Behavioural Improvement of People with Autism Spectrum Disorder | Chapter 7 | Language, Literature and Education: Research Updates Vol. 2

People with Autism Spectrum Disorder (ASD) are defined by the International Classification of Mental Disorders. The basic aim of this study is to prove whether an integrated psycho-pedagogical program, structured in accordance with the psychosocial and educational mediation model, would lead to greater behavioural and educational action training in people with Autism Spectrum Disorder (ASD). The program has basically focused on psycho-cyto-cognitive mediation criteria, based on the progressive creation of neural networks and connections between information and acquired behaviours according to the particular needs of people with ASD selected according to the basic competencies initially assessed. An experimental research design on three measures has been based, on one pre-test (I), and two post-tests (II-III) was realized. A total of 14 children with ASD participated in the intervention program specific ad hoc applied for two years. Results found through comparative analysis Friedman Test and Multivariate Tests Within- Subjects Effects, showed that the intensive intervention improved children´s behaviour and their functional adaptation to the context and, in conclusion, social life and inclusion improved. More experiments and larger data sets will be needed however the indications are there that a collective learning environment needs to be created, therefore this is a very timely paper. This can be tested further. In conclusion, the integrated program can be considered an effective intervention to promote the development of social skills.

 

Author (s) Details

 

Manuel Ojea Rúa
University of Vigo, Spain.

 

Andrea Vieira Vázquez
Teacher - Guidance Counselor in Secondary School, Lugo, Spain.

 

Please see the book here:- https://doi.org/10.9734/bpi/lleru/v2/4016 

The Analysis of the Risk Management in Child Obesity Using Deep Learning Neural Network | Chapter 21 | Innovative Solutions: A Systematic Approach towards Sustainable Future

The research proposal is to manage and monitor the obesity in children by the huge database. The data base meticulously analyses the data and interpret it and derive complete details about the growth process in children by using the neural network model that identifies the obesity risk. The model then dutifully alerts parents when there is an observable increase in the child's weight, advising them proactively on what measures need to be taken to address and mitigate this weight gain. In addition to tracking the child's physical activity, the device provides parents with graphs and reports that show how the child has been performing.

The study aims at developing a neural network weights model to recognize the risk of obesity by considering the parameters like Body mass index, physical fitness level, normal heart beat rate, jumping points. The model will be trained and tested on a dataset of medical data. The performance of the model will be assessed in terms of accuracy, precision, and recall. The model will then be used to classify people into risk categories. The model will be trained using supervised learning techniques, with the relevant parameters as input and the obesity risk as the output. The model will then be tested on the dataset to evaluate the accuracy, precision, and recall. Finally, the model will be used to classify people into risk categories.

 

Author (s) Details

 

Ramesh
Department of Civil, Sri Siddhartha Institute of Technology, Tumkur, India.

 

Divyashree D V
Department of Management studies, MES Institute of Management, Bangalore, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-49238-47-3/CH21

Artificial Intelligence in Dentistry-A Review Article | Chapter 15 | New Visions in Medicine and Medical Science Vol. 2

 The field of Artificial Intelligence (AI) has experienced great development and growth over the past two decades. AI has tremendous potential in the health care field. In dentistry, AI is being used for a variety of purposes. Once considered to be a science fiction is now becoming reality in health care. AI is a fast-growing technology that enables machines to perform tasks with the cognitive skills of humans. Neural networks which are commonly used in dentistry are a part of AI, and are very similar to the human brain in their work and they can solve the given problems and make fast decisions. More research work and advancements are needed in the use of neural networks in dentistry to use them in the daily practice. This review is about usage and development of AI in recent years in the field of dentistry.

Author(s) Details:

Vytheeswari R.,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Sudarshan R.,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Madhulika Naidu,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Anitha M.,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Nandini Priya M.,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Anu M.,
Department of Oral Medicine and Radiology, Best Dental Science College, Madurai, India.

