Month: November 2024
Assessing the impact of climate change by using Mann–Kendall, Pettitt and statistical downscaling model (case study: Tabriz station)
Abstract
Climate change is one of the most important phenomena in large cities. This phenomenon causes various disasters such as floods, drought, water insecurity, water war and summer heat waves in cities. In this research, different methods, including the statistical downscaling method, Mann–Kendall, Pettitt, a precipitation index (PI), a temperature index, a weighted precipitation index (WPI), a weighted temperature index (WTI) and frequency analysis, have been used for assessment of precipitation and temperature time series in Tabriz city, located in the northwest of Iran. Here, data from the base time period (i.e., 1951–2022) and future time period (2022–2100) were considered to analyze. Three distinct scenarios were used in the study, namely RCP 2.6, RCP 4.5 and RCP 8.5. Results indicated that in the base period, the monthly and annual precipitation time series showed insignificant statistical trends. In the base period, the mean of the annual precipitation time series decreased suddenly such that its mean value declined from 316.32 mm (in the first sub period, i.e., 1951–1982) to 261.51 mm (in the subsequent sub period, i.e., 1982–2022). Also, the average temperature time series on monthly and annual scales showed statistically significant upward trends. A significant change in the average annual temperature was detected in 1994, in which its mean value jumped from 11.76 to 13.32 °C. Future annual precipitation (2022–2100) time series showed a statistically significant upward trend using RCP 2.6. However, using the RCP 4.5 and RCP 8.5 scenarios, trends in this parameter will not be significant in the future period. In addition, in the future period, the average annual air temperature in Tabriz has been shown to be increased from 12.35 to 12.75 °C using the three used RCPs. The values of three indices, namely TI, WTI, PI and WPI, indicated that in the future, the number of dry and warm periods will be more than the wet and cold periods. Also, the frequency analysis showed that the intensity, duration and precipitation pattern in the future period will be somewhat different from that of the base period. In Tabriz, the average annual temperature in most of the future years will be between 12 and 13 °C. Therefore, it can be concluded that climate change has affected Tabriz's climate since the end of the nineteenth century and is anticipated to continue in the following years.
Optimizing U-Net CNN performance: a comparative study of noise filtering techniques for enhanced thermal image analysis
Abstract
Infrared thermal imaging presents a promising avenue for detecting physiological phenomena such as hot flushes in animals, presenting a non-invasive and efficient approach for monitoring health and behavior. However, thermal images often suffer from various types of noise, which can impede the accuracy of analysis. In this study, the efficacy of different noise filtering algorithms is investigated utilizing filtering algorithms as preprocessing steps to enhance U-Net convolutional neural network (CNN) performance in processing animal skin infrared image sets for hot flush recognition. This study compares the performance of four commonly used filtering methods: mean, median, Gaussian, and bilateral filters. The impact of each filtering technique on noise reduction and preservation of features critical for hot flush detection is evaluated in a machine learning hot flush detection algorithm. The optimal filtering for skin thermal imaging was a median filter which significantly improved the U-Net CNN’s ability to accurately identify hot flush patterns, achieving an Intersection over Union score of 92.6% compared to 90.4% without filters. This research contributes to the advancement of thermal image processing methodologies for animal health monitoring applications, providing valuable insights for researchers and practitioners in the field of veterinary medicine and animal behavior studies utilizing autonomous thermal image segmentation.
