architecture. Overall, these results suggest that the application of vector parallelization in tandem with GPU acceleration significantly improves the efficiency of CKKS even while accounting for vector parallelization overhead, providing impact in future zero trust operations.

Keywords: CKKS scheme, runtime efficiency, fully homomorphic encryption (FHE), GPU acceleration, vector parallelization

Procedia PDF Downloads 28

Authors: Samia Dardouri, Ridha Bouallegue

Abstract:

Scheduling is the process of dynamically allocating physical resources to User Equipment (UE) based on scheduling algorithms implemented at the LTE base station. Various algorithms have been proposed by network researchers as the implementation of scheduling algorithm which represents an open issue in Long Term Evolution (LTE) standard. This paper makes an attempt to study and compare the performance of PF, MLWDF and EXP/PF scheduling algorithms. The evaluation is considered for a single cell with interference scenario for different flows such as Best effort, Video and VoIP in a pedestrian and vehicular environment using the LTE-Sim network simulator. The comparative study is conducted in terms of system throughput, fairness index, delay, packet loss ratio (PLR) and total cell spectral efficiency.

Keywords: LTE, multimedia flows, scheduling algorithms, mobile computing

Procedia PDF Downloads 385

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 75

Authors: Chothmal

Abstract:

In this paper, we present a route discovery process which uses the signal strength on a link as a parameter of its inclusion in the route discovery method. The proposed signal-to-interference and noise ratio (SINR) based multipath reactive routing protocol is named as SINR-MP protocol. The proposed SINR-MP routing protocols has two following two features: a) SINR-MP protocol selects routes based on the SINR of the links during the route discovery process therefore it select the routes which has long lifetime and low frame error rate for data transmission, and b) SINR-MP protocols route discovery process is multipath which discovers more than one SINR based route between a given source destination pair. The multiple routes selected by our SINR-MP protocol are node-disjoint in nature which increases their robustness against link failures, as failure of one route will not affect the other route. The secondary route is very useful in situations where the primary route is broken because we can now use the secondary route without causing a new route discovery process. Due to this, the network overhead caused by a route discovery process is avoided. This increases the network performance greatly. The proposed SINR-MP routing protocol is implemented in the trail version of network simulator called Qualnet.

Keywords: ad hoc networks, quality of service, video streaming, H.264/SVC, multiple routes, video traces

Procedia PDF Downloads 252

Authors: Senay Yitmen

Abstract:

This research investigated individual’s support and helping intentions towards Syrian refugees in Turkey. This is examined in relation to perceived threat and negative emotions, and also to the perceptions of whether one’s intimate social network (family and friends) considers Syrians a threat (descriptive network norm) and whether this network morally supports Syrian refugees (injunctive norms). A questionnaire study was conducted among Turkish participants (n= 565) and the results showed that perception of threat was associated with negative emotions which, in turn, were related to less support of Syrian refugees. Additionally, descriptive norms moderated the relationship between perceived threat and negative emotions towards Syrian refugees. Furthermore, injunctive norms moderated the relationship between negative emotions and support to Syrian refugees. Specifically, the findings indicate that perceived threat is associated with less support of Syrian refugees through negative emotions when descriptive norms are weak and injunctive norms are strong. Injunctive norms appear to trigger a dilemma over the decision to conform or not to conform: when one has negative emotions as a result of perceived threat, it becomes more difficult to conform to the moral obligation of injunctive norms which is associated with less support of Syrian refugees. Hence, these findings demonstrate that both descriptive and injunctive norms are important and play different roles in individual’s support of Syrian refugees.

Keywords: descriptive norms, emotions, injunctive norms, the perception of threat

Procedia PDF Downloads 191

Authors: Sajida Rasheed, Imran Hashmi, Luiza Campos, Qizhi Zhou, Kim Keu

Abstract:

A quadratic model (p ˂ 0.0001) was developed by using central composite design of 50 experimental runs (42 non-center + 8 center points) to assess efficiency of background chlorine residuals in combating accidental microbial episode in a prototype distribution network (DN) (rig). A known amount of background chlorine residuals were maintained in DN and a required number of bacteria, Escherichia coli K-12 strain were introduced by an injection port in the pipe loop system. Samples were taken at various time intervals at different pipe lengths. Spread plate count was performed to count bacterial number. The model developed was significant. With microbial concentration and time (p ˂ 0.0001), pipe length (p ˂ 0.022), background chlorine residuals (p ˂ 0.07) and time^2 (p ˂ 0.09) as significant factors. The ramp function of variables shows that at the microbial count of 10^6, at 0.76 L/min, and pipe length of 133 meters, a background residual chlorine 0.16 mg/L was enough for complete inactivation of microbial episode in approximately 18 minutes.

Keywords: central composite design (CCD), distribution network, Escherichia coli, residual chlorine

Procedia PDF Downloads 465

Authors: Yu-Ting Tsai, Chiun-Chieh Hsu, Yu-Chun Chu

Abstract:

In recent years, due to the development of wireless network technology, many researchers have devoted to the study of wireless sensor networks. The applications of wireless sensor network mainly use the sensor nodes to collect the required information, and send the information back to the users. Since the sensed area is difficult to reach, there are many restrictions on the design of the sensor nodes, where the most important restriction is the limited energy of sensor nodes. Because of the limited energy, researchers proposed a number of ways to reduce energy consumption and balance the load of sensor nodes in order to increase the network lifetime. In this paper, we proposed the Energy-Balanced Clustering method with Auxiliary Members on Wireless Sensor Networks（EBCAM）based on the cluster routing. The main purpose is to balance the energy consumption on the sensed area and average the distribution of dead nodes in order to avoid excessive energy consumption because of the increasing in transmission distance. In addition, we use the residual energy and average energy consumption of the nodes within the cluster to choose the cluster heads, use the multi hop transmission method to deliver the data, and dynamically adjust the transmission radius according to the load conditions. Finally, we use the auxiliary cluster members to change the delivering path according to the residual energy of the cluster head in order to its load. Finally, we compare the proposed method with the related algorithms via simulated experiments and then analyze the results. It reveals that the proposed method outperforms other algorithms in the numbers of used rounds and the average energy consumption.

Keywords: auxiliary nodes, cluster, load balance, routing algorithm, wireless sensor network

Procedia PDF Downloads 275

Authors: Noor Azwa Azreen Binti Abd. Aziz, Muhamad Zaim Bin Mohd Rozi

Abstract:

Moving towards the 4th Industrial Revolution, artificial intelligence (AI) is now more popular than ever. This subject is gaining significance every day and is continually expanding, often merging with other fields. Instead of merely being passive observers, there are benefits to understanding modern technology by delving into its inner workings. However, in a world teeming with digital information, the impact of AI on the spread of disinformation has garnered significant attention. The dissemination of inaccurate or misleading information is referred to as misinformation, posing a serious threat to democratic society, public debate, and individual decision-making. This article delves deep into the connection between AI and the dissemination of false information, exploring its potential, risks, and ethical issues as AI technology advances. The rise of AI has ushered in a new era in the dissemination of misinformation as AI-driven technologies are increasingly responsible for curating, recommending, and amplifying information on online platforms. While AI holds the potential to enhance the detection and mitigation of misinformation through natural language processing and machine learning, it also raises concerns about the amplification and propagation of false information. AI-powered deepfake technology, for instance, can generate hyper-realistic videos and audio recordings, making it increasingly challenging to discern fact from fiction.

Keywords: artificial intelligence, digital information, disinformation, ethical issues, misinformation

Procedia PDF Downloads 95

Authors: B. Ratchaneepun, N.S. Bardell

Abstract:

It is recognized that people are the main drivers in almost all the processes that affect airworthiness assurance. This is especially true in the area of aircraft maintenance, which is an essential part of continuing airworthiness. This work investigates what impact English language proficiency, the intersection of the military and Thai cultures, and the lack of initial and continuing human factors training have on the work performance of maintenance personnel in the Royal Thai Air Force (RTAF). A quantitative research method based on a cross-sectional survey was used to gather data about these three key aspects of “people” in a military airworthiness environment. 30 questions were developed addressing the crucial topics of English language proficiency, impact of culture, and human factors training. The officers and the non-commissioned officers (NCOs) who work for the Aeronautical Engineering Divisions in the RTAF comprised the survey participants. The survey data were analysed to support various hypotheses by using a t-test method. English competency in the RTAF is very important since all of the service manuals for Thai military aircraft are written in English. Without such competency, it is difficult for maintenance staff to perform tasks and correctly interpret the relevant maintenance manual instructions; any misunderstandings could lead to potential accidents. The survey results showed that the officers appreciated the importance of this more than the NCOs, who are the people actually doing the hands-on maintenance work. Military culture focuses on the success of a given mission, and leverages the power distance between the lower and higher ranks. In Thai society, a power distance also exists between younger and older citizens. In the RTAF, such a combination tends to inhibit a just reporting culture and hence hinders safety. The survey results confirmed this, showing that the older people and higher ranks involved with RTAF aircraft maintenance believe that the workplace has a positive safety culture and climate, whereas the younger people and lower ranks think the opposite. The final area of consideration concerned human factors training and non-technical skills training. The survey revealed that those participants who had previously attended such courses appreciated its value and were aware of its benefits in daily life. However, currently there is no regulation in the RTAF to mandate recurrent training to maintain such knowledge and skills. The findings from this work suggest that the people involved in assuring the continuing airworthiness of the RTAF would benefit from: (i) more rigorous requirements and standards in the recruitment, initial training and continuation training regarding English competence; (ii) the development of a strong safety culture that exploits the uniqueness of both the military culture and the Thai culture; and (iii) providing more initial and recurrent training in human factors and non-technical skills.

Keywords: aircraft maintenance, continuing airworthiness, military culture, people, Royal Thai Air Force

Procedia PDF Downloads 132

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 78

Authors: T. Arkle, D. Pournaras, S. Lam, B. Kumar

Abstract:

Introduction: Fundoplication is widely recognised as the best surgical option for gastro-oesophageal reflux disease (GORD) in the general population. However, there is controversy surrounding the use of conventional fundoplication in obese patients. Whilst the intra-operative failure of fundoplication, including wrap disruption, is reportedly higher in obese individuals, the more significant issue surrounds symptom recurrence post-surgery. Could a bariatric procedure be considered in obese patients for weight management, to treat the GORD, and to also reduce the risk of recurrence? Roux-en-Y gastric bypass, a widely performed bariatric procedure, has been shown to be highly successful both in controlling GORD symptoms and in weight management in obese patients. Furthermore, NICE has published clear guidelines on eligibility for bariatric surgery, with the main criteria being type 3 obesity or type 2 obesity with the presence of significant co-morbidities that would improve with weight loss. This study aims to identify the proportion of patients who undergo conventional fundoplication for GORD and/or hiatus hernia, which would have been eligible for bariatric surgery referral according to NICE guidelines. Methods: All patients who underwent fundoplication procedures for GORD and/or hiatus hernia repair at a single NHS foundation trust over a 10-year period will be identified using the Trust’s health records database. Pre-operative patient records will be used to find BMI and the presence of significant co-morbidities at the time of consideration for surgery. This information will be compared to NICE guidelines to determine potential eligibility for the bariatric surgical referral at the time of initial surgical intervention. Results: A total of 321 patients underwent fundoplication procedures between January 2011 and December 2020; 133 (41.4%) had available data for BMI or to allow BMI to be estimated. Of those 133, 40 patients (30%) had a BMI greater than 30kg/m², and 7 (5.3%) had BMI >35kg/m². One patient (0.75%) had a BMI >40 and would therefore be automatically eligible according to NICE guidelines. 4 further patients had significant co-morbidities, such as hypertension and osteoarthritis, which likely be improved by weight management surgery and therefore also indicated eligibility for referral. Overall, 3.75% (5/133) of patients undergoing conventional fundoplication procedures would have been eligible for bariatric surgical referral, these patients were all female, and the average age was 60.4 years. Conclusions: Based on this Trust’s experience, around 4% of obese patients undergoing fundoplication would have been eligible for bariatric surgical intervention. Based on current evidence, in class 2/3 obese patients, there is likely to have been a notable proportion with recurrent disease, potentially requiring further intervention. These patient’s may have benefitted more through undergoing bariatric surgery, for example a Roux-en-Y gastric bypass, addressing both their obesity and GORD. Use of patient written notes to obtain BMI data for the 188 patients with missing BMI data and further analysis to determine outcomes following fundoplication in all patients, assessing for incidence of recurrent disease, will be undertaken to strengthen conclusions.

Keywords: bariatric surgery, GORD, Nissen fundoplication, nice guidelines

Procedia PDF Downloads 60

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 77

Authors: Xiang Shijie, Zhou Dong, Tian Dan

Abstract:

Speaker recognition is a crucial task in the field of speech processing, aimed at identifying individuals based on their vocal characteristics. However, existing speaker recognition methods face numerous challenges. Traditional methods primarily rely on audio signals, which often suffer from limitations in noisy environments, variations in speaking style, and insufficient sample sizes. Additionally, relying solely on audio features can sometimes fail to capture the unique identity of the speaker comprehensively, impacting recognition accuracy. To address these issues, we propose a multi-modal network architecture that simultaneously processes both audio and text signals. By gradually integrating audio and text features, we leverage the strengths of both modalities to enhance the robustness and accuracy of speaker recognition. Our experiments demonstrate significant improvements with this multi-modal approach, particularly in complex environments, where recognition performance has been notably enhanced. Our research not only highlights the limitations of current speaker recognition methods but also showcases the effectiveness of multi-modal fusion techniques in overcoming these limitations, providing valuable insights for future research.

Keywords: feature fusion, memory network, multimodal input, speaker recognition

Procedia PDF Downloads 40

Authors: Nathan Junell S. Arjona, Al-Noor O. Guinal, Marc Leugin V. Logronio, Jean Clark L. Naga

Abstract:

This study looks at how digital culture is shown in David Fincher's movie "The Social Network." It uses a mix of methods from different theories, including Saussurean semiotics, Castells' Network Society theory, and Jenkins' ideas on digital culture. The research focuses on three important scenes from the film, analyzing them in a clear three-step process. This reveals how movies tell stories about the rise of technology. By using a detailed approach, the study shows that digital platforms connect people but can also create gaps in their experiences. The main findings highlight how the film portrays social networks as important cultural systems. It uncovers the power struggles and identities shaped by technology. The research explains how movies help us understand changes in digital culture, challenging old ways of thinking about technology. This analysis connects film studies, digital sociology, and cultural theory, providing a solid way to understand how technology is represented in modern media. By exploring how technology is turned into cultural stories, the study offers important insights into the changing world of digital culture.

Keywords: digital culture, media, social media representation, digital identity

Procedia PDF Downloads 5