Search results for: loss function
3018 Transmission Loss Allocation via Loss Function Decomposition and Current Projection Concept
Authors: M.R. Ebrahimi, Z. Ghofrani, M. Ehsan
Abstract:
One of the major problems in liberalized power markets is loss allocation. In this paper, a different method for allocating transmission losses to pool market participants is proposed. The proposed method is fundamentally based on decomposition of loss function and current projection concept. The method has been implemented and tested on several networks and one sample summarized in the paper. The results show that the method is comprehensive and fair to allocating the energy losses of a power market to its participants.Keywords: Transmission loss, loss allocation, current projectionconcept, loss function decomposition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17493017 Estimation of Bayesian Sample Size for Binomial Proportions Using Areas P-tolerance with Lowest Posterior Loss
Authors: H. Bevrani, N. Najafi
Abstract:
This paper uses p-tolerance with the lowest posterior loss, quadratic loss function, average length criteria, average coverage criteria, and worst outcome criterion for computing of sample size to estimate proportion in Binomial probability function with Beta prior distribution. The proposed methodology is examined, and its effectiveness is shown.Keywords: Bayesian inference, Beta-binomial Distribution, LPLcriteria, quadratic loss function.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17523016 Loss Function Optimization for CNN-Based Fingerprint Anti-Spoofing
Authors: Yehjune Heo
Abstract:
As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.
Keywords: Anti-spoofing, CNN, fingerprint recognition, loss function, optimizer.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4223015 Ranking - Convex Risk Minimization
Authors: Wojciech Rejchel
Abstract:
The problem of ranking (rank regression) has become popular in the machine learning community. This theory relates to problems, in which one has to predict (guess) the order between objects on the basis of vectors describing their observed features. In many ranking algorithms a convex loss function is used instead of the 0-1 loss. It makes these procedures computationally efficient. Hence, convex risk minimizers and their statistical properties are investigated in this paper. Fast rates of convergence are obtained under conditions, that look similarly to the ones from the classification theory. Methods used in this paper come from the theory of U-processes as well as empirical processes.
Keywords: Convex loss function, empirical risk minimization, empirical process, U-process, boosting, euclidean family.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14163014 Beyond Taguchi’s Concept of the Quality Loss Function
Authors: Atul Dev, Pankaj Jha
Abstract:
Dr. Genichi Taguchi looked at quality in a broader term and gave an excellent definition of quality in terms of loss to society. However the scope of this definition is limited to the losses imparted by a poor quality product to the customer only and are considered during the useful life of the product and further in a certain situation this loss can even be zero. In this paper, it has been proposed that the scope of quality of a product shall be further enhanced by considering the losses imparted by a poor quality product to society at large, due to associated environmental and safety related factors, over the complete life cycle of the product. Moreover, though these losses can be further minimized with the use of techno-safety interventions, the net losses to society however can never be made zero. This paper proposes an entirely new approach towards defining product quality and is based on Taguchi’s definition of quality.
Keywords: Existing concept, goal post philosophy, life cycle, proposed concept, quality loss function.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20083013 Vector Control Using Series Iron Loss Model of Induction, Motors and Power Loss Minimization
Authors: Kheldoun Aissa, Khodja Djalal Eddine
Abstract:
The iron loss is a source of detuning in vector controlled induction motor drives if the classical rotor vector controller is used for decoupling. In fact, the field orientation will not be satisfied and the output torque will not truck the reference torque mostly used by Loss Model Controllers (LMCs). In addition, this component of loss, among others, may be excessive if the vector controlled induction motor is driving light loads. In this paper, the series iron loss model is used to develop a vector controller immune to iron loss effect and then an LMC to minimize the total power loss using the torque generated by the speed controller.Keywords: Field Oriented Controller, Induction Motor, Loss ModelController, Series Iron Loss.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27063012 Optimization of a Triangular Fin with Variable Fin Base Thickness
Authors: Hyung Suk Kang
Abstract:
A triangular fin with variable fin base thickness is analyzed and optimized using a two-dimensional analytical method. The influence of fin base height and fin base thickness on the temperature in the fin is listed. For the fixed fin volumes, the maximum heat loss, the corresponding optimum fin effectiveness, fin base height and fin tip length as a function of the fin base thickness, convection characteristic number and dimensionless fin volume are represented. One of the results shows that the optimum heat loss increases whereas the corresponding optimum fin effectiveness decreases with the increase of fin volume.Keywords: A triangular fin, Convection characteristic number, Heat loss, Fin base thickness.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 41263011 Loss of P16/INK4A Protein Expression is a Common Abnormality in Hodgkin's Lymphoma
Authors: Fawzi Irshaid, Fatiha Dilmi, Khaled Tarawneh, Raji Hadeth, Adnan Jaran, Ahad Al-Khatib
Abstract:
P16/INK4A is tumor suppressor protein that plays a critical role in cell cycle regulation. Loss of P16 protein expression has been implicated in pathogenesis of many cancers, including lymphoma. Therefore, we sought to investigate if loss of P16 protein expression is associated with lymphoma and/or any specific lymphoma subtypes (Hodgkin-s lymphoma (HL) and nonHodgkin-s lymphoma (NHL)). Fifty-five lymphoma cases consisted of 30 cases of HL and 25 cases of NHL, with an age range of 3 to 78 years, were examined for loss of P16 by immunohistochemical technique using a specific antibody reacting against P16. In total, P16 loss was seen in 33% of all lymphoma cases. P16 loss was identified in 47.7% of HL cases. In contrast, only 16% of NHL showed loss of P16. Loss of P16 was seen in 67% of HL patients with 50 years of age or older, whereas P16 loss was found in only 42% of HL patients with less than 50 years of age. P16 loss in HL is somewhat higher in male (55%) than in female (30%). In subtypes of HL, P16 loss was found exclusively in all cases of lymphocyte depletion, lymphocyte predominance and unclassified cases, whereas P16 loss was seen in 39% of mixed cellularity and 29% of nodular sclerosis cases. In low grade NHL patients, P16 loss was seen in approximately one-third of cases, whereas no or very rare of P16 loss was found in intermediate and high grade cases. P16 loss did not show any correlation with age or gender of NHL patients. In conclusion, the high rate of P16 loss seen in our study suggests that loss of P16 expression plays a critical role in the pathogenesis of lymphoma, particularly with HL.
Keywords: B-cells, immunostaining, P16 protein, Reed-Sternberg cells, tumors.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16673010 Improved Rare Species Identification Using Focal Loss Based Deep Learning Models
Authors: Chad Goldsworthy, B. Rajeswari Matam
Abstract:
The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.
Keywords: Convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14253009 Adaptive Few-Shot Deep Metric Learning
Authors: Wentian Shi, Daming Shi, Maysam Orouskhani, Feng Tian
Abstract:
Currently the most prevalent deep learning methods require a large amount of data for training, whereas few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.
Keywords: Few-shot learning, triplet network, adaptive margin, deep learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9173008 An Extension of the Kratzel Function and Associated Inverse Gaussian Probability Distribution Occurring in Reliability Theory
Authors: R. K. Saxena, Ravi Saxena
Abstract:
In view of their importance and usefulness in reliability theory and probability distributions, several generalizations of the inverse Gaussian distribution and the Krtzel function are investigated in recent years. This has motivated the authors to introduce and study a new generalization of the inverse Gaussian distribution and the Krtzel function associated with a product of a Bessel function of the third kind )(zKQ and a Z - Fox-Wright generalized hyper geometric function introduced in this paper. The introduced function turns out to be a unified gamma-type function. Its incomplete forms are also discussed. Several properties of this gamma-type function are obtained. By means of this generalized function, we introduce a generalization of inverse Gaussian distribution, which is useful in reliability analysis, diffusion processes, and radio techniques etc. The inverse Gaussian distribution thus introduced also provides a generalization of the Krtzel function. Some basic statistical functions associated with this probability density function, such as moments, the Mellin transform, the moment generating function, the hazard rate function, and the mean residue life function are also obtained.KeywordsFox-Wright function, Inverse Gaussian distribution, Krtzel function & Bessel function of the third kind.
Keywords: Fox-Wright function, Inverse Gaussian distribution, Krtzel function & Bessel function of the third kind.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17253007 Main Control Factors of Fluid Loss in Drilling and Completion in Shunbei Oilfield by Unmanned Intervention Algorithm
Authors: Peng Zhang, Lihui Zheng, Xiangchun Wang, Xiaopan Kou
Abstract:
Quantitative research on the main control factors of lost circulation has few considerations and single data source. Using Unmanned Intervention Algorithm to find the main control factors of lost circulation adopts all measurable parameters. The degree of lost circulation is characterized by the loss rate as the objective function. Geological, engineering and fluid data are used as layers, and 27 factors such as wellhead coordinates and Weight on Bit (WOB) used as dimensions. Data classification is implemented to determine function independent variables. The mathematical equation of loss rate and 27 influencing factors is established by multiple regression method, and the undetermined coefficient method is used to solve the undetermined coefficient of the equation. Only three factors in t-test are greater than the test value 40, and the F-test value is 96.557%, indicating that the correlation of the model is good. The funnel viscosity, final shear force and drilling time were selected as the main control factors by elimination method, contribution rate method and functional method. The calculated values of the two wells used for verification differ from the actual values by -3.036 m3/h and -2.374 m3/h, with errors of 7.21% and 6.35%. The influence of engineering factors on the loss rate is greater than that of funnel viscosity and final shear force, and the influence of the three factors is less than that of geological factors. The best combination of funnel viscosity, final shear force and drilling time is obtained through quantitative calculation. The minimum loss rate of lost circulation wells in Shunbei area is 10 m3/h. It can be seen that man-made main control factors can only slow down the leakage, but cannot fundamentally eliminate it. This is more in line with the characteristics of karst caves and fractures in Shunbei fault solution oil and gas reservoir.
Keywords: Drilling fluid, loss rate, main controlling factors, Unmanned Intervention Algorithm.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4083006 Application of Particle Swarm Optimization for Economic Load Dispatch and Loss Reduction
Authors: N. Phanthuna, J. Jaturacherdchaiskul, S. Lerdvanittip, S. Auchariyamet
Abstract:
This paper proposes a particle swarm optimization (PSO) technique to solve the economic load dispatch (ELD) problems. For the ELD problem in this work, the objective function is to minimize the total fuel cost of all generator units for a given daily load pattern while the main constraints are power balance and generation output of each units. Case study in the test system of 40-generation units with 6 load patterns is presented to demonstrate the performance of PSO in solving the ELD problem. It can be seen that the optimal solution given by PSO provides the minimum total cost of generation while satisfying all the constraints and benefiting greatly from saving in power loss reduction.
Keywords: Particle Swarm Optimization, Economic Load Dispatch, Loss Reduction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19003005 Economic Loss due to Ganoderma Disease in Oil Palm
Authors: K. Assis, K. P. Chong, A. S. Idris, C. M. Ho
Abstract:
Oil palm or Elaeis guineensis is considered as the golden crop in Malaysia. But oil palm industry in this country is now facing with the most devastating disease called as Ganoderma Basal Stem Rot disease. The objective of this paper is to analyze the economic loss due to this disease. There were three commercial oil palm sites selected for collecting the required data for economic analysis. Yield parameter used to measure the loss was the total weight of fresh fruit bunch in six months. The predictors include disease severity, change in disease severity, number of infected neighbor palms, age of palm, planting generation, topography, and first order interaction variables. The estimation model of yield loss was identified by using backward elimination based regression method. Diagnostic checking was conducted on the residual of the best yield loss model. The value of mean absolute percentage error (MAPE) was used to measure the forecast performance of the model. The best yield loss model was then used to estimate the economic loss by using the current monthly price of fresh fruit bunch at mill gate.
Keywords: Ganoderma, oil palm, regression model, yield loss, economic loss.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 32403004 On Bayesian Analysis of Failure Rate under Topp Leone Distribution using Complete and Censored Samples
Abstract:
The article is concerned with analysis of failure rate (shape parameter) under the Topp Leone distribution using a Bayesian framework. Different loss functions and a couple of noninformative priors have been assumed for posterior estimation. The posterior predictive distributions have also been derived. A simulation study has been carried to compare the performance of different estimators. A real life example has been used to illustrate the applicability of the results obtained. The findings of the study suggest that the precautionary loss function based on Jeffreys prior and singly type II censored samples can effectively be employed to obtain the Bayes estimate of the failure rate under Topp Leone distribution.
Keywords: loss functions, type II censoring, posterior distribution, Bayes estimators.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25623003 Calculus Logarithmic Function for Image Encryption
Authors: Adil AL-Rammahi
Abstract:
When we prefer to make the data secure from various attacks and fore integrity of data, we must encrypt the data before it is transmitted or stored. This paper introduces a new effective and lossless image encryption algorithm using a natural logarithmic function. The new algorithm encrypts an image through a three stage process. In the first stage, a reference natural logarithmic function is generated as the foundation for the encryption image. The image numeral matrix is then analyzed to five integer numbers, and then the numbers’ positions are transformed to matrices. The advantages of this method is useful for efficiently encrypting a variety of digital images, such as binary images, gray images, and RGB images without any quality loss. The principles of the presented scheme could be applied to provide complexity and then security for a variety of data systems such as image and others.
Keywords: Linear Systems, Image Encryption, Calculus.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24023002 In Silico Analysis of Pax6 Interacting Proteins Indicates Missing Molecular Links in Development of Brain and Associated Disease
Authors: Ratnakar Tripathi, Rajnikant Mishra
Abstract:
The PAX6, a transcription factor, is essential for the morphogenesis of the eyes, brain, pituitary and pancreatic islets. In rodents, the loss of Pax6 function leads to central nervous system defects, anophthalmia, and nasal hypoplasia. The haplo-insufficiency of Pax6 causes microphthalmia, aggression and other behavioral abnormalities. It is also required in brain patterning and neuronal plasticity. In human, heterozygous mutation of Pax6 causes loss of iris [aniridia], mental retardation and glucose intolerance. The 3- deletion in Pax6 leads to autism and aniridia. The phenotypes are variable in peneterance and expressivity. However, mechanism of function and interaction of PAX6 with other proteins during development and associated disease are not clear. It is intended to explore interactors of PAX6 to elucidated biology of PAX6 function in the tissues where it is expressed and also in the central regulatory pathway. This report describes In-silico approaches to explore interacting proteins of PAX6. The models show several possible proteins interacting with PAX6 like MITF, SIX3, SOX2, SOX3, IPO13, TRIM, and OGT. Since the Pax6 is a critical transcriptional regulator and master control gene of eye and brain development it might be interacting with other protein involved in morphogenesis [TGIF, TGF, Ras etc]. It is also presumed that matricelluar proteins [SPARC, thrombospondin-1 and osteonectin etc] are likely to interact during transport and processing of PAX6 and are somewhere its cascade. The proteins involved in cell survival and cell proliferation can also not be ignored.
Keywords: Interacting Proteins, Pax6, PIP, STRING
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19683001 A New Definition of the Intrinsic Mode Function
Authors: Zhihua Yang, Lihua Yang
Abstract:
This paper makes a detailed analysis regarding the definition of the intrinsic mode function and proves that Condition 1 of the intrinsic mode function can really be deduced from Condition 2. Finally, an improved definition of the intrinsic mode function is given.
Keywords: Empirical Mode Decomposition (EMD), Hilbert-Huang transform(HHT), Intrinsic Mode Function(IMF).
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 35973000 Harnessing the Power of Loss: On the Discriminatory Dynamic of Non-Emancipatory Organization Identity
Authors: Rickard Grassman
Abstract:
In this paper, Lacanian theory will be used to illustrate the way discourses interact with the material by way of reifying antagonisms to shape our sense of identities in and around organizations. The ability to ‘sustain the loss’ is, in this view, the common structure here discerned in the very texture of a discourse, which reifies ‘lack’ as an ontological condition into something contingently absent (loss) that the subject hopes to overcome (desire). These fundamental human tendencies of identification are illustrated in the paper by examples drawn from history, cinema, and literature. Turning to a select sample of empirical accounts from a management consultancy firm, it is argued that this ‘sustaining the loss’ operates in discourse to enact identification in an organizational context.
Keywords: Lacan, identification, discourse, desire and loss.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 92999 Optimal Capacitor Allocation for loss reduction in Distribution System Using Fuzzy and Plant Growth Simulation Algorithm
Authors: R. Srinivasa Rao
Abstract:
This paper presents a new and efficient approach for capacitor placement in radial distribution systems that determine the optimal locations and size of capacitor with an objective of improving the voltage profile and reduction of power loss. The solution methodology has two parts: in part one the loss sensitivity factors are used to select the candidate locations for the capacitor placement and in part two a new algorithm that employs Plant growth Simulation Algorithm (PGSA) is used to estimate the optimal size of capacitors at the optimal buses determined in part one. The main advantage of the proposed method is that it does not require any external control parameters. The other advantage is that it handles the objective function and the constraints separately, avoiding the trouble to determine the barrier factors. The proposed method is applied to 9 and 34 bus radial distribution systems. The solutions obtained by the proposed method are compared with other methods. The proposed method has outperformed the other methods in terms of the quality of solution.Keywords: Distribution systems, Capacitor allocation, Loss reduction, Fuzzy, PGSA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22812998 Optimal Capacitor Placement in a Radial Distribution System using Plant Growth Simulation Algorithm
Authors: R. Srinivasa Rao, S. V. L. Narasimham
Abstract:
This paper presents a new and efficient approach for capacitor placement in radial distribution systems that determine the optimal locations and size of capacitor with an objective of improving the voltage profile and reduction of power loss. The solution methodology has two parts: in part one the loss sensitivity factors are used to select the candidate locations for the capacitor placement and in part two a new algorithm that employs Plant growth Simulation Algorithm (PGSA) is used to estimate the optimal size of capacitors at the optimal buses determined in part one. The main advantage of the proposed method is that it does not require any external control parameters. The other advantage is that it handles the objective function and the constraints separately, avoiding the trouble to determine the barrier factors. The proposed method is applied to 9, 34, and 85-bus radial distribution systems. The solutions obtained by the proposed method are compared with other methods. The proposed method has outperformed the other methods in terms of the quality of solution.
Keywords: Distribution systems, Capacitor placement, loss reduction, Loss sensitivity factors, PGSA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 52822997 Modeling Salam Contract for Profit and Loss Sharing
Authors: Dchieche Amina, Aboulaich Rajae
Abstract:
Profit and loss sharing suggests an equitable sharing of risks and profits between the parts involved in a financial transaction. Salam is a contract in which advance payment is made for goods to be delivered at a future date. The purpose of this work is to price a new contract for profit and loss sharing based on Salam contract, using Khiyar Al Ghabn which is an agreement of choice in case of misrepresent facts.Keywords: Islamic finance, Shariah compliance, profit and loss sharing, derivatives, risks, hedging, salam contract.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19272996 Parametric Approach for Reserve Liability Estimate in Mortgage Insurance
Authors: Rajinder Singh, Ram Valluru
Abstract:
Chain Ladder (CL) method, Expected Loss Ratio (ELR) method and Bornhuetter-Ferguson (BF) method, in addition to more complex transition-rate modeling, are commonly used actuarial reserving methods in general insurance. There is limited published research about their relative performance in the context of Mortgage Insurance (MI). In our experience, these traditional techniques pose unique challenges and do not provide stable claim estimates for medium to longer term liabilities. The relative strengths and weaknesses among various alternative approaches revolve around: stability in the recent loss development pattern, sufficiency and reliability of loss development data, and agreement/disagreement between reported losses to date and ultimate loss estimate. CL method results in volatile reserve estimates, especially for accident periods with little development experience. The ELR method breaks down especially when ultimate loss ratios are not stable and predictable. While the BF method provides a good tradeoff between the loss development approach (CL) and ELR, the approach generates claim development and ultimate reserves that are disconnected from the ever-to-date (ETD) development experience for some accident years that have more development experience. Further, BF is based on subjective a priori assumption. The fundamental shortcoming of these methods is their inability to model exogenous factors, like the economy, which impact various cohorts at the same chronological time but at staggered points along their life-time development. This paper proposes an alternative approach of parametrizing the loss development curve and using logistic regression to generate the ultimate loss estimate for each homogeneous group (accident year or delinquency period). The methodology was tested on an actual MI claim development dataset where various cohorts followed a sigmoidal trend, but levels varied substantially depending upon the economic and operational conditions during the development period spanning over many years. The proposed approach provides the ability to indirectly incorporate such exogenous factors and produce more stable loss forecasts for reserving purposes as compared to the traditional CL and BF methods.
