Information

Research

Jump to: Review

25 pages, 4027 KiB

Open AccessArticle

Edge-Optimized Deep Learning Architectures for Classification of Agricultural Insects with Mobile Deployment

by Muhammad Hannan Akhtar, Ibrahim Eksheir and Tamer Shanableh

Information 2025, 16(5), 348; https://doi.org/10.3390/info16050348 - 25 Apr 2025

Viewed by 122

Abstract

The deployment of machine learning models on mobile platforms has ushered in a new era of innovation across diverse sectors, including agriculture, where such applications hold immense promise for empowering farmers with cutting-edge technologies. In this context, the threat posed by insects to [...] Read more.

The deployment of machine learning models on mobile platforms has ushered in a new era of innovation across diverse sectors, including agriculture, where such applications hold immense promise for empowering farmers with cutting-edge technologies. In this context, the threat posed by insects to crop yields during harvest has escalated, fueled by factors such as evolution and climate change-induced shifts in insect behavior. To address this challenge, smart insect monitoring systems and detection models have emerged as crucial tools for farmers and IoT-based systems, enabling interventions to safeguard crops. The primary contribution of this study lies in its systematic investigation of model optimization techniques for edge deployment, including Post-Training Quantization, Quantization-Aware Training, and Data Representative Quantization. As such, we address the crucial need for efficient, on-site pest detection tools in agricultural settings. We provide a detailed analysis of the trade-offs between model size, inference speed, and accuracy across different optimization approaches, ensuring practical applicability in resource-constrained farming environments. Our study explores various methodologies for model development, including the utilization of Mobile-ViT and EfficientNet architectures, coupled with transfer learning and fine-tuning techniques. Using the Dangerous Farm Insects Dataset, we achieve an accuracy of 82.6% and 77.8% on validation and test datasets, respectively, showcasing the efficacy of our approach. Furthermore, we investigate quantization techniques to optimize model performance for on-device inference, ensuring seamless deployment on mobile devices and other edge devices without compromising accuracy. The best quantized model, produced through Post-Training Quantization, was able to maintain a classification accuracy of 77.8% while significantly reducing the model size from 33 MB to 9.6 MB. To validate the generalizability of our solution, we extended our experiments to the larger IP102 dataset. The quantized model produced using Post-Training Quantization was able to maintain a classification accuracy of 59.6% while also reducing the model size from 33 MB to 9.6 MB, thus demonstrating that our solution maintains a competitive performance across a broader range of insect classes. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

30 pages, 10066 KiB

Open AccessArticle

Farmer Ants Optimization Algorithm: A Novel Metaheuristic for Solving Discrete Optimization Problems

by Ali Asghari, Mahdi Zeinalabedinmalekmian, Hossein Azgomi, Mahmoud Alimoradi and Shirin Ghaziantafrishi

Information 2025, 16(3), 207; https://doi.org/10.3390/info16030207 - 6 Mar 2025

Viewed by 561

Abstract

Currently, certain complex issues are classified as NP-hard problems, for which there is no exact solution, or they cannot be solved in a reasonable amount of time. As a result, metaheuristic algorithms have been developed as an alternative. These algorithms aim to approximate [...] Read more.

Currently, certain complex issues are classified as NP-hard problems, for which there is no exact solution, or they cannot be solved in a reasonable amount of time. As a result, metaheuristic algorithms have been developed as an alternative. These algorithms aim to approximate the optimal solution rather than providing a definitive one. Over recent years, these algorithms have gained considerable attention from the research community. Nature and its inherent principles serve as the primary inspiration for the development of metaheuristic algorithms. A notable subgroup of these algorithms is evolutionary algorithms, which are modeled based on the behavior of social and intelligent animals and organisms. However, each metaheuristic algorithm typically excels only with specific types of problems. As a result, researchers continuously endeavor to develop new algorithms. This study introduces a novel metaheuristic algorithm known as the Farmer Ants Optimization Algorithm (FAOA). The algorithm is inspired by the life of farmer ants, which cultivate mushrooms for food, protect them from pests, and nourish them as they grow. These behaviors, based on their social dynamics, serve as the foundation for the proposed algorithm. Experiments conducted on various engineering and classical problems have demonstrated that the FAOA provides acceptable solutions for discrete optimization problems. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

23 pages, 8844 KiB

Open AccessArticle

Innovating Gastronomy through Information Technology: A Bibliometric Analysis of 3D Food Printing for Present and Future Research

by Ibrahim A. Elshaer, Alaa M. S. Azazz, Mohamed A. Zayed, Faleh A. Ameen, Sameh Fayyad, Amr Mohamed Fouad, Noha Ibrahim Khalil and Eslam Ahmed Fathy

Information 2024, 15(8), 471; https://doi.org/10.3390/info15080471 - 8 Aug 2024

Cited by 6 | Viewed by 2956

Abstract

Three-dimensional food printing (3DFP) has now emerged as the new paradigm shift in culinary arts and is leading to a dramatic transformation of traditional cuisine. This paper aims to conduct a bibliometric analysis of the literature associated with 3DFP research. In the Scopus [...] Read more.

