2690-6791ISSN (Online)
2769-786XISSN (Print)
Nowadays, multimedia files play a basic role in supporting evidence analysis for making decisions about a crime through looking at files as a digital guide or evidence. Multimedia files such as JPG images are a common format because many documents and memorial images on laptops are valuable. In addition, many JPG images on Laptops are valuable and have fewer structure contents, making recovery possible when their file system is missing. However, intelligent systems for fully recovering corrupted JPG images into their original form is a challenging research issue. In this research, a support vector machine (SVM) as intelligent classifier algorithm is proposed to classify JPG or non-JEG image clusters as part of multimedia files. The SVM classifies the data clusters on three content-based feature extraction (entropy, byte frequency distribution, and rate of change approach to derive cluster features) methods to optimize the identification of JPG image content. The SVM classifier is applied using a radial basis and polynomial kernel functions in MATLAB software. The experimental results show that the accuracy of classification of the SVM classifier with the polynomial function is 96.21%, and the SVM classifier with the radial basis function is 57.58%.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110101
Vol. 11 Issue. 1 PP. 01-11, (2024)
In the era of smart cities, the pursuit of sustainability stands as a paramount goal, with energy management playing a central role. This paper is dedicated to the exploration of early energy consumption prediction as a linchpin in the realization of sustainable smart cities. Employing advanced long short-term memory (LSTM) networks, we introduce a potent predictive model tailored to anticipate energy consumption patterns within urban environments. Notably, our model achieves remarkable performance metrics, with a root mean square error of 547.71 and a strikingly low mean absolute percentage error (MAPE) of 1.22. Through meticulous comparisons against baseline models, our LSTM-based approach emerges as a beacon of accuracy, reliability, and sustainability. Beyond predictive analytics, our research offers actionable insights for urban planners and policymakers, fostering the creation of greener, more sustainable, and ecologically responsible smart cities that harmonize technological innovation with environmental stewardship. As smart cities continue to evolve, our work lays the foundation for a future where sustainability is not merely a goal but a reality.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110102
Vol. 11 Issue. 1 PP. 12-20, (2024)
Corporate strategies have employed techniques that enter the domain of shadow and espionage in this rapidly developing, technologically competitive business environment. Supporting a security strategy is a way to counter these possible dangers. To preserve corporate success in the marketplace, network security needs to be crucial to the protection of electronic documents. Encryption technology has become more important in recent years for protecting online digital documents. This research was motivated by the fact that document verification has become quite time-consuming and difficult due to a variety of challenging and laborious processes. Existing technologies often malfunction when a single kind of encryption, such as AES, Data Encryption Standard (DES), or Rivest, Shamir, Adleman (RSA), is utilized at the request of the customer. Therefore, this study proposes hybrid cryptography, which integrates two novel algorithms into existing encryption protocols. A digital signature is generated for the data when a user uploads a data. The data are encrypted in parallel using the suggested Secured Hash Function-256 (SHA-256) method with improved DES and RSA (SHA-256+Enhanced DES+RSA). The proposed encryption method was shown to be more accurate than previous studies in experimental evaluations of data encryption.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110103
Vol. 11 Issue. 1 PP. 21-28, (2024)
Advanced technologies such as the Internet of Things provide an integrated platform for weather focusing, including rainfall and flood prediction. Large rainfall data frequently contain noise, which can be difficult to analyze using a standard time series model due to violated assumptions. Singular spectrum analysis (SSA) is a model-free time series analysis method that is widely used. This study aims to predict the rainfall trends in the Special Region of Yogyakarta, Indonesia, using the Recurrent SSA (SSA-R) and Vector SSA (SSA-V). The SSA-R forecasts using the recurrent continuation directly with the linear recurrent formula, while the SSA-V is a modified recurrent method. This study used 50 years of monthly rainfall data (1970-2019) from 25 stations in the special region of Yogyakarta, Indonesia. The SSA steps for forecasting rainfall data include decomposition (embedding and singular value decomposition), reconstruction (grouping and diagonal averaging), and evaluating the SSA model using w-correlation (if w-correlation is close to zero, returning to the decomposition stage; otherwise, continue the process), forecasting, evaluating the forecast results using root mean square error (RMSE), mean absolute error, r, and mean forecast error, and finally selecting the best model (either the SSA-R or SSA-V model). The results showed that the SSA-R performed better than SSA-V due to the smallest RMSE in the dry, rainy, and inter-monsoon seasons. The SSA-R model’s forecast results revealed faint, constant patterns for the dry, and rainy seasons and an increasing pattern for the inter-monsoon season. The novelty of this study is to compare the performance of the SSA-R and SSA-V models in the large rainfall data in the special region of Yogyakarta, Indonesia.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110104
