Maximum Label Research Articles

A Collaborative Domain Adversarial Network for Unlabeled Bearing Fault Diagnosis

At present, data-driven fault diagnosis has made significant achievements. However, in actual industrial environments, labeled fault data are difficult to obtain, making the industrial application of intelligent fault diagnosis models very challenging. This limitation even prevents intelligent fault diagnosis algorithms from being applicable in real-world industrial settings. In light of this, this paper proposes a Collaborative Domain Adversarial Network (CDAN) method for the fault diagnosis of rolling bearings using unlabeled data. First, two types of feature extractors are employed to extract features from both the source and target domain samples, reducing signal redundancy and avoiding the loss of critical signal features. Second, the multi-kernel clustering algorithm is used to compute the differences in input feature values, create pseudo-labels for the target domain samples, and update the CDAN network parameters through backpropagation, enabling the network to extract domain-invariant features. Finally, to ensure that unlabeled target domain data can participate in network training, a pseudo-label strategy using the maximum probability label as the true label is employed, addressing the issue of unlabeled target domain data not being trainable and enhancing the model’s ability to acquire reliable diagnostic knowledge. This paper validates the CDAN using two publicly available datasets, CWRU and PU. Compared with four other advanced methods, the CDAN method improved the average recognition accuracy by 7.85% and 5.22%, respectively. This indirectly proves the effectiveness and superiority of the CDAN in identifying unlabeled bearing faults.

Development and In vitro and In vivo efficacy investigation of multifunctional, targeted, theranostic liposomes for imaging and photodynamic therapy of glioblastoma

The challenge of effectively diagnosing and treating glioblastoma, which has a high incidence and low survival rate, remains unresolved. Consequently, research efforts have increased to develop specific and effective diagnostic and therapeutic agents. In this study, N-acetyl glucosamine-modified, IR780-encapsulated, PEG-coated, nanosized, 68Ga-labeled, neutral, and positively charged theranostic liposomes were developed for GLUT1 targeting for PET/CT and NIR imaging and PDT/PTT of GBM. Characterization, in vitro release profile, stability, radiolabeling efficiency, and labeling stability were evaluated. In vitro cell uptake studies were conducted in RG2 and U87 GBM cell lines, NIR images were obtained in the RG2 and U87 cell lines, and fluorescence microscope images were obtained in the RG2 cell line. PDT/PTT activities were assessed after exposure to NIR light (808 nm, 0.8–1 W/cm2). Cytotoxicity was studied in RG2, U87, and L929 cell lines. In vivo studies were performed in GBM model nude mice. The liposomes had an optimum mean particle size (181–193 nm), high encapsulation efficiency (79–84 %), and zeta potential (−5 to −7 mV). The maximum 68Ga labeling efficiency was achieved with an incubation at 80 °C, pH: 3.5, and 5 min. Liposomes remained stable for 30 days at 4 °C. While the intracellular uptake of targeted formulations was higher than non-targeted ones, it was similar for positively charged and neutral formulations. In U87 and RG2 cell lines, cell viability remained above 50 % for liposomal formulations at a concentration of 1.5 μg/mL exposed to NIR light (808 nm, 0.8–1 W/cm2). The formulations showed significant PDT/PTT activity under NIR light and lower cytotoxicity in the L929 than in RG2 and U87 cell lines. In vivo bioluminescence images and biodistribution studies in U87 tumor-bearing nude mice revealed higher tumor uptake of targeted, IR780-encapsulated liposomal formulations in tumor tissue compared to non-targeted ones. Liposomal formulations showed higher tumor uptake than the free IR780 solution. The data suggest that targeted liposomes have potential as theranostic agents for PDT/PTT and multifunctional glioblastoma imaging.