Please see the link here: https://stm.bookpi.org/NVMMS-V2/article/view/13838

GMTDS Algorithm for Dynamic Management of Transaction under Different Workload Condition: A Novel Approach | Chapter 8 | Research Updates in Mathematics and Computer Science Vol. 1

 This paper highlights a Novel GMTDS Algorithm for Dynamic Management of Transaction under Different Workload Condition. In today’s scenario large enterprise world spread across different locations, continents or having a diverse presence over the globe, where data is enormous and handling such large data over distributed computing becomes critical in real-time database system. Transaction processing ensures that related data is added to or deleted from the database simultaneously, thus preserving data integrity in your application. In transaction processing, data is not written to the database until a commit command is issued. Ensuring that the sequence of updates in the stable warehouses at various locations is safely confirmed or canceled as a single full item of work is a critical task for the distributed environment's transaction management system. Working with Real-Time Database System (RTDBS) and that to on a distributed computing system is a tough task. When we work with distributed environment over larger database, we need to take care of the transaction time period as well as number of transactions that are actually executed (committed) and number of transactions fail. The application on dynamic RTDBS becomes more complex when certain deadlines need to be completed. In this paper, we had carried out the test of CRUD (Create, Read, Update, and Delete) operation on transactional Real-time databases in real time dynamic distributed environment by using the existing EDF, GEDF algorithm and we had compared these algorithms with our proposed GMTDS (Generic Multi-dimensional Transaction Management under Dynamic Settings) algorithm in standalone and distributed environment with a dynamic self adaptive approach for management of transactions.

 

To validate the efficacy of the GMTDS algorithm, comprehensive simulations were conducted under various workload scenarios. Comparative analysis against existing transaction management algorithms showcase the advantages and improvements offered by GMTDS in terms of response times, throughput, and adaptability.

Author(s) Details:

Mohammad Sharfoddin Khatib,
Computer Science and Engineering Department, Anjuman, College of Engineering and Technology, Sadar, Nagpur-440001, India.

Mohammad Atique,
P.G Department of Computer Science and Engineering, Director, UGC –MMTC (Formerly HRDC) S. G. B. Amravati University, Amravati, India.

Sayyed Qudsiya Naaz,
Computer Science and Engineering Department, Anjuman, College of Engineering and Technology, Sadar, Nagpur-440001, India.

Please see the link here: https://stm.bookpi.org/RUMCS-V1/article/view/13675

Forecasting Daily Exchange Rates with Artificial Neural Network (ANN) | Chapter 3 | Current Topics on Business, Economics and Finance Vol. 2

 The forming and forecasting of supposed exchange rate dynamics has long existed a focus of financial and financial studies. Artificial intelligence (AI) modeling has currently received greatly of attention as a new method in business-related and financial predicting. This research suggests an alternate blueprint for forecasting regularly exchange rates that is based on affected neural network (ANN).Our practical research is based on a set of Tunisian everyday data. In order to judge this strategy, we compare allure performance to that of a statement autoregressive conditional heteroskedasticity (GARCH) model. The results show that the projected nonlinear autoregressive (NAR) model is a reliable and fast prediction means. This discovery admits businesses and policymakers to plan in a more excellent manner.

Author(s) Details:

Fahima Charef,
Department of Finance, FSEGT, University of Tunis Elmanar, Tunis, Tunisia.

Fethi Ayachi,
Department of economic, High School of Economics and Trade of Tunis, CEMAFI, Nice, France.

Please see the link here: https://stm.bookpi.org/CTBEF-V2/article/view/9790

Prediction Model of Water Quality and Detection of Vibrio Cholerae Bacteria | Chapter 07 | Research Developments in Science and Technology Vol. 6

 Greenhouse horticulture is a popular method for growing high-value crops with a large profit margin. To enable excellent management of environmental elements, fuzzy inference systems have been successfully used in prediction and control models. The goal of this research is to discover the many relationships in fuzzy inference systems now used for greenhouse modelling, prediction, and humidity management, as well as their change through time, in order to design more robust and understandable models. The major goal is to apply optimization techniques to find distinct linkages inside fuzzy inference systems, their configurations, and models, which are currently used for greenhouse forecast, control, and humidity modelling. The procedure is based on the PRISMA working guide. Four academic databases were combed through for a total of 93 questionnaires. Its bibliometric features have been retrieved and analysed, which helps the survey achieve its goal. Finally, it was discovered that combining Mamdani's fuzzy inference systems with optimization and fuzzy clustering methodologies, as well as tactics like model-based predictive control, assures great accuracy and interpretability.

Author(S) Details

Camilo Enrique Rocha Calderón
Universidad Distrital Francisco José de Caldas, Faculty of Engineering, Intelligent Internet Research Group, Bogotá D.C., Colombia.

Octavio José Salcedo Parra
Universidad Distrital Francisco José de Caldas, Faculty of Engineering, Intelligent Internet Research Group, Bogotá D.C., Colombia and Universidad Nacional de Colombia, Department of Systems and Industrial Engineering, Faculty of Engineering, Bogotá D.C, Colombia.

Sebastian Camilo Vanegas Ayala
Universidad Distrital Francisco José de Caldas, Faculty of Engineering, Intelligent Internet Research Group, Bogotá D.C., Colombia.

View Book:- https://stm.bookpi.org/RDST-V6/article/view/7013

Continuous Bangla Speech Processing: Segmentation, Classification and Recognition | Book Publisher International

 The goal of this research is to create a continuous voice recognition system that covers speech word segmentation, feature extraction, speech word classification, and recognition in Bangla. This study proposes four dynamic thresholding algorithms for segmenting continuous Bangla speech sentences into words and sub-words: I Algorithm-1 (based on modified k-means algorithm), (ii) Algorithm-2 (based on fuzzy-means algorithm), (iii) Algorithm-3 (based on modified Otsu's algorithm), and (iv) Algorithm-4 (based on modified Otsu's algorithm) (short-time speech features based algorithm). This research also introduces a new method for identifying the voiced portions of continuous speech in speech segmentation called the blocking black area method.

According to the amount of syllables in the segmented words, they are divided into several classes. This study provides a time-saving classification method called syllable-based classification for speech categorization. Speech spectrogram features and short-time speech features were evaluated during feature extraction. This study suggests three forms of speech features for feature generation: I short-time speech features, (ii) binary features, and (iii) MFCC features. Short-time speech characteristics and binary features are both employed in speech segmentation and recognition. Various windowing functions have been used in the creation of MFCC features. A comprehensive study on neural networks and performance analysis with various improved and faster back-propagation (BP) algorithms (such as BP with momentum, variable learning rate BP, resilient BP, conjugate gradient BP, and Levenberg-Marquardt BP algorithms) has been conducted for speech recognition. To design, train, and simulate the feedforward neural network with the BP learning algorithm, the Matlab Neural Network Toolbox 9.8.0 (R2020a) was utilised. The traditional BP algorithm's convergence is rather sluggish, which is why this paper provides several better and faster BP methods to handle voice recognition difficulties.

Several Bangla words were continually delivered to justify the produced system. 100 (one hundred) well-defined Bangla sentences were recorded from 5 (five) male speakers of various ages to test the system's performance, and 656 words were provided in the 100 Bangla sentences. As a result, the speech database has 500 Bangla speech sentences including 3,280 speech terms. With Algorithm-1 (based on modified k-means algorithm), 96.19 percent with Algorithm-2 (based on fuzzy-means algorithm), 90.58 percent with Algorithm-3 (based on modified Otsu's algorithm), and 95.9 percent with Algorithm-4 (based on short-time speech features based algorithm), the segmentation system achieved an average segmentation accuracy of 95.55 percent. The classification method has a 91.42 percent accuracy rate on average. For recognising segmented voice words, the recognition system achieved a recognition rate of 83 percent using the robust BP algorithm, 90 percent using the conjugate gradient BP algorithm, and 90 percent using the Levenberg-Marquardt BP algorithm, respectively.

Author(s) Details

M. M. Rahman
Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Bangladesh.

View Book:- https://stm.bookpi.org/CBSPSCR/article/view/5959

Research Issues on Datamining | Book Publisher International

 Data mining is a set of techniques for removing randomness from large and complicated databases and uncovering hidden patterns. The extraction of new knowledge from large databases is known as datamining (DM), sometimes known as knowledge discovery from databases (KDD). Data mining is the process of discovering previously undiscovered, valid patterns and relationships in big data sets using advanced data analysis techniques. Data mining techniques can estimate future trends and actions to help individuals make better decisions. Datamining has a range of applications. Identifying trends and patterns is a powerful tool for businesses across all sectors and industries.

Modern intrusion detection systems must deal with a number of difficulties. These applications must be dependable, expandable, controllable, and cost-effective to maintain. In recent years, data mining-based intrusion detection systems (IDSs) have demonstrated high accuracy, good generalisation to novel types of intrusion, and consistent behaviour in a changing environment. In order to find the optimum neural network, the number of hidden layers in various neural network topologies is compared. Misuse detection is a method of attempting to detect instances of network attacks by comparing current behaviour to the expected activities of an intruder. Artificial neural networks can detect and classify network activity even when the input is sparse, imperfect, and nonlinear.

The major goal of this research is to investigate privacy and security concerns among cloud computing users and consumers in a dispersed setting. Machine learning, natural language processing (NLP), and data mining techniques are used in conjunction to automatically detect and uncover patterns in a variety of sources. Both continuous and discontinuous changes can be dealt with using predictive analytics. Predictive analytics uses classification, prediction, and, to some extent, affinity analysis as analytical tools.

The semantic context and syntactic components are the focus of current text or document mining research. We investigated a mining model to categorise documents based on the Order of Context, Concept, and Semantic Relations in order to accomplish this, and with the inspiration garnered from our previous research efforts (OCCSR). Users will be able to get valuable information from virtually connected data warehouses using data mining techniques based on Cloud computing, cutting infrastructure and storage expenses. From the cloud, data mining can extract useful and potentially helpful information. The 3Vs are three features that are commonly used to define big data (Volume, Velocity and Variety). The report examines Big Data analytics methodologies, settings, and technologies in critical domains, as well as how they contribute in the creation of analytics solutions for Clouds.

 

Clustering is a type of unsupervised learning approach that is used to find a new set of categories. The processing time for grid-based clustering is typically determined by the size of the grid rather than the data. Three clustering algorithms are compared: hierarchical clustering, density-based clustering, and K Means clustering.

The majority of current approaches to identifying misuse rely on rule-based expert systems to identify indicators of previously detected attacks. We give a quick review of the numerous Artificial Intelligence techniques used in the design, development, and deployment of Intrusion Detection Systems (IDS) for defending computer and communication networks from intruders, as well as their improvements. Knowledge Discovery in Data (KDD) aims to extract information that isn't immediately apparent through meticulous and detailed analysis and interpretation. Analytics uses KDD, data mining, text mining, statistical and quantitative analysis, explanatory and predictive models, and advanced and interactive visualisation tools to drive choices and actions.

Author(s) Details

E. Kesavulu Reddy
Department of Computer Science, S. V. University College of CM & CS, Tirupati, Andhra Pradesh-517502, India.

View Book:- https://stm.bookpi.org/RID/article/view/5216  

Study on Nonlinear Internal Model Control Based Neural Networks: An Application to MIMO Non-Square Systems | Chapter 3 | Novel Perspectives of Engineering Research Vol. 4

 Internal Model Control (IMC) of discrete under-actuated and over-actuated non-linear systems is the subject of this book chapter. Because of their complexity, non-square systems create a number of challenges in terms of control. As a result, synthesising a non-linear internal controller is challenging. The proposed solution then combines the IMC structure with neural networks to make it easier to realise an approximate inverse of the non-linear model of the process to be controlled.

A neural network can be introduced in the internal model controller of the basic IMC structure using two methods: direct and indirect. To reflect the system's inverse dynamics, the neural network is trained using the direct method with the system's input/output data. The neural network depicts the system dynamics in the indirect method. For both overactuated and underactuated systems, the simulation results are satisfactory, demonstrating the efficiency of the suggested control technique in guaranteeing satisfactory nominal and robust performance.

Author(S) Details

Imen Saidi
Laboratory of Research in Automatic Control, University of Tuins El Manar, National Engineering School of Tunis, Tunis, Tunisia.

Islem Bejaoui
Laboratory of Research in Automatic Control, University of Tuins El Manar, National Engineering School of Tunis, Tunis, Tunisia.

Nahla Touati
Laboratory of Research in Automatic Control, University of Tuins El Manar, National Engineering School of Tunis, Tunis, Tunisia.

View Book:- https://stm.bookpi.org/NPER-V4/article/view/5103

Development of New Hybrid Artificial Neural Network Based Control of Doubly Fed Induction Generator| Chapter 6 | New Approaches in Engineering Research Vol. 9

 The performance of a hybrid Artificial Neural Network (ANN) with Proportional Integral (PI) control approach for a Doubly Fed Induction Generator (DFIG) based wind energy generation system is compared to that of NN and PI control techniques in this chapter. With the growing use of wind power, a dynamic performance analysis of the Doubly Fed Induction Generator under a variety of operating conditions is required. This chapter proposes three control strategies: the first employs a PI controller, the second uses an ANN controller, and the third utilises a PID controller.a combination of ANN and PI The results obtained using MATLAB/Simulink show that the proposed control strategies are effective. According to the findings, the Hybrid control technique improves the DFIG's dynamic performance. As seen by the reported results, the Hybrid ANN-based system that estimates the generator's control parameters has good qualities.

Author (S) Details

Dr. G. Venu Madhav
Department of Electrical and Electronics Engineering, Anurag University, India.

Dr. Y. P. Obulesu
School of Electrical Engineering, VIT University, India.

View Book :-https://stm.bookpi.org/NAER-V9/article/view/2819

Modeling of Heavy Metal (Ni, Mn, Co, Zn, Cu, Pb, and Fe) and PAH Content in Stormwater Sediments Based on Weather and Physico-Geographical Characteristics of the Catchment: An Advance Data-Mining Approach | Chapter 8 | Modern Advances in Geography, Environment and Earth Sciences Vol. 4

 The processes that determine the quality of sediment in drainage systems are dynamic and complicated. However, because these topics have not been widely examined in research studies, there is relatively little information available on the effects of both watershed characteristics and meteorological circumstances on sediment chemical properties. The amount of selected heavy metals (Ni, Mn, Co, Zn, Cu, Pb, and Fe) and polycyclic aromatic hydrocarbons (PAHs) in sediments from the stormwater drainage systems of four catchments in the city of Kielce, Poland, is reported in this work. The effects of various physico-geographical catchment parameters and atmospheric conditions on pollutant concentrations in sediments were also investigated. Using artificial neural networks, statistical models for forecasting the quality of stormwater sediments were built based on the findings (multilayer perceptron neural networks). The chemical composition of sediments was found to be influenced by a variety of factors, including catchment characteristics and meteorological conditions. Catchment variables (land use, drainage system length) influenced heavy metal concentrations in sediments significantly more than meteorological conditions. The content of PAHs in sediments, on the other hand, was mostly influenced by the catchment's atmospheric conditions. The multilayer perceptron models built for this study performed well in terms of prediction; the mean absolute error of the forecast (Ni, Mn, Zn, Cu, and Pb) was less than 21%. As a result, the models have a lot of promise, as they might be used in things like spatial planning when environmental factors (such sediment quality in stormwater drainage systems) are taken into account. The construction of forecasting models was the strategy offered in this study. They can be used to aid spatial planning and development in a variety of ways.

Author(s) Details

Lukasz Bak
Department of Geotechnics and Water Engineering, Faculty of Environmental, Geomatic and Energy Engineering, Kielce University of Technology, Kielce 25-314, Poland.

Bartosz Szelag
Department of Geotechnics and Water Engineering, Faculty of Environmental, Geomatic and Energy Engineering, Kielce University of Technology, Kielce 25-314, Poland.

Aleksandra Salata
Department of Water and Wastewater Technology, Faculty of Environmental, Geomatic and Energy Engineering, Kielce University of Technology, Kielce 25-314, Poland.

Jan Studzinski
Systems Research Institute of Polish Academy of Sciences, Warsaw 01-447, Poland.

View Book :- https://stm.bookpi.org/MAGEES-4/article/view/1057

Studies on Developing a Neuro Fuzzy Model to Predict the Properties of AlSi12 Alloy | Chapter 7 | Emerging Trends in Engineering Research and Technology Vol. 11

 The results of alteration and vibration are investigated and compared with unmodified alloy during solidification of Aluminum-Silicon eutectic alloy (AlSi12). As modifiers, Sodium and Strontium are used. Using a vibration table, horizontal sinusoidal vibration was imposed at various frequencies. Modification treatment has been found to enhance characteristics such as ultimate tensile strength (UTS), percentage elongation, stiffness, durability, cutting power, electrical conductivity, thermal conductivity, fluidity, porosity and fatigue strength, and optimum values have been found for modifier sodium and strontium weight addition. The network model of a self-organized feature map (SOFM) is created The kit uses Neuro Solutions. To optimise the model generated, genetic algorithms are used. In addition, the neuro fuzzy model (CANFIS) was developed and the results were compared with the developed neural network model. Sensitivity analysis is carried out to measure the relative value of the model's inputs and how the output of the model differs in response to an input variance. The models developed were experimentally tested.

Author (s) Details

Dr. K. Srinivasulu Reddy
Mechanical Engineering Department, Sreenidhi Institute of Science and Technology, Hyderabad, Telangana-501 301, India.

View Book :- https://bp.bookpi.org/index.php/bpi/catalog/book/335

Determination of the PV Module Surface Temperature Based on Neural Network Using Solar Radiation and Surface Temperature: Recent Development | Chapter 14 | Recent Advances in Science and Technology Research Vol. 1

Different attempts have been carried out to determine the PV module surface temperatures using mathematical models of the PV module, empirical formula and by neural networks. Neural network (NN) doesn’t require any analysis of the system or scientific details; it only needs data from the system for training purposes. The present research describes the estimation of the PV module surface temperature using NN based on measured ambient temperatures and incident solar radiation. The NN is composed of input layer with two inputs (solar radiation and ambient temperature), hidden layer that has eight neurons and output layer to estimate the PV module surface temperature. Error back propagation algorithm was used to train the NN. The result showed that, the estimation accuracy of the PV module surface temperatures by the NN reached more than 96% of the measured values.

Author(s) Details

Dr. Aiat Hegazy
Department Solar Energy, National Research Centre, El Buhouth St., Dokki, Giza, Egypt.

Dr. E. T. El Shenawy
Department Solar Energy, National Research Centre, El Buhouth St., Dokki, Giza, Egypt.

Dr. M. A. Ibrahim
Department Solar Energy, National Research Centre, El Buhouth St., Dokki, Giza, Egypt.

View Book: - http://bp.bookpi.org/index.php/bpi/catalog/book/175