We overview recent progress in growth aspects of group III-nitride heterostructures for deep ultraviolet (DUV) light-emitting diodes (LEDs), with particular emphasis on the growth approaches for attaining high-quality AlN and high Al-molar fraction AlGaN. The discussion commences with the introduction of the current status of group III-nitride DUV LEDs and the remaining challenges. This segues into discussion of LED designs enabling high device performance followed by the review of advances in the methods for the growth of bulk single crystal AlN intended as a native substrate together with a discussion of its UV transparency. It should be stated, however, that due to the high-cost of bulk AlN substrates at the time of this writing, the growth of DUV LEDs on foreign substrates such as sapphire still dominates the field. On the deposition front, the heteroepitaxial growth approaches incorporate high-temperature metal organic chemical vapor deposition (MOCVD) and pulsed-flow growth, a variant of MOCVD, with the overarching goal of enhancing adatom surface mobility, and thus epitaxial lateral overgrowth which culminates in minimization the effect of lattice- and thermal-mismatches. This is followed by addressing the benefits of pseudomorphic growth of strained high Al-molar fraction AlGaN on AlN. Finally, methods utilized to enhance both p- and n-type conductivity of high Al-molar fraction AlGaN are reviewed.

Deep-ultraviolet (UV) light-emitting diodes (LEDs) based on AlGaN crystals have low light-emission efficiency; therefore, there is a need to improve this light-emission efficiency for a wide range of applications such as water and air sterilizations. UV-light-transparent device structures are considered one of the many solutions toward increasing light output power. To this end, the present study focused on developing a transparent AlGaN-based tunnel junction (TJ) as the anode of a deep-UV LED. Deep-UV LEDs composed of n+/p+-type AlGaN TJs were fabricated under the growth condition that reduced the carrier compensation in the n+-type AlGaN layers. The operating voltage was 10.8 V under the direct current (DC) operation of 63 A/cm2. In addition, magnesium zinc oxide (MgZnO)/Al reflective electrodes were fabricated to enhance the output power of the AlGaN homoepitaxial TJ LED. The output power was 57.3 mW under a DC operation of 63 A/cm2, and it was 1.7 times higher than that realized using the conventional Ti/Al electrodes. The combination of the AlGaN-based TJ and MgZnO/Al reflective contact allows further improvement of the light output power. This study confirms that the AlGaN TJ is a promising UV-transmittance structure that can obtain a high light-extraction efficiency.

The Dead Sea basin is the lowest terrestrial site on the globe and is internationally recognized as a photoclimatotherapy center. Since the last century, questions raised regarding the possible presence of a unique incident ultraviolet irradiation, allowing successful treatment of psoriasis, atopic dermatitis and other dermatological diseases. Aim: Determine the characteristics of the solar ultraviolet irradiation and understand the mechanism of action of photoclimatotherapy while applying the results to clinical protocols of treatment. Methods: A meteorological station was established at the Dead Sea basin to continuously measure global, UVB and UVA irradiation. The same irradiation parameters are also being monitored continuously by a set of identical ultraviolet irradiation instruments installed on the campus of the Ben-Gurion University of the Negev, in Beer Sheva. Results: This study details the results of these long-term measurements, ae well as their correlation with the success obtained by clinicians treating psoriasis patients. Conclusions: A database of more than 25 years has enabled the medical staff to establish tailor-made protocols for sun-exposure time intervals as a function of particular month and hour of day. The availability of such information has significantly improved the results of photoclimatotherapy for psoriasis and at the same time increasing the safety of sun-exposure at the Dead Sea.

In this study we focus on measurements and modeled UV index at the region of Athens, Greece, during a period of a low ozone event. During the period of 12 to 19 of May 2020, total column ozone (TOC) showed extremely low values 35-55 DU (up to 15%) decrease from the climatic mean (being lower than the -2σ). This condition favors the increase of UV erythemal irradiance, since stratospheric ozone is the most important attenuator at the UVB spectral region. A parallel intrusion of Saharan Dust aerosols in the region has masked a large part of the low ozone effect on UV irradiance. In order to investigate the event, we have used spectral solar irradiance measurements from the Precision Solar Radiometer (PSR), total column ozone from the BREWER spectrophotometer and Radiative Transfer Model (RTM) calculations. Model calculations of UV Index (UVI) showed an increase of ~30% compared to the long term normal UVI due to the low TOC while at the same time and for particular days, aerosols masked this effect by ~20%. The study points out the importance of accurate measurements or forecasts of both ozone and aerosols when deriving UVI under unusual low ozone-high aerosol conditions.

Abstract: Ultraviolet (UV) induces skin photoaging, which is characterized by thickening, wrinkling, pigmentation, and dryness. Astaxanthin, a ketocarotenoid from Haematococcus pluvialis, has been extensively studied with respect to its possible effect on skin health as well as UV protection. In addition, astaxanthin attenuates increases in the generation of reactive oxygen species (ROS) and capillary regression of skeletal muscle. In the present study, we investigated whether astaxanthin would protect UV-induced photoaging and capillary regression in the skin of HR-1 hairless mice. UV induces wrinkle formation, thickness and capillary regression in dermis of hairless mice and the administration of astaxanthin decreased the UV-induced wrinkle formation, skin thickness, and increase in collagen fibers in skin. Astaxanthin supplementation also inhibited the levels of ROS generation and attenuated the decreases in wrinkle formation, thickness and capillary number in the skin. We also found an inverse correlation between wrinkling and capillary number, and the photoaging associated with capillary regression in skin. These results suggest that astaxanthin can protect against photoaging caused by ultraviolet irradiation and the effects of astaxanthin in photoaging inhibition may be associated with the protection of capillary regression in skin.

Ultraviolet imaging has been applied in volcanology over the last ten years or so. This provides considerably higher temporal and spatial resolution volcanic gas emission rate data than available previously, enabling the volcanology community to investigate a range of far faster plume degassing processes, than achievable hitherto. To date this has covered rapid oscillations in passive degassing through conduits and lava lakes, as well as puffing and explosions, facilitating exciting connections to be made for the first time between previously rather separate sub disciplines of volcanology. Firstly, there has been corroboration between geophysical and degassing datasets at ≈ 1 Hz expediting more holistic investigations of volcanic source-process behaviour. Secondly, there has been the combination of surface observations of gas release, with fluid dynamic models (numerical, mathematical and laboratory) for gas flow in conduits, in attempts to link subterranean driving flow processes to surface activity types. There has also been considerable research and development concerning the technique itself, covering error analysis and most recently adaptation of smartphone sensors for this application, to deliver gas fluxes at a significantly lower instrumental price point than possible previously. At this decadal juncture in the application of UV imaging in volcanology, this article provides an overview of what has been achieved to date as well as a forward look to potential future research directions, in particular covering the first use of UV cameras to generate volcanic gas composition ratio imagery.

It is familiar that the Casimir self-energy of a homogeneous dielectric ball is divergent, although a finite self-energy can be extracted through second order in the deviation of the permittivity from the vacuum value. The exception occurs when the speed of light inside the spherical boundary is the same as that outside, so the self-energy of a perfectly conducting spherical shell is finite, as is the energy of a dielectric-diamagnetic sphere with $\varepsilon\mu=1$, a so-called isorefractive or diaphanous ball. Here we re-examine that example, and attempt to extend it to an electromagnetic $\delta$-function sphere, where the electric and magnetic couplings are equal and opposite. Unfortunately, although the energy expression is superficially ultraviolet finite, additional divergences appear that render it difficult to extract a meaningful result in general, but some limited results are presented.

In this study, we present comprehensive climatologies of effective ultraviolet (UV) quantities and photosynthetically active radiation (PAR) over Cyprus for the period 2004 to 2023, leveraging the synergy of earth observation (EO) data and radiative transfer model simulations. The EO dataset, encompassing satellite and re-analysis data for aerosols, total ozone column, and water vapor, alongside cloud modification factors, to capture the nuanced dynamics of Cyprus's atmospheric conditions. With a temporal resolution of 15 minutes and a spatial of 0.05°x0.05°, these climatologies undergo rigorous validation against established satellite datasets and are further evaluated through comparisons with ground-based global horizontal irradiance measurements provided by the Meteorological Office of Cyprus. This dual-method validation approach not only underscores the models' accuracy but also highlights their proficiency in capturing intra-daily cloud coverage variations. Our analysis extends to investigating the long-term trends of these solar radiation quantities, examining their interplay with changes in cloud attenuation, aerosol optical depth (AOD), and total ozone column (TOC). Significant decreasing trends in the noon ultraviolet index (UVI), of -2 to -4% per decade have been found in Autumn, especially marked on the island’s Northeastern part, mainly originating from the (significant) positive trends in TOC. The significant decreasing trends in TOC, of -2 to -3% per decade that were found in Spring do not result in correspondingly significant positive trends in the noon UVI since variations in cloudiness and aerosols also have a strong impact on the UVI in this season. The seasonal trends in the Daylight Integral (DLI) were generally not significant. These insights provide a valuable foundation for further studies aimed at developing public health strategies and enhancing agricultural productivity, highlighting the critical importance of accurate and high-resolution climatological data.

Quality-changed behavior of ultraviolet light absorber (UVA: UV-326) in polymers (PP, HDPE, LDPE, PLA and PS) over time during degradation was studied with an enhanced degradation method (EDM) using sulfate ion radical in seawater. EDM was employed to homogeneously degrade the entire polymer samples containing the UVA. The PP and PS samples containing 5-phr UVA films whitened rapidly due to formation of numerous grooves or crushed particles. The UVA loss rate of PS with the higher Tg was much slower. The crystalline polymers, with the exception of PS, were similar in the behavior of the change in UVA loss rate with respect to degradation time. The significant increase in initial loss rate observed during EDM degradation was due to microplasticization. A similar increase in microplasticization rate occurred with the PS, but the intermolecular interaction between UVA and PS did not result in as pronounced its increase in loss rate as with other polymers. The UVA chemical structure was not altered by EDM degradation. These results revealed that the UVA leaching from the polymer matrix was the primary cause of the loss.

Krill oil (KO) shows promise as a natural marine-derived ingredient for improving skin health. This study investigated its antioxidant, anti-inflammatory, anti-wrinkle, and moisturizing effects on skin cells and UVB-induced skin photoaging in hairless mice. In vitro assays on HDF, HaCaT, and B16/F10 cells, and in vivo experiments on 66 hairless mice, were conducted. Mice received oral KO administration (100, 200, or 400 mg/kg) once a day for 15 weeks and UVB radiation three times a week. In vitro, KO significantly countered UVB-induced oxidative stress, reduced wrinkles, and prevented skin water loss by enhancing collagen and hyaluronic synthesis. In vivo, all KO dosages showed dose-dependent inhibition of oxidative stress-induced inflammatory photoaging-related skin changes. Skin mRNA expressions for hyaluronan synthesis and collagen synthesis genes also increased dose-dependently after KO treatment. Histopathological analysis confirmed that Krill Oil (KO) ameliorated the damage caused by UVB-irradiated skin tissues. These findings suggest that KO may be a valuable intervention to mitigate UVB-induced skin photoaging and address various skin concerns.

Ultraviolet (UV) radiation has both harmful and beneficial effects on human health. It can cause skin damage and cancer, but also provides the primary source of vitamin D. Additionally, UV radiation affects energy metabolism in mice with metabolic diseases and has protective effects on hypertension and cardiovascular diseases.Metabolic Syndrome is a collection of metabolic dysfunctions such as dyslipidemia, hypertension, hyperglycemia, abdominal/central obesity, and insulin resistance. Chronic UVR exposure suppressed obesity and type 2 diabetes in high-fat diet-fed mice, while vitamin D supplementation did not replicate these effects. On the other hand, topical application of nitric oxide (NO) donors replicated UV effects on mice, and NO scavengers prevented the positive impact of UV. UVR may prevent the development of obesity and metabolic syndrome through mechanisms that depend on UVR-induced NO, not vitamin D. Exposure to sunshine has a protective impact on blood pressure and cardiovascular disease. Although lower vitamin D concentration is linked to increased hypertension and the incidence of CVD, oral vitamin D supplementation does not decrease blood pressure or the risk of CVD, indicating that vitamin D may not mediate the beneficial effects of sun exposure. Instead, NO plays a crucial role as an endogenous vasodilator, produced by the vascular endothelium. Solar UVA may release nitrogen oxides from skin storage into the bloodstream, lowering blood pressure and cardiovascular mortality.In conclusion, UVR exposure could be a promising non-pharmacological intervention for metabolic syndrome, hypertension, and CVD prevention, and NO may play a crucial role in mediating these effects. Further research is needed to explore the precise mechanisms and identify the optimal doses and exposure times of UVR.

It is commonly believed that exposing Cannabis sativa (cannabis) plants to ultraviolet (UV) radiation can enhance Δ⁹-tetrahydrocannabinol (Δ⁹-THC) concentrations in female inflorescences and associated foliar tissues. However, a lack of published scientific studies has left knowledge-gaps in the effects of UV on cannabis that must be elucidated before UV can be utilized as a horticultural management tool in commercial cannabis production. In this study we investigated the effects of UV exposure level on photosynthesis, growth, inflorescence yield, and secondary metabolite composition of two indoor-grown cannabis cultivars: ‘Low Tide’ (LT) and ‘Breaking Wave’ (BW). After growing vegetatively for 2 weeks under a canopy-level photosynthetic photon flux density (PPFD) of ≈225 μmol·m^–2·s^–1 in an 18-h light/6-h dark photoperiod, plants were grown for 9 weeks in a 12-h light/12-h dark “flowering” photoperiod under a canopy-level PPFD of ≈400 µmol·m^–2·s^–1 and 3.5 h·d^–1 of supplemental UV radiation with UV photon flux densities (UV-PFD) ranging from 0.01 to 0.8 μmol·m^–2·s^–1 provided by light-emitting diodes (LEDs) with a peak wavelength of 287 nm (i.e., biologically-effective UV doses of 0.16 to 13 kJ·m^–2·d^–1). The severity of UV-induced morphology (e.g., whole-plant size and leaf size reductions, leaf malformations, and stigma browning) and physiology (e.g., reduced leaf photosynthetic rate and reduced F_v/F_m) symptoms worsened as UV exposure level increased. While the proportion of dry inflorescence yield that was derived from apical tissues decreased in both cultivars with increasing UV exposure level, total dry inflorescence yield only decreased in LT. The equivalent Δ⁹-THC and cannabidiol (CBD) concentrations also decreased in LT inflorescences with increasing UV exposure level. While the total terpene content in inflorescences decreased with increasing UV exposure level in both cultivars, the relative concentrations of individual terpenes varied by cultivar. The potential for using UV to enhance cannabis quality must still be confirmed before it can be used as a production tool for modern, indoor-grown cannabis cultivars.

Powerful emitters of the ultraviolet C (UVC) light in the wavelength range of 230-280nm are necessary for the development of effective and safe optical disinfection technologies, high-sensitive optical spectroscopy and non-line-of-sight optical communication. This review considers such UVC-emitters with electron-beam pumping of heterostructures with quantum wells in the (Al,Ga)N material system. The important advantages of these emitters include the absence of the critical problem of p-type doping and the possibility of achieving record (up to several tens of watts for peak values) output optical power values in the UVC range. The review consistently considers about a decade of world experience in the implementation of various UV emitters with various types of thermionic, field-emission, and plasma-cathode electron guns (sources) used to excite various designs of active (light-emitting) regions in heterostructures with quantum wells AlxGa1-xN/AlyGa1-yN (x = 0 − 0.5, y = 0.6 − 1) fabricated either by metal-organic chemical vapor deposition or by plasma-activated molecular beam epitaxy. Special attention is paid to the production of heterostructures with multiple quantum wells/two-dimensional(2D) quantum disks GaN/AlN with a monolayer (1ML ~ 0.25nm) thickness, which ensures a high internal quantum efficiency of radiative recombination in the UVC range, low elastic stresses in heterostructures, and a high output UVC-optical powers.

The global population is at risk of vitamin D deficiency due to low exposure to sunlight and low intake of the vitamin through diet. The aim was to investigate in women the association between vitamin D status and parathyroid hormone (PTH), ultraviolet radiation, lifestyle, ethnicity, social conditions, and residential greenness. A 1-year longitudinal study assessed vitamin D status in 309 women, latitude 51° 14' N. Blood samples were taken four times throughout the year for analysis of 25(OH)D and serum PTH concentration. After each seasonal visit, the individuals completed 4-day diet diaries and used two dosimeter badges for 1 week to estimate weekly UVR exposure. A questionnaire was applied to provide information about lifestyle and their ethnicity. Residential greenness was measured by Normalized Difference Vegetation Index (NDVI), within a 1000 m radius around each participant’s home address. Women living in greener spaces were more likely to have improved vitamin D status (RR: 1.51; 95%CI: 1.13 – 2.02), as well as those who were more exposed to UVR (RR: 2.05; 95%CI: 1.44 – 2.92). Our results provided a first insight into the connection between vitamin D, residential greenness, and lifestyle in a region of temperate climate and with a high degree of urbanization.

The surface behavior of the ZnO-based films could be modulated via a postannealing and ultraviolet (UV) irradiation with different powers and time, respectively. These present results could provide modulate the microstructure related in grain-size distribution and photocatalytic behavior for potential guide in the field of wide bandgap semiconducting oxides. The ZnO films were prepared onto Corning-1737 glass substrates by using radio-frequency magnetron sputtering without supplying oxygen source at room temperature. For the purpose of obtaining modulable grain microstructures, the as-prepared ZnO films (Z0) were treated via a postannealing modification in vacuum furnace at 300°C for 30 minutes after deposition (Z300) accompanied with the adjustable internal stress. The contact angle (CA) value of ZnO film reduced from 95° to 68° was owning to the different grain microstructure accompanied by a change in size variation. In addition, the UV light with different irradiation powers could also be used to improve the hydrophilicity varied from hydrophobic status to superhydrophilic status due to the desirable surface characteristics of the photocatalytic action. In addition, the photocatalytic activity of ZnO film exhibited efficient photodegradation of methylene blue (MB) under UV irradiation, with a chemical reaction constant of 2.93×10-3 min−1. In this present work, we demonstrated that the CA value of the ZnO films not only caused from hydrophobic to hydrophilic status accompanied by a change in grain size combined with internal stress but also induced by the UV light irradiation combined with photocatalytic activity simultaneously. On the other hand, the enhanced surface plasmonic resonance could be observed that is due to couple electron and photon oscillations and can be generated at the interface between a flat, continuous Pt capping nanolayer. This designed structure could also be considered as a Pt electrode pattern onto ZnO (metal Pt/ ceramic ZnO) for multifunctional heterostructured sensors and devices in near future.

Australia and New Zealand have the highest incidence of skin cancer. Sport is a fundamental part of Australasian culture, beginning in childhood, often with life-long participation. Participating in outdoor sports can contribute significantly to the lifetime ultraviolet radiation (UVR) dose individuals receive and their risk of developing skin cancer. This systematic scoping review explores the use of sun-protection by outdoor sporting participants in Australasia and considers how sun-protection practices may be better evaluated and improved in the community. A search of electronic databases using the search strategy “sun protection” AND “sport” AND “Australia” yielded 17 studies published in English from January 1992 to August 2021. Study methods included using UV-dosimeters to measure individual UVR-exposure; remote estimates of clothing-adjusted UVR-exposure; direct observation of sun-protection practices; and self-reported sun-exposure and sun-protection. Despite 40-years of ‘Slip Slop Slap’ campaigns in Australia, the use of sun-protection in most outdoor sports is inadequate. The paucity of comparable data limited our analyses, demonstrating a need for standardized, objective evaluation tools. Such tools, if used across a range of sports, should inform the development of workable recommendations that sporting clubs could implement and adopt into policy, thus empowering them to better protect the health of their participants.

Tanning beds have been classified as carcinogenic to humans. As a result, many countries have enacted laws regulating the use of commercial tanning beds, including bans for minors. However, there is no international overview of the current legal status of access restrictions for minors that provides details on their specific design regarding age limits and possible exceptions to the statutory regulation. Therefore, we performed a comprehensive web search of current tanning bed legislation for minors on the three continents North America, Australia, and Europe. Our findings regarding existence and concrete design of access restrictions are presented graphically using maps. We found a wide variety of different legislations. In Australia, a total ban on tanning beds exists, while in New Zealand tanning bed use is banned for minors. In Europe about half of the countries have implemented a strict ban for minors. In North America we found differences in the age limit for access restrictions between the states, provinces and territories for those regions that implemented a ban for minors. In the United States, some states have rather ‘soft bans’ that allow use by minors with different types of parental consent. The patchwork in legislation calls for harmonization. Therefore, our comparison is an important starting point for institutions such as the World Health Organization or the European Commission to advance their goals towards a harmonization of tanning bed legislation in general and for minors in particular.

Purpose:To explore (theoretically) the key parameters and their influence on the time profiles of photosensitizer (riboflavin), free radicals, singlet oxygen, oxygen and the efficacy of corneal collagen crosslinking (CXL)in both type-I and oxygen-mediated type-II mechanisms, specially the role of oxygen and the initiator regeneration. Methodology:Coupled kinetic equations are derived and numerically solved under the quasi-steady state condition for the 2-pathway mechanisms of CXL. The key parameters explored include (bI, V, Q', K, K',Q,P) and their influence on the time profiles of photosensitizer (riboflavin, C), radicals (R), singlet oxygen(S), oxygen (X) and efficacy (E), parameters of (K,K',Q) define the relative strength of type-I and type-II process. The oxygen depletion profile, X(t), and the associated singlet oxygen, S(t), depend on the parameters of V, Q' and the initial value of oxygen. The coupling strength given by (bI) governs almost all profiles, where b is an effective absorption parameter and I is the UV light intensity.Results:Our numerical method for CXL dynamic profiles demonstrated the following important features: (i) Type-I and type-II coexit in CXL, in the presence of oxygen. However, there is no type-II when oxygen is depleted or in a condition without oxygen. (ii) Type-I with bimolecular termination, the radical R(t) is a function of [K'(bIgC)]^0.5, leading to the steady-state efficacy given by a scaling law of 1/(bI)^0.5, in contract to that of type-II which is almost independent to the light intensity. (iii) The depletion rate (2 to 5 minutes) of X(t) is much faster than that of C(t) (10 to 20 minutes), (iv) Thepure type-II profile, has a transition point from straight line to saturating curve and matches the depletion point of singlet oxygen S(t). (v) Improved CXL efficacy of type-I and type-II may be achieved by external supply of photoinitiator (riboflavin) and oxygen, respectively.

Daily exposure of skin to environmental stressors leads to molecular and morphological changes ascribed as premature aging. These stressors include solar radiation, industrial pollution, fossil fuel and carbon emissions, which cause cellular damage that induces an inflammatory response in skin. Several inflammatory components are known to be involved in triggering the senescence-associated secretory phenotype (SASP) which is known to accelerate aging. It is hypothesized that preventing induction of inflammation by environmental stressors can prevent premature aging. Since it is known that nicotinamide (Nam) has anti-inflammatory properties, we tested whether Nam can inhibit environmental stressor-induced inflammation. Exposure of keratinocytes to UVB, urban dust, diesel exhaust, and cigarette smoke extract stimulated production of the inflammatory mediators PGE2, IL-6, and IL-8 and induced gene expression patterns associated with apoptosis, DNA repair, and cell cycle control. In all cases, Nam treatment significantly inhibited these stress-induced responses. Nam also reduced IL-8 levels stimulated by the combination of topically applied particulate matter (PM2.5) and UV exposure in 3D skin equivalents. Under 5% 02 conditions that more closely mimic physiological 02 levels, Nam had a heightened inhibitory effect on UVB-induced PGE2 levels in keratinocytes. In a UV-challenge study, treatment with Nam reduced skin surface IL-1RA/IL-1 inflammatory biomarkers and erythema that were induced by solar simulated radiation. These findings provide a body of evidence that Nam can mitigate in part the skin’s inflammatory response elicited by exposure to environmental stressors. This supports the potential that Nam can inhibit premature aging and help maintain skin’s functionality and appearance.

The efficiency of microbial inactivation in water is highly dependent on the type of treatment technology used as well as the characteristics of the water to be treated. Wastewater from poultry slaughterhouses carries a significant number of microorganisms posing threat to humans and the environment in general. Therefore, the treatment of poultry slaughterhouse wastewater requires the use of appropriate purification systems with high removal efficiency for microbial agents. In this study, the performance of an integrated treatment plant with electrolysis, ultrafiltration, and ultraviolet radiation as the principal treatment units is investigated in terms of microbial inactivation from poultry slaughterhouse wastewater. In this case, Total microbial number, Total coliform bacteria, Thermo-tolerant coliform bacteria, Pathogenic flora, including Salmonella coliphages, Spores of sulfite-reducing clostridia, Pseudomonas aeruginosa, and Staphylococcus aureus Enterococcus were studied. About 63.95% to 99.83% of the microbes were removed by the EC treatment unit, as well as 99.86% to 100% removal efficiency was achieved after the combined treatment. However, the Pseudomonas aeruginosa was the only microbial agent detected in the final effluent after the combined treatment. The phenomenon suggests that an upgrade to the treatment plant may be required to achieve 100% removal assurance for Pseudomonas aeruginosa.

The efficiency of microbial inactivation in water is highly dependent on the type of treatment technology used as well as the characteristics of the water to be treated. Wastewater from poultry slaughterhouses carries a significant number of microorganisms posing threat to humans and the environment in general. Therefore, the treatment of poultry slaughterhouse wastewater requires the use of appropriate purification systems with high removal efficiency for microbial agents. In this study, the performance of an integrated treatment plant with electrolysis, ultrafiltration, and ultraviolet radiation as the principal treatment units is investigated in terms of microbial inactivation from poultry slaughterhouse wastewater. In this case, Total microbial number, Total coliform bacteria, Thermo-tolerant coliform bacteria, Pathogenic flora, including Salmonella coliphages, Spores of sulfite-reducing clostridia, Pseudomonas aeruginosa, and Staphylococcus aureus Enterococcus were studied. About 63.95% to 99.83% of the microbes were removed by the EC treatment unit, as well as 99.86% to 100% removal efficiency was achieved after the combined treatment. However, the Pseudomonas aeruginosa was the only microbial agent detected in the final effluent after the combined treatment. The phenomenon suggests that an upgrade to the treatment plant may be required to achieve 100% removal assurance for Pseudomonas aeruginosa.

The Absorbing/scattering nature of aerosols affects the total radiative forcing and this absorption to total extinction ratio is quantified by single scattering albedo (SSA). Effect of SSA in the Ultraviolet (UV) irradiance is less studied and limited measurements are available. SSA retrieved at Athens, Greece during 2009-2014 from Ultraviolet Multifilter Radiometer (UVMFR) at 332 and 368 nm, were used to calculate incoming UV irradiance, alongside with ones from AERONET at visible wavelengths, from OMI satellite at 342.5 nm and from AEROCOM climatological database at 300 nm. UVA and UVB irradiances were estimated using a Radiative Transfer Model and we found that relative differences could be as high as 20%, while average relative differences varied from 2% to 8.7 % for the whole experimental period. Both UVA and UVB drop by a rate of ~12% for 0.05 aerosol absorption optical depth compared to ones estimated using SSA at visible range. Brewer irradiance measurements at 324nm were used to validate simulated irradiances and a better agreement was found when UVMFR SSAs were used with an average difference of 0.86%, while when using visible or climatological input, relative differences were estimated +4.91 and +4.15% accordingly.

To resolve the controversial issues of UV-light-initiatedcornealcollagen cross-linking (CXL) by theoretical formulas and measured clinical outcomes. The controversial issues are addressed and resolved by analytical formulas including: the validation of Bunsen Roscoe law (BRL), the cutoff light intensity, the minimum corneal thickness, the demarcation line depth, the role of oxygen riboflavin (RF) concentration. The overall CXL efficacy is governed by UV-A light intensity, dose, exposure time, mode of exposure (pulsed or CW), riboflavin concentration, diffusion and drops pre-operation and interoperation administration, concentration of oxygen in the stromal tissue (pre-op and inter-op), and environmental conditions. The length of the riboflavin presoaking time and viscosity of the riboflavin film also affect the crosslink depth. Analytic formulas are derived for the scaling laws for type-I and type-II efficacy, given by the square-root of light intensity, and light dose, respectively. The controversial issues of CXL may be partially resolved via analytic formulas, and compared with measurements. The scaling laws of type-I and type-II efficacy are different and given by analytic formulas. Our formulas also predict the maximum light intensity and the minimum corneal thickness, which are consistent with measurements.

The interaction of ultraviolet radiation with biological matter results in direct damage such as pyrimidine dimers in DNA. It also results in indirect damage provoked by the production of Reactive Oxygen Species (ROS) catalyzed by photo-sensitizers. Photosensitizers can be endogenous (e.g. Tryptophan) or exogenous (e.g. TiO2 and other photo-stable UVA sunscreens). Direct damage triggers an inflammatory response and the oxidative and proteolytic bursts that characterize its onset. The inflammatory reaction multiplies the effects of one single photon. Indirect damage, such as the peroxidative cascade in membrane lipids, can extend to thousands of molecular modifications per absorbed photon. Sunscreens should therefore be formulated in the presence of appropriate anti-oxidants. Superoxide and Singlet Oxygen are the main ROS that need to be tackled: this review describes some of the molecular, biochemical, cellular and clinical consequences of exposure to UV radiation as well as some results associated with scavengers and quenchers of Superoxide and Singlet Oxygen, as well as with inhibitors of singlet Oxygen production.

This study examined the use of high dosages of ultraviolet germicidal irradiation (UVGI) (253.7 nm) to deal with various concentrations of air pollutants, such as formaldehyde (HCHO), total volatile organic compounds (TVOC), under various conditions of humidity. We also estimated the emission of ozone as a secondary pollutant of UVGI as treatment. A number of irradiation methods were applied for various durations in field studies to examine the efficiency of removing HCHO, TVOC, bacteria, and fungi. The removal efficiency of air pollutants (HCHO and bacteria) through long-term exposure to UVGI appears to increase with time. The effects on TVOC and fungi concentration were insignificant in the first week; however, improvements were observed in the second week. No differences were observed among the various irradiation methods in this study regarding the removal of HCHO and TVOC; however significant differences were observed in the removal of bacteria and fungi.

Genetic engineering and directed evolution are effective methods to address the low yield and poor industrialization level of microbial target products. The current research focus is on how to efficiently and rapidly screen beneficial mutants from constructed large-scale mutation libraries. Traditional screening methods such as plate screening and well plate screening are severely limited in their development and application due to their low efficiency and high costs. In the past decade, microfluidic technology has become an important high-throughput screening technology due to its fast speed, low cost, high automation, and high screening throughput, and it has developed rapidly. Droplet-based microfluidic high-throughput screening has been widely used in various fields such as strain/enzyme activity screening, pathogen detection, single-cell analysis, drug discovery, and chemical synthesis, and has been widely applied in industries such as materials, food, chemicals, textiles, and biomedicine. In particular, in the field of enzyme research, droplet-based microfluidic high-throughput screening has shown excellent performance in discovering enzymes with new functions, improved catalytic efficiency or stability, acid-base tolerance, etc. Currently, droplet-based microfluidic high-throughput screening technology has achieved high-throughput screening of enzymes such as glycosidase, lipase, peroxidase, protease, amylase, oxidase, and transaminase, as well as high-throughput detection of products such as riboflavin, coumarin, 3-dehydroquinate, lactic acid, and ethanol. This article reviews the application of droplet-based microfluidics in high-throughput screening, with a focus on high-throughput screening strategies based on UV, visible, and fluorescence spectroscopy, including labeled optical signal detection screening, as well as label-free electrochemical detection, mass spectrometry, Raman spectroscopy, nuclear magnetic resonance, etc. Furthermore, the research progress and development trends of droplet-based microfluidic technology in enzyme modification and strain screening are also introduced.

Ultraviolet (UV) radiation is a strong environmental carcinogen responsible for the pathogenesis of most skin cancers, such as malignant melanoma (MM) and non-melanoma (keratinocyte) skin cancers. The carcinogenic role of UV was firmly established based on epidemiological evidence and molecular findings of the characteristic mutation signatures which occur during excision repair of cyclobutane pyrimidine dimers and 6,4-photoproducts. The role of UV in the pathogenesis of mycosis fungoides (MF), the most common primary cutaneous T-cell lymphoma, remains controversial. Here, we performed whole exome sequencing of 61 samples of MF cells microdissected from the cutaneous lesions, and compared their mutational signatures to 340 MM. The vast majority of MM mutations had a typical UV mutational signature (SBS 7, SBS 38, DSB 1) underscoring the key role of ultraviolet as a mutagen. In contrast, the SBS 7 signature in MF comprised <5% of all mutations. SBS 7 was higher in the intraepidermal MF cells (when compared to the dermal cells) and in the cells from tumors as compared to early-stage plaques. In conclusion, our data do not support the pathogenic role of UV in the pathogenesis of MF and suggest that the UV mutations are the result of the cumulative, environmental ultraviolet exposure of cutaneous lesions, rather than an early mutagenic event.

More than twenty-five years ago the Global Solar UV index (UVI) has been introduced as a simple means of visualizing the intensity of ultraviolet radiation and to alert people to the need for sun protection. In our survey among directors of 436 kindergartens in southern Germany we investigated the level of awareness and knowledge about the UVI as well as the practical consequences for sun protection in kindergartens. Less than half of the directors (n=208, 47.7%) had ever heard of the UVI, and only a small minority of them (n=34, 8.7%) used the daily UVI information to adapt sun protective measures in their kindergartens. Detailed knowledge about the UVI was a rarity among the respondents. The proportion of respondents with self-perceived detailed UVI knowledge was five times higher than actual knowledge assessed by an in-depth structured interview using open-ended questions about the UVI (14.2% vs. 2.8%). No clear relationship of UVI awareness, knowledge, and use to directors' age and gender was found. The UVI-related variables also showed no association with directors' knowledge of risk factors for skin cancer and their attitudes towards tanned skin. Overall, the results paint a sobering picture regarding the penetration of the UVI into sun protection policies of German kindergartens. Future public health campaigns should target increasing awareness and understanding of the UVI as well as its importance for sun protection of children.

Hydroa vacciniforme (HV) is a rare form of photosensitivity disorders in children and is frequently associated with Epstein-Barr virus (EBV) infection, whereas HV-like lymphoproliferative disorders (HVLPD) describe a spectrum of EBV-associated T-cell or NK-cell lymphoproliferations with HV-like cutaneous manifestations, including EBV-positive HV, atypical HV, and HV-like lymphoma. Classic HV occurs in childhood with vesiculopapules on sun-exposed areas, which is usually induced by sunlight and ultraviolet irradiation, and mostly resolves by early adult life. Unlike classic HV, atypical or severe HV manifests itself as recurrent papulovesicular eruptions in sun-exposed and sun-protected areas associated occasionally with facial edema, fever, lymphadenopathy, oculomucosal lesions, gastrointestinal involvement, and hepatosplenomegaly. Notably, atypical or severe HV may progress to EBV-associated systemic T-cell or natural killer (NK)-cell lymphoma after a chronic course. Although rare in the United States and Europe, atypical or severe HV and HV-like lymphoma are predominantly reported in children from Asia and Latin America with high EBV DNA levels, low numbers of NK cells, and T cell clones in the blood. In comparison with the conservative treatment used for patients with classic HV, systemic therapy such as immunomodulatory therapy is recommended as the first-line therapy for patients with atypical or severe HV. This review aims to provide an integrated, overview of current evidence and knowledge of HV and HVLPD to elucidate the pathophysiology, practical issues, environmental factors, and the impact of EBV infection.

The optimal regime of three-photon resonant excitation of a helium atom by a femtosecond ul-traviolet (UV) pulse was discovered and numerically studied, at which the maximum power of the third harmonic of the UV field is achieved in the spectrum of dipole acceleration (the second time derivative of the induced dipole moment) of the atom. It is shown that the optimal frequency of the UV field nearly coincides with the frequency of the three-photon transition 1s2 – 1s2p, taking into account its shift as a result of the dynamic Stark effect, and the intensity of the UV field is dictated by the condition of maximizing the product of the populations of the 1s2 and 1s2p states, averaged over the time interval during which the UV field is non-zero. For the considered UV field durations, from 10 to 100 cycles of the carrier frequency (from units to tens of femtoseconds), the optimal intensity lies in the range from 10^14 W/cm^2 to several units of 10^14 W/cm^2. It is shown that with an optimal choice of the frequency and intensity of the UV field, the dynamics of excitation of bound and continuum states, as well as the shape of the time envelope of the dipole acceleration of the atom, weakly depend on the duration of the UV field envelope; only their time scale changes significantly. In addition, under the optimal conditions the average power of the third harmonic signal in the dipole acceleration spectrum is practically independent of the duration of the UV field envelope.

This study evaluated the use of filtration and UV-A photocatalysis for the reduction of particulate matter (PM) and airborne bacterial pathogens in swine barns. Two MERV filters (8 and 15) were used to mitigate PM concentrations measured at the PM 1, PM 2.5, respirable PM, and PM 10 ranges. Filtration was also used to generate different levels of airborne pathogens to be treated by UV-A. Results show that MERV 8 and 15 filters effectively reduced PM concentrations (96-98%) in air exhausted from a swine barn (p ranged from < 0.01 to 0.04). UV-A photocatalysis did not mitigate PM concentrations. UV-A photocatalysis treatment reduced measured colony-forming units (CFUs) by 15-95%. The CFU percent reduction was higher when airborne PM concentration was low. The numeric results suggested a real mitigation effect despite p-values that did not meet the usual statistical cut-off of <0.05 for significance due to the large variability of the CFU control samples. Normalization of measured airborne pathogen concentrations by smaller PM size range concentrations led to emerging significant treatment differences for CFUs. A significant decrease (~60% reduction; p < 0.03) in the concentration of viable airborne bacteria was shown for all PM below the 10-micron range.

Aims:To update analytic formulas for the overall efficacy of corneal collagen crosslinking (CXL) including both type-I and oxygen-mediated type-II mechanisms, the role of oxygen and the initiator regeneration. Study Design:modeling the kinetics of CXL in UV light and using riboflavin as the photosensitizer.Place and Duration of Study:New Taipei City, Taiwan, between June, 2021 and July, 2021.Methodology:Coupled kinetic equations are derived under the quasi-steady state condition for the 2-pathway mechanisms of CXL. For type-I CXL, the riboflavin (RF) triplet state [T] may interact directly with the stroma collagen substrate [A] to form radical (R) and regenerate initiator. For type-II process, [T] interacts with oxygen to form a singlet oxygen [¹O₂]. Both reactive radical (R) and [¹O₂], can relax to their ground state, or interact with the substrate [A]) for crosslinking. Based on a safety dose, the minimum corneal thickness formula is derived. Results:Our updated theory/modeling showed that oxygen plays a limited and transient role in the process, in consistent with that of Kamave [2]. In contrary, Kling et al [3] believed that type-II is the predominant mechanism, which however conflicting with the epi-on CXL results. For both type-I and type-II, a transient state conversion (crosslink) efficacy in an increasing function of light intensity (or dose), whereas, its steady state efficacy is a deceasing function of light intensity. RF depletion in type-I is compensated by the RF regeneration term (RGE) which is a decreasing function of oxygen. For the case of perfect regeneration case (or when oxygen=0), RF is a constant due to the catalytic cycle. Unlike the conventional Dresden rule of 400 um thickness, thin cornea CXL is still safe as far as the dose is under a threshold dose (E*), based on our minimum thickness formula (Z*). Our formula for thin cornea is also clinically shown by Hafez et al forultra thin (214 nm) CXL. Conclusion: For both type-I and type-II, a transient state conversion (crosslink) efficacy in an increasing function of light intensity (or dose), whereas, its steady state efficacy is a deceasing function of light intensity. Ultra thin cornea is still safe as far as it is under a threshold dose (E*), based on our minimum thickness formula.

It is known that eumelanin (EM) is photoprotective while pheomelanin (PM) is phototoxic. A recent study using a mouse model demonstrated that PM produces reactive oxygen species (ROS) that cause DNA damage and eventually lead to melanomagenesis. A biochemical study showed that PM possesses a pro-oxidant activity. PM consists of benzothiazine (BT) and benzothiazole (BZ) moieties, the former being transformed to the latter by heat or light. In this study, we compared the effects of ultraviolet A (UVA) irradiation using synthetic PMs with different BT to BZ ratios and using various coat color mouse hairs. We found that UVA irradiation of BZ-PM increased glutathione (GSH) consumption and generated more H₂O₂ than UVA irradiation of BT-PM. Non-irradiated controls did not exhibit strong pro-oxidant activities. Upon UVA irradiation, yellow mouse hairs oxidized GSH and produced H₂O₂ faster than black or albino mouse hairs. Next, to examine the mechanism of the pro-oxidant activity of BT-PM and BZ-PM, we examined the pro-oxidant activities of 7-(2-amino-2-carboxyethyl)-dihydro-1,4-benzothiazine-3-carboxylic acid (DHBTCA) and 6-(2-amino-2-carboxyethyl)-4-hydroxybenzothiazole (BZ-AA) as BT and BZ monomers, respectively. Their pro-oxidant activities were similar, but a large difference was seen in the effects of ROS scavengers, which suggests that the redox reactions may proceed via singlet oxygen in BZ-AA and via superoxide anions in DHBTCA. These results show that UVA enhances the pro-oxidant activity of PM, in particular BZ-PM.

Conventional flame retardant (FR) application processes for textiles involve aqueous processing which is resource intensive in terms of energy and water usage. Recent research using sol-gel and layer-by-layer chemistries, while claimed to be based on more environmentally-sustainable chemistry, still require aqueous media with the continuing problem of water management and drying processes being required. This paper outlines the initial forensic work to characterise commercially produced viscose/flax, cellulosic furnishing fabrics which have had conferred upon them durable flame retardant (FR) treatments using a novel, patented atmospheric plasma/UV excimer laser facility for processing textiles with the formal name - Multiplexed Laser Surface Enhancement (MLSE) system. This system (MTIX Ltd., UK), is claimed to offer the means of directly bonding of flame retardant precursor species to the component fibres introduced either before plasma/UV exposure or into the plasma/UV reaction zone itself, thereby eliminating a number of wet processing cycles. Nine commercial fabrics, pre-impregnated with a semi-durable, proprietary FR finish and subjected to the MLSE process have been analysed for their flame retardant properties before and after a 40 °C 30 min water soak. For one fabric, the pre-impregnated fabric was subjected to a normal heat cure treatment which conferred the same level of durability as the plasma/UV-treated analogue. TGA and LOI were used to further characterise their burning behaviour and the effect of the treatment on surface fibre morphologies were assessed. Scanning electron microscopy indicated that negligible changes had occurred to surface topography of the viscose fibres occurred during plasma/UV excimer processing.

GaN ultraviolet photodetector with metal-semiconductor-metal structure is achieved by growing on a periodic trapezoid column-shape patterned sapphire substrate using metalorganic chemical vapor deposition. Under 5-V reverse bias, the photodetector fabricated on such patterned sapphire substrate exhibits a lower dark current, a higher photocurrent, and a 476 % enhancement in the maximum responsivity as compare with those of the photodetector fabricated on conventional flat sapphire substrate. It is also found that the much larger UV-to-visible rejection ratio and the fact that responsivity drops in a smaller cut-off region are observed from photodetector fabricated by using a periodic trapezoid column-shape patterned sapphire substrate. These phenomena may all be attributed to the reduction of threading dislocation density and the improved quality of GaN film, as well as the internal reflection and/or scattering effect on the interface between GaN film and the periodic trapezoid column-shape pattern of the substrate.

Deep learning is an emerging area of machine learning (ML) research. It comprises multiple hidden layers of artificial neural networks. The deep learn- ing methodology applies nonlinear transformations and model abstractions of high level in large databases. The recent advancements in deep learning architec- tures within numerous fields have already provided significant contributions in artificial intelligence. This article presents a state of the art survey on the contri- butions and the novel applications of deep learning. The following review chron- ologically presents how and in what major applications deep learning algorithms have been utilized. Furthermore, the superior and beneficial of the deep learning methodology and its hierarchy in layers and nonlinear operations are presented and compared with the more conventional algorithms in the common applica- tions. The state of the art survey further provides a general overview on the novel concept and the ever-increasing advantages and popularity of deep learning.

Proper treatment of infectious air could potentially mitigate the spread of airborne viruses such as porcine reproductive and respiratory syndrome virus (PRRSV). The objective of this research is to test the effectiveness of ultraviolet (UV) in inactivating aerosolized PRRSV, specifically, four UV lamps, UV-A (365 nm, both fluorescent and LED-based), "excimer" UV-C (222 nm), and germicidal UV-C (254 nm), were tested. The two UV-C lamps effectively irradiated fast-moving PRRSV aerosols with short treatment times (<2 s). One-stage and two-stage UV inactivation models estimated the UV doses needed for target percentage (%) reductions on PRRSV titer. UV-C (254 nm) dose needed for 3-log (99.9%) reduction was 0.521 and 0.0943 mJ/cm2, respectively, based on one-stage and two-stage models. An order of magnitude lower UV-C (222 nm) doses were needed for a 3-log reduction, i.e., 0.0882 and 0.048 mJ/cm2, based on one-stage and two-stage models, respectively. However, the cost of 222-nm excimer lamps is still economically prohibitive for scaling-up trials. The UV-A (365 nm) lamps could not reduce PRRSV titers for tested doses up to 4.11 mJ/cm2. Pilot-scale or farm-scale testing of UV-C on PRRSV aerosols simulating barn ventilation rates are recommended based on its effectiveness and reasonable costs comparable to HEPA filtration.

"Deep fake" technologies are often associated with face-swapping algorithms based on images or videos. Although much research is focused on developing these techniques, there is still room for improvement, especially in human and visual assessment. In this study, we present an innovative approach to the problem of face replacement based on one model while preserving background features. Our model uses the Adaptive Attentional Denormalization method from FaceShifter while integrating identity features from the ArcFace and BiSeNet models to support the attribute extraction process. We used Fast GAN as a generative model to optimize and accelerate the training process on smaller data sets. Our research proves the effectiveness of the proposed approach by combining innovative methods and architectures in one coherent solution.

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL through a wide range of capabilities from reinforcement learning (RL) and deep learning (DL) for handling sophisticated dynamic business environments offers vast opportunities. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this work, we first consider a brief review of DL, RL, and deep RL methods in diverse applications in economics providing an in-depth insight into the state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher accuracy as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

Diabetes mellitus is a popular life-threatening disease and patients may gradually have started suffering from other diabetes-causing diseases such as heart attacks, stroke, hypertension, blurry vision, blindness, foot ulcer, amputation, kidney damage and other organ failures before diagnosis. Early detection can help reduce the fatality of this disease. Deep learning models have proven very useful in disease detection and computer-aided diagnosis. In this work, we proposed a deep unsupervised machine learning model for early detection of diabetes using voting ensemble feature selection and deep belief neural networks (DBN). Dataset was obtained from an online repository containing responses of prediagnosed patients to direct questionnaires administered in Sylhet Diabetes Hospital in Sylhet, Bangladesh. The dataset was preprocessed and preprocessed. Features were reduced using the ensemble feature selector. The DBN model was pretrained and tuned to obtain optimal performance. The model was also compared with other models with no multiple hidden layers. The DBN performed at its relative best with F1-measure, precision and recall of 1.00, 0.92 and 1.00 respectively. We conclude that DBN is a useful tool for an unsupervised early prediction of Type II diabetes mellitus.

We propose a deep-learning approach for the joint MIMO detection and channel decoding problem. Conventional MIMO receivers adopt a model-based approach for MIMO detection and channel decoding in linear or iterative manners. However, due to the complex MIMO signal model, the optimal solution to the joint MIMO detection and channel decoding problem (i.e., the maximum likelihood decoding of the transmitted codewords from the received MIMO signals) is computationally infeasible. As a practical measure, the current model-based MIMO receivers all use suboptimal MIMO decoding methods with affordable computational complexities. This work applies the latest advances in deep learning for the design of MIMO receivers. In particular, we leverage deep neural networks (DNN) with supervised training to solve the joint MIMO detection and channel decoding problem. We show that DNN can be trained to give much better decoding performance than conventional MIMO receivers do. Our simulations show that a DNN implementation consisting of seven hidden layers can outperform conventional model-based linear or iterative receivers. This performance improvement points to a new direction for future MIMO receiver design.

Deep networks-based hashing has gained significant popularity in recent years, particularly in the field of image retrieval. However, most existing methods only focus on extracting semantic information from the final layer, disregarding valuable structural information that contains important semantic details crucial for effective hash learning. To address this limitation and improve image retrieval accuracy, we propose a novel deep hashing method called Deep Supervised Hashing by Fusing Multiscale Deep Features (DSHFMDF). Our approach involves extracting multiscale features from multiple convolutional layers and fusing them to generate more robust representations for efficient image retrieval. Experimental results on CIFAR10 and NUS-WIDE datasets demonstrate that our method surpasses the performance of state-of-the-art hashing techniques.

Groundwater is the most extracted raw material in the world with global annual withdrawal rates of 800–1500 km3/year. In East and Southern Africa, 70 % of the population are reliant on shallow groundwater as their primary drinking water source. With increased population growth, intensification of agriculture and industrialization, conflicting demands on groundwater present a challenge to achieve the Sustainable Development Goals (6,3,11,12,15). Between 2015 and 2018, the Horn of Africa was affected by a series of climatic induced events, namely El Nino, La Nina and the Indian Ocean Diopole. These events modified the variability of rainfall patterns and resulted in long periods of low rainfall, low recharge and high evapotranspiration. As a result, shallow aquifers in alluvial deposits of Somali region have low yields and produce brackish and saline water. That situation prompted humanitarian water professionals to finance the transportation of water from selected locations with high groundwater potential through water trucks to areas facing groundwater depletion and drought. To address this challenge, UNICEF explored alternative, sustainable deeper groundwater sources that could be extracted using solar water pumping technology for multi water use. This paper describes a three-phase methodology of deep groundwater development of wells in the Ogaden Jesoma sandstone aquifers of the Somali region of the Horn of Africa to a depth of 600 meters below ground level. The results concluded that the deep sandstone aquifer of Jesoma can provide fresh water with yields of 15 l/s to the local population of Somali region. to the study provided insights into deep groundwater identification and development as well as adaptive deep boreholes drilling as a source for climate resilient water supplies.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

It is widely believed that the dramatic transformation of the spherical outflows of AGB stars into the extreme aspherical geometries seen during the planetary nebula (PN) phase is linked to binarity and driven by the associated production of fast jets and central disks/torii. The key to understanding the engines that produce these jets and the jet-shaping mechanisms lies in the study of objects in transition between the AGB and PN phases. I discuss the results of our recent studies with high-angular-resolution (with ALMA & HST) and at high-energies (with GALEX, XMM-Newton & Chandra) of several such objects, which reveal new details of close binary interactions and high-speed outflows. These include two PPNe (the Boomerang Nebula and IRAS16342-3814), and the late carbon star, V Hya. The Boomerang is notable for a massive, high-speed outflow that has cooled below the microwave background temperature, making it the coldest object in the Universe. IRAS16342 is the prime example of the class of water-fountain PPNe (very young PPNe with high-velocity H₂O masers) and shows the signature of a precessing jet. V Hya ejects high-speed bullets every 8.5 years associated with the periastron passage of a companion in an eccentric orbit. I discuss our work on AGB stars with strongly-variable high-energy (FUV, X-ray) emission, suggesting that these objects are in the early stages of binary interactions that result in the formation of accretion disks and jets.

The rise of the Internet has enabled people to express their opinions on various subjects through social media, blogs, and website comments. As a result, there has been a significant increase in research on sentiment analysis. However, most of the research efforts have focused on analyzing sentiment in English-language data, neglecting the wealth of information available in other languages. In this paper, we provide a comprehensive review of the current state-of-the-art in multilingual sentiment analysis. The survey investigates techniques for data preprocessing, representation learning, and feature extraction in multilingual sentiment analysis. It explores cross-lingual transfer learning, domain adaptation, and data augmentation methods that enhance the performance of sentiment analysis models, particularly in low-resource languages and domains. It provides insights into the state-of-the-art approaches, challenges, and opportunities in this evolving field and encourages further advancements in multilingual sentiment analysis research.

When training deep neural networks tasks, the most popular choices are cross-entropy loss. On the other hand, in general speaking, a decent loss function can take on shapes that are considerably more flexible and ought to be adapted for different activities and datasets. In most of the classification tasks, generally if the true class is not correctly recognized by the network (top1), that class is placed among the five classes with the highest probability (top5). This shows that the network does not necessarily recognize the correct class with a low probability, but a class similar to it (such as 3 vs. 8 in mnist) assigns a higher probability and this causes a mistake in that task. Accordingly, we proposed a loss function deals with the error of class that the neural network incorrectly recognized as correct, in addition to the correct class error. We call our proposed loss as False Positive Loss (FPL), with the intention of viewing and designing loss functions not only through the utilization of true class but also through the utilization of the value of false positive classes. One of the core properties of our proposed loss is full adaptability, which makes False Positive Loss be fully capable of getting reformulated by using other widely used loss functions formulas based on the task or the need of the users. Extensive experimental results demonstrate that our suggested loss function outperforms other well-known losses on a variety of tasks and datasets. As can be observed, the performance of our False Positive Loss is superior to that of the cross-entropy loss when it comes to tasks involving 2D picture classification. We have compared our loss with cross entropy as the most common classification loss function on some models (such as ResNet-18, ResNet-50 and Efficientnet-V2) through classification known as a basic computer vision task. with both random or pre-trained initial weights. As a result, in some cases the models with our loss outperform the same tasks with cross entropy from the viewpoint of some metric (i.e. accuracy and FP). For example, the resnet-50 on cifar-10 dataset with random initialization indicated a top1 accuracy of 94.93 with cross entropy and 95.25 with our loss, while for top5 accuracy the results are 99.86 and 99.87, respectively.

We study the brain segmentation by dividing the brain into multiple tissues. Given possible brain segmentation by deep, machine learning can be efficiently exploited to expedite the segmentation process in the clinical practice. To accomplish segmentation process, a MRI and tissues transfer using generative adversarial networks is proposed. Given the better result, we propose the transfer model using GAN. For the case of the brain tissues, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) are segmented. Empirical results show that this proposed model significantly improved segmentation results compared to the stat-of-the-art results. Furthermore, a dice coefficient (DC) metric is used to evaluate the model performance.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

In this paper we propose a computational framework that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models in SBML that are currently stored in public databases. With the proposed framework, existing SBML mechanistic models may be upgraded to hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and stored back in model databases, where they can be further analyzed as regular SBML models. The application of this approach is illustrated with three well-known case studies: the threonine synthesis model in Escherichia coli, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Theories on life’s origin generally acknowledge the advantage of a semi-permeable vesicle (protocell) for enhancing the chemical reaction-diffusion processes involved in abiogenesis. However, more and more evidence indicates that the origin of life concerned the photo-chemical dissipative structuring of the fundamental molecules under UV-C light. In this paper, we analyze the Mie UV scattering properties of such a vesicle made from long chain fatty acids. We find that the vesicle could have provided early life with a shield from the faint, but dangerous, hard UV-C ionizing light (180-210 nm) that probably bathed Earth’s surface from before the origin of life and until perhaps 1,500 million years after, until the formation of a protective ozone layer as a result of the evolution of oxygenic photosynthesis.

The study aimed to investigate the impact of incorporating deep learning strategies in mathematics instruction on students' problem-solving abilities, critical thinking skills, academic achievement, and mathematical skills development. The study population consisted of 280 students, with a sample size of 162 participants. Employing a purely quantitative approach, data collection utilized questionnaires and achievement tests as instruments. Data analysis involved simple linear regression, descriptive analysis, and Pearson correlation. The results of the study revealed that there was no significant enhancement observed in students' problem-solving abilities and critical thinking skills when deep learning strategies were incorporated into mathematics instruction. Additionally, students' attitudes towards deep learning activities in mathematics showed no effect on their academic achievement. Furthermore, students' engagement levels in deep learning activities did not impact their development of mathematical skills. Lastly, the frequency of deep learning activities in the mathematics classroom did not show a significant relationship with students' academic performance. These findings suggest that the implementation of deep learning strategies in mathematics instruction did not yield notable improvements in the specified areas based on the study outcomes.

To identify objects in images, a complex set of skills is needed that includes understanding the context and being able to determine the borders of objects. In computer vision, this task is known as semantic segmentation and it involves categorizing each pixel in an image. It is crucial in many real-world situations: for autonomous vehicles, it enables the identification of objects in the surrounding area; in medical diagnosis, it enhances the ability to detect dangerous pathologies early, thereby reducing the risk of serious consequences. In this study, we compare the performance of various ensembles of convolutional and transformer neural networks. Ensembles can be created, e.g, by varying the loss function, data augmentation method or the learning rate strategy. Our proposed ensemble, which is based on the simple average rule, demonstrates exceptional performance on several datasets. All the resources used in this study are available online at the following GitHub repository: https://github.com/LorisNanni.

Polar Mesospheric Summer Echoes (PMSEs) are radar echoes that are observed in the mesosphere during the Arctic summer months in the polar regions. By studying PMSE, researchers can gain insights into physical and chemical processes that occur in the upper atmosphere specifically in the 80 to 90 km altitude range. In this paper, we employ fully convolutional networks such as UNET and UNET++ for the purposes of segmenting PMSE from the EISCAT VHF dataset. First, experiments are performed to find suitable weights and hyperparameters for UNET and UNET++. Second, different loss functions are tested to find one suitable for our task. Third, as the number of PMSE samples used is relatively small that can lead to poor generalization. To address this, image-level and object-level augmentation methods are employed. Four, we briefly explain our findings by employing layerwise relevance propagation.

In the field of low power wireless networks, one of the techniques on which many researchers are putting their efforts is related to positioning methodologies such as fingerprinting in dense urban areas. This paper presents an experimental study aimed at quantifying the mean location estimation error in densely urbanized areas.Using a dataset made available by the University of Antwerp, a neural network was implemented with the aim of providing the position of the end-devices. In this way it was possible to measure the mean location estimation error in an area with high urban density. The results obtained show an accuracy in the localization of the end-device of less than 150 meters.This result would make it possible to use the fingerprint instead of alternative, energy consuming, methodologies such as GPS in IoT (Internet of Things) applications where battery life is the primary requirement to be met.

Deep learning, specifically the supervised approach, has proved to be a breakthrough in depth prediction. However, the generalization ability of deep networks is still limited, and they cannot maintain a satisfactory performance on some inputs. Addressing a similar problem in the segmentation field, a scheme (f-BRS) has been proposed to refine predictions in the inference time. f-BRS adapts an intermediate activation function to each input by using user clicks as sparse labels. Given the similarity between user clicks and sparse depth maps, this paper aims at extending the application of f-BRS to depth prediction. Our experiments show that f-BRS, fused with a depth estimation baseline, is trapped in local optima, and fails to improve the network predictions. To resolve that, we propose a double-stage adaptive refinement scheme (DARS). In the first stage, a Delaunay-based correction module significantly improves the depth generated by a baseline network. In the second stage, a particle swarm optimizer (PSO) delineates the estimation through fine-tuning f-BRS parameters—that is, scales and biases. DARS is evaluated on an outdoor benchmark, KITTI, and an indoor benchmark, NYUv2 while for both the network is pre-trained on KITTI. The proposed scheme outperformed rival methods on both datasets.

Numerous approaches address over-fitting in neural networks: by imposing a penalty on the parameters of the network (L1, L2, etc); by changing the network stochastically (drop-out, Gaussian noise, etc.); or by transforming the input data (batch normalization, etc.). In contrast, we aim to ensure that a minimum amount of supporting evidence is present when fitting the model parameters to the training data. This, at the single neuron level, is equivalent to ensuring that both sides of the separating hyperplane (for a standard artificial neuron) have a minimum number of data points — noting that these points need not belong to the same class for the inner layers. We firstly benchmark the results of this approach on the standard Fashion-MINST dataset, comparing it to various regularization techniques. Interestingly, we note that by nudging each neuron to divide, at least in part, its input data, the resulting networks make use of each neuron, avoiding a hyperplane completely on one side of its input data (which is equivalent to a constant into the next layers). To illustrate this point, we study the prevalence of saturated nodes throughout training, showing that neurons are activated more frequently and earlier in training when using this regularization approach. A direct consequence of the improved neuron activation is that deep networks are now easier to train. This is crucially important when the network topology is not known a priori and fitting often remains stuck in a suboptimal local minima. We demonstrate this property by training a network of increasing depth (and constant width): most regularization approaches will result in increasingly frequent training failures (over different random seeds) whilst the proposed evