Saved Queries

Tomato is one of the most popular and widely cultivated fruits and vegetables in the world. In large-scale cultivation, manual picking is inefficient and labor-intensive, which is likely to lead to a decline in the quality of the fruits. Although mechanical picking can improve efficiency, it is affected by factors such as leaf occlusion and changes in light conditions in the tomato growth environment, resulting in poor detection and recognition results. To address these challenges, this study proposes a tomato detection method based on Graph-CenterNet. The method employs Vision Graph Convolution (ViG) to replace traditional convolutions, thereby enhancing the flexibility of feature extraction, while reducing one downsampling layer to strengthen global information capture. Furthermore, the Coordinate Attention (CA) module is introduced to optimize the processing of key information through correlation computation and weight allocation mechanisms. Experiments conducted on the Tomato Detection dataset demonstrate that the proposed method achieves average precision improvements of 7.94%, 10.58%, and 1.24% compared to Faster R-CNN, CenterNet, and YOLOv8, respectively. The results indicate that the improved Graph-CenterNet method significantly enhances the accuracy and robustness of tomato detection in complex environments. Full article

(This article belongs to the Section Precision and Digital Agriculture)

►▼ Show Figures

Figure 1

28 pages, 8967 KiB

Open AccessArticle

Adaptive Global Dense Nested Reasoning Network into Small Target Detection in Large-Scale Hyperspectral Remote Sensing Image

by Siyu Zhan, Yuxuan Yang, Muge Zhong, Guoming Lu and Xinyu Zhou

Remote Sens. 2025, 17(6), 948; https://doi.org/10.3390/rs17060948 (registering DOI) - 7 Mar 2025

Abstract

Small and dim target detection is a critical challenge in hyperspectral remote sensing, particularly in complex, large-scale scenes where spectral variability across diverse land cover types complicates the detection process. In this paper, we propose a novel target reasoning algorithm named Adaptive Global Dense Nested Reasoning Network (AGDNR). This algorithm integrates spatial, spectral, and domain knowledge to enhance the detection accuracy of small and dim targets in large-scale environments and simultaneously enables reasoning about target categories. The proposed method involves three key innovations. Firstly, we develop a high-dimensional, multi-layer nested U-Net that facilitates cross-layer feature transfer, preserving high-level features of small and dim targets throughout the network. Secondly, we present a novel approach for computing physicochemical parameters, which enhances the spectral characteristics of targets while minimizing environmental interference. Thirdly, we construct a geographic knowledge graph that incorporates both target and environmental information, enabling global target reasoning and more effective detection of small targets across large-scale scenes. Experimental results on three challenging datasets show that our method outperforms state-of-the-art approaches in detection accuracy and achieves successful classification of different small targets. Consequently, the proposed method offers a robust solution for the precise detection of hyperspectral small targets in large-scale scenarios. Full article

(This article belongs to the Special Issue Integrating Deep Learning with Image Perception for Advanced Remote Sensing Applications)

►▼ Show Figures

Figure 1

23 pages, 1939 KiB

Open AccessArticle

Enhancing Mobile App Development for Sustainability: Designing and Evaluating the SBAM Design Cards

by Chiara Tancredi, Roberta Presta, Laura Mancuso and Roberto Montanari

Sustainability 2025, 17(6), 2352; https://doi.org/10.3390/su17062352 (registering DOI) - 7 Mar 2025

Abstract

Behavioral changes are critical for addressing sustainability challenges, which have become increasingly urgent due to the growing impact of global greenhouse gas emissions on ecosystems and human livelihoods. However, translating awareness into meaningful action requires practical tools to bridge this gap. Mobile applications, utilizing strategies from human–computer interaction (HCI) such as gamification, nudging, and persuasive technologies, have proven to be powerful in promoting sustainable behaviors. To support designers in developing effective apps of this kind, theory-based design guidelines were created, drawing on established theories and design approaches aimed at shaping and encouraging virtuous user behaviors fostering sustainability. To make these guidelines more accessible and enhance their usability during the design phase, this study presents their transformation into the SBAM card deck, a deck of 11 design cards. The SBAM cards aim to simplify theoretical concepts, stimulate creativity, and provide structured support for design discussions, helping designers generate solutions tailored to specific project contexts. This study also evaluates the effectiveness of the SBAM cards in the design process through two workshops with design students. Results show that the cards enhance ideation, foster creativity, and improve designers’ perceived self-efficacy compared to the exploitation of the same design guidelines information presented in traditional textual formats. This paper discusses the SBAM cards design and evaluation methodology, findings, and implications, offering insights into how the SBAM design cards can bridge the gap between theory and practice in sustainability-focused mobile app development. To ensure broader accessibility, the SBAM cards have been made available to the public through a dedicated website. Full article