A network intrusion detection system based on deep learning in the IoT
Abstract
As industrial and everyday devices become increasingly interconnected, the data volume within the Internet of Things (IoT) has experienced a substantial surge. This surge in data presents a heightened risk of IoT environments being vulnerable to cyber attacks, which poses a significant threat to the seamless functioning of both industrial and daily activities. Therefore, the implementation of Network Intrusion Detection System (IDS) is vital for safeguarding the security of IoT network environments. This paper introduces a network intrusion detection model based on deep learning (DL). The model aims to enhance detection accuracy by extracting features from both the spatial and temporal dimensions of network traffic data. To tackle the challenge of low detection accuracy arising from data imbalance, in this study, a Conditional Tabular Generative Adversarial Network (CTGAN) is utilized to generate synthetic data for the minority class. The objective is to enhance the volume of minority class samples, address data imbalance, and subsequently enhance the accuracy of network intrusion detection. The classification performance of the proposed model is validated on UNSW-NB15, CIC-IDS2018, and CIC-IOT2023 datasets. The experimental findings demonstrate that the suggested model attains elevated levels of classification accuracy across all three datasets. The model presented in this article is particularly well suited to handle multi-class intrusion detection tasks. The model demonstrates superior performance compared to other models used for comparison.
Depiction of Drought Over Africa in the Light of Changing Climate from CMIP6 Models
Abstract
Drought stands as a prevalent weather-related natural climatic disaster on a global scale. This study employs twenty GCMs from CMIP6 to investigate hydrological drought characteristics (frequency, duration, and intensity) across Africa under four SSPs (shared socioeconomic pathway) scenarios: SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5 spanning three designated periods: 2021–2040 (near-term), 2041–2060 (mid-term), and 2081–2100 (long-term). The (SPEI) at a 12-month scale and employs bias correction on the multi-model ensemble mean extracted from GCMs of the CMIP6 project via cumulative distribution function (CDF). Mann–Kendall approach was implemented for trend and the SPEI-12-based drought trend from 1979 to 2014 displays a negative trajectory of − 0.05/a for Africa, with similar figures for specific regions: Northern Africa (NAF) at − 0.06/a, Sahara (SAH) at − 0.05/a, Western Africa (WAF) at − 0.01/a, Central Africa (CAF) at − 0.02/a, Eastern Africa (EAF) at − 0.06/a, and Southern Africa (SAF) at − 0.03/a. Notably, the severe drought characteristics are manifested as a 6-month duration, 12 occurrences, and an intensity of − 1.9 events over Africa. The highest duration and frequency are observed over NAF at 7.5-month and 15.1 occurrences, respectively, while the most extreme intensity of − 2.3 events is noted over SAH. In addition, future droughts are expected to be lower frequency, extended duration, and more intense. Extreme scenarios indicate values of − 2.1, − 2.2, and − 2.6 events for Africa in the periods 2021–2040, 2041–2060, and 2081–2100, respectively, compared to − 1.99 in the historical period. The intensity of the drought is expected to increase across all sub-regions, with SAH and NAF projecting the worst conditions with − 2.4, − 2.8, and − 3.0 events respectively for SAH and − 2.2, − 2.7, and − 3.0 events for NAF. Africa’s droughts are predicted to last 6, 8, and 13 months, significantly longer than the usual 4-month period. As the historical events of 17 times is anticipated to drop to 6, 5, and 3 times, respectively. The insights derived from this study could provide a foundational basis for devising effective drought adaptation strategies in Africa. Given the anticipated severity of drought events, prioritizing plans to cope with such challenges is of paramount importance.
Novel dual-image encryption scheme based on memristive cellular neural network and K-means alogrithm
Abstract
In this paper, we propose a lossless encryption method based on dual images. A cosine perturbation is added to the generalized voltage-controlled memristor, thus constituting a generalized voltage-controlled cosine memristor. And the characteristics of the memristor are analyzed and introduced into a four-dimensional cellular neural network, thus constituting the memristor-based four-dimensional cellular neural network (M4DCNN). The parameters of the M4DCNN are adjusted to achieve a hyperchaotic state for the diffusion and scrambling stages of the image. On the key, the partial key is obtained by K-means algorithm to make the key more random. In the scrambling phase, perturbed logistic chaotic map is introduced in this paper, which makes the image pixels better satisfy the avalanche effect. Through security analysis and comparison with other encryption methods, it is found that the encryption method shows to have good encryption effect in various indexes such as key sensitivity, key space, pixel correlation, information entropy, resistance to shear attack, resistance to noise attack, UACI and NPCR analysis.