Search results for: export trade data

Authors: Huynh Viet Khai, Mitsuyasu Yabe

Abstract:

The study investigated the economic value of biodiversity attributes that could provide policy-makers reliable information to estimate welfare losses due to biodiversity reductions and analyse the trade-off between biodiversity and economics. In order to obtain the non-market benefits of biodiversity conservation, an indirect utility function and willingness to pay for biodiversity attributes were applied using the approach of choice modelling with the analysis of conditional logit model. The study found that Mekong Delta residents accepted their willingness to pay for VND 913 monthly for a one percent increase in healthy vegetation, VND 360 for an additional mammal species and VND 2,440 to avoid the welfare losses of 100 local farmers.

Keywords: choice modelling, genetic resources, wetland conservation, marginal willingness to pay

Procedia PDF Downloads 310

Authors: Andres M. Tuates Jr., Ofero A. Caparino

Abstract:

Plastics have achieved a dominant position in agriculture because of their transparency, lightness in weight, impermeability to water and their resistance to microbial attack. However, this generates a higher quantity of wastes that are difficult to dispose of by farmers. To address these problems, the project aim to develop and evaluate the biodegradable film for mango fruit bag during development. The PBS and starch were melt-blended in a twin-screw extruder and then blown into film extrusion machine. The physic-chemical-mechanical properties of biodegradable fruit bag were done following standard methods of test. Field testing of fruit bag was also conducted to evaluate its durability and efficiency field condition. The PHilMech-FiC fruit bag is made of biodegradable material measuring 6 x 8 inches with a thickness of 150 microns. The tensile strength is within the range of LDPE while the elongation is within the range of HDPE. It is projected that after thirty-six (36) weeks, the film will be totally degraded. Results of field testing show that the quality of harvested fruits using PHilMech-FiC biodegradable fruit bag in terms of percent marketable, non-marketable and export, peel color at the ripe stage, flesh color, TSS, oBrix, percent edible portion is comparable with the existing bagging materials such as Chinese brown paper bag and old newspaper.

Keywords: cassava starch, PBS, biodegradable, chemical, mechanical properties

Procedia PDF Downloads 260

Authors: Walid Cherif

Abstract:

Data mining has, over recent years, seen big advances because of the spread of internet, which generates everyday a tremendous volume of data, and also the immense advances in technologies which facilitate the analysis of these data. In particular, classification techniques are a subdomain of Data Mining which determines in which group each data instance is related within a given dataset. It is used to classify data into different classes according to desired criteria. Generally, a classification technique is either statistical or machine learning. Each type of these techniques has its own limits. Nowadays, current data are becoming increasingly heterogeneous; consequently, current classification techniques are encountering many difficulties. This paper defines new measure functions to quantify the resemblance between instances and then combines them in a new approach which is different from actual algorithms by its reliability computations. Results of the proposed approach exceeded most common classification techniques with an f-measure exceeding 97% on the IRIS Dataset.

Keywords: data mining, knowledge discovery, machine learning, similarity measurement, supervised classification

Procedia PDF Downloads 451

Authors: Ankur Mundhra, Shubhadeep Chakraborty, Y. R. Singh, Vishal Das

Abstract:

Seismic data scaling affects the dynamic range of a data and with present day lower costs of storage and higher reliability of Hard Disk data, scaling is not suggested. However, in dealing with data of different vintages, which perhaps were processed in 16 bits or even 8 bits and are need to be processed with 32 bit available data, scaling is performed. Also, scaling amplifies low amplitude events in deeper region which disappear due to high amplitude shallow events that saturate amplitude scale. We have focused on significance of scaling data to aid interpretation. This study elucidates a proper seismic loading procedure in workstations without using default preset parameters as available in most software suites. Differences and distribution of amplitude values at different depth for seismic data are probed in this exercise. Proper loading parameters are identified and associated steps are explained that needs to be taken care of while loading data. Finally, the exercise interprets the un-certainties which might arise when correlating scaled and unscaled versions of seismic data with synthetics. As, seismic well tie correlates the seismic reflection events with well markers, for our study it is used to identify regions which are enhanced and/or affected by scaling parameter(s).