(This article belongs to the Special Issue Environmental Behavior and Climate Change)

►▼ Show Figures

Figure 1

19 pages, 9739 KiB

Open AccessArticle

Rockfall Hazard Evaluation in a Cultural Heritage Site: Case Study of Agia Paraskevi Monastery, Monodendri, Greece

by Spyros Papaioannou, George Papathanassiou and Vassilis Marinos

Geosciences 2025, 15(3), 92; https://doi.org/10.3390/geosciences15030092 (registering DOI) - 7 Mar 2025

Abstract

Rockfall is considered the main geohazard in mountainous areas with steep morphology. The main objective of this study is to assess the rockfall hazard in the cultural heritage site of the Monastery of Agia Paraskevi, Monodendri, in northern Greece, where a recent rockfall event occurred, destroying a small house and the protective fence constructed to protect the Monastery of Agia Paraskevi. To evaluate the rockfall potential, engineering geological-oriented activities were carried out, such as geostructurally oriented field measurements, aiming to simulate the rockfall path and to compute the kinetic energy and the runout distance. In addition, using remote sensing tools such as Unmanned Aerial Vehicles (UAVs), we were able to inspect the entire slope face and detect the locations of detached blocks by measuring their volume. As a result, it was concluded that the average volume of the expected detached blocks is around 1.2 m³, while the maximum kinetic energy along a rockfall trajectory ranges from 1850 to 2830 kJ, depending on the starting point (source). Furthermore, we discussed the level of similarity between the outcomes arising from the data obtained by the traditional field survey and the UAV campaigns regarding the structural analysis of discontinuity sets. Full article

►▼ Show Figures

Figure 1

12 pages, 7869 KiB

Open AccessArticle

Design of an E-Band Multiplexer Based on Turnstile Junction

by Shaohang Li, Yuan Yao, Xiaohe Cheng and Junsheng Yu

Electronics 2025, 14(6), 1072; https://doi.org/10.3390/electronics14061072 (registering DOI) - 7 Mar 2025

Abstract

This paper presents an E-band four-channel multiplexer based on a turnstile junction. The proposed multiplexer consists of a power distribution unit featuring a turnstile junction topology and four Chebyshev bandpass filters. Thanks to the implementation of a rotating gate connection structure as the distribution unit, the overall compactness was enhanced, and the complexity of optimization was significantly reduced. Furthermore, this configuration offers a well-organized spatial port distribution, facilitating scalability for additional channels. According to the frequency band planning and design requirements of the communication system, an E-band four-channel multiplexer was designed and manufactured using high-precision computer numerical control (CNC) milling technology, achieving an error margin of ±5 μm. The experimental results indicate that the passbands are 70.6–73.07 GHz, 73.7–76.07 GHz, 82.55–82.9 GHz, and 83.4–85.9 GHz. The in-band insertion loss of each channel is below 1.7 dB, while the return loss at the common port exceeds 12 dB. The measured results align closely with simulations, demonstrating promising potential for practical applications. Full article

(This article belongs to the Section Microwave and Wireless Communications)

►▼ Show Figures

Figure 1

13 pages, 2163 KiB

Open AccessArticle

ViBEx: A Visualization Tool for Gene Expression Analysis

by Michael H. Terrefortes-Rosado, Andrea V. Nieves-Rivera, Humberto Ortiz-Zuazaga and Marie Lluberes-Contreras

BioMedInformatics 2025, 5(1), 13; https://doi.org/10.3390/biomedinformatics5010013 (registering DOI) - 7 Mar 2025