Vol. 11 Issue. 1 PP. 29-43, (2024)
Feature selection is an important preprocessing step in many data science and machine learning applications. Although there exist several sophisticated feature selection algorithms, their benefits are sometimes overshadowed by their complexity and slow execution. Therefore, in many cases, a more simple algorithm may be better suited. In this paper, we demonstrate that a rudimentary forward selection algorithm can achieve optimal performance with a low time complexity. Our study is based on an extensive empirical evaluation of the forward feature selection algorithm in the context of linear regression. Concretely, we compare the forward selection algorithm against the gold standard exhaustive search algorithm based on several datasets. The results show that the forward selection algorithm achieves high performance with relatively fast execution. Given the simplicity, accuracy, and speed of the forward feature selection algorithm, we recommend it as a primary feature selection method for most regression applications. Our results are particularly pertinent in the case of big data and real-time analysis.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110105
Vol. 11 Issue. 1 PP. 44-54, (2024)
This study delves into optimizing sustainable inventory management practices through the integration of advanced data analytics methodologies. In response to the complex dynamics of modern supply chains, where inventory control significantly impacts sustainability goals, this research aims to address the intricate interplay between decentralized decision-making, government policies, and strategic choices within supply chain networks. Employing models such as Game Theory and Gated Recurrent Unit (GRU), alongside statistical analyses, our investigation explores the transformative potential of informed decision-making frameworks. Through a comprehensive evaluation of inventory data, including statistical analyses, visual representations, and model evaluations, we illuminate the nuanced relationships and dependencies prevalent within inventory control strategies. Our findings underscore the significance of data-driven decision-making in optimizing inventory practices, mitigating risks, and fostering sustainability within supply chains. The insights gleaned from this study advocate for the continued application of advanced data analytics to pave the way for resilient, environmentally conscious, and economically viable supply chain practices.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110106
Vol. 11 Issue. 1 PP. 55-64, (2024)
An essential part of electrifying bus networks is deciding on the appropriate charging strategy among the many available alternatives, such as opportunistic (rapid) charging techniques and overnight (slow) charging. The broad usage of electric buses in public transportation networks and the increasing demand for environmentally friendly transportation options have elevated the significance of this step. This research establishes a multi-criteria decision-making (MCDM) fusion method for choosing the optimal electric bus charging strategy by considering various variables, including operational, quality-of-service, social, environmental, and economic factors. To determine what matters most for making decisions in this field, we surveyed electric bus specialists and reviewed the literature extensively. We used the TOPSIS method as an MCDM fusion method to combine the criteria and alternatives. We compute the weights of criteria by the average method. Then, the TOPSIS fusion method selects and ranks the alternatives. We collected the 20 criteria and five alternatives in this study. We show that overnight is the best charging strategy in the electric bus system. We performed a sensitivity analysis to show the different cases in criteria weights, then ranked the alternatives under different weights to establish the stability of the results.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110107
Vol. 11 Issue. 1 PP. 65-74, (2024)
The retail landscape thrives on the synthesis of advanced analytics and business intelligence techniques, pivotal in navigating the complexities of consumer behavior and market dynamics. This study addresses the imperative to optimize retail strategies by leveraging historical sales data from 45 diverse stores with multifaceted departments. The challenge of predicting retail sales prices guided our methodology, employing convolutional neural network architectures and Root Mean Square Error (RMSE) as the principal error metric. Through iterative computations and feature extractions, our model aimed to discern intricate patterns and correlations within the retail domain, underpinning strategic decision-making processes. Analysis of the integrated methodologies illuminated critical insights into the intricate interplay of factors impacting retail operations. The findings underscored the significance of these techniques in informing strategic decisions, highlighting their potential to elevate sales performance and operational efficiencies. Our study culminates in advocating for the application and refinement of predictive models across diverse retail contexts, proposing further research into real-time application and interpretability methods.
Read MoreDoi: https://doi.org/10.54216/JISIoT.110108
Vol. 11 Issue. 1 PP. 75-83, (2024)