The complexity of computing optimum labelings for temporal connectivity

A graph is temporally connected if a strict temporal path exists from every vertex u to every other vertex v. This paper studies temporal design problems for undirected temporally connected graphs. Given a connected undirected graph G, the goal is to determine the smallest total number of time-labels |λ| needed to ensure temporal connectivity, where |λ| denotes the sum, over all edges, of the size of the set of labels associated to an edge. The basic problem, called Minimum Labeling (ML) can be solved optimally in polynomial time. We introduce the Min. Aged Labeling (MAL) problem, which involves connecting the graph with an upper-bound on the maximum label, the Min. Steiner Labeling (MSL) problem, focusing on connecting specific important vertices, and the age-restricted version of MSL, Min. Aged Steiner Labeling (MASL). We show that MAL is NP-complete, MASL is W[1]-hard, and while MSL remains NP-hard, it is FPT with respect to the number of terminals.

Further results on the radio number for some construction of the path, complete, and complete bipartite graphs

Let G be a connected graph with diam(G). Then d(u,v) indicates the distance of u and v in G. For any pair of distinct vertices u,v of G, mapping from c:V(G)→N such that dG(u,v)+|c(u)−c(v)|≥diam(G)+1. The maximum label assigned to any vertex of G under a radio labeling c is known as the span of c. The radio number rn(G) of G is defined as the minimum span among all possible radio labelings of G. This paper aims to determine the radio number rn(c) for specific constructed families of graphs with diameter 3, such as P22(N(m,n)), K3,m(Knc), K3,m(nP3), K3,3(2K1,n), and K5(F3n).

Field efficacy of a biopesticide and a predatory mite for suppression of Scirtothrips dorsalis (Thysanoptera: Thripidae) in strawberry.

Chilli thrips, Scirtothrips dorsalis Hood (Thysanoptera: Thripidae) has emerged as a severe invasive pest of strawberry Fragaria × ananassa Duchesne in the United States. The objective of this study was to assess the field efficacy of a biopesticide and thrips predator, Amblyseius swirskii Athias-Henriot for S. dorsalis management in field grown strawberry compared to synthetic insecticide applications that are current industry standard (spinetoram) conducted at UF/IFAS GCREC, FL during 2021-2022 and 2022-2023 in a 2-year field study. The following treatments were applied in the field: (1) biopesticide, capsicum oleoresin extract + garlic oil + canola oil application at maximum label rate; (2) predatory mite of thrips, A. swirskii released at 30 predators per plot; (3) spinetoram applied at maximum label rate; and (4) biopesticide applied 24 h before release of A. swirskii. A control plot with no insecticide or predatory mite releases was maintained. Results show that the capsicum extract can be used for management of S. dorsalis, especially during the latter stages of strawberry field season when resistance to spinetoram is high. The field performance of A. swirskii was variable and extensive research is needed to highlight factors affecting field performance of predatory mites for thrips management.

A novel adaptive neighborhood rough sets based on sparrow search algorithm and feature selection

Neighborhood rough sets-based methods have been widely used for feature selection. However, the existing methods have some problems in neighborhood construction, such as the application of the same neighborhood radius for all samples. Thus, this paper proposed a novel adaptive neighborhood rough set model based on Sparrow Search Algorithm (SSA) to tackle the above problems, and applied the model to feature selection. First, we reconsidered the problems mentioned above from the viewpoint of optimization where the neighborhood radius of the target sample is considered as the solution to the optimization, and the maximum percentage of the label of the neighborhood formed is considered as the target to the optimization. Second, SSA is introduced to design the adaptive neighborhood construction to tackle the optimization problem where all candidate neighborhood radii of the target sample are considered as sparrows, the maximum and minimum distances between the target sample and other samples are considered as the search range, and the maximum label rate defined in this paper is considered as the search target. Then, a novel adaptive neighborhood rough set model is proposed by using the adaptive neighborhood construction. Third, we proposed a feature selection algorithm based on the adaptive neighborhood rough set model. Finally, the experimental results on seventeen datasets demonstrate the effectiveness of our algorithm. The running time of the proposed algorithm is at least one time less than classical algorithms under the condition that the classification performance is better, the accuracy increases 3% and the balanced accuracy increases 4%.

Environmental fate of monosodium methanearsonate (MSMA)-Part 2: Modeling sequestration and transformation.

Monosodium methanearsonate(MSMA), a sodium salt of monomethylarsonic acid (MMA),is a selective contact herbicide used for the control of a broad spectrum of weeds. In water, MSMA dissociates to ions of sodium (Na+) and monomethylarsonate (MMA-)thatis stable and does not transform abiotically. In soils characteristic of MSMA use, several simultaneous processes can occur: (1) microbial methylation of MMA to dimethylarsinic acid (DMA), (2) microbial demethylation of MMA to inorganic arsenic (iAs), (3) methylation of iAs to MMA, and (4) sorption and sequestration of MMA and its metabolites to soil minerals. Sequestered residues are residues that cannot be desorbed from soil in environmental conditions. Sequestration is rapid in the initial several days after MSMA application and continues at a progressively slower rate over time. Once sequestered, MMA and its metabolites are inaccessible to soil microorganisms and cannot be transformed. The rate and extent of the sorption and sequestration as well as the mobility of MMA and its metabolites depend on the local edaphic conditions. In typical MSMA use areas, the variability of the edaphic conditions is constrained. The goal of this research was to estimate the amount of iAs potentially added to drinking water as a result of the use of MSMA, with models and scenarios developed by the US Environmental Protection Agency for pesticide risk assessment. In this project, the estimated drinking water concentrations (EDWCs) for iAs were assessed as the average concentration in the reservoir over a 30-year simulation with annual applications of MSMA at maximum label rates. When the total area of suitable land was assumed to be treated, EDWCs ranged from <0.001 to 0.12 µg/L. When high estimates of actually treated acreage are considered, the EDWCs are below 0.06 µg/L across all scenarios. Integr Environ Assess Manag 2024;20:2076-2087. © 2024 The Author(s). Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Solitary fibrous tumor of the prostate: Case report and review of the literature

Solitary Fibrous Tumor (SFT), typically found in the pleura, is exceptionally rare in the prostate. We present the case of a 54-year-old man with prostatic SFT, initially revealed as an abdominopelvic mass. Subsequent investigations shown a vascular tumor. The pathological examination found a 23 cm tumor originating from the prostate, composed of short spindle-shaped and polygonal cells with mild nuclear atypia. Occasional mitoses were observed, with vascular invasion. Immunohistochemically, the tumor cells strongly expressed CD34 and STAT6. The maximum Ki-67 labeling index for the tumor cells was 4%. This case report has highlighted one of the rare occurrences of solitary fibrous tumor. A comprehensive microscopic examination paired with an immunohistochemical analysis will be necessary to establish an accurate diagnosis.

Solitary Fibrous Tumor of the Prostate: Case Report and Review of the Literature

Solitary fibrous tumor (SFT), typically found in the pleura, is exceptionally rare in the prostate. We present the case of a 54-year-old man with prostatic SFT, initially revealed as an abdominopelvic mass. Subsequent investigations shown a vascular tumor. The pathological examination found a 23-cm tumor originating from the prostate, composed of short spindle-shaped and polygonal cells with mild nuclear atypia. Occasional mitoses were observed, with vascular invasion. Immunohistochemically, the tumor cells strongly expressed CD34 and STAT6. The maximum Ki-67 labeling index for the tumor cells was 4%. This case report has highlighted one of the rare occurrences of solitary fibrous tumor. A comprehensive microscopic examination paired with an immunohistochemical analysis will be necessary to establish an accurate diagnosis.