Abstract

Background: Variations in the states of Gene Regulatory Networks significantly influence disease outcomes and drug development. Boolean Networks serve as a tool to conceptualize and understand the complex relationships between genes. Threshold computation methods are used for the binarization of gene expression and the Boolean representation of its Gene Regulatory Network. This study aims to provide a platform that facilitates the exploration of the impact of different threshold computation methods on the binarization of gene expression and the subsequent Boolean representation of Gene Regulatory Networks. Methods: Threshold computation methods are implemented for binarizing gene expression, enabling the Boolean representation of the Gene Regulatory Networks. Variations in gene expression discretization and threshold computation methods often lead to differing Boolean representations, which may affect the subsequent analysis. Lluberes proposed a framework for analyzing gene expression when binarization varies based on these factors. This theoretical framework was implemented using the Python Dash framework. Results: A visualization tool has been developed to implement this framework. The tool allows users to upload gene expression datasets and interact with a dashboard to explore gene expression binarization and the inferred Boolean Networks. Conclusions: The developed visualization tool provides a platform that facilitates the exploration of how different binarization methods impact the interpretation of Gene Regulatory Networks, offering insights for disease research and drug development. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

►▼ Show Figures

Figure 1

19 pages, 748 KiB

Open AccessArticle

Cyberbullying Perpetration and Socio-Behavioral Correlates in Italian and Spanish Preadolescents: A Cross-National Study and Serial Mediation Analysis

by Gianluca Mariano Colella, Rocco Carmine Servidio, Anna Lisa Palermiti, Maria Giuseppina Bartolo, Paula García-Carrera, Rosario Ortega-Ruiz and Eva M. Romera

Int. J. Environ. Res. Public Health 2025, 22(3), 389; https://doi.org/10.3390/ijerph22030389 (registering DOI) - 7 Mar 2025

Abstract

The spread of information and communication technologies (ICTs) has brought advantages and disadvantages, particularly impacting youth, who use the Internet and social media applications daily. In preadolescents’ social development, problematic social media use (PSMU) and cyberbullying (CB) are potential risk factors across several countries. PSMU is defined as the lack of regulation of social media platforms that is associated with negative outcomes in everyday life, while CB refers to using digital technology to harass, threaten, or embarrass another person. Among preadolescents, CB perpetration is frequently associated with cybervictimization (CV) experiences. The underlying mechanisms that drive this relationship have received limited attention. The aim of the cross-national comparative study, rooted in the general aggression model, is to investigate the direct and indirect effects between cyberbullying perpetration and cybervictimization, testing a model involving PSMU and moral disengagement (MD) as serial mediators in this association. A total of 895 Italian and Spanish preadolescents (M_age = 11.23, SD_age = 1.064) completed a self-report survey during school hours. Descriptive statistics were computed, and a serial mediation model was run. The results show that CV is positively associated with CB, and that PSMU and MD positively serially mediate the CV–CB link. This study’s insights suggest the need for tailored educational interventions targeting European youth, to promote more positive online social interactions and a safer digital environment. Full article

(This article belongs to the Special Issue The Impact of Internet and Social Media Use on Young People's Mental Health)

►▼ Show Figures

Figure 1

Figure 1
Theoretical model of serial mediation effects, linking cybervictimization and cyberbullying through the serial mediating actions of PSMU and MD. Full article ">Figure 2
Non-standardized estimate results from the serial mediating research model. ** p > 0.001. Full article ">

19 pages, 13823 KiB

Open AccessArticle

Autonomous Agricultural Robot Using YOLOv8 and ByteTrack for Weed Detection and Destruction

by Ardin Bajraktari and Hayrettin Toylan

Machines 2025, 13(3), 219; https://doi.org/10.3390/machines13030219 (registering DOI) - 7 Mar 2025

Abstract

Automating agricultural machinery presents a significant opportunity to lower costs and enhance efficiency in both current and future field operations. The detection and destruction of weeds in agricultural areas via robots can be given as an example of this process. Deep learning algorithms can accurately detect weeds in agricultural fields. Additionally, robotic systems can effectively eliminate these weeds. However, the high computational demands of deep learning-based weed detection algorithms pose challenges for their use in real-time applications. This study proposes a vision-based autonomous agricultural robot that leverages the YOLOv8 model in combination with ByteTrack to achieve effective real-time weed detection. A dataset of 4126 images was used to create YOLO models, with 80% of the images designated for training, 10% for validation, and 10% for testing. Six different YOLO object detectors were trained and tested for weed detection. Among these models, YOLOv8 stands out, achieving a precision of 93.8%, a recall of 86.5%, and a [email protected] detection accuracy of 92.1%. With an object detection speed of 18 FPS and the advantages of the ByteTrack integrated object tracking algorithm, YOLOv8 was selected as the most suitable model. Additionally, the YOLOv8-ByteTrack model, developed for weed detection, was deployed on an agricultural robot with autonomous driving capabilities integrated with ROS. This system facilitates real-time weed detection and destruction, enhancing the efficiency of weed management in agricultural practices. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

►▼ Show Figures

Figure 1

22 pages, 516 KiB

Open AccessSystematic Review

Positron Emission Tomography–Magnetic Resonance Imaging, a New Hybrid Imaging Modality for Dentomaxillofacial Malignancies—A Systematic Review

by Anastasia Mitsea, Nikolaos Christoloukas, Spyridoula Koutsipetsidou, Periklis Papavasileiou, Georgia Oikonomou and Christos Angelopoulos

Diagnostics 2025, 15(6), 654; https://doi.org/10.3390/diagnostics15060654 (registering DOI) - 7 Mar 2025

Abstract

Background/Objectives: Emerging hybrid imaging modalities, like Positron Emission Tomography/Computed Tomography (PET/CT) and Positron Emission Tomography/Magnetic Resonance Imaging (PET/MRI), are useful for assessing head and neck cancer (HNC) and its prognosis during follow-up. PET/MRI systems enable simultaneous PET and MRI scans within a single session. These combined PET/MRI scanners merge MRI’s better soft tissue contrast and the molecular metabolic information offered by PET. Aim: To review scientific articles on the use of hybrid PET/MRI techniques in diagnosing dentomaxillofacial malignancies. Method: The available literature on the use of PET/MRI for the diagnosis of dentomaxillofacial malignancies in four online databases (Scopus, PubMed, Web of Science, and the Cochrane Library) was searched. Eligible for this review were original full-text articles on PET/MRI imaging, published between January 2010 and November 2024, based on experimental or clinical research involving humans. Results: Out of the 783 articles retrieved, only twelve articles were included in this systematic review. Nearly half of the articles (5 out of 12) concluded that PET/MRI is superior to PET, MRI, and PET/CT imaging in relation to defining malignancies’ size. Six articles found no statistically significant results and the diagnostic accuracy presented was similar in PET/MRI versus MRI and PET/CT images. Regarding the overall risk of bias, most articles had a moderate risk. Conclusions: The use of PET/MRI in HNC cases provides a more accurate diagnosis regarding dimensions of the tumor and thus a more accurate surgical approach if needed. Further prospective studies on a larger cohort of patients are required to obtain more accurate results on the application of hybrid PET/MRI. Full article

(This article belongs to the Special Issue Advances in Dental Imaging, Oral Diagnosis, and Forensic Dentistry)

►▼ Show Figures

Figure 1

Figure 1
PRISMA flow diagram. Full article ">

21 pages, 1178 KiB

Open AccessArticle

User Behavior on Value Co-Creation in Human–Computer Interaction: A Meta-Analysis and Research Synthesis

by Xiaohong Chen and Yuan Zhou

Electronics 2025, 14(6), 1071; https://doi.org/10.3390/electronics14061071 (registering DOI) - 7 Mar 2025

Abstract

Value co-creation in online communities refers to a process in which all participants within a platform’s ecosystem exchange and integrate resources while engaging in mutually beneficial interactive processes to generate perceived value-in-use. User behavior plays a crucial role in influencing value co-creation in human–computer interaction. However, existing research contains controversies, and there is a lack of comprehensive studies exploring which factors of user behavior influence it and the mechanisms through which they operate. This paper employs meta-analysis to examine the factors and mechanisms based on 42 studies from 2006 to 2023 with a sample size of 30,016. It examines the relationships at the individual, interaction, and environment layers and explores moderating effects through subgroup analysis. The results reveal a positive overall effect between user behavior and value co-creation performance. Factors including self-efficacy, social identity, enjoyment, and belonging (individual layer); information support, social interaction, trust, and reciprocity (interaction layer); as well as shared values, incentives, community culture, and subjective norms (environment layer) positively influence value co-creation. The moderating effect of situational and measurement factors indicates that Chinese communities and monocultural environments have more significant effects than international and multicultural ones, while community type is not significant. Structural equation models and subjective collaboration willingness have a stronger moderating effect than linear regression and objective behavior, which constitutes a counterintuitive finding. This study enhances theoretical research on user behavior and provides insights for managing value co-creation in human–computer interaction. Full article

(This article belongs to the Special Issue Human-Robot Interaction and Applications: Challenges and Future Perspectives)

►▼ Show Figures

Figure 1

Figure 1
Data Collection and Sample Selection. Full article ">Figure 2
Overall Effect on Value Co-creation Performance. Full article ">Figure 3
Individual Layer on Value Co-creation Performance. Full article ">Figure 4
Interaction Layer on Value Co-creation Performance. Full article ">Figure 5
Environment Layer on Value Co-creation Performance. Full article ">

18 pages, 5239 KiB

Open AccessArticle

A Facile Two-Step High-Throughput Screening Strategy of Advanced MOFs for Separating Argon from Air

by Xiaoyi Xu, Bingru Xin, Zhongde Dai, Chong Liu, Li Zhou, Xu Ji and Yiyang Dai

Nanomaterials 2025, 15(6), 412; https://doi.org/10.3390/nano15060412 (registering DOI) - 7 Mar 2025

Abstract

Metal–organic frameworks (MOFs) based on the pressure swing adsorption (PSA) process show great promise in separating argon from air. As research burgeons, the number of MOFs has grown exponentially, rendering the experimental identification of materials with significant gas separation potential impractical. This study introduced a high-throughput screening through a two-step strategy based on structure–property relationships, which leveraged Grand Canonical Monte Carlo (GCMC) simulations, to swiftly and precisely identify high-performance MOF adsorbents capable of separating argon from air among a vast array of MOFs. Compared to traditional approaches for material development and screening, this method significantly reduced both experimental and computational resource requirements. This research pre-screened 12,020 experimental MOFs from a computationally ready experimental MOF (CoRE MOF) database down to 7328 and then selected 4083 promising candidates through structure–performance correlation. These MOFs underwent GCMC simulation assessments, showing superior adsorption performance to traditional molecular sieves. In addition, an in-depth discussion was conducted on the structural characteristics and metal atoms among the best-performing MOFs, as well as the effects of temperature, pressure, and real gas conditions on their adsorption properties. This work provides a new direction for synthesizing next-generation MOFs for efficient argon separation in labs, contributing to energy conservation and consumption reduction in the production of high-purity argon gas. Full article

(This article belongs to the Section Inorganic Materials and Metal-Organic Frameworks)

►▼ Show Figures

Figure 1

Figure 1
Workflow for high-throughput screening of MOF adsorbents designed to separate argon from air. Full article ">Figure 2
The structure–property relationship based on oxygen as the adsorbent; the structure–property relationship based on nitrogen as the adsorbent is described in <a href="#app1-nanomaterials-15-00412" class="html-app">Figure S6</a>. (a) LCD; (b) PLD; (c) density; (d) VSA; (e) GSA; (f) VF. Full article ">Figure 3
t-SNE algorithm visualized the sampling points and the pre-screening database. Full article ">Figure 4
The relationship between the working capacity and selectivity of MOF adsorbents within the optimal structural range. The yellow, green, and purple spheres separately refer to MOFs with top 10%, top 20%, and bottom 80% APSs for nitrogen or oxygen as the target adsorbate. The grey boxes refer to MOFs with high adsorption capabilities for nitrogen or oxygen. (a) The target adsorbate is nitrogen; (b) the target adsorbate is oxygen. Full article ">Figure 5
The relationship between the APS and R% of MOF adsorbents. The purple spheres refer to MOFs with R% > 80%, the yellow spheres refer to MOFs with R% < 80% and the top 10% APSs, and the green spheres refer to MOFs with R% < 80% and bottom 90% APSs for nitrogen or oxygen as the target adsorbate. (a) The target adsorbate is nitrogen; (b) the target adsorbate is oxygen. Full article ">Figure 6
(a) Proportion of OMSs in top MOFs; (b) proportion of OMSs in MOFs of the same metal. Full article ">Figure 7
Metal ligand types and numbers of all candidate MOFs. Full article ">Figure 8
Comparison of adsorption properties of top MOFs and zeolites. Full article ">Figure 9
The impact of temperature and desorption pressure on the adsorbent’s APSA and regenerability. With the changes in temperature: (a) the variation of the APSA; (b) the variation of the R% for nitrogen as the target adsorbate; (c) the variation of the R% for oxygen as the target adsorbate. With the changes in pressure: (d) the variation of the APSA; (e) the variation of the R% for nitrogen as the target adsorbate; (f) the variation of the R% for oxygen as the target adsorbate. Full article ">

18 pages, 949 KiB

Open AccessArticle

Accelerating Pattern Recognition with a High-Precision Hardware Divider Using Binary Logarithms and Regional Error Corrections

by Dat Ngo, Suhun Ahn, Jeonghyeon Son and Bongsoon Kang

Electronics 2025, 14(6), 1066; https://doi.org/10.3390/electronics14061066 (registering DOI) - 7 Mar 2025

Abstract

Pattern recognition applications involve extensive arithmetic operations, including additions, multiplications, and divisions. When implemented on resource-constrained edge devices, these operations demand dedicated hardware, with division being the most complex. Conventional hardware dividers, however, incur substantial overhead in terms of resource consumption and latency. To address these limitations, we employ binary logarithms with regional error correction to approximate division operations. By leveraging approximation errors at boundary regions to formulate logarithm and antilogarithm offsets, our approach effectively reduces hardware complexity while minimizing the inherent errors of binary logarithm-based division. Additionally, we propose a six-stage pipelined hardware architecture, synthesized and validated on a Zynq UltraScale+ FPGA platform. The implementation results demonstrate that the proposed divider outperforms conventional division methods in terms of resource utilization and power savings. Furthermore, its application in image dehazing and object detection highlights its potential for real-time, high-performance computing systems. Full article

(This article belongs to the Special Issue Biometrics and Pattern Recognition)

►▼ Show Figures

Figure 1

Figure 1
Block diagram of binary logarithm-based division. The red-dashed blocks require approximation techniques that introduce errors into the quotient. Full article ">Figure 2
Illustration of errors introduced by Mitchell’s algorithm. (a) Error resulting from the approximation <math display="inline"><semantics> <mrow> <msub> <mi>log</mi> <mn>2</mn> </msub> <mrow> <mo>(</mo> <mn>1</mn> <mo>+</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>≈</mo> <mi>x</mi> </mrow> </semantics></math>. (b) Distribution of division errors when applying Mitchell’s algorithm. Full article ">Figure 3
Comparison of methods improving upon Mitchell’s algorithm. (a) Approximation lines used in each method, with the region <math display="inline"><semantics> <mrow> <mn>0.8</mn> <mo>≤</mo> <mi>x</mi> <mo>≤</mo> <mn>0.9</mn> </mrow> </semantics></math> enlarged for better visualization. (b) Corresponding approximation errors. Full article ">Figure 4
Approximation lines corresponding to different offset definitions. (a) <math display="inline"><semantics> <msub> <mo>Δ</mo> <mi>right</mi> </msub> </semantics></math>. (b) <math display="inline"><semantics> <msub> <mo>Δ</mo> <mi>center</mi> </msub> </semantics></math>. (c) <math display="inline"><semantics> <msub> <mo>Δ</mo> <mi>avg</mi> </msub> </semantics></math>. The fraction is divided into four regions, with an enlarged view of the third region for clarity. Full article ">Figure 5
Approximation error analysis of the proposed method. (a) Comparison of errors among different methods. (b) Approximation errors of the proposed method for varying values of M. Full article ">Figure 6
Hardware architecture of the proposed divider. REG, MSB, and LSB denote register, most significant bit, and least significant bit, respectively. The “…” symbol indicates that the data path for the divisor is identical to that of the dividend. Full article ">Figure 7
YOLOv9 object detection results on aerial images under varying haze levels using IFDH. Yellow labels represent airplanes, and blue labels represent birds. Full article ">

43 pages, 1727 KiB

Open AccessReview

A Review of the Authentication Techniques for Internet of Things Devices in Smart Cities: Opportunities, Challenges, and Future Directions

by Ashwag Alotaibi, Huda Aldawghan and Ahmed Aljughaiman

Sensors 2025, 25(6), 1649; https://doi.org/10.3390/s25061649 (registering DOI) - 7 Mar 2025

Abstract

Smart cities have witnessed a transformation in urban living through the Internet of Things (IoT), which has improved connectedness, efficiency, and sustainability. However, the adoption of IoT devices presents significant security vulnerabilities, particularly in authentication. The specific limitations of IoT contexts, such as constrained computational resources, are frequently not adequately addressed by traditional authentication techniques. The existing methods of authentication used for IoT devices in smart cities are critically examined in this review study. We evaluate the advantages and disadvantages of each mechanism, emphasizing real-world applicability. Additionally, we examine cutting-edge developments that offer improved security and scalability, such as blockchain technology, biometric authentication, and machine learning-based solutions. This study aims to identify gaps and propose future research directions to develop robust authentication frameworks that protect user privacy and data integrity. Full article

(This article belongs to the Special Issue Advanced IoT Systems in Smart Cities: 2nd Edition)

►▼ Show Figures

Figure 1

16 pages, 2001 KiB

Open AccessReview

Cryptographic Techniques in Artificial Intelligence Security: A Bibliometric Review

by Hamed Taherdoost, Tuan-Vinh Le and Khadija Slimani

Cryptography 2025, 9(1), 17; https://doi.org/10.3390/cryptography9010017 (registering DOI) - 7 Mar 2025

Abstract

With the rise in applications of artificial intelligence (AI) across various sectors, security concerns have become paramount. Traditional AI systems often lack robust security measures, making them vulnerable to adversarial attacks, data breaches, and privacy violations. Cryptography has emerged as a crucial component in enhancing AI security by ensuring data confidentiality, authentication, and integrity. This paper presents a comprehensive bibliometric review to understand the intersection between cryptography, AI, and security. A total of 495 journal articles and reviews were identified using Scopus as the primary database. The results indicate a sharp increase in research interest between 2020 and January 2025, with a significant rise in publications in 2023 and 2024. The key application areas include computer science, engineering, and materials science. Key cryptographic techniques such as homomorphic encryption, secure multiparty computation, and quantum cryptography have gained prominence in AI security. Blockchain has also emerged as an essential technology for securing AI-driven applications, particularly in data integrity and secure transactions. This paper highlights the crucial role of cryptography in safeguarding AI systems and provides future research directions to strengthen AI security through advanced cryptographic solutions. Full article

►▼ Show Figures

Figure 1

Figure 1
Number of documents included over last five years. Full article ">Figure 2
Fields’ distribution of documents included. Full article ">Figure 3
Countries of documents’ authors. Full article ">Figure 4
Cluster of keywords (Created using <a href="http://vosviewer.com" target="_blank">vosviewer.com</a> accessed 5 January 2025). Full article ">

22 pages, 817 KiB

Open AccessArticle

Clinical and Operational Applications of Artificial Intelligence and Machine Learning in Pharmacy: A Narrative Review of Real-World Applications

by Maree Donna Simpson and Haider Saddam Qasim

Pharmacy 2025, 13(2), 41; https://doi.org/10.3390/pharmacy13020041 (registering DOI) - 7 Mar 2025

Abstract

Over the past five years, the application of artificial intelligence (AI) including its significant subset, machine learning (ML), has significantly advanced pharmaceutical procedures in community pharmacies, hospital pharmacies, and pharmaceutical industry settings. Numerous notable healthcare institutions, such as Johns Hopkins University, Cleveland Clinic, and Mayo Clinic, have demonstrated measurable advancements in the use of artificial intelligence in healthcare delivery. Community pharmacies have seen a 40% increase in drug adherence and a 55% reduction in missed prescription refills since implementing artificial intelligence (AI) technologies. According to reports, hospital implementations have reduced prescription distribution errors by up to 75% and enhanced the detection of adverse medication reactions by up to 65%. Numerous businesses, such as Atomwise and Insilico Medicine, assert that they have made noteworthy progress in the creation of AI-based medical therapies. Emerging technologies like federated learning and quantum computing have the potential to boost the prediction of protein–drug interactions by up to 300%, despite challenges including high implementation costs and regulatory compliance. The significance of upholding patient-centred care while encouraging technology innovation is emphasised in this review. Full article

(This article belongs to the Special Issue The AI Revolution in Pharmacy Practice and Education)

►▼ Show Figures

Figure 1

Figure 1
Literature search approach. Full article ">

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (107,044)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI