Indicator Values Research Articles

Feed-food and land use competition of lowland and mountain dairy cow farms

Dairy cows and other ruminants contribute to human nutrition as they are able to convert feed components containing human inedible fibre concentrations (e.g. roughage and by-products from the food processing industry) into valuable animal-sourced food. A number of crops often fed to dairy cows (e.g. soy or cereals) are however potentially edible by humans too. Additionally, land used to grow dairy cattle feed may compete with crop production for human consumption. Two different methods to assess the competition between feed consumption of dairy cows and human food supply were thus refined and tested on 25 Swiss dairy farms. With respect to the potential human edibility of the feeds used in dairy production, the human-edible feed conversion ratio (eFCR) was applied. The land use ratio (LUR) was used to relate the food production potential, per area of land utilised, with the dairy production output. Low to medium eFCR, with values ranging from 0.02 to 0.68 were found, as an average proportion of 0.74 of total DM intake consisted of roughage. In contrast, we found relatively high LUR (0.69–5.93) for most farms. If the land area used to produce feed for cows was used for crop production (applying a crop rotation), 23 of the 25 farms could have produced more edible protein and all farms more human-edible energy. Indicator values strongly depend on the underlying scenarios, such as the human-edible proportion of feeds or the suitability of land and climate for crop production. Reducing the amount of human-edible feeds in dairy farming by feeding by-products from the food processing industry and improving forage quality may be suitable strategies to reduce eFCR, but relying on low-opportunity cost feeds may restrict milk performance level per cow. On farm level, improving overall efficiency and therefore using less land (especially area suitable for crop production) per kg product decreases LUR. However, the most promising strategy to mitigate land use competition may be to localise dairy production to land areas not suitable for crop production. Both methods (eFCR and LUR) should be used in parallel. They offer an opportunity to holistically evaluate the net contribution of dairy production to the human food supply under different environmental conditions and stress the importance of production systems well suited to specific farm site characteristics.

Thermal plasma-driven looping for metal scrap processing with hydrogen

In the present research, a novel process was proposed and assessed using an equilibrium thermochemical modelling study to evaluate the performance of a combined disruptive technology of thermal plasma and thermochemical looping to utilise hydrogen for iron reduction processing. The study was aimed at conducting a high-level power performance assessment of the process by integrating a built-in power block with a focus on a novel equilibrium thermal plasma technology for reducing iron scrap particles. The effect of thermal plasma operating parameters such as temperature (1000 °C < T < 1800 °C) and hydrogen-to-iron ratio in the feed stream to the thermal plasma reactor (0 < H2/metal < 20) on the performance of the system was numerically investigated using Aspen coupled with Matlab. Also, the self-sustaining factor was evaluated coupled with a quantitative analysis of the sustainability and lifecycle of the process aiming at better understanding the impact of the proposed system on the environment. Results showed that the system is crucially sensitive to the ratio of H2/metal such that the overall power demand of the reactor can change in a way that the dominant regime of the plasma can change from endothermic (partial reduction of iron) to exothermic (complete reduction, combustion of iron) once the hydrogen to metal ratio exceeds ∼ 2.5. It was also identified that an increase in the temperature of the combustor decreased the power demand for the thermal plasma reactor. Similarly, with increasing the temperature, a ramp-up in the self-sustaining factor was observed reaching 0.8 showing that 80 % of the energy of the auxiliaries can be maintained using the built-in heat recovery and power block. The thermal efficiency of the system was also a strong function of the H2/metal ratio reaching ∼ 0.4 at the H2/metal ratio of ∼ 2.5 reflecting the fact that the proposed process efficiency is within the state-of-the-art power production systems. The sustainability assessments showed that the process offers a high circular economy capability of the process with above-the-average lifetime and Material Circularity Indicator values.

When Grinnellian generalist species seem to be more sensitive to altered habitats than specialists: the case of Orthoptera communities settled in coastal dunes

Summary Numerous examples documented that species generalists for habitats are less sensitive to altered environment than specialists. However, in arid environments, an example indicated an opposite trend due to special adaptive features of organisms. We tested this hypothesis in the case of grasshopper communities, settled in the coastal dunes of northeast Algeria, as several aspects of dunes constitute stressful conditions resembling those of deserts. To define the dune-specific grasshoppers (specialists) and the dune non-specific ones (generalists), we applied the indicator value index to monthly samplings conducted in four coastal dune sites and 12 other sites of grasslands, fallow lands and scrublands in the same area. The degree of disturbance of each coastal dune site was deduced from the alteration of plant cover and richness. We investigated the relation between the specialist and generalist richness and abundance with the degree of perturbation using linear regressions. Results showed contrasting patterns for specialist and generalist grasshoppers: both abundance and richness of the generalists significantly decrease with an increasing degree of perturbation, while specialists show little to no changes. The higher resistance of specialist grasshoppers over generalists toward disturbance was not linked to the plant dune-specialists or generalists. This study is one of very few illustrating the relative resistance of specialized species toward disturbance.

Weeds as Bioindicators of Ecological Conditions in Organic Carrot and Onion Crop

Summary The obtained results indicate the possibility of weed control in organic intercropping production systems of carrots and onions with the application of corn gluten, together with the ecological assessment of habitat based on bioindicator values of weed species. A total of 29 weed taxons are present in the intercoped and pure crops of carrots and onions, grown without (CO) and with the application of corn gluten (CO-G). Although floristically uniformed, 24 taxons (CO) and 23 taxons (CO-G), the total weediness on the CO-G variants was 24% higher. The highest value of fresh weed biomass was recorded on the treatment of pure onion crop with gluten application (2844.85 g/m2), while the lowest value was recorded on the treatment of intercropped carrot and onion (1004.99 g/m2). Ecological assessment of habitat, based on indicator values and abundance of weed species, indicates favorable climatic conditions with favorable temperature (Tx̄ - 4) and light (Lx̄ - 4) regime, which refers to temperate continental climate conditions (Kx̄ - 2,7). Soil indicators indicate slightly drier conditions (Fx̄ – 2,6), slightly acidic to neutral pH (Rx̄ – 3,3), rich in nutrients (Nx̄ – 4), with moderate humus content (Hx̄ – 3), moderate aeration (Dx̄ – 2,8) and locally salted (s) with the participation of salinity indicators in the amount of 54% (CO) and 40% (CO-G). The presence of heavy metals tolerance (m) indicators in the amount of 46% (CO-G) and 41% (CO) should not be neglected, which imposes the need for additional analysis of soil for heavy metal content. Based on the analysis of obtained indicator values, it can be concluded that these ecological conditions correspond to the development of carrots and onions and that the lowest values of fresh weed biomass were recorded on the treatment of intercropping of carrots and onions, without application of corn gluten.

How gradients of climate and soil determine Mediterranean annual‐rich dryland vegetation

AbstractQuestionsDryland annual plant communities constitute the most species‐rich small‐scale vegetation in the Mediterranean. Nevertheless, the composition and diversity of these units and the factors controlling their variation are still insufficiently understood. Therefore, we investigated species composition and richness patterns in relation to important environmental gradients provided by climate and soil.LocationCentral Crete, Greece.MethodsThe study is based on 82 plots of 4 m2 sampled at altitudes between 11 and 1400 m a.s.l. We conducted vegetation relevés and soil analyses. We used generalised additive models to model species richness and community characteristics along the studied gradients. We then performed distance‐based redundancy analysis to determine the main environmental factors influencing species composition. To determine species of diagnostic value for bedrock types, we applied an indicator species analysis. Correlation tests were used to test the performance of the South Aegean Plant Indicator Values on our dataset.ResultsWe recorded 347 taxa (species and subspecies) of 43 plant families, and mean species numbers of 47.2 ± 12.5 per plot. While overall species richness varied only slightly along the analysed environmental gradients, significant changes were observed for relative proportions of species from different life forms and families. Soil pH and elevation had the highest influence on the variation in species composition (21.0% explained). We found 22 species indicative of calcareous rock and 24 species indicative of lime‐deficient rock types. The South Aegean Plant Indicator Values were relatively strongly correlated with environmental variables.ConclusionsResults indicate considerable species turnover both along climatic (elevation) and soil gradients, highlighting the special importance of soil pH. The data provided by our study are expected to supply relevant ecological background information for a pending classification of East Mediterranean annual‐rich vegetation.

Motivation of farmer group members in the application of balanced fertilization in maize (Zea mays) plant cultivation

Balanced fertilizer application technology aims not only to increase crop production but also to improve fertilizer efficiency and protect the environment from agrochemical pollution. However, its application in the field still faces several barriers, both technical and non-technical. This study aims to determine the level of farmer motivation to apply balanced fertilization in maize production, identify the factors that influence the level of farmer motivation, and develop effective strategies. In addition, the study aims to compare maize plant growth between farmers' habits and the application of balanced fertilization. The methods used in this study were descriptive and multiple linear regression. The descriptive quantitative method was used while the data were collected through observation, questionnaires, interviews, and literature studies. The population consisted of 181 maize farmers who were members of farmer groups. The respondents were 65 individuals selected through purposive sampling from 181 individuals who were members of farmer groups and engaged in maize cultivation. In addition, field experiments were conducted with two treatments: farmers' custom or P0, consisting of urea 400 + NPK 15-15-15 100 kg/ha + fertilizer scattered on the soil surface, and balanced fertilization or P1, consisting of urea 300 + NPK 15-15-15 300 kg/ha + fertilizer buried in the soil. The results of the study showed that the farmers' motivation to apply balanced fertilization was in the medium category with 67.7%. The study also identified two significant factors that influenced the farmers' motivation, namely the function of farmer groups with p = 0.004 and government support with p = 0.001. To increase farmer motivation, socialization programs should focus on the lowest indicator value, which was the ability of farmers to apply balanced fertilization. The field experiments showed that the growth of maize plants in the balanced fertilizer treatment was significantly better than that in the farmer's habit treatment. This was indicated by plant height, number of leaves, dry kernel yield, and cob+husk yield.

Data Cleansing With Minimum Distortion for ML-Based Equipment Anomaly Detection

Semiconductor manufacturing has been extensively exploiting machine-learning (ML) to process equipment sensory data (ESD) for near-real time anomaly detection (AD). ESD characteristics are highly diversified and data lengths vary among processing steps and cycles. Cleansing ESD with minimum distortion (CMD) to fit the fixed-length input requirement by ML-based AD is critical to AD effectiveness and is challenging. This paper presents a novel CMD method of four innovations: i) statistical mode-based equalization of step data lengths for the least number of step data length changes, ii) importance indicator value (IIV) of a data sample based on its relative difference with the subsequent sample, and iii) step data segmentation into groups based on samples of significant IIVs and the least-entropy-group-to-cleanse-first rule, and iv) cleansing the least IIV sample(s) in the selected group for step data length equalization. CMD application to ESD demonstrates its characteristics preservation property. Simulation experiments are on an integration of data cleansing with an unsupervised ML-based AD system, STALAD. Comparisons with two benchmark methods over AD scenarios of small-scale drifts and shifts show that CMD not only is superior in facilitating accurate detection by STALAD but also helps detect anomaly much earlier than using the two benchmarks.

SPECIES OF &lt;i&gt;PUCCINELLIA&lt;/i&gt; (POACEAE) IN PLANT COMMUNITIES IN THE SOUTH OF WESTERN SIBERIA

The study is based on analysis of 1415 relevés representing communities with presence or dominance of Puccinellia tenuissima, P. gigantea, and P. kulundensis from the southern part of Western Siberia. The ecological plasticity of these species has been shown. Their phytocenotic optimum is revealed using the species indicator values in relation to soil moisture and richness-salinity gradients. The communities dominated by P. tenuissima are most common in the south of Western Siberia. This is the reason of the highest ecological plasticity of this species. In contrast, P. kulundensis is the most environmentally stable and shows the greatest dominant potential. Among the studied species P. gigantea rarely achieves high cover. The West-Siberian communities dominated by endemic P. kulundensis are described as a new association Puccinellietum kulundensis ass. nov. from the class Festuco-Puccinellietea Soó ex Vicherek 1973, the order Scorzonero-Juncetalia gerardii Vicherek 1973 and the alliance Cirsion esculenti Golub 1994.