Management Efficacy and Response to Post-Application Precipitation of Fungicides for Southern Stem Rot of Peanut and Evaluation of Co-Application with Micronized Sulfur

Southern stem rot (SSR) is caused by Athelia rolfsii and is an economically important disease of peanut (Arachis hypogaea L.). Application of protectant fungicides is an effective management component for reducing levels of this soil-borne disease. The majority of peanut hectarage in South Carolina and Mississippi is rainfed. Timely precipitation has the potential to aid the movement of foliar-applied fungicides through the canopy and into contact with soil interfaces where SSR infections occur. Questions have arisen as to the quantitative relationship of post-application precipitation and fungicide-active ingredient efficacy in managing SSR and protecting associated pod yield potentials. To examine this, fungicide efficacy experiments were screened for inclusion in a meta-analysis, from which eleven experiments conducted from 2015 to 2023 were selected and paired with environmental data from nearby weather stations. Precipitation during the two days following fungicide application was associated with significant reduction in SSR incidence (logit rate of −0.0039/mm) and increased pod yield (log slope of 0.0028/mm). Active ingredient interactions with precipitation among pod yield but not SSR incidence data were present for benzovindiflupyr plus azoxystrobin, flutolanil, and tebuconazole. Fungicides with the greatest levels of control per application at maximum label rates were inpyrfluxam (18.8%), benzovindiflupyr plus azoxystrobin (15.4%), flutolanil (12.3%), and prothioconazole plus tebuconazole (10.5%). Micronized sulfur neither contributed to SSR control nor pod yield increase. Tebuconazole was associated with the greatest % SSR control per fungicide product cost (0.47%/$/ha/application) but was also the treatment with the least amount of control (3.5%) at its maximum label rate. Maximum label rates of benzovindiflupyr plus azoxystrobin (USD 637) and inpyrfluxam (USD 548) were estimated as conferring the greatest returns over the chlorothalonil-only control. Results serve as a helpful reference for farmers and practitioners in selecting fungicide management options and targeting application times, as feasible, to utilize natural precipitation to improve management outcomes.

An Inclusive Distance Irregularity Strength of n-ary Tree

An inclusive distance vertex irregular labelling of a simple graph G is a function of the vertex set of to positive integer set such that the sum of its vertex label and the labels of all vertices adjacent to the vertex are distinct. The minimum of maximum label of the vertices is said to be inclusive distance irregularity strength of G, denoted by dis(G). The purpose of this research is showing that dis(T_{n,2})= (n^2+2)/2 where T_{n,2} is a complete n-ary tree to level two.

EVALUATION OF THERMAL FOGGER FOR EFFECTIVENESS OF LARVICIDE-ADULTICIDE MIXTURE AGAINST AEDES AEGYPTI

A hand-held thermal fogger was evaluated to spray a mixture of adulticide (Aqualuer 20-20® containing permethrin and piperonyl butoxide) and a biological larvicide (VectoBac®12AS, containing Bacillus thuringiensis subspecies israelensis). Adulticide was applied at maximum label rate of 37 mL/ha while larvicide rates were 0.58, 1.76, 2.64, and 3.50 L/ha (Maximum label rate 2.34 L/ha). Two rows, 7.6 m apart, of bioassay cages containing susceptible 25, 5-7 days old female Aedes aegypti were used to assess effectiveness of the adulticide. Along with each cage were two 473 mL empty plastic cups at 0 and 1.3 m above ground to collect the larvicide. Two control cages and two empty cups were placed upwind in the field for five minutes and removed before the spray. The study was conducted in the evening with five separated replications of a rate. The exposed cages and cups were retrieved from the field and brought back to the laboratory for further observations and tests to determine mortality at 24 and 48 h, respectively. All the adults in all treatment cages and all tests died within 24 h of the spray application. In the lab, larval mortality was assessed by introducing Ae. aegypti larvae, where mortality decreased with increasing distance from the spray line and increased with increasing application rate. The larval mortality at all distances was strongly correlated with application rate (R2 = 0.98). The highest rate used produced 64 -95% larval mortality at all distances. The results indicate that Aqualuer 20-20 and VectoBac 12AS can be applied simultaneously as a mixture achieving complete adult control and considerable larval control.