Three-dimensional food printing (3DFP) has now emerged as the new paradigm shift in culinary arts and is leading to a dramatic transformation of traditional cuisine. This paper aims to conduct a bibliometric analysis of the literature associated with 3DFP research. In the Scopus database, an initial search provided 2188 documents. Applying the PRISMA criteria reduced these documents by narrowing the research to 545 articles. The bibliometric analysis confirmed the growth of research interest in the topic over the past ten years, demonstrating a substantial rise in publications between 2021 and 2023. We also investigated major journals and authors who play the most significant role in the field. The study also provides insight into how 3DFP is applied to deliver delicious, healthy, and visually appealing meals and mitigate food waste. It also highlights and strengthens the argument for design possibilities to manufacture such shapes and include other raw materials. This bibliometric analysis not only visualizes 3DFP’s research trend but also provides future research directions, focusing on its role in the food industry and gastronomy as well as its contribution to sustainable development. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

15 pages, 2015 KiB

Open AccessArticle

Gated Convolution and Stacked Self-Attention Encoder–Decoder-Based Model for Offline Handwritten Ethiopic Text Recognition

by Direselign Addis Tadesse, Chuan-Ming Liu and Van-Dai Ta

Information 2023, 14(12), 654; https://doi.org/10.3390/info14120654 - 9 Dec 2023

Cited by 1 | Viewed by 2170

Abstract

Offline handwritten text recognition (HTR) is a long-standing research project for a wide range of applications, including assisting visually impaired users, humans and robot interactions, and the automatic entry of business documents. However, due to variations in writing styles, visual similarities between different [...] Read more.

Offline handwritten text recognition (HTR) is a long-standing research project for a wide range of applications, including assisting visually impaired users, humans and robot interactions, and the automatic entry of business documents. However, due to variations in writing styles, visual similarities between different characters, overlap between characters, and source document noise, designing an accurate and flexible HTR system is challenging. The problem becomes serious when the algorithm has a low learning capacity and when the text used is complex and has a lot of characters in the writing system, such as Ethiopic script. In this paper, we propose a new model that recognizes offline handwritten Ethiopic text using a gated convolution and stacked self-attention encoder–decoder network. The proposed model has a feature extraction layer, an encoder layer, and a decoder layer. The feature extraction layer extracts high-dimensional invariant feature maps from the input handwritten image. Using the extracted feature maps, the encoder and decoder layers transcribe the corresponding text. For the training and testing of the proposed model, we prepare an offline handwritten Ethiopic text-line dataset (HETD) with 2800 samples and a handwritten Ethiopic word dataset (HEWD) with 10,540 samples obtained from 250 volunteers. The experiment results of the proposed model on HETD show a 9.17 and 13.11 Character Error Rate (CER) and Word Error Rate (WER), respectively. However, the model on HEWD shows an 8.22 and 9.17 CER and WER, respectively. These results and the prepared datasets will be used as a baseline for future research. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

12 pages, 2607 KiB

Open AccessArticle

CRI-Based Smart Lighting System That Provides Characteristics of Natural Light

by Seung-Taek Oh and Jae-Hyun Lim

Information 2023, 14(12), 628; https://doi.org/10.3390/info14120628 - 23 Nov 2023

Viewed by 2214

Abstract

Natural light continuously changes its correlated color temperature (CCT) from sunrise to sunset, providing the best color reproducibility and healthy light. In the lighting field, efforts have been made to improve the Color Rendering Index (CRI) to provide light quality at the same [...] Read more.

Natural light continuously changes its correlated color temperature (CCT) from sunrise to sunset, providing the best color reproducibility and healthy light. In the lighting field, efforts have been made to improve the Color Rendering Index (CRI) to provide light quality at the same level as natural light. A unique light source technology that mixes and controls multiple LED light sources with different spectral or CCT characteristics or provides a high color rendering index has been introduced. However, the characteristics of natural light, which provide high CRI light while changing color temperature every moment, could not be reproduced as they were. Therefore, in this paper, we propose a CRI-based smart lighting system that reproduces natural light characteristics, provides light with high color reproducibility, and maintains homeostasis even under the changing environment of natural light CCT. After extracting the CCT for each day from the characteristics of measured natural light, the light with the highest CRI under the CCT condition for each hour was provided through a CRI-based CCT matching algorithm. Performance evaluation was conducted for four-channel LED experimental lighting. For each clear and cloudy day, daily natural light was reproduced with a light quality higher than average CRI 98 within the MAE range of CCT 6.78 K. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

15 pages, 21230 KiB

Open AccessArticle

Data Augmentation Method for Pedestrian Dress Recognition in Road Monitoring and Pedestrian Multiple Information Recognition Model

by Huiyong Wang, Liang Guo, Ding Yang and Xiaoming Zhang

Information 2023, 14(2), 125; https://doi.org/10.3390/info14020125 - 15 Feb 2023

Viewed by 1985

Abstract

Road intelligence monitoring is an inevitable trend of urban intelligence, and clothing information is the main factor to identify pedestrians. Therefore, this paper establishes a multi-information clothing recognition model and proposes a data augmentation method based on road monitoring. First, we use Mask [...] Read more.

