Search results for: neural networking algorithm

Authors: A. Baviskar, C. Sandeep, K. Shankar

Abstract:

Solving Multi-objective Optimization Problems requires faster convergence and better spread. Though existing Evolutionary Algorithms (EA's) are able to achieve this, the computation effort can further be reduced by hybridizing them with innovative strategies. This study is focuses on converging to the pareto front faster while adapting the advantages of Strength Pareto Evolutionary Algorithm-II (SPEA-II) for a better spread. Two different approaches based on optimizing the objective functions independently are implemented. In the first method, the decision variables corresponding to the optima of individual objective functions are strategically used to guide the search towards the pareto front. In the second method, boundary points of the pareto front are calculated and their decision variables are seeded to the initial population. Both the methods are applied to different constrained and unconstrained multi-objective test functions. It is observed that proposed guided search based algorithm gives better convergence and diversity than several well-known existing algorithms (such as NSGA-II and SPEA-II) in considerably less number of iterations.

Keywords: boundary points, evolutionary algorithms (EA's), guided search, strength pareto evolutionary algorithm-II (SPEA-II)

Procedia PDF Downloads 277

Authors: Mabrouka Algherinai, Fatma Karkouri

Abstract:

Today, Short Message Service (SMS) is an important means of communication. SMS is not only used in informal environment for communication and transaction, but it is also used in formal environments such as institutions, organizations, companies, and business world as a tool for communication and transactions. Therefore, there is a need to secure the information that is being transmitted through this medium to ensure security of information both in transit and at rest. But, encryption has been identified as a means to provide security to SMS messages in transit and at rest. Several past researches have proposed and developed several encryption algorithms for SMS and Information Security. This research aims at comparing the performance of common Asymmetric encryption algorithms on SMS security. The research employs the use of three algorithms, namely RSA, McEliece, and RABIN. Several experiments were performed on SMS of various sizes on android mobile device. The experimental results show that each of the three techniques has different key generation, encryption, and decryption times. The efficiency of an algorithm is determined by the time that it takes for encryption, decryption, and key generation. The best algorithm can be chosen based on the least time required for encryption. The obtained results show the least time when McEliece size 4096 is used. RABIN size 4096 gives most time for encryption and so it is the least effective algorithm when considering encryption. Also, the research shows that McEliece size 2048 has the least time for key generation, and hence, it is the best algorithm as relating to key generation. The result of the algorithms also shows that RSA size 1024 is the most preferable algorithm in terms of decryption as it gives the least time for decryption.

Keywords: SMS, RSA, McEliece, RABIN

Procedia PDF Downloads 165

Authors: Delowar Hossain, Genci Capi

Abstract:

This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function that is good enough. After finishing the evolution process, we receive the optimal number of DL parameters. To evaluate the performance of our method, we consider the object recognition and robot grasping tasks. Experimental results show that our method is efficient for robot object recognition and grasping.

Keywords: deep learning, genetic algorithm, object recognition, robot grasping

Procedia PDF Downloads 353

Authors: Firas Gerges, Frank Y. Shih

Abstract:

Malignant melanoma, known simply as melanoma, is a type of skin cancer that appears as a mole on the skin. It is critical to detect this cancer at an early stage because it can spread across the body and may lead to the patient's death. When detected early, melanoma is curable. In this paper, we propose a deep learning model (convolutional neural networks) in order to automatically classify skin lesion images as malignant or benign. Images underwent certain pre-processing steps to diminish the effect of the normal skin region on the model. The result of the proposed model showed a significant improvement over previous work, achieving an accuracy of 97%.

Keywords: deep learning, skin cancer, image processing, melanoma

Procedia PDF Downloads 150

Authors: Farhad Asadi, Mohammad Javad Mollakazemi

Abstract:

In this paper, Bayesian online inference in models of data series are constructed by change-points algorithm, which separated the observed time series into independent series and study the change and variation of the regime of the data with related statistical characteristics. variation of statistical characteristics of time series data often represent separated phenomena in the some dynamical system, like a change in state of brain dynamical reflected in EEG signal data measurement or a change in important regime of data in many dynamical system. In this paper, prediction algorithm for studying change point location in some time series data is simulated. It is verified that pattern of proposed distribution of data has important factor on simpler and smother fluctuation of hazard rate parameter and also for better identification of change point locations. Finally, the conditions of how the time series distribution effect on factors in this approach are explained and validated with different time series databases for some dynamical system.

Keywords: time series, fluctuation in statistical characteristics, optimal learning, change-point algorithm

Procedia PDF Downloads 428

Authors: Masoud Abedi, Abbas Malekpour, Peter Luksch, Mohammad Reza Mojtabaei

Abstract:

The use of short texts in communication has been greatly increasing in recent years. Applying different languages in short texts has led to compulsory use of Unicode strings. These strings need twice the space of common strings, hence, applying algorithms of compression for the purpose of accelerating transmission and reducing cost is worthwhile. Nevertheless, other compression methods like gzip, bzip2 or PAQ due to high overhead data size are not appropriate. The Huffman algorithm is one of the rare algorithms effective in reducing the size of short Unicode strings. In this paper, an algorithm is proposed for compression of very short Unicode strings. At first, every new character to be sent to a destination is inserted in the proposed mapping table. At the beginning, every character is new. In case the character is repeated for the same destination, it is not considered as a new character. Next, the new characters together with the mapping value of repeated characters are arranged through a specific technique and specially formatted to be transmitted. The results obtained from an assessment made on a set of short Persian and Arabic strings indicate that this proposed algorithm outperforms the Huffman algorithm in size reduction.

Keywords: Algorithms, Data Compression, Decoding, Encoding, Huffman Codes, Text Communication

Procedia PDF Downloads 349

Authors: Antonin Ponsich, Eric Alfredo Rincon Garcia, Roman Anselmo Mora Gutierrez, Miguel Angel Gutierrez Andrade, Sergio Gerardo De Los Cobos Silva, Pedro Lara Velzquez

Abstract:

The electoral zone design problem consists in redrawing the boundaries of legislative districts for electoral purposes in such a way that federal or state requirements are fulfilled. In Mexico, this process has been historically carried out by the National Electoral Institute (INE), by optimizing an integer nonlinear programming model, in which population equality and compactness of the designed districts are considered as two conflicting objective functions, while contiguity is included as a hard constraint. The solution technique used by the INE is a Simulated Annealing (SA) based algorithm, which handles the multi-objective nature of the problem through an aggregation function. The present work represents the first intent to apply a classical Multi-Objective Evolutionary Algorithm (MOEA), the second version of the Non-dominated Sorting Genetic Algorithm (NSGA-II), to this hard combinatorial problem. First results show that, when compared with the SA algorithm, the NSGA-II obtains promising results. The MOEA manages to produce well-distributed solutions over a wide-spread front, even though some convergence troubles for some instances constitute an issue, which should be corrected in future adaptations of MOEAs to the redistricting problem.

Keywords: multi-objective optimization, NSGA-II, redistricting, zone design problem

Procedia PDF Downloads 367

Authors: N. Larbi, F. Debbat

Abstract:

Wireless communication systems have changed dramatically and shown spectacular evolution over the past two decades. These radio technologies are engaged in a quest endless high-speed transmission coupled to a constant need to improve transmission quality. Various radio communication systems being developed use code division multiple access (CDMA) technique. This work analyses a hybrid honey bees mating optimization algorithm (HBMO) applied to multiuser detection (MuD) in CDMA communication systems. The HBMO is a swarm-based optimization algorithm, which simulates the mating process of real honey bees. We apply a hybridization of HBMO with simulated annealing (SA) in order to improve the solution generated by the HBMO. Simulation results show that the detection based on Hybrid HBMO, in term of bit error rate (BER), is viable option when compared with the classic detectors from literature under Rayleigh flat fading channel.

Keywords: BER, DS-CDMA multiuser detection, genetic algorithm, hybrid HBMO, simulated annealing

Procedia PDF Downloads 437

Authors: Fulufhelo Oscar Maphiri-Makananise

Abstract:

The main purpose of this paper is to explore and provide substantiated evidence based on the usage patterns of Information and Communication Technologies (ICTs) by females in the Vhembe District in Limpopo-Province, South Africa. The study presents a broader picture and understanding about the usage of ICTs from female’s perspective. The significance of this study stems from the need to discover the role, relevance and usage patterns of ICTs such as smartphones, computers, laptops, and iPods, internet and social networking sites among females following the trends of new media technologies in the society. The main objective of the study was to investigate the usability and accessibility of ICTs to empower the Vhembe District females in South Africa. The study used quantitative research method together with elements of qualitative research to determine the major ideas, perceptions and usage patterns of ICTs by females in the District. Data collection involved structured and self-administered questionnaire with both closed-ended and open-ended questions. Two groups of respondents participated in this study. Media Studies female students (n=50) at the University of Venda provided their ideas and perceptions about the usefulness and usage patterns of ICTs such as smartphones, internet and computers at the university level, while the second group were (n=50) Makhado comprehensive school learners who also provided their perceptions and ideas about the use of ICTs at the high school level. Also, the study provides a more balanced, accurate and rational results on the pertinent issues that concern the use of ICTs by females in the Vhembe District. The researcher also believes that the findings of the study are useful as a guideline and model for ICT intervention that work as an empowerment to women in South Africa. The study showed that the main purpose of using ICTs by females was to search information for writing assignments, conducting research, dating, exchanging ideas and networking with friends and relatives that are also members of social networking sites and maintaining existing friends in real life. The study further revealed that most females were using ICTs for social purposes and accessing the internet than entertaining themselves. The finding also indicated a high number of females that used ICTs for e-learning (62%) and social purposes (85%). Moreover, the study centred on providing strong insightful information on the females’ usage patterns and their perceptions of ICTs in the Vhembe district of Limpopo province.

Keywords: female users, information and communication technologies, internet, usage patterns

Procedia PDF Downloads 217

Authors: Marziyeh Bahrami, Hamed Pahlevan Hsseini, Behnam Ghamami, Arman Alvanpour, Hamed Ezzati, Amir Salar Sadeghi

Abstract:

One of the ways to increase the efficiency of services in the system of agents and, of course, in the world of cloud computing, is to use virtualization techniques. The aim of this research is to create changes in cloud computing services that will reduce as much as possible the energy consumption related to the migration of virtual machines and, in some way, the energy related to the allocation of resources and reduce the amount of pollution. So far, several methods have been proposed to increase the efficiency of cloud computing services in order to save energy in the cloud environment. The method presented in this article tries to prevent energy consumption by data centers and the subsequent production of carbon and biological pollutants as much as possible by increasing the efficiency of cloud computing services. The results show that the proposed algorithm, using the improvement in virtualization techniques and with the help of a genetic algorithm, improves the efficiency of cloud services in the matter of migrating virtual machines and finally saves consumption. becomes energy.

Keywords: consumption reduction, cloud computing, genetic algorithm, live migration, virtual Machine

Procedia PDF Downloads 61

Authors: El Asnaoui Khalid, Aksasse Brahim, Ouanan Mohammed

Abstract:

In this paper, we are interested in the problem of finding similar images in a large database. For this purpose we propose a new algorithm based on a combination of the 2-D histogram intersection in the HSV space and statistical moments. The proposed histogram is based on a 3x3 window and not only on the intensity of the pixel. This approach can overcome the drawback of the conventional 1-D histogram which is ignoring the spatial distribution of pixels in the image, while the statistical moments are used to escape the effects of the discretisation of the color space which is intrinsic to the use of histograms. We compare the performance of our new algorithm to various methods of the state of the art and we show that it has several advantages. It is fast, consumes little memory and requires no learning. To validate our results, we apply this algorithm to search for similar images in different image databases.

Keywords: 2-D histogram, statistical moments, indexing, similarity distance, histograms intersection

Procedia PDF Downloads 457

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 74

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN

Procedia PDF Downloads 120

Authors: Niharika Verma, Sandeep Santosh

Abstract:

DOA technique is a localization technique used in the communication field. Various algorithms have been developed for direction of arrival estimation like MUSIC, ROOT MUSIC, etc. These algorithms depend on various parameters like antenna array elements, number of snapshots and various others. Basically the MUSIC spectrum is evaluated and peaks obtained are considered as the angle of arrivals. The angles evaluated using this process depends on the scanning interval chosen. The accuracy of the results obtained depends on the coarseness of the interval chosen. In this paper, golden section search is applied to the MUSIC algorithm and therefore, more accurate results are achieved. Initially the coarse DOA estimations is done using the MUSIC algorithm in the range -90 to 90 degree at the interval of 10 degree. After the peaks obtained then fine DOA estimation is done using golden section search. Also, the partitioning method is applied to estimate the number of signals incident on the antenna array. Dependency of the algorithm on the number of snapshots is also being explained. Hence, the accurate results are being determined using this algorithm.

Keywords: Direction of Arrival (DOA), golden section search, MUSIC, number of snapshots

Procedia PDF Downloads 447

Authors: Ingrid Argote, John Archila, Marcelo Becker

Abstract:

In agriculture, intelligent systems applications have generated great advances in automating some of the processes in the production chain. In order to improve the efficiency of those systems is proposed a vision system to estimate the amount of fruits in sweet orange trees. This work presents a system proposal using capture of thermal images and fuzzy logic. A bibliographical review has been done to analyze the state-of-the-art of the different systems used in fruit recognition, and also the different applications of thermography in agricultural systems. The algorithm developed for this project uses the metrics of the fuzzines parameter to the contrast improvement and segmentation of the image, for the counting algorith m was used the Hough transform. In order to validate the proposed algorithm was created a bank of images of sweet orange Citrus (L.) Osbeck acquired in the Maringá Farm. The tests with the algorithm Indicated that the variation of the tree branch temperature and the fruit is not very high, Which makes the process of image segmentation using this differentiates, This Increases the amount of false positives in the fruit counting algorithm. Recognition of fruits isolated with the proposed algorithm present an overall accuracy of 90.5 % and grouped fruits. The accuracy was 81.3 %. The experiments show the need for a more suitable hardware to have a better recognition of small temperature changes in the image.

Keywords: Agricultural systems, Citrus, Fuzzy logic, Thermal images.

Procedia PDF Downloads 230

Authors: Sanjay Kumar Parjapati, Ajai Jain

Abstract:

This paper presents optimization of makespan for ‘n’ jobs and ‘m’ machines flexible job shop scheduling problem with sequence dependent setup time using genetic algorithm (GA) approach. A restart scheme has also been applied to prevent the premature convergence. Two case studies are taken into consideration. Results are obtained by considering crossover probability (pc = 0.85) and mutation probability (pm = 0.15). Five simulation runs for each case study are taken and minimum value among them is taken as optimal makespan. Results indicate that optimal makespan can be achieved with more than one sequence of jobs in a production order.

Keywords: flexible job shop, genetic algorithm, makespan, sequence dependent setup times

Procedia PDF Downloads 333

Authors: Vani Singhal, Jitendra Parmar, Satyendra Singh Chouhan

Abstract:

Unseen class discovery has now become an important part of a machine-learning algorithm to judge new classes. Unseen classes are the classes on which the machine learning model is not trained on. With the advancement in technology and AI replacing humans, the amount of data has increased to the next level. So while implementing a model on real-world examples, we come across unseen new classes. Our aim is to find the number of unseen classes by using a hierarchical-based active learning algorithm. The algorithm is based on hierarchical clustering as well as active sampling. The number of clusters that we will get in the end will give the number of unseen classes. The total clusters will also contain some clusters that have unseen classes. Instead of first discovering unseen classes and then finding their number, we directly calculated the number by applying the algorithm. The dataset used is for intent classification. The target data is the intent of the corresponding query. We conclude that when the machine learning model will encounter real-world data, it will automatically find the number of unseen classes. In the future, our next work would be to label these unseen classes correctly.

Keywords: active sampling, hierarchical clustering, open world learning, unseen class discovery

Procedia PDF Downloads 173

Authors: Annalakshmi G., Sakthivel Murugan S.

Abstract:

This paper presents a local directional encoded derivative binary pattern (LDEDBP) feature extraction method that can be applied for the classification of submarine coral reef images. The classification of coral reef images using texture features is difficult due to the dissimilarities in class samples. In coral reef image classification, texture features are extracted using the proposed method called local directional encoded derivative binary pattern (LDEDBP). The proposed approach extracts the complete structural arrangement of the local region using local binary batten (LBP) and also extracts the edge information using local directional pattern (LDP) from the edge response available in a particular region, thereby achieving extra discriminative feature value. Typically the LDP extracts the edge details in all eight directions. The process of integrating edge responses along with the local binary pattern achieves a more robust texture descriptor than the other descriptors used in texture feature extraction methods. Finally, the proposed technique is applied to an extreme learning machine (ELM) method with a meta-heuristic algorithm known as weighted distance grey wolf optimizer (GWO) to optimize the input weight and biases of single-hidden-layer feed-forward neural networks (SLFN). In the empirical results, ELM-WDGWO demonstrated their better performance in terms of accuracy on all coral datasets, namely RSMAS, EILAT, EILAT2, and MLC, compared with other state-of-the-art algorithms. The proposed method achieves the highest overall classification accuracy of 94% compared to the other state of art methods.

Keywords: feature extraction, local directional pattern, ELM classifier, GWO optimization

Procedia PDF Downloads 164

Authors: Lee Jeong Min, Lee Mi Hee, Eo Yang Dam

Abstract:

Geospatial feature extraction is a very important issue in the remote sensing research. In the meantime, the image classification based on statistical techniques, but, in recent years, data mining and machine learning techniques for automated image processing technology is being applied to remote sensing it has focused on improved results generated possibility. In this study, artificial neural network and decision tree technique is applied to classify the high-resolution satellite images, as compared to the MLC processing result is a statistical technique and an analysis of the pros and cons between each of the techniques.

Keywords: remote sensing, artificial neural network, decision tree, maximum likelihood classification

Procedia PDF Downloads 347

Authors: Jaimin Patel

Abstract:

Cloud computing is one of the most sharp and important movement in various computing technologies. It provides flexibility to users, cost effectiveness, location independence, easy maintenance, enables multitenancy, drastic performance improvements, and increased productivity. On the other hand, there are also major issues like security. Being a common server, security for a cloud is a major issue; it is important to provide security to protect user’s private data, and it is especially important in e-commerce and social networks. In this paper, encryption algorithms such as Advanced Encryption Standard algorithms, their vulnerabilities, risk of attacks, optimal time and complexity management and comparison with other algorithms based on software implementation is proposed. Encryption techniques to improve the performance of AES algorithms and to reduce risk management are given. Secure Hash Algorithms, their vulnerabilities, software implementations, risk of attacks and comparison with other hashing algorithms as well as the advantages and disadvantages between hashing techniques and encryption are given.

Keywords: Cloud computing, encryption algorithm, secure hashing algorithm, brute force attack, birthday attack, plaintext attack, man in middle attack

Procedia PDF Downloads 282

Authors: Ahmed Z. Gabr, Ahmed A. Helal, Hussein E. Said

Abstract:

With the incessant increase of power systems capacity and voltage grade, the safety of grounding grid becomes more and more prominent. In this paper, the designing substation grounding grid is presented by means of genetic algorithm (GA). This approach purposes to control the grounding cost of the power system with the aid of controlling grounding rod number and conductor lengths under the same safety limitations. The proposed technique is used for the design of the substation grounding grid in Khalda Petroleum Company “El-Qasr” power plant and the design was simulated by using CYMGRD software for results verification. The result of the design is highly complying with IEEE 80-2000 standard requirements.

Keywords: genetic algorithm, optimum grounding grid design, power system analysis, power system protection, single layer model, substation

Procedia PDF Downloads 537

Authors: Yifan Hou, Haibo Liu, Le Jiang, Wandong Su, Binqing Wang

Abstract:

Road defect detection is crucial for modern urban management and infrastructure maintenance. Traditional road defect detection methods mostly rely on manual labor, which is not only inefficient but also difficult to ensure their reliability. However, existing deep learning-based road defect detection models have poor detection performance in complex environments and lack robustness to multi-scale targets. To address this challenge, this paper proposes a distinct detection framework based on the one stage algorithm network structure. This article designs a deep feature extraction network based on RCSDarknet, which applies channel shuffling to enhance information fusion between tensors. Through repeated stacking of RCS modules, the information flow between different channels of adjacent layer features is enhanced to improve the model's ability to capture target spatial features. In addition, a multi-scale feature fusion mechanism with weighted dual flow paths was adopted to fuse spatial features of different scales, thereby further improving the detection performance of the model at different scales. To validate the performance of the proposed algorithm, we tested it using the RDD2022 dataset. The experimental results show that the enhancement algorithm achieved 84.14% mAP, which is 1.06% higher than the currently advanced YOLOv8 algorithm. Through visualization analysis of the results, it can also be seen that our proposed algorithm has good performance in detecting targets of different scales in complex scenes. The above experimental results demonstrate the effectiveness and superiority of the proposed algorithm, providing valuable insights for advancing real-time road defect detection methods.

Keywords: roads, defect detection, visualization, deep learning

Procedia PDF Downloads 13

Authors: Abdullah A. AlShaher

Abstract:

In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2^nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We then proceed by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.

Keywords: character recognition, regression curves, handwritten Arabic letters, expectation maximization algorithm

Procedia PDF Downloads 145

Authors: Nonlapun Meenil, Pisitpong Intarapong, Thitima Wongsheree, Pranchalee Samanpiboon

Abstract:

In Thailand, once pineapples are harvested, they must be classified into two classes based on their sweetness: sweet and unsweet. This paper has studied and developed the assessment of internal quality of pineapples using a low-cost compact spectroscopy sensor according to the Spectroscopy approach and Neural Network (NN). During the experiments, Batavia pineapples were utilized, generating 100 samples. The extracted pineapple juice of each sample was used to determine the Soluble Solid Content (SSC) labeling into sweet and unsweet classes. In terms of experimental equipment, the sensor cover was specifically designed to install the sensor and light source to read the reflectance at a five mm depth from pineapple flesh. By using a spectroscopy sensor, data on visible and near-infrared reflectance (Vis-NIR) were collected. The NN was used to classify the pineapple classes. Before the classification step, the preprocessing methods, which are Class balancing, Data shuffling, and Standardization were applied. The 510 nm and 900 nm reflectance values of the middle parts of pineapples were used as features of the NN. With the Sequential model and Relu activation function, 100% accuracy of the training set and 76.67% accuracy of the test set were achieved. According to the abovementioned information, using a low-cost compact spectroscopy sensor has achieved favorable results in classifying the sweetness of the two classes of pineapples.

Keywords: neural network, pineapple, soluble solid content, spectroscopy

Procedia PDF Downloads 79

Authors: Jiameng Wang, Yunfei Yin, Xiyu Deng

Abstract:

Parallel optimization is one of the important research topics of data mining at this stage. Taking Classification and Regression Tree (CART) parallelization as an example, this paper proposes a parallel data mining algorithm based on SSP-OGini-PCCP. Aiming at the problem of choosing the best CART segmentation point, this paper designs an S-SP model without data association; and in order to calculate the Gini index efficiently, a parallel OGini calculation method is designed. In addition, in order to improve the efficiency of the pruning algorithm, a synchronous PCCP pruning strategy is proposed in this paper. In this paper, the optimal segmentation calculation, Gini index calculation, and pruning algorithm are studied in depth. These are important components of parallel data mining. By constructing a distributed cluster simulation system based on SPARK, data mining methods based on SSP-OGini-PCCP are tested. Experimental results show that this method can increase the search efficiency of the best segmentation point by an average of 89%, increase the search efficiency of the Gini segmentation index by 3853%, and increase the pruning efficiency by 146% on average; and as the size of the data set increases, the performance of the algorithm remains stable, which meets the requirements of contemporary massive data processing.

Keywords: classification, Gini index, parallel data mining, pruning ahead

Procedia PDF Downloads 124

Authors: Sofia Ayouche, Rachid Ellaia, Rajae Aboulaich

Abstract:

Today, insurers may use the yield curve as an indicator evaluation of the profit or the performance of their portfolios; therefore, they modeled it by one class of model that has the ability to fit and forecast the future term structure of interest rates. This class of model is the Nelson-Siegel-Svensson model. Unfortunately, many authors have reported a lot of difficulties when they want to calibrate the model because the optimization problem is not convex and has multiple local optima. In this context, we implement a hybrid Particle Swarm optimization and Nelder Mead algorithm in order to minimize by least squares method, the difference between the zero-coupon curve and the NSS curve.

Keywords: optimization, zero-coupon curve, Nelson-Siegel-Svensson, particle swarm optimization, Nelder-Mead algorithm

Procedia PDF Downloads 430

Authors: Yili Chen, Xiaokun Liang, Zhicheng Zhang, Yaoqin Xie

Abstract:

In an effort to restore visual perception in retinal diseases, an electronic retinal prosthesis with thousands of electrodes has been developed. The image processing strategies of retinal prosthesis system converts the original images from the camera to the stimulus pattern which can be interpreted by the brain. Practically, the original images are with more high resolution (256x256) than that of the stimulus pattern (such as 25x25), which causes a technical image processing challenge to do large-capacity image information reduction. In this paper, we focus on developing an efficient image processing stimulus pattern extraction algorithm by using a single cue saliency map for extracting salient objects in the image with an optimal trimming threshold. Experimental results showed that the proposed stimulus pattern extraction algorithm performs quite well for different scenes in terms of the stimulus pattern. In the algorithm performance experiment, our proposed SCSPE algorithm have almost five times of the score compared with Boyle’s algorithm. Through experiment s we suggested that when there are salient objects in the scene (such as the blind meet people or talking with people), the trimming threshold should be set around 0.4max, in other situations, the trimming threshold values can be set between 0.2max-0.4max to give the satisfied stimulus pattern.

Keywords: retinal prosthesis, image processing, region of interest, saliency map, trimming threshold selection

Procedia PDF Downloads 249

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

Abstract:

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

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

Procedia PDF Downloads 622

Authors: Mehrdad Shafiei Dizaji, Hoda Azari

Abstract:

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

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

Procedia PDF Downloads 43

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 39