A mixture of mesotrione and atrazine harms adults and larvae of the predatory wasp Polistes satan

Herbicides have been intensively used for weed control, raising concerns about their potentially adverse effects on non-target organisms. Research on the effects of these common agrochemicals on beneficial insects and the ecosystem services they provide (e.g., predation and pollination) is scarce. Therefore, we tested whether a commercial formulation comprising a mixture of mesotrione and atrazine was detrimental to adult females and larvae of the Neotropical predatory social wasp Polistes satan, which is an effective natural enemy of crop pests. Wasps were individually fed syrups contaminated with different concentrations of the herbicide above and below the maximum label rate (MLR = 12 mL/L). Survival was assessed. The locomotor activity, immune response, and midgut morphology of adults as well as the immune response of the larvae were also studied. Herbicide concentrations far above the MLR (12, 40, and 100 times) caused adult mortality, whereas lower concentrations (0.5, 1, and 6 times) did not. Herbicide exposure at 0.5 to 12 times the MLR increased adult activity. Adult exposure at 0.1 or 0.5 times the MLR did not affect melanotic encapsulation of foreign bodies but led to changes in the morphology of the midgut epithelium and peritrophic matrix. In larvae, the ingestion of herbicide at 0.1 or 0.2 times the MLR (corresponding to 9.6 and 19.2 ng of herbicide per individual) did not cause mortality but decreased their melanization-encapsulation response. Increased locomotor activity in herbicide-exposed adults can affect their foraging activity. The altered midgut morphology of adults coupled with the decreased immune response in larvae caused by herbicide exposure at realistic concentrations can increase the susceptibility of wasps to infections. Therefore, herbicides are toxic to predatory wasps.

Using path coloring of graphs for communication in social networks

An L (p1, p2, p3, … , pm)- labeling of a graph G, has the vertices of G assigned with non-negative integers, such that the vertices at distance j should have at least pj as their label difference. If m = 3 and p1 = 3, p2 = 2, p3 = 1, it is called an L (3, 2, 1)-labeling which is widely studied in the literature. In this paper, we define an L (3, 2, 1)-path coloring of G as a labeling g : V (G) → Z+ such that between every pair of vertices there exists at least one path P where in the labeling restricted to this path is an L (3, 2, 1)-labeling. Among the labels assigned to any vertex of G under g, the maximum label is called the span of g. The L (3, 2, 1)-connection number of a graph G, denoted by k3c (G) is defined as the minimum value of span of g taken over all such labelings g. We call graphs with the special property that k3c (G) = |V (G) | as L (3, 2, 1)-path graceful. In this paper, we obtain k3c (G) of graphs that possess a Hamiltonian path and carry forward the discussion to certain classes of graphs which do not possess a Hamiltonian path, which is novel to this paper. Although different kinds of labeling are studied in the literature with different mathematical constraints imposed, the idea of showing the existence of a graph with a given number as its minimum labeling number has rarely been addressed. We show that given any positive integer, there always exists an L (3, 2, 1)-path graceful graph with the given integer as its k3c (G), thus addressing the inverse question. Finally exploiting the fact that there is no gap on the k3c (G) number line, we give an application of path colorings for secure communication on social networking sites. Efforts to deploy graph coloring in task scheduling, interference-free transmission, etc have been dealt by earlier researchers. In this paper, we deploy the L (3, 2, 1)-path coloring technique defined by us for secure communication in social networks, which has not been dealt with so far.

Effects of select herbicides for management of American lotus, white waterlily, and watershield

Literature describing effective control measures for the floating-leaved plants American lotus (Nelumbo lutea Willd.), white waterlily (Nymphaea odorata Aiton), and watershield (Brasenia schreberi J.F. Gmel.) is minimal as these are usually considered as desirable species. However, floating-leaved plants can cause ecological, economic, and social problems when undergoing demographic expansions, usually following alterations of natural hydrologic cycles. Therefore, a mesocosm trial was conducted to determine the potential of foliar applications of seven aquatic herbicides to reduce abundance of the three target species at maximum and half-maximum label rates. Three of the herbicides (glyphosate, imazamox, and florpyrauxifen-benzyl) provided short- and long-term suppression (.75% reduction) of white waterlily and watershield leaf density or biomass. As a followup trial, field work was conducted using glyphosate, imazamox, and florpyrauxifen-benzyl to determine plant response to these herbicides in a natural setting. All herbicides resulted in long-term (52 wk after treatment) leaf density reduction of white waterlily (64 to 100% reduction) and watershield (46 to 75% reduction; except 2.83 kg ae ha 1 glyphosate) in field sites while the abundance of American lotus increased. Reduction of white waterlily and watershield may have reduced competition thereby favoring higher abundance of lotus. Regardless, long-term (52-wk) reduction of white waterlily and watershield suggest the potential for these herbicides as operational management tools for nuisance populations of these species. Future work should evaluate chemical techniques for control of American lotus, where both timing of leaf emergence and potential interactions with other plant species must be considered in the design of those studies.

Field Evaluation of Fyfanon Ew Against Aedes Aegypti: A Low Odor Ultra-Low Volume Formulation of Malathion.

A low odor formulation of ultra-low volume (ULV) malathion (Fyfanon EW®) mosquito adulticide was evaluated in the field for its efficacy using caged female Aedes aegypti. Cages were placed in three rows, 30 m apart at 30, 60, and 90 m from the spray line. The product was applied at the manufacturer's suggested operational rate of 0.28 liter/min (9.5 fl oz/min) and at the maximum label rate of 0.37 liter/min (12.6 fl oz/min) with a Guardian 190ES truck mounted ULV sprayer. At 1 h post-treatment for the manufacturer's suggested operational rate, adult mortality ranged from 85% at 30 m to 46% at 90 m (overall average 65.5%). At 24 h post-treatment, mortality was significantly greater at each distance with complete control of caged mosquitoes at 30 m and >95% at 90 m. Overall, 24-h average mortality at this rate was 96.8%. At the maximum label rate, mosquito mortality at 1 h was considerably greater at all distances and ranged from about 89% to 75% with an overall average of 84.3%. At 24 h post-treatment, complete mortality was recorded at all transect distances at this higher rate. In conclusion, our results showed that at 24 h, Fyfanon EW® was considered very effective when applied by ULV truck mounted ground equipment for area-wide control of mosquitoes.

Effects of Insecticide Drench Application against Immatures of Systena frontalis in Container-grown Hydrangea paniculata

Systena frontalis (F.) (Coleoptera: Chrysomelidae), commonly referred to as the redheaded flea beetle, is a serious pest in container nurseries, as adult feeding defoliates nursery crops and affects plant salability. Because the foliar application of insecticides provides inconsistent efficacy, additional and alternative control tactics are sought to target immatures of this pest in growing media. Thus, the objective was to determine the effects of non-neonicotinoid insecticides applied as a drench to growing media on immatures of S. frontalis. In 2021 and 2022, nine active ingredients were evaluated in four trials in a Georgia nursery and at a Virginia research and extension center. If available, the maximum label rates for flea beetles or other coleopteran pests were applied once to Hydrangea paniculata Siebold containers (11.4 L, 3 gal) as a drench application. The emergence of S. frontalis adults from treated growing media and foliar feeding damage was lower for the tetraniliprole (TetrinoTM) and spinetoram + sulfoxaflor (XXpire®) treatments than for nontreated plants. Cyclaniliprole (SarisaTM) and chlorantraniliprole (Acelepryn®) suppressed S. frontalis adult eclosion with less feeding damage than the nontreated plants. Tetraniliprole, spinetoram + sulfoxaflor, and cyclaniliprole are not labeled for drench application. Dinotefuran (Safari®) effectively reduced adult emergence and feeding damage. Species used in this study: Redheaded flea beetle, Systena frontalis (F.); panicled hydrangea, Hydrangea paniculata Siebold. Chemicals used in this study: Cyantraniliprole (Mainspring®GNL), chlorantraniliprole (Acelepryn®), tetraniliprole (TetrinoTM), cyclaniliprole (SarisaTM), Spinetoram + Sulfoxaflor (XXpire®), tolfenpyrad (Apta®), Chromobacterium (Grandevo®CG), flupyradifurone (AltusTM), dinotefuran (Zylam® Liquid, Safari® 20G), and polyterpenes pinene (NuFilm® P).

Risk of control failure to insecticides malathion, profenophos + cypermethrin mixture, and fipronil in boll weevil (Coleoptera: Curculionidae) populations from Bahia, Brazil

BackgroundTo control the boll weevil Anthonomus grandis grandis (Coleoptera: Curculionidae), a key pest of cotton in the Americas, insecticides have been intensively used to manage their populations, increasing selection pressure for resistant populations. Thus, this study aimed to detect insecticide resistance and assess insecticide control failure likelihood of boll weevil populations exposed to malathion, profenophos + cypermethrin, and fipronil insecticides.ResultsTwelve populations of the boll weevil were collected from commercial cotton fileds of the state of Bahia, northeastern Brazil. These populations were exposed to malathion, profenophos + cypermethrin mixture, and fipronil, at their respective maximum label dose for field applications. Three replicates of 10 adult beetles were exposed to the insecticides and mortality was recorded after 24 h treatment. The control failure likelihood was determined after 48 h. Highest median lethal times (LT50) were observed for malathion and the profenophos + cypermethrin mixture. Resistance to at least one insecticide was detected in 11 populations; three populations were resistant to malathion and profenophos + cypermethrin; seven were resistant to all insecticides tested. The resistance levels were low (< 10-fold) for the three insecticides. Among 12 populations tested, 58% of them exhibited significant risk of control failure for the insecticides malathion and profenophos + cypermethrin. The insecticide fipronil was efficient for the control of the boll weevil in 83% of the populations.ConclusionsThe results confirm the significant risk of insecticide control failure in the boll weevil populations to the main compounds used in the region. Thus, proper insecticide resistance management plans are necessary for the boll weevil in the region, particularly for malathion and profenophos + cypermethrin insecticides.

Dynamic budget allocation for sparsely labeled drifting data streams

Learning from non-stationary data streams is inherently challenging due to their evolving nature and concept drift. Furthermore, the assumption that all instances come labeled is often impractical in real-world applications. Many strategies have been proposed to tackle learning from sparsely labeled data streams. However, they typically rely on fixed labeling budgets, which can be a limitation in the context of drifting data streams. In this study, we introduce a novel active learning strategy that dynamically manages the labeling budget to optimize its utilization and adapt promptly to concept drift. Our approach continuously monitors the data stream for concept drift, and upon detecting such drift, it dynamically increases the maximum labeling budget for a predefined time window. This adjustment provides the classifier with more flexibility to adapt to the new concept. We conducted experiments using 7 synthetic data generators encompassing various drifting scenarios and 7 real-world data streams with different labeling budgets. Our results demonstrate that offering a flexible budget to the classifier can significantly enhance performance compared to merely increasing a fixed budget. Notably, our strategy outperformed state-of-the-art active learning strategies, all while maintaining a comparable or lower number of labeled instances. Experiments are available at https://github.com/gabrieljaguiar/DBAL.

Multi-label feature selection via maximum dynamic correlation change and minimum label redundancy

Multi-label feature selection via maximum dynamic correlation change and minimum label redundancy