Keywords: clipping, compression, resolution, seismic scaling

Procedia PDF Downloads 454

Authors: Zofia Romanowska

Abstract:

Recently there have been significant changes in the Polish energy market. Due to the government's decision to strengthen energy security as well as to strengthen the implementation of the European Union common energy policy, the Polish energy market has been undergoing significant changes. In the face of these, it is necessary to answer the question about the direction the Polish energy rationing sector is going, how wide apart the powers of the state are and also whether the real regulator of energy projects in Poland is not in fact the European Union itself. In order to determine the role of the state as a regulator of the energy market, the study analyses the basic instruments of regulation, i.e. the licenses, permits and permissions to conduct various activities related to the energy market, such as the production and sale of liquid fuels or concessions for trade in natural gas. Bearing in mind that Polish law is part of the widely interpreted European Union energy policy, the legal solutions in neighbouring countries are also being researched, including those made in Germany, a country which plays a key role in the shaping of EU policies. The correct interpretation of the new legislation modifying the current wording of the Energy Law Act, such as obliging the entities engaged in the production and trade of liquid fuels (including abroad) to meet a number of additional requirements for the licensing and providing information to the state about conducted business, plays a key role in the study. Going beyond the legal framework for energy rationing, the study also includes a legal and economic analysis of public and private goods within the energy sector and delves into the subject of effective remedies. The research caused the relationships between progressive rationing introduced by the legislator and the rearrangement rules prevailing on the Polish energy market to be taken note of, which led to the introduction of greater transparency in the sector. The studies refer to the initial conclusion that currently, despite the proclaimed idea of liberalization of the oil and gas market and the opening of market to a bigger number of entities as a result of the newly implanted changes, the process of issuing and controlling the conduction of the concessions will be tightened, guaranteeing to entities greater security of energy supply. In the long term, the effect of the introduced legislative solutions will be the reduction of the amount of entities on the energy market. The companies that meet the requirements imposed on them by the new regulation to cope with the profitability of the business will in turn increase prices for their services, which will be have an impact on consumers' budgets.

Keywords: license, energy law, energy market, public goods, regulator

Procedia PDF Downloads 233

Authors: Diego Rodrigues, Marcelo Lisboa, Elismar Batista, Marcos Dias

Abstract:

Based on data on child labor, this work arises questions about how to understand and locate the factors that make up the child labor rates, and which properties are important to analyze these cases. Using data mining techniques to discover valid patterns on Brazilian social databases were evaluated data of child labor in the State of Tocantins (located north of Brazil with a territory of 277000 km2 and comprises 139 counties). This work aims to detect factors that are deterministic for the practice of child labor and their relationships with financial indicators, educational, regional and social, generating information that is not explicit in the government database, thus enabling better monitoring and updating policies for this purpose.

Keywords: social data, government decision making, association of social data, data mining

Procedia PDF Downloads 351

Authors: Sadam Alwadi

Abstract:

Outlier values become a problem that frequently occurs in the data observation or recording process. Thus, the need for data imputation has become an essential matter. In this work, it will make use of the methods described in the prior work to detect the outlier values based on a collection of stock market data. In order to implement the detection and find some solutions that maybe helpful for investors, real closed price data were obtained from the Amman Stock Exchange (ASE). Tukey and Maximum Overlapping Discrete Wavelet Transform (MODWT) methods will be used to impute the detect the outlier values.

Keywords: outlier values, imputation, stock market data, detecting, estimation

Procedia PDF Downloads 71

Authors: P. Jayashree, S. Rajkumar

Abstract:

With social networks and smart devices generating a multitude of data, effective data management is the need of the hour for networks and cloud applications. Some applications need effective storage while some other applications need effective communication over networks and data reduction comes as a handy solution to meet out both requirements. Most of the data compression techniques are based on data statistics and may result in either lossy or lossless data reductions. Though lossy reductions produce better compression ratios compared to lossless methods, many applications require data accuracy and miniature details to be preserved. A variety of data compression algorithms does exist in the literature for different forms of data like text, image, and multimedia data. In the proposed work, a generic progressive compression algorithm, based on probabilistic encoding, called PEINS is projected as an enhancement over irrational number stored coding technique to cater to storage issues of increasing data volumes as a cost effective solution, which also offers data security as a secondary outcome to some extent. The proposed work reveals cost effectiveness in terms of better compression ratio with no deterioration in compression time.