Analysis of Listen Before Talk Protocol Implementation in Terrestrial Network Using Multi-Node LoRa Communication

Wireless communication today plays a very important role in technological development but often faces challenges in terms of reliability and quality of data transmission; this study implements the Listen Before Talk (LBT) protocol in the terrestrial network environment through Multi-Node LoRa communication to test its effectiveness in avoiding packet loss ending the quality of communication in variations of the land environment. Test results showed that LBT effectively produced zero percentage packet loss at 50 to 500 meters. At the same time, LoRa devices could maintain communication quality even though the Received Signal Strength Indicator (RSSI) value decreased with the distance. The findings provide positive indications of the potential of LBT protocols inning data transmission integrity in terrestrial environments and foster the development of reliable and high-quality wireless communications in complex ground network environments.

PERFORMANSI KELOMPOK TANI HUTAN (KTH) DALAM PENGELOLAAN HUTAN KEMASYARAKATAN: DIMENSI KELOLA KELEMBAGAAN, KAWASAN, DAN USAHA

This research examines the essence of Social Forestry, including community forestry, which consists of three aspects: institutional, area, and business management. The method is an exploratory approach with data taken using survey methods and field observations. The dimensions of institutional arrangements, forest area management, and enterprises are measured using indicators from the Head of Extension and Human Resources Development Agency Regulation No. P.5/P2SDM/Set/Kum.1/7/2020. The assessment results for KTH Tunas Maju's institutional performance in the area management dimension showed a score of 205 or 56.94% of the maximum indicator value of 360. The assessment for area management performance reached a score of 120, equivalent to 60% of the maximum indicator value of 200. The business management performance score was 215, or 48.86% of the maximum indicator value 440. Consequently, KTH Tunas Maju's overall score is 540, placing it in the "Intermediate-level KTH" category. Considering the existing potential, there is still substantial space for improvement in its performance. Indicators that require enhancement include increased participation of women in leadership positions and membership within the group, the addition of group activity plans, frequency of group meetings, member attendance rates, completeness of secretarial and administrative functions, involvement of managers and members in capacity-building activities and training, and the necessity for a Community Forestry Extension Officer. Furthermore, expanding business partnerships, diversifying products, and increasing business capital is essential.

Application of Meta-Programming Techniques for Accelerating Software Development and Improving Quality

A contemporary software tool has been devised to evaluate software quality through metric analysis techniques. This tool calculates pertinent metrics utilizing quality indicators and establishes a composite quality indicator value for software products. The intricacies of software quality assessment processes have been elucidated, including the examination of software quality's standardization as well as the presentation level of its model. This enables the potential for enhancement through the formulation of suitable criteria for quality assessment, refining models for metric analysis, and quantitatively measuring quality across all phases of project implementation. Notably, the use of metric analysis to gauge software quality reveals a lack of standardized metrics, resulting in varying assessment methods and metrics from different measurement system providers. Interpreting metric values also proves challenging for most software users due to a lack of clarity and informativeness. Furthermore, it has been discovered that while decisions based on cost, development duration, and designer company reputation influence software implementation choices, they do not always guarantee optimal software quality.

Grassland‐use intensity maps for Switzerland based on satellite time series: Challenges and opportunities for ecological applications

AbstractLand‐use intensification in grassland ecosystems (i.e. increased mowing frequency, intensified grazing) has a strong negative effect on biodiversity and ecosystem services. However, accurate information on grassland‐use intensity is difficult to acquire and restricted to the local or regional level. Recent studies have shown that mowing events can be mapped for large areas using satellite image time series. The transferability of such approaches, especially to mountain areas, has been little explored, however, and the relevance for ecological applications in biodiversity and conservation has hardly been investigated. Here, we used a rule‐based algorithm to produce annual maps for 2018–2021 of grassland‐management events, that is, mowing and/or grazing, for Switzerland using Sentinel‐2 and Landsat 8 satellite data. We assessed the detection of management events based on independent reference data, which we acquired from daily time series of publicly available webcams that are widely distributed across Switzerland. We further examined the relationships between the generated grassland‐use intensity measures and plant species richness and ecological indicator values derived from a nationwide field survey. The webcam‐based verification for 2020 and 2021 revealed that most detected management events were actual mowing/grazing events (≥78%), but that a substantial number of events were not detected (up to 57%), particularly grazing events at higher elevations. We found lower plant species richness and higher mean ecological indicator values for nutrients and mowing tolerance with more frequent management events and those starting earlier in the year. A large proportion of the variance was explained by our use‐intensity measures. Our findings therefore highlight that remotely assessed management events can characterise land‐use intensity at fine spatial and temporal resolutions across broad scales and can explain plant biodiversity patterns in grasslands.

Biomonitoring with bryophytes in managed forested areas. Three examples from the southern Italian Apennines

Three sites in the southern Italian Apennines were selected to assess correlation between forest structure and bryophyte flora. In two of the sites, the Index of Air Purity (IAP)–based on cover data of epiphytic bryophytes–was evaluated. The results show that bryophyte populations–and consequently IAP–are affected by forest structure and development, and that studies including different sites require a precise assessment of silvicultural characteristics to allow comparisons. Indicator values of mosses and liverworts were also taken into consideration in characterizing ecologically the three sites.

Animal welfare and farm economy-exploring the relationship between dairy animal welfare indicators and economic efficiency

This paper explores the associations between a set of mainly health and productivity related animal welfare indicators in dairy farming calculated based on herd recordings, and short-term economic efficiency. To explore this association, we merged a dataset with animal welfare indicators and a dataset with farm economic data from 459 Norwegian farms. Gross margin including direct payments together with milk quota, farmland and number of animals and were used to calculate economic efficiency. The analysis was performed in two steps. First, Data Envelopment Analysis (DEA) was used to rank the farms according to efficiency. Second, the machine learning method boosting was applied to analyze the associations between economic efficiency and the different welfare indicators. The findings show that for most welfare indicators, at indicator values below the national average a positive association exists between increasing indicator values and economic efficiency. For some indicators such as for example Fertility, Calves and Youngstock, this positive association continues also beyond the national average. However, for other indicators such as for example Claw and Udder health, a curvilinear relationship exists with a turning point from where the efficiency is negatively associated with increasing indicator values. Possible explanations for the associations between economic efficiency and animal welfare indicators are outlined.

Changes in ambient particulate matter exposure and evaluation of its health relevance in Germany

Abstract Introduction To evaluate the health relevance of fine particulate matter (PM2.5), it is necessary to assess the PM2.5 exposure of the populations. For this purpose, time series (2010-2021) for two PM2.5 indicators for Germany were developed: (1) the mean population-weighted PM2.5 exposure per year and (2) the proportion of the population exceeding the recent WHO air quality guideline value for PM2.5 of 5 µg/m3 (annual mean). Methods To calculate the two indicators for the period 2010-2021, nationwide modelled annual means of PM2.5 background concentrations were used. They were joined with spatial information on population density from the 2011 census. The population data were additionally scaled for each year according to the official population update. On this basis, the population could be assigned to different PM2.5 exposure classes per year. Results Over the years considered, the mean population-weighted PM2.5 exposure in Germany decreased by approximately 41 %: in 2021, the indicator value of 9.3 µg/m3 was significantly lower than in 2010 with 15.9 µg/m3. However, throughout the time series, almost 100 % of the German population was exposed to PM2.5 annual mean concentrations above the current WHO air quality guideline value. Conclusions Generally, the decreasing PM2.5 exposure of the German population is very positive. Measures taken in recent years to reduce emissions from stationary sources and the transport sector have contributed significantly to this development. On the other hand, the large proportion of the population above the WHO guideline value shows that the current annual average PM2.5 reduction is still far from being sufficient to protect human health. In fact, far-reaching measures are required to significantly reduce particulate matter concentrations in Germany. Key messages • The mean population-weighted particulate matter exposure in Germany has decreased significantly in recent years. • The exposure reduction in Germany is still not sufficient. To protect human health, further and far-reaching measures are required to significantly reduce particulate matter concentrations in Germany.

Distribution patterns of alpine flora for long-term monitoring of global change along a wide elevational gradient in the Western Himalayas

In the current context of climate change, the Western Himalayas are thought to be warming faster than the global average rate. Despite this rapid warming, our understanding of alpine vegetation composition and the underlying factors shaping its patterns in the Western Himalayan alpine highlands of Pakistan remains limited. Extensive field sampling was conducted at 24 sites ranging in altitude from 3300 m to 4200 m. The entire altitudinal range was divided into three belts i.e., low-altitude sites, medium-altitude sites, and high-altitude sites (HAS). Results revealed that alpine flora consisted of 251 species (belonging to 51 families. The findings revealed that 83 of the 251 species evaluated contributed significantly to the change in species composition between three altitudinal sites. The species that contributed the most to the variance in species composition between communities made up 75 % of the total, demonstrating that these species are important in structuring plant communities at different altitudes. Among the alpine flora, a significant (49 %) dominance was observed from nine families, comprising a total of 123 species. The largest family, Asteraceae, had the highest number of species, followed by Poaceae and Rosaceae. Hemicryptophytes emerged as the prevailing life form, while Microphylls were the dominant leaf type. Phytosociological Indices revealed that diversity levels decreased with increasing altitude, indicating a significant impact of altitude on plant diversity. Canonical correspondence analysis suggested that altitude, grazing, and soil erosion are important in explaining variance in plant distribution patterns in the alpine flora. Twelve indicator species were discovered in three different altitudinal groups. In the LAS, Bistorta affinis, Geranium himalayense, Poa nemoralis, and Sibbaldia cuneata, had a significant indicator value, whereas in the medium-altitude sites MAS Allium humile, Bistorta affinis, Juniperus communis, and Rhododendron campanulatum had significant p-values. In high altitude sites HAS, indicator plants were Bistorta affinis, Juniperus communis. Our results identified 51 vulnerable species with very low abundance values whereas 17 threatened species having extremely low (<0.1) abundance values are a vital conservation priority in the region. Results may be helpful to formulate immediate conservation management strategies to conserve the precious floristic wealth of the alpine Region.

A global indicator of soil macroinvertebrate community composition, abundance and diversity

Macroinvertebrate communities are highly sensitive indicators of physical and chemical soil qualities. Their evaluation in field conditions is rather simple and could serve as proxy for soil-based ecosystem services that farmers and field technicians could use. We tested the hypothesis that an indicator of soil macroinvertebrate communities, with 14 taxonomic groups characterized at the order level, could be used in any region of the world to assess these communities. A synthetic indicator was calculated using data from 9 reference sites from tropical, subtropical and temperate regions, a set of 3694 data of the open access Macrofauna database and a new site for validation. Invertebrates were extracted with the standard ISO/TSBF methodology and characterized with a set of 14 large taxonomic units, plus an index of taxonomic richness and total density. At each of the 9 reference sites, 27 to 252 sample points, representing different types of plant covers and/or soil management options, were considered and compared with their respective local synthetic GISQ indicator values. These indicators, elaborated from Principal Component Analysis of the sample points data, are set to vary from 0.1 to 1.0 according to the composition, diversity and abundance of the community. Analyses showed great similarities among sites, with Factors 1 (from 21.9 to 36.9 % variance explained) expressing the overall abundance and diversity of the communities and Factors 2 (8.9 to 15.83 %) opposing sites with dominant soil ecosystem engineer populations (Earthworms, Ants, Termites and some Coleoptera) to sites dominated by litter transformer populations (Diplopoda, Isopoda and others). Indicator formulae were designed based on PCA analyses of each data set and a global formula was established with the Macrofauna database. Very high correlations (>0.95) were obtained among values calculated with local data set and the general formula calculated with data of the Macrofauna database, in 8 of 9 sites and in the validation site. We discuss the importance of having a single formula to transform data obtained with a simple standard field method in the building of public policies for soil-based ecosystem services payment.

REM-Based Indoor Localization with an Extra-Trees Regressor

As a widely established and accessible infrastructure, wireless local area networks (WLANs) have emerged as a viable option for indoor localization for both mobile and stationary users. However, WLANs present several challenges that must be fulfilled to achieve localization based on Wi-Fi signals and to obtain proper coverage prediction maps. This paper presents a study based on the application of extra-trees regression (ETR) for indoor localization using coverage prediction maps. The aim of the proposed method is to accurately estimate a user’s position within a radio environment map (REM) area using collected signal strength indicator (RSSI) values collected by a mobile robot. Our methodology consists of utilizing the RSSI collected values to construct the REM, which is then leveraged to create a dataset for indoor localization. This process involves tracking a user’s movements within a specific area of interest while considering a single access point. The proposed scheme explores various machine learning (ML) regression algorithms, with hyperparameter tuning carried out to optimize their performance through 10-fold cross-validation. To assess the REM, we employed metrics, such as the root mean square error, absolute error, and R-squared error. Additionally, we evaluated the indoor localization accuracy using location error metrics. Among the ML techniques assessed, our proposed ETR-based approach demonstrates the highest performance based on these error metrics. The combination of generating coverage maps and utilizing regression techniques for localization presents a potent approach for analyzing the radio frequency environment in indoor spaces.

An explainable hybrid deep learning architecture for WiFi-based indoor localization in Internet of Things environment

The indoor positioning service is one of the essential services needed in the Internet of Things ecosystem. Recently, many researchers have focused on the fingerprinting method, which is a method based on signal mapping with the Received Signal Strength Indicator (RSSI) values obtained from the WiFi access points. However, the fingerprinting method is particularly challenging due to some difficulties, such as RSSI variance over time, device diversity, and similarities of fingerprints in indoor networks. For this reason, machine learning and deep learning methods are used for many purposes, such as estimating the location of the building, floor, or the rooms. Detecting the location of a room or more than one reference point in a room becomes a more difficult problem because neighboring reference points’ fingerprints are very similar to each other. This study proposes a WiFi-based XAI-empowered deep learning architecture to predict the reference points in a room or corridor. We present a hybrid deep learning-based method that uses Long-Short-Term Memory to capture long-term dependencies between the signal features, and Convolutional Neural Network to extract local spatial signal patterns. Our deep learning aims to enrich fingerprinting data of each sample to capture more meaningful feature maps coming from different angles. Moreover, the method applies effective filtering and dimension scaling on the data to regulate the RSS values and capture more discriminative patterns using particle filter and sparse autoencoder. To provide local and global explanations for indoor localization estimations, the proposed architecture comprises two Explainable Artificial Intelligence techniques as Interpretable Model-Agnostic Explanations, and SHapley Additive exPlanations. The experimental results demonstrate that the proposed architecture achieves higher accuracy values for all datasets than the baseline deep learning methods.

Vulnerable node identification method for distribution networks based on complex networks and improved TOPSIS theory

AbstractA method for identifying vulnerable nodes in distribution networks is proposed, which is based on complex networks and optimized TOPSIS. This method aims to address the issues of one‐sided evaluation indicators and inaccurate indicator weights that are present in existing methods for identifying vulnerable nodes in distribution networks. Based on the theory of complex networks, a comprehensive set of vulnerability indicators for distribution network nodes is constructed by considering both the topology structure and system operation status of the distribution network. The TOPSIS comprehensive evaluation model for optimization is proposed to enhance the selection process of optimal and worst indicator values. The advantages and disadvantages of each indicator are characterized using Mahalanobis distance. The calculation of proximity is optimized by establishing a virtual negative ideal solution, which makes the identification of vulnerable nodes more reasonable. The simulation results demonstrate that this method is more effective in identifying vulnerable nodes in the power grid compared to traditional methods, and has significant practical applications.