Template-Type: ReDIF-Article 1.0 Author-Name: Ali Waqas Author-X-Name-First: Ali Author-X-Name-Last: Waqas Author-Name: Muhammad Saleem Author-X-Name-First: Muhammad Author-X-Name-Last: Saleem Author-Name: Abdul Khaliq Author-X-Name-First: Abdul Author-X-Name-Last: Khaliq Author-Name: Amanullah Yasin Author-X-Name-First: Amanullah Author-X-Name-Last: Yasin Title: An intelligent timestamp data manipulation methodology for customer level resource efficient short-term electric load forecasting Abstract: Electricity supply companies need to know the expected load consumption to perform better scheduling and planning. Prediction of electric-load usage thus becomes a time-series forecasting problem. Traditionally used statistical, knowledge-based and hybrid techniques for forecasting do not ensure a high level of accuracy, while more accurate techniques like deep learning are computationally expensive and require additional non-temporal data. We propose a significantly accurate but computationally efficient methodology using 'stack ensembling' with two different data manipulations and compare their results with selected baseline predictors as well as existing literature. We only use timestamp information for feature extraction to keep this study independent of non-time features. We achieve a maximum improvement of 34.98% in terms of MAPE over chosen base predictor ARIMA. Limitations of our work include a low degree of accuracy for outliers' estimation in the electric-load consumption on which we plan to improve upon in future work. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 198-216 Issue: 3 Volume: 15 Year: 2023 Keywords: ARIMA; calendar features; electricity; ensembling; forecasting; intelligent data manipulation; load prediction; machine learning; planning; persistence; scheduling; stacking. File-URL: http://www.inderscience.com/link.php?id=133011 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:3:p:198-216 Template-Type: ReDIF-Article 1.0 Author-Name: Gaurav Kumar Gupta Author-X-Name-First: Gaurav Kumar Author-X-Name-Last: Gupta Author-Name: Dilip Kumar Sharma Author-X-Name-First: Dilip Kumar Author-X-Name-Last: Sharma Title: Depression detection using semantic representation based semi-supervised deep learning Abstract: Depression detection has become an arduous task in social media due to its complicated association with mental disorders. This work focuses on extracting the depressive features in the social network from the unstructured and structured data through the semantic representation and semi-supervised deep learning model for depression detection (SSDD). The proposed approach primarily performs the hybrid features analysis, unsupervised learning-based depression-influencing features representation, and supervised learning-based depressed user detection processes. Initially, the SSDD investigates the different demographic and content-based features from syntactic and semantic relations. Secondly, adopting the deep autoencoder as the unsupervised learning model leverages the extraction of the depression-indicative features representing the texts with the word embedding. Finally, it determines the depressive texts using the bi-directional long short-term memory (Bi-LSTM) model and facilitates the detection of depressed social users by analysing the profile features, detected depressive tweets, and hybrid knowledge. The experimental results outperform the existing depression detection model. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 217-237 Issue: 3 Volume: 15 Year: 2023 Keywords: Twitter; semi-supervised; hybrid knowledge; semantic; negation; depression-indicative; deep autoencoder; Bi-directional long short-term memory; Bi-LSTM. File-URL: http://www.inderscience.com/link.php?id=133012 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:3:p:217-237 Template-Type: ReDIF-Article 1.0 Author-Name: Andrew F. Ward Author-X-Name-First: Andrew F. Author-X-Name-Last: Ward Author-Name: Mage Marmol Author-X-Name-First: Mage Author-X-Name-Last: Marmol Author-Name: David Lopez-Lopez Author-X-Name-First: David Author-X-Name-Last: Lopez-Lopez Author-Name: Patricia Carracedo Author-X-Name-First: Patricia Author-X-Name-Last: Carracedo Author-Name: Angel A. Juan Author-X-Name-First: Angel A. Author-X-Name-Last: Juan Title: Data analytics and artificial intelligence in e-marketing: techniques, best practices and trends Abstract: More than ever, enterprises today can make use of data, forecasting models, and intelligent