Keywords: compression ratio, generic compression, irrational number storage, probabilistic encoding

Procedia PDF Downloads 273

Authors: Femi Elegbeleye, Omobayo Esan, Muienge Mbodila, Patrick Bowe

Abstract:

This paper focused on cost effective storage architecture using fog and cloud data storage gateway and presented the design of the framework for the data privacy model and data analytics framework on a real-time analysis when using machine learning method. The paper began with the system analysis, system architecture and its component design, as well as the overall system operations. The several results obtained from this study on data privacy model shows that when two or more data privacy model is combined we tend to have a more stronger privacy to our data, and when fog storage gateway have several advantages over using the traditional cloud storage, from our result shows fog has reduced latency/delay, low bandwidth consumption, and energy usage when been compare with cloud storage, therefore, fog storage will help to lessen excessive cost. This paper dwelt more on the system descriptions, the researchers focused on the research design and framework design for the data privacy model, data storage, and real-time analytics. This paper also shows the major system components and their framework specification. And lastly, the overall research system architecture was shown, its structure, and its interrelationships.

Keywords: IoT, fog, cloud, data analysis, data privacy

Procedia PDF Downloads 82

Authors: Naser Zouri

Abstract:

Purpose: Measures of formulate and implementation strategy shows amount of product rate-market based strategic management category such as courtesy, competence, and compliance to reach the high loyalty of financial ecosystem. Despite, it solves the market place error intention to fair trade organization. Finding: Finding shows the ability of executives’ level of management to motivate and better decision-making to solve the treatments in business organization. However, it made ideal level of each interposition policy for a hypothetical household. Methodology/design. Style of questionnaire about the data collection was selected to survey of both pilot test and real research. Also, divide of questionnaire and using of Free Scale Semiconductor`s between the finance employee was famous of this instrument. Respondent`s nominated basic on non-probability sampling such as convenience sampling to answer the questionnaire. The way of realization costs to performed the questionnaire divide among the respondent`s approximately was suitable as a spend the expenditure to reach the answer but very difficult to collect data from hospital. However, items of research survey was formed of implement strategy, environment, supply chain, employee from impact of implementation strategy on reach to better financial consequences and also formulate strategy, comprehensiveness strategic design, organization performance from impression on formulate strategy and financial consequences. Practical Implication: Dynamic capability approach of formulate and implement strategy focuses on the firm-specific processes through which firms integrate, build, or reconfigure resources valuable for making a theoretical contribution. Originality/ value of research: Going beyond the current discussion, we show that case studies have the potential to extend and refine theory. We present new light on how dynamic capabilities can benefit from case study research by discovering the qualifications that shape the development of capabilities and determining the boundary conditions of the dynamic capabilities approach. Limitation of the study :Present study also relies on survey of methodology for data collection and the response perhaps connection by financial employee was difficult to responds the question because of limitation work place.

Keywords: financial ecosystem, loyalty, Malaysian market error, dynamic capability approach, rate-market, optimization intelligence strategy, courtesy, competence, compliance

Procedia PDF Downloads 286

Authors: Nordila Ahmad, Thamer Mohammad, Bruce W. Melville, Zuliziana Suif

Abstract:

Current methods for predicting local scour at wide bridge piers, were developed on the basis of laboratory studies and very limited scour prediction were tested with field data. Laboratory wide pier scour equation from previous findings with field data were presented. A wide range of field data were used and it consists of both live-bed and clear-water scour. A method for assessing the quality of the data was developed and applied to the data set. Three other wide pier-scour equations from the literature were used to compare the performance of each predictive method. The best-performing scour equation were analyzed using statistical analysis. Comparisons of computed and observed scour depths indicate that the equation from the previous publication produced the smallest discrepancy ratio and RMSE value when compared with the large amount of laboratory and field data.

Keywords: field data, local scour, scour equation, wide piers

Procedia PDF Downloads 387

Authors: Gheyzer Villegas, Edgardo Cedeño, Veruska Mata, Edmundo Chauran

Abstract:

One of the most significant changes that occurred in global commerce was the emergence of cryptocurrencies and blockchain technology. There is still much debate about the adoption of the economic model based on crypto assets, and myriad international projects and initiatives are being carried out to try and explore the potential that this new field offers. The Hive blockchain is a prime example of this, featuring two use cases: of how trade based on its native currencies can give successful results in the exchange of goods and services and in the financing of social impact projects. Its decentralized management model and visionary administration of its development fund have become a key part of its success.

Keywords: Hive, business, network, blockchain

Procedia PDF Downloads 46

Authors: Inkyu Kim, SangMan Moon

Abstract:

This IEEE 802.11b protocol provides up to 11Mbps data rate, whereas aerospace industry wants to seek higher data rate COTS data link system in the UAV. The Total Maximum Throughput (TMT) and delay time are studied on many researchers in the past years This paper provides theoretical data throughput performance of UAV formation flight data link using the existing 802.11b performance theory. We operate the UAV formation flight with more than 30 quad copters with 802.11b protocol. We may be predicting that UAV formation flight numbers have to bound data link protocol performance limitations.

Keywords: UAV datalink, UAV formation flight datalink, UAV WLAN datalink application, UAV IEEE 802.11b datalink application

Procedia PDF Downloads 372

Authors: Radoslav Židek, Veronika Šidlová, Radovan Kasarda, Birgit Fuerst-Waltl

Abstract:

Machine learning represents a set of topics dealing with the creation and evaluation of algorithms that facilitate pattern recognition, classification, and prediction, based on models derived from existing data. The data can present identification patterns which are used to classify into groups. The result of the analysis is the pattern which can be used for identification of data set without the need to obtain input data used for creation of this pattern. An important requirement in this process is careful data preparation validation of model used and its suitable interpretation. For breeders, it is important to know the origin of animals from the point of the genetic diversity. In case of missing pedigree information, other methods can be used for traceability of animal´s origin. Genetic diversity written in genetic data is holding relatively useful information to identify animals originated from individual countries. We can conclude that the application of data mining for molecular genetic data using supervised learning is an appropriate tool for hypothesis testing and identifying an individual.

Keywords: genetic data, Pinzgau cattle, supervised learning, machine learning

Procedia PDF Downloads 534

Authors: Nidhi Gopal

Abstract:

Routing is the process of moving a packet of data from source to destination and enables messages to pass from one computer to another and eventually reach the target machine. A router is a networking device that forwards data packets between computer networks. It is connected to two or more data lines from different networks (as opposed to a network switch, which connects data lines from one single network). This paper mainly emphasizes upon the study of router device, its top level architecture, and how various sub-modules of router i.e. Register, FIFO, FSM and Synchronizer are synthesized, and simulated and finally connected to its top module.

Keywords: data packets, networking, router, routing

Procedia PDF Downloads 783

Authors: M. Ndeley

Abstract:

Now our days, Almost all manufacturing facilities need to use production planning and scheduling systems to increase productivity and to reduce production costs. Real-life production operations are subject to a large number of unexpected disruptions that may invalidate the original schedules. In these cases, rescheduling is essential to minimize the impact on the performance of the system. In this work we consider flow shop layouts that have seldom been studied in the rescheduling literature. We generate and employ three types of disruption that interrupt the original schedules simultaneously. We develop rescheduling algorithms to finally accomplish the twofold objective of establishing a standard framework on the one hand; and proposing rescheduling methods that seek a good trade-off between schedule quality and stability on the other.

Keywords: flow shop scheduling, uncertainty, rescheduling, stability

Procedia PDF Downloads 430

Authors: Julius Onyancha, Valentina Plekhanova

Abstract:

One of the significant issues facing web users is the amount of noise in web data which hinders the process of finding useful information in relation to their dynamic interests. Current research works consider noise as any data that does not form part of the main web page and propose noise web data reduction tools which mainly focus on eliminating noise in relation to the content and layout of web data. This paper argues that not all data that form part of the main web page is of a user interest and not all noise data is actually noise to a given user. Therefore, learning of noise web data allocated to the user requests ensures not only reduction of noisiness level in a web user profile, but also a decrease in the loss of useful information hence improves the quality of a web user profile. Noise Web Data Learning (NWDL) tool/algorithm capable of learning noise web data in web user profile is proposed. The proposed work considers elimination of noise data in relation to dynamic user interest. In order to validate the performance of the proposed work, an experimental design setup is presented. The results obtained are compared with the current algorithms applied in noise web data reduction process. The experimental results show that the proposed work considers the dynamic change of user interest prior to elimination of noise data. The proposed work contributes towards improving the quality of a web user profile by reducing the amount of useful information eliminated as noise.

Keywords: web log data, web user profile, user interest, noise web data learning, machine learning

Procedia PDF Downloads 247

Authors: Nutnicha Wongpadungkiat, Suwit Siriwatanayotin, Aluck Thipayarat, Punchira Vongsawasdi, Chotika Viriyarattanasak

Abstract:

Chicken products are major export product of Thailand. With a dramatically increasing consumption of chicken product in the world, there are abundant wastes from chicken meat processing industry. Recently, much research in the development of value-added products from chicken meat industry has focused on the production of protein hydrolysate, utilized as food ingredients for human diet and animal feed. The present study aimed to determine the effect of thermal pre-treatment on functional properties of chicken protein hydrolysate. Chicken breasts were heated at 40, 60, 80 and 100ºC prior to hydrolysis by Alcalase at 60ºC, pH 8 for 4 hr. The hydrolysate was freeze-dried, and subsequently used for assessment of its functional properties molecular weight by gel electrophoresis (SDS-PAGE). The obtained results show that increasing the pre-treatment temperature increased oil holding capacity and emulsion stability while decreasing antioxidant activity and water holding capacity. The SDS-PAGE analysis showed the evidence of protein aggregation in the hydrolysate treated at the higher pre-treatment temperature. These results suggest the connection between molecular weight of the hydrolysate and its functional properties.

Keywords: chicken protein hydrolysate, enzymatic hydrolysis, thermal pretreatment, functional properties

Procedia PDF Downloads 248

Authors: Zeba Mahmood

Abstract:

The modern business organizations are adopting technological advancement to achieve competitive edge and satisfy their consumer. The development in the field of Information technology systems has changed the way of conducting business today. Business operations today rely more on the data they obtained and this data is continuously increasing in volume. The data stored in different locations is difficult to find and use without the effective implementation of Data mining and Knowledge management techniques. Organizations who smartly identify, obtain and then convert data in useful formats for their decision making and operational improvements create additional value for their customers and enhance their operational capabilities. Marketers and Customer relationship departments of firm use Data mining techniques to make relevant decisions, this paper emphasizes on the identification of different data mining and Knowledge management techniques that are applied to different business industries. The challenges and issues of execution of these techniques are also discussed and critically analyzed in this paper.

Keywords: knowledge, knowledge management, knowledge discovery in databases, business, operational, information, data mining

Procedia PDF Downloads 514

Authors: Adarsh Shroff

Abstract:

Big data is a collection of dataset so large and complex that it becomes difficult to process using data base management tools. To perform operations like search, analysis, visualization on big data by using data mining; which is the process of extraction of patterns or knowledge from large data set. In recent years, the data mining applications become stale and obsolete over time. Incremental processing is a promising approach to refreshing mining results. It utilizes previously saved states to avoid the expense of re-computation from scratch. This project uses i2MapReduce, an incremental processing extension to Map Reduce, the most widely used framework for mining big data. I2MapReduce performs key-value pair level incremental processing rather than task level re-computation, supports not only one-step computation but also more sophisticated iterative computation, which is widely used in data mining applications, and incorporates a set of novel techniques to reduce I/O overhead for accessing preserved fine-grain computation states. To optimize the mining results, evaluate i2MapReduce using a one-step algorithm and three iterative algorithms with diverse computation characteristics for efficient mining.

Keywords: big data, map reduce, incremental processing, iterative computation

Procedia PDF Downloads 330

Authors: Jerry Q. Cheng

Abstract:

Currently, in analyzing large-scale recurrent event data, there are many challenges such as memory limitations, unscalable computing time, etc. In this research, a divide-and-conquer method is proposed using parametric frailty models. Specifically, the data is randomly divided into many subsets, and the maximum likelihood estimator from each individual data set is obtained. Then a weighted method is proposed to combine these individual estimators as the final estimator. It is shown that this divide-and-conquer estimator is asymptotically equivalent to the estimator based on the full data. Simulation studies are conducted to demonstrate the performance of this proposed method. This approach is applied to a large real dataset of repeated heart failure hospitalizations.

Keywords: big data analytics, divide-and-conquer, recurrent event data, statistical computing

Procedia PDF Downloads 145

Authors: Alina Gilmanova

Abstract:

China’s dependency on coal for energy is causing pollution in China and abroad. To supply the increasing energy demand and being under the pressure from international society to reduce the emissions, China was pushed to develop renewable energy. The increasing subsidies in Renewable energy sources (RES) led not only to the price-cutting but also affecting the international trade in green technology sector. In order to evaluate the role of RES in foreign policy of China, I am going to give an (i) overview of RES development in China and examine the cooperation between China and (ii) developed, (ii) developing and emerging countries. The conclusive remarks are intended to address the question of how the present Chinese renewable energy development is impacting its foreign policy and international society.

Keywords: renewable energy, China, foreign affairs, brics, cooperation

Procedia PDF Downloads 623

Authors: Ashiff Khan, A. Seetharaman, Abhijit Dasgupta

Abstract:

The new era of big data (BD) is influencing chemical industries tremendously, providing several opportunities to reshape the way they operate and help them shift towards intelligent manufacturing. Given the availability of free software and the large amount of real-time data generated and stored in process plants, chemical industries are still in the early stages of big data adoption. The industry is just starting to realize the importance of the large amount of data it owns to make the right decisions and support its strategies. This article explores the importance of professional competencies and data science that influence BD in chemical industries to help it move towards intelligent manufacturing fast and reliable. This article utilizes a literature review and identifies potential applications in the chemical industry to move from conventional methods to a data-driven approach. The scope of this document is limited to the adoption of BD in chemical industries and the variables identified in this article. To achieve this objective, government, academia, and industry must work together to overcome all present and future challenges.

Keywords: chemical engineering, big data analytics, industrial revolution, professional competence, data science

Procedia PDF Downloads 66

Authors: Carlson Murray, Ali Lazrak

Abstract:

Robust experimental evidence of systematic violations of expected utility (EU) establishes that individuals facing risk overweight utility from low probability gains and losses when making choices. These findings motivated development of models of preferences with probability weighting functions, such as rank dependent utility (RDU). We solve for the optimal investing strategy of an RDU investor in a dynamic binomial setting from which we derive implications for investing behavior. We show that relative to EU investors with constant relative risk aversion, commonly measured probability weighting functions produce optimal RDU terminal wealth with significant downside protection and upside exposure. We additionally find that in contrast to EU investors, RDU investors optimally choose a portfolio that contains fair bets that provide payo↵s that can be interpreted as lottery outcomes or exposure to idiosyncratic returns. In a calibrated version of the model, we calculate that RDU investors would be willing to pay 5% of their initial wealth for the freedom to trade away from an optimal EU wealth allocation. The dynamic trading strategy that supports the optimal wealth allocation implies portfolio weights that are independent of initial wealth but requires higher risky share after good stock return histories. Optimal trading also implies the possibility of non-participation when historical returns are poor. Our model fills a gap in the literature by providing new quantitative and qualitative predictions that can be tested experimentally or using data on household wealth and portfolio choice.

Keywords: behavioral finance, probability weighting, portfolio choice

Procedia PDF Downloads 409

Authors: M. Sumana, K. S. Hareesha

Abstract:

Secure computations are essential while performing privacy preserving data mining. Distributed privacy preserving data mining involve two to more sites that cannot pool in their data to a third party due to the violation of law regarding the individual. Hence in order to model the private data without compromising privacy and information loss, secure multiparty computations are used. Secure computations of product, mean, variance, dot product, sigmoid function using the additive and multiplicative homomorphic property is discussed. The computations are performed on vertically partitioned data with a single site holding the class value.

Keywords: homomorphic property, secure product, secure mean and variance, secure dot product, vertically partitioned data

Procedia PDF Downloads 400

Authors: Kittivate Boonyopakorn

Abstract:

The purposes of this study were to investigate the method of the English use of the businessmen and to study their behavior of the utilization for the ASEAN economic community. The participants were divided into the three types of the merchants including the construction contractors, the construction material traders, and SME entrepreneurs. Survey questionnaires and interviews were used in this study. The findings showed that in the type of traders, 23 of the participants are construction contractors, 121 are construction material traders, and 206 are SME entrepreneurs. The study of English in language institute is highly 51.4%. The use of Google in translating English into Thai is 41.7%. Learning English themselves is 41.1% respectively. The businessmen study English for readiness for their trade.

Keywords: way of rnglish use, businessmen, ASEAN economic community, Chonburi province

Procedia PDF Downloads 228

Authors: Shayan Mohajer Hamidi

Abstract:

Federated learning has emerged as a promising approach for distributed model training while preserving data privacy. However, the challenges of communication overhead, limited network resources, and slow convergence hinder its widespread adoption. On the other hand, knowledge distillation has shown great potential in compressing large models into smaller ones without significant loss in performance. In this paper, we propose an innovative framework that combines federated learning and knowledge distillation to address these challenges and enhance the efficiency of distributed learning. Our approach, called Federated Knowledge Distillation (FKD), enables multiple clients in a federated learning setting to collaboratively distill knowledge from a teacher model. By leveraging the collaborative nature of federated learning, FKD aims to improve model compression while maintaining privacy. The proposed framework utilizes a coded teacher model that acts as a reference for distilling knowledge to the client models. To demonstrate the effectiveness of FKD, we conduct extensive experiments on various datasets and models. We compare FKD with baseline federated learning methods and standalone knowledge distillation techniques. The results show that FKD achieves superior model compression, faster convergence, and improved performance compared to traditional federated learning approaches. Furthermore, FKD effectively preserves privacy by ensuring that sensitive data remains on the client devices and only distilled knowledge is shared during the training process. In our experiments, we explore different knowledge transfer methods within the FKD framework, including Fine-Tuning (FT), FitNet, Correlation Congruence (CC), Similarity-Preserving (SP), and Relational Knowledge Distillation (RKD). We analyze the impact of these methods on model compression and convergence speed, shedding light on the trade-offs between size reduction and performance. Moreover, we address the challenges of communication efficiency and network resource utilization in federated learning by leveraging the knowledge distillation process. FKD reduces the amount of data transmitted across the network, minimizing communication overhead and improving resource utilization. This makes FKD particularly suitable for resource-constrained environments such as edge computing and IoT devices. The proposed FKD framework opens up new avenues for collaborative and privacy-preserving distributed learning. By combining the strengths of federated learning and knowledge distillation, it offers an efficient solution for model compression and convergence speed enhancement. Future research can explore further extensions and optimizations of FKD, as well as its applications in domains such as healthcare, finance, and smart cities, where privacy and distributed learning are of paramount importance.

Keywords: federated learning, knowledge distillation, knowledge transfer, deep learning

Procedia PDF Downloads 54

Authors: C. Nathanailides, S. Anastasiou, A. Dimitroglou, P. Logothetis, G. Kanlis

Abstract:

In the present work we reviewed historical data of the Greek Marine aquaculture industry including adoption of new methods and technological innovation. The results indicate that the industry exhibited a rapid rise in production efficiency, employment and adoption of new technologies which reduced outbreaks of diseases, reduced production risk and the price of the farmed fish. The improvements of total quality practices and technological input on the Greek Aquaculture industry include improved survival, growth and body shape of farmed fish, which resulted from development of new aquaculture feeds and the genetic selection of the bloodstock. Also improvements in the quality of the final product were achieved via technological input in the methods and technology applied during harvesting, packaging, and transportation-preservation of farmed fish ensuring high quality of the product from the fish farm to the plate of the consumers. These parameters (health management, nutrition, genetics, harvesting and post-harvesting methods and technology) changed significantly over the last twenty years and the results of these improvements are reflected in the production efficiency of the Aquaculture industry and the quality of the final product. It is concluded that the Greek aquaculture industry exhibited a rapid growth, adoption of technologies and supply was stabilized after the global financial crisis, nevertheless, the development of the Greek aquaculture industry is currently limited by international trade sanctions, credit crunch, and increased taxation and not by limited technology or resources.

Keywords: innovation, aquaculture, total quality, management

Procedia PDF Downloads 361

Authors: Pradeep Singh, Shrish Verma

Abstract:

Software fault prediction models are created by using the source code, processed metrics from the same or previous version of code and related fault data. Some company do not store and keep track of all artifacts which are required for software fault prediction. To construct fault prediction model for such company, the training data from the other projects can be one potential solution. The earlier we predict the fault the less cost it requires to correct. The training data consists of metrics data and related fault data at function/module level. This paper investigates fault predictions at early stage using the cross-project data focusing on the design metrics. In this study, empirical analysis is carried out to validate design metrics for cross project fault prediction. The machine learning techniques used for evaluation is Naïve Bayes. The design phase metrics of other projects can be used as initial guideline for the projects where no previous fault data is available. We analyze seven data sets from NASA Metrics Data Program which offer design as well as code metrics. Overall, the results of cross project is comparable to the within company data learning.

Keywords: software metrics, fault prediction, cross project, within project.

Procedia PDF Downloads 324

Authors: Vish Putcha, Chandrasekhar Putcha, Siva Hari

Abstract:

In the current digital era of free trading and pandemic-driven remote work culture, markets worldwide gained momentum for retail investors to trade from anywhere easily. The number of retail traders rose to 24% of the market from 15% at the pre-pandemic level. Most of them are young retail traders with high-risk tolerance compared to the previous generation of retail traders. This trend boosted the growth of subscription-based market predictors and market data vendors. Young traders are betting on these predictors, assuming one of them is correct. However, 90% of retail traders are on the losing end. This paper presents multiple indicators and attempts to derive behavioral patterns from the underlying stocks. The two major indicators that traders and investors follow are technical and fundamental. The famous investor, Warren Buffett, adheres to the “Value Investing” method that is based on a stock’s fundamental Analysis. In this paper, we present multiple indicators from various methods to understand the behavior patterns of stocks. For this research, we picked five stocks with a market capitalization of more than $200M, listed on the exchange for more than 20 years, and from different industry sectors. To study the behavioral pattern over time for these five stocks, a total of 8 indicators are chosen from fundamental, technical, and financial indicators, such as Price to Earning (P/E), Price to Book Value (P/B), Debt to Equity (D/E), Beta, Volatility, Relative Strength Index (RSI), Moving Averages and Dividend yields, followed by detailed mathematical Analysis. This is an interdisciplinary paper between various disciplines of Engineering, Accounting, and Finance. The research takes a new approach to identify clear indicators affecting stocks. Statistical Analysis of the data will be performed in terms of the probabilistic distribution, then follow and then determine the probability of the stock price going over a specific target value. The Chi-square test will be used to determine the validity of the assumed distribution. Preliminary results indicate that this approach is working well. When the complete results are presented in the final paper, they will be beneficial to the community.

Keywords: stock pattern, stock market analysis, stock predictions, trading, investing, fundamental analysis, technical analysis, quantitative trading, financial analysis, behavioral analysis

Procedia PDF Downloads 62