Keywords: Actuarial loss reserving techniques, logistic regression, parametric function, volatility.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4172995 Evaluating Generative Neural Attention Weights-Based Chatbot on Customer Support Twitter Dataset
Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli
Abstract:
Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are increasingly important in automated customer service. These models, adept at recognizing complex relationships between input and output sequences, are essential for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the model’s focus during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the context of chatbots utilizing the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Using the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k = 3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k = 3). These findings emphasize the crucial influence of selecting an appropriate attention-scoring function to enhance the performance of seq2seq models for chatbots, particularly highlighting the model integrating tanh activation as a promising approach to improving chatbot quality in customer support contexts.
Keywords: Attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 952994 Fast Factored DCT-LMS Speech Enhancement for Performance Enhancement of Digital Hearing Aid
Authors: Sunitha. S.L., V. Udayashankara
Abstract:
Background noise is particularly damaging to speech intelligibility for people with hearing loss especially for sensorineural loss patients. Several investigations on speech intelligibility have demonstrated sensorineural loss patients need 5-15 dB higher SNR than the normal hearing subjects. This paper describes Discrete Cosine Transform Power Normalized Least Mean Square algorithm to improve the SNR and to reduce the convergence rate of the LMS for Sensory neural loss patients. Since it requires only real arithmetic, it establishes the faster convergence rate as compare to time domain LMS and also this transformation improves the eigenvalue distribution of the input autocorrelation matrix of the LMS filter. The DCT has good ortho-normal, separable, and energy compaction property. Although the DCT does not separate frequencies, it is a powerful signal decorrelator. It is a real valued function and thus can be effectively used in real-time operation. The advantages of DCT-LMS as compared to standard LMS algorithm are shown via SNR and eigenvalue ratio computations. . Exploiting the symmetry of the basis functions, the DCT transform matrix [AN] can be factored into a series of ±1 butterflies and rotation angles. This factorization results in one of the fastest DCT implementation. There are different ways to obtain factorizations. This work uses the fast factored DCT algorithm developed by Chen and company. The computer simulations results show superior convergence characteristics of the proposed algorithm by improving the SNR at least 10 dB for input SNR less than and equal to 0 dB, faster convergence speed and better time and frequency characteristics.Keywords: Hearing Impairment, DCT Adaptive filter, Sensorineural loss patients, Convergence rate.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21722993 Numerical Investigation on the Progressive Collapse Resistance of an RC Building with Brick Infills under Column Loss
Authors: Meng-Hao Tsai, Tsuei-Chiang Huang
Abstract:
Interior brick-infill partitions are usually considered as non-structural components and only their weight is accounted for in practical structural design. In this study, their effect on the progressive collapse resistance of an RC building subjected to sudden column loss is investigated. Three notional column loss conditions with four different brick-infill locations are considered. Column-loss response analyses of the RC building with and without brick infills are carried out. Analysis results indicate that the collapse resistance is only slightly influenced by the brick infills due to their brittle failure characteristic. Even so, they may help to reduce the inelastic displacement response under column loss. For practical engineering, it is reasonably conservative to only consider the weight of brick-infill partitions in the structural analysis.Keywords: Progressive collapse, column loss, brick-infill partition, compression strut.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21392992 Studying Mistaken Theory of Calendar Function of Iran-s Cross-Vaults
Authors: Ali Salehipour
Abstract:
After presenting the theory of calendar function of Iran-s cross-vaults especially “Niasar" cross-vault in recent years, there has been lots of doubts and uncertainty about this theory by astrologists and archaeologists. According to this theory “Niasar cross-vault and other cross-vaults of Iran has calendar function and are constructed in a way that sunrise and sunset can be seen from one of its openings in the beginning and middle of each season of year". But, mentioning historical documentaries we conclude here that the theory of calendar function of Iran-s cross-vaults does not have any strong basis and individual cross-vaults had only religious function in Iran.Keywords: cross-vault, fire temple, Calendar function, Sassanid period
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15952991 Investigation of Heat Loss in Ethanol-Water Distillation Column with Direct Vapour Recompression Heat Pump
Authors: Christopher C. Enweremadu, Hilary L. Rutto
Abstract:
Vapour recompression system has been used to enhance reduction in energy consumption and improvement in energy effectiveness of distillation columns. However, the effects of certain parameters have not been taken into consideration. One of such parameters is the column heat loss which has either been assumed to be a certain percent of reboiler heat transfer or negligible. The purpose of this study was to evaluate the heat loss from an ethanol-water vapour recompression distillation column with pressure increase across the compressor (VRCAS) and compare the results obtained and its effect on some parameters in similar system (VRCCS) where the column heat loss has been assumed or neglected. Results show that the heat loss evaluated was higher when compared with that obtained for the column VRCCS. The results also showed that increase in heat loss could have significant effect on the total energy consumption, reboiler heat transfer, the number of trays and energy effectiveness of the column.Keywords: Compressor, distillation column, heat loss, vapourrecompression.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 49982990 Performance Evaluation of the OCDM/WDM Technique for Optical Packet Switches
Authors: V. Eramo, L. Piazzo, M. Listanti, A. Germoni, A Cianfrani
Abstract:
The performance of the Optical Code Division Multiplexing/ Wavelength Division Multiplexing (WDM/OCDM) technique for Optical Packet Switch is investigated. The impact on the performance of the impairment due to both Multiple Access Interference and Beat noise is studied. The Packet Loss Probability due to output packet contentions is evaluated as a function of the main switch and traffic parameters when Gold coherent optical codes are adopted. The Packet Loss Probability of the OCDM/WDM switch can reach 10-9 when M=16 wavelengths, Gold code of length L=511 and only 24 wavelength converters are used in the switch.
Keywords: Optical code division multiplexing, bufferless optical packet switch, performance evaluation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14452989 Comparison between Beta Wavelets Neural Networks, RBF Neural Networks and Polynomial Approximation for 1D, 2DFunctions Approximation
Authors: Wajdi Bellil, Chokri Ben Amar, Adel M. Alimi
Abstract:
This paper proposes a comparison between wavelet neural networks (WNN), RBF neural network and polynomial approximation in term of 1-D and 2-D functions approximation. We present a novel wavelet neural network, based on Beta wavelets, for 1-D and 2-D functions approximation. Our purpose is to approximate an unknown function f: Rn - R from scattered samples (xi; y = f(xi)) i=1....n, where first, we have little a priori knowledge on the unknown function f: it lives in some infinite dimensional smooth function space and second the function approximation process is performed iteratively: each new measure on the function (xi; f(xi)) is used to compute a new estimate f as an approximation of the function f. Simulation results are demonstrated to validate the generalization ability and efficiency of the proposed Beta wavelet network.
Keywords: Beta wavelets networks, RBF neural network, training algorithms, MSE, 1-D, 2D function approximation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1922