Road intelligence monitoring is an inevitable trend of urban intelligence, and clothing information is the main factor to identify pedestrians. Therefore, this paper establishes a multi-information clothing recognition model and proposes a data augmentation method based on road monitoring. First, we use Mask R-CNN to detect the clothing category information in the monitoring; then, we transfer the mask to the k-means cluster to obtain the color and finally obtain the clothing color and category. However, the monitoring scene and dataset are quite different, so a data augmentation method suitable for road monitoring is designed to improve the recognition ability of small targets and occluded targets. The small target mAP (mean average precision) recognition ability is improved by 12.37% (from 30.37%). The method of this study can help find relevant passers-by in the actual monitoring scene, which is conducive to the intelligent development of the city. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

20 pages, 1059 KiB

Open AccessArticle

Toward Efficient Similarity Search under Edit Distance on Hybrid Architectures

by Madiha Khalid, Muhammad Murtaza Yousaf and Muhammad Umair Sadiq

Information 2022, 13(10), 452; https://doi.org/10.3390/info13100452 - 26 Sep 2022

Cited by 3 | Viewed by 3499

Abstract

Edit distance is the most widely used method to quantify similarity between two strings. We investigate the problem of similarity search under edit distance. Given a collection of sequences, the goal of similarity search under edit distance is to find sequences in the [...] Read more.

Edit distance is the most widely used method to quantify similarity between two strings. We investigate the problem of similarity search under edit distance. Given a collection of sequences, the goal of similarity search under edit distance is to find sequences in the collection that are similar to a given query sequence where the similarity score is computed using edit distance. The canonical method of computing edit distance between two strings uses a dynamic programming-based approach that runs in quadratic time and space, which may not provide results in a reasonable amount of time for large sequences. It advocates for parallel algorithms to reduce the time taken by edit distance computation. To this end, we present scalable parallel algorithms to support efficient similarity search under edit distance. The efficiency and scalability of the proposed algorithms is demonstrated through an extensive set of experiments on real datasets. Moreover, to address the problem of uneven workload across different processing units, which is mainly caused due to the significant variance in the size of the sequences, different data distribution schemes are discussed and empirically analyzed. Experimental results have shown that the speedup achieved by the hybrid approach over inter-task and intra-task parallelism is 18 and 13, respectively. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

23 pages, 2823 KiB

Open AccessArticle

Modification of the DIBR and MABAC Methods by Applying Rough Numbers and Its Application in Making Decisions

by Duško Tešić, Marko Radovanović, Darko Božanić, Dragan Pamucar, Aleksandar Milić and Adis Puška

Information 2022, 13(8), 353; https://doi.org/10.3390/info13080353 - 25 Jul 2022

Cited by 16 | Viewed by 2736

Abstract

This study considers the problem of selecting an anti-tank missile system (ATMS). The mentioned problem is solved by applying a hybrid multi-criteria decision-making model (MCDM) based on two methods: the DIBR (Defining Interrelationships Between Ranked criteria) and the MABAC (Multi-Attributive Border Approximation area [...] Read more.

This study considers the problem of selecting an anti-tank missile system (ATMS). The mentioned problem is solved by applying a hybrid multi-criteria decision-making model (MCDM) based on two methods: the DIBR (Defining Interrelationships Between Ranked criteria) and the MABAC (Multi-Attributive Border Approximation area Comparison) methods. The methods are modified by applying rough numbers, which present a very suitable area for considering uncertainty following decision-making processes. The DIBR method is a young method with a simple mathematical apparatus which is based on defining the relation between ranked criteria, that is, adjacent criteria, reducing the number of comparisons. This method defines weight coefficients of criteria, based on the opinion of experts. The MABAC method is used to select the best alternative from the set of the offered ones, based on the distance of the criteria function of every observed alternative from the border approximate area. The paper has two main innovations. With the presented decision-making support model, the ATMS selection problem is raised to a higher level, which is based on a proven mathematical apparatus. In terms of methodology, the main innovation is successful application of the rough DIBR method, which has not been treated in this way in the literature so far. Additionally, an analysis of the literature related to the research problem as well as to the methods used is carried out. After the application of the model, the sensitivity analysis of the output results of the presented model to the change of the weight coefficients of criteria is performed, as well as the comparison of the results of the presented model with other methods. Finally, the proposed model is concluded to be stable and multi-criteria decision-making methods can be a reliable tool to help decision makers in the selection process. The presented model has the potential of being applied in other case studies as it has proven to be a good means for considering uncertainty. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