algorithms to optimise their marketing strategies and customise their campaigns to better fit the needs of each potential client. First, this paper reviews the existing literature regarding the use of data analytics methods and artificial intelligence algorithms in the e-marketing field. Then, the paper discusses how modern enterprises can benefit from these tools to efficiently deal with a myriad of marketing possibilities, including strategies they can use in order to fulfill their customers' needs or to generate new markets for their products and services. Several examples of real-life applications are analysed with the aim of illustrating the potential of these techniques. Finally, we use some statistical/machine learning techniques to perform a text mining analysis of a selected subset of scientific articles, which allows us to identify the main trends in the field. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 147-178 Issue: 3 Volume: 15 Year: 2023 Keywords: e-marketing; data analytics; artificial intelligence; machine learning. File-URL: http://www.inderscience.com/link.php?id=133019 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:3:p:147-178 Template-Type: ReDIF-Article 1.0 Author-Name: Megha Chopra Author-X-Name-First: Megha Author-X-Name-Last: Chopra Author-Name: Archana Purwar Author-X-Name-First: Archana Author-X-Name-Last: Purwar Title: Food recognition using enhanced squirrel search optimisation algorithm and convolutional neural network Abstract: Owning to the sedentary lifestyle, dietary assessment has become a significant research area. Automated food assessment initiates with food classification. Image classification commences with segmentation. Apparently, thresholding is the elemental method to perform segmentation. Although, there are many ways to optimise the solution of multi-level thresholding, this paper proposes a squirrel search algorithm (SSA)-based optimised solution for multi-level thresholding. It applies convolutional neural network (CNN) to recognise food images. Further, the paper has proposed a new enhanced squirrel search algorithm (ESSA) to improve the food recognition accuracy. The results show that ESSA improves the performance of image segmentation and classification. The performance of the proposed algorithm is evaluated using food datasets UEC-256 and UEC-100 and accuracy of 83.1% and 82.1% was obtained respectively. Proposed algorithm is also compared with existing work taken under this study and it has been observed that it outperformed them. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 238-254 Issue: 3 Volume: 15 Year: 2023 Keywords: food recognition; squirrel search algorithm; SSA; enhanced squirrel search algorithm; ESSA; thresholding; segmentation. File-URL: http://www.inderscience.com/link.php?id=133023 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:3:p:238-254 Template-Type: ReDIF-Article 1.0 Author-Name: Varun Gupta Author-X-Name-First: Varun Author-X-Name-Last: Gupta Author-Name: Parvin Kumar Author-X-Name-First: Parvin Author-X-Name-Last: Kumar Author-Name: Sourav Diwania Author-X-Name-First: Sourav Author-X-Name-Last: Diwania Author-Name: Nitin Kumar Saxena Author-X-Name-First: Nitin Kumar Author-X-Name-Last: Saxena Author-Name: Natwar Singh Rathore Author-X-Name-First: Natwar Singh Author-X-Name-Last: Rathore Title: Pre-processing of ECG signal based on ANF and ICA: a comparison Abstract: For removing noises from recorded ECG signal, adaptive notch filter (ANF) and independent component analysis (ICA) are used in this paper. In ANF, notch filter is obtained by adding bandpass filter (BPF) and voltage amplifier of unity gain. ANF is obtained by cascading of notch filter and adaptive filter which makes it more robust in respect of locating the poles and zeros on the respective constrained circle. On the other hand, ICA establishes the new coordinates which are non-orthogonal and statistically independent. It solves the problem of blind source separation (BSS). The novelty of this work is that for the first time ICA is used for pre-processing of variety of ECG signals with linear discriminant analysis (LDA) classifier/detector. The motivation behind to use LDA was that, it minimises the variance and maximises the class distance of the two variables by which chances of false detection becomes very low. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 179-197 Issue: 3 Volume: 15 Year: 2023 Keywords: electrocardiogram; ECG; noises; adaptive notch filter; ANF; independent component analysis; ICA; poles and zeros; non-orthogonal and statistically independent; linear discriminant analysis; LDA; signal-to-noise ratio; SNR. File-URL: http://www.inderscience.com/link.php?id=133024 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:3:p:179-197 Template-Type: ReDIF-Article 1.0 Author-Name: Abdulrhman M. Alshareef Author-X-Name-First: Abdulrhman M. Author-X-Name-Last: Alshareef Author-Name: Mohammed Khojah Author-X-Name-First: Mohammed Author-X-Name-Last: Khojah Title: The impact of online trading from a personal and technical perspective on trade stocks in emerging markets Abstract: Stock markets are an attractive investment environment for new investors from different financial backgrounds. In emerging markets, the risk ratio is considered high; however, the profit margin is attractive. The task of obtaining future information and forecasting is considered an essential advantage for financial institutions. The premise is that the emerging markets did not have the chance to get the trading policy derived from their own environment. Therefore, we wanted to investigate what aspects of objectives investors comprehend as a suitable policy to comply with. This study investigates the means and the fundamental objectives of short-term investment. It focuses on the personal and technical perspectives of investors in emerging markets. The results bare the relationship between means objectives and fundamental objectives. This contribution aids academics and decision-makers in finding the most relevant aspects that influence the investor's decision to trade stocks in emerging markets regarding personal and technical perspectives. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 76-96 Issue: 1/2 Volume: 15 Year: 2023 Keywords: stock trading; stock market; emerging markets; value theory; fundamental objectives; means objectives. File-URL: http://www.inderscience.com/link.php?id=132551 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:76-96 Template-Type: ReDIF-Article 1.0 Author-Name: S. Shitharth Author-X-Name-First: S. Author-X-Name-Last: Shitharth Author-Name: Hariprasath Manoharan Author-X-Name-First: Hariprasath Author-X-Name-Last: Manoharan Author-Name: Lakshmi Narayanan Author-X-Name-First: Lakshmi Author-X-Name-Last: Narayanan Author-Name: Takkedu Malathi Author-X-Name-First: Takkedu Author-X-Name-Last: Malathi Author-Name: S. Vatchala Author-X-Name-First: S. Author-X-Name-Last: Vatchala Author-Name: Kommu Gangadhara Rao Author-X-Name-First: Kommu Gangadhara Author-X-Name-Last: Rao Title: Prognosis of urban environs using time series analysis for preventing overexploitation using artificial intelligence Abstract: In the process of urban environment, the optimisation of network enactment is shifted from operation to maintenance and monitoring stage. During such conversion it is necessary to indicate the time series representation for preventing the overexploitation problem that happens due to more number of natural resources. It is necessary to use a set of historical data to check the behaviour of current state operations at varying time periods using an intelligent optimiser. Thus this study explores the implementation of time series analysis using artificial intelligence (AI) where accurate predictions are made in the entire urban environment even with big edifices. The major difference that is observed in the proposed method as compared to existing method is that two different boundary regions are chosen with distinct point values and only in two directions the monitoring device is installed. Since AI is involved in the entire process entire characteristics on forecasting current state procedure is represented using modified evolutionary optimisation (MEO) which observes entire biological nature of neighbouring environs. Additionally comparison analysis is made using MATLAB with five case studies where the proposed method proves to be much effective for about 70% as compared to existing models. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 97-115 Issue: 1/2 Volume: 15 Year: 2023 Keywords: time series; urban environment; artificial intelligence; AI; forecast. File-URL: http://www.inderscience.com/link.php?id=132558 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:97-115 Template-Type: ReDIF-Article 1.0 Author-Name: Debabrata Dansana Author-X-Name-First: Debabrata Author-X-Name-Last: Dansana Author-Name: Prafulla Kumar Behera Author-X-Name-First: Prafulla Kumar Author-X-Name-Last: Behera Title: Effect of noise uncertainty during spectrum sensing for cognitive radio ad hoc networks Abstract: Cognitive radio network is a technique where underutilised licensed spectrum allows opportunistic access to unlicensed secondary users. Different spectrum sensing algorithms are used to sense the presence or absence of primary licensed users in noisy and fading channel. This paper provides a comparative analysis of different spectrum sensing algorithms for cognitive radio network based on dynamic threshold and noise uncertainty. Spectrum sensing in cognitive radio network based on fixed threshold are sensitive to noise, therefore these are not efficient enough. The use of dynamic threshold improves performance of the spectrum detection without much computational complexity. Different computer simulations are provided for the dynamic threshold with and without noise uncertainty for spectrum sensing of cognitive radio network. The performance of the spectrum sensing techniques is evaluated by receiver operating characteristics (ROC) curves over additive white Gaussian noise (AWGN) and different fading channels (Rayleigh and Nakagami-m). Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 41-56 Issue: 1/2 Volume: 15 Year: 2023 Keywords: spectrum sensing; dynamic threshold; cognitive radio ad hoc network; CRAHN; fading channel; noise uncertainty; receiver operating characteristics; ROC; additive White Gaussian noise; AWGN; signal-to-noise-ratio; SNR. File-URL: http://www.inderscience.com/link.php?id=132560 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:41-56 Template-Type: ReDIF-Article 1.0 Author-Name: Gowri R. Choudhary Author-X-Name-First: Gowri R. Author-X-Name-Last: Choudhary Author-Name: Iti Sharma Author-X-Name-First: Iti Author-X-Name-Last: Sharma Title: Using free open-source tools for text visualisation over unstructured corpus effectively Abstract: Text visualisation is an essential analytical task in many applications. Researchers from such fields can utilise the graphical output but need tools for its generation due to lack of expertise. Though several open-source tools are available, there is a challenge in choosing a suitable tool and preparing a compatible input because the corpora are often self-collected and unstructured. This paper describes ten popular open-source text visualisation tools for word-clouds. It is observed here that these tools take only a single text file as input while unstructured corpora have multiple-file format. So further in this paper a priority window technique is proposed to convert corpus into a small single text file that retains the characteristics similar to a standard model found in structured corpora. Experiments are performed over a self-collected corpus to demonstrate a real-life scenario from journalism application. The output word clouds show the effectiveness of proposed frequency-based technique. This technique is aimed at ease of use by users that lack expertise of data mining. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 129-146 Issue: 1/2 Volume: 15 Year: 2023 Keywords: text visualisation; summarisation; text mining; word-cloud; open-source visualisation tools; term weighting; feature weighting. File-URL: http://www.inderscience.com/link.php?id=132561 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:129-146 Template-Type: ReDIF-Article 1.0 Author-Name: Vaishali Nirgude Author-X-Name-First: Vaishali Author-X-Name-Last: Nirgude Author-Name: Sheetal Rathi Author-X-Name-First: Sheetal Author-X-Name-Last: Rathi Title: Improving the accuracy of real field pomegranate fruit diseases detection and visualisation using convolution neural networks and grad-CAM Abstract: Pomegranate (<i>Punica granatum</i> L) is one of the vital cash fruit crops of arid and semiarid regions in India. The occurrence of pests and diseases affects the development and quality of fruits. Our objective is to develop an automated pomegranate disease detection system on an actual field image dataset using convolution neural networks. The collected images are classified into six categories namely healthy, bacterial blight, anthracnose, fruit spot, fusarium wilt, and fruit borer. In this paper, we have measured the performance of CNN-based architectures VGG16, VGG19, InceptionV3, Resnet50, and Xception with hyperparameter tuning. The experimental results show that Resnet50 is a suitable model for our dataset with a disease detection accuracy of 98.55%. To deal with DL 'black box' problem, the gradient-weighted class activation mapping (Grad-CAM) model is integrated with ResNet50 to highlight the important regions on the fruits to locate accurate diseases and recommend appropriate disease treatment to farmers. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 57-75 Issue: 1/2 Volume: 15 Year: 2023 Keywords: convolution neural network; CNN; pomegranate; disease detection; black box; agriculture; gradient-weighted class activation mapping; grad-CAM; deep learning. File-URL: http://www.inderscience.com/link.php?id=132562 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:57-75 Template-Type: ReDIF-Article 1.0 Author-Name: Anand Khandare Author-X-Name-First: Anand Author-X-Name-Last: Khandare Author-Name: Nipun Agarwal Author-X-Name-First: Nipun Author-X-Name-Last: Agarwal Author-Name: Amruta Bodhankar Author-X-Name-First: Amruta Author-X-Name-Last: Bodhankar Author-Name: Ankur Kulkarni Author-X-Name-First: Ankur Author-X-Name-Last: Kulkarni Author-Name: Ishaan Mane Author-X-Name-First: Ishaan Author-X-Name-Last: Mane Title: Study of Python libraries for NLP Abstract: Without words, any language is incomplete, and grammar is responsible for driving those words. Interaction with computers is similar to human conversation in that it requires words and signs to communicate with one another. The traditional method of interacting with a computer by clicking and tapping on options is gradually being replaced by a more seamless approach that includes conversations. This modern mode of communication includes speaking to the computer in a more natural manner, similar to how we speak to other people. Natural language processing is the science behind how humans can interact with computers more intuitively. The goal of this domain is to figure out how to make computers understand and make sense of commonly spoken human language in addition to the usual and rationally defined set of instructions. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 116-128 Issue: 1/2 Volume: 15 Year: 2023 Keywords: artificial intelligence; machine learning; natural language processing; NLP; Python; Python libraries. File-URL: http://www.inderscience.com/link.php?id=132564 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:116-128 Template-Type: ReDIF-Article 1.0 Author-Name: Rohit Rastogi Author-X-Name-First: Rohit Author-X-Name-Last: Rastogi Author-Name: Rohan Tyagi Author-X-Name-First: Rohan Author-X-Name-Last: Tyagi Author-Name: Tribhuvan Mishra Author-X-Name-First: Tribhuvan Author-X-Name-Last: Mishra Author-Name: Vaishnavi Mishra Author-X-Name-First: Vaishnavi Author-X-Name-Last: Mishra Author-Name: Utkarsh Pratap Shahi Author-X-Name-First: Utkarsh Pratap Author-X-Name-Last: Shahi Title: Analysis of PCS-QoL to investigate the holistic health for sustainable way of living in smart cities of 21st century Abstract: Quality of life (QoL) is defined as a standard for well-being of a human being consisting of factors such as comfort, happiness, mental, physical, social, emotional and spiritual health. Today as the countries are growing towards the concept of smart cities and technology, it has become a sole responsibility to bring into notice an analysis of holistic health for sustainable way of living in smart cities of 21st century. In order to examine the QoL of human beings SF-36 questionnaires' has been used. The questionnaire was projected to 500 people belonging to different group of age and a response of 205 people was collected. The dataset is analysed through python libraries such as NumPy, pandas and matplotlib and in the results the variation of PCS value according to gender and profession is plotted, shown and several other parameter variations is analysed. The results predicts about the QoL of people belonging to different age groups, different occupations and different educational backgrounds. Hence, this paper is a perfect model that represents and inspects each and every angle of wellness of human being required for sustainable way of living in the smart cities of 21st century. Journal: Int. J. of Data Analysis Techniques and Strategies Pages: 4-40 Issue: 1/2 Volume: 15 Year: 2023 Keywords: short form; SF; quality of life; QoL; holistic health; smart cities; sustainable development; physical component summary; PCS; questionnaire; machine learning; data sciences. File-URL: http://www.inderscience.com/link.php?id=132565 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:injdan:v:15:y:2023:i:1/2:p:4-40