11 pages, 560 KiB

Open AccessArticle

On the Malleability of Consumer Attitudes toward Disruptive Technologies: A Pilot Study of Cryptocurrencies

by Horst Treiblmaier and Evgeny Gorbunov

Information 2022, 13(6), 295; https://doi.org/10.3390/info13060295 - 10 Jun 2022

Cited by 5 | Viewed by 3004

Abstract

The digital transformation of core marketing activities substantially impacts relations between consumers and companies. Novel technologies are usually complex, making their underlying functionality as well as the desirable and undesirable implications hard to grasp for ordinary consumers. Cryptocurrencies are a prominent yet controversial [...] Read more.

The digital transformation of core marketing activities substantially impacts relations between consumers and companies. Novel technologies are usually complex, making their underlying functionality as well as the desirable and undesirable implications hard to grasp for ordinary consumers. Cryptocurrencies are a prominent yet controversial and poorly understood example of an innovation that may transform companies’ future marketing activities. In this study, we investigate how easily consumers’ attitudes toward cryptocurrencies can be shaped by splitting a convenience sample of 100 consumers into two equal groups and exposing them to true, but biased, information about cryptocurrencies (including market forecasts), respectively, highlighting either the advantages or disadvantages of the technology. We subsequently found a significant difference in the trust, security and risk perceptions between the two groups; specifically, more positive attitudes pertaining to trust, security, risk and financial gains prevailed in the group exposed to positively-skewed information, while perceptions regarding trust, risk and the sustainability of cryptocurrencies were weaker among the group exposed to negatively-skewed information. These findings reveal some important insights into how easily consumer attitudes toward new technologies can be shaped through the presentation of lopsided information and call for further in-depth research in this important yet under-researched field. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

14 pages, 552 KiB

Open AccessArticle

Digital Transformation in Healthcare 4.0: Critical Factors for Business Intelligence Systems

by Fotis Kitsios and Nikolaos Kapetaneas

Information 2022, 13(5), 247; https://doi.org/10.3390/info13050247 - 12 May 2022

Cited by 20 | Viewed by 7147

Abstract

The health sector is one of the most knowledge-intensive and complicated globally. It has been proven repeatedly that Business Intelligence (BI) systems in the healthcare industry can help hospitals make better decisions. Some studies have looked at the usage of BI in health, [...] Read more.

The health sector is one of the most knowledge-intensive and complicated globally. It has been proven repeatedly that Business Intelligence (BI) systems in the healthcare industry can help hospitals make better decisions. Some studies have looked at the usage of BI in health, but there is still a lack of information on how to develop a BI system successfully. There is a significant research gap in the health sector because these studies do not concentrate on the organizational determinants that impact the development and acceptance of BI systems in different organizations; therefore, the aim of this article is to develop a framework for successful BI system development in the health sector taking into consideration the organizational determinants of BI systems’ acceptance, implementation, and evaluation. The proposed framework classifies the determinants under organizational, process, and strategic aspects as different types to ensure the success of BI system deployment. Concerning practical implications, this paper gives a roadmap for a wide range of healthcare practitioners to ensure the success of BI system development. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Figure 1

Review

Jump to: Research

18 pages, 1217 KiB

Open AccessReview

User Experience and Usability of Voice User Interfaces: A Systematic Literature Review

by Akshay Madhav Deshmukh and Ricardo Chalmeta

Information 2024, 15(9), 579; https://doi.org/10.3390/info15090579 - 19 Sep 2024

Viewed by 7160

Abstract

As voice user interfaces (VUIs) rapidly transform the landscape of human–computer interaction, their potential to revolutionize user engagement is becoming increasingly evident. This paper aims to advance the field of human–computer interaction by conducting a bibliometric analysis of the user experience associated with [...] Read more.

As voice user interfaces (VUIs) rapidly transform the landscape of human–computer interaction, their potential to revolutionize user engagement is becoming increasingly evident. This paper aims to advance the field of human–computer interaction by conducting a bibliometric analysis of the user experience associated with VUIs. It proposes a classification framework comprising six research categories to systematically organize the existing literature, analyzes the primary research streams, and identifies future research directions within each category. This systematic literature review provides a comprehensive analysis of the development and effectiveness of VUIs in facilitating natural human–machine interaction. It offers critical insights into the user experience of VUIs, contributing to the refinement of VUI design to optimize overall user interaction and satisfaction. Full article

(This article belongs to the Special Issue Intelligent Information Technology)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Intelligent Information Technology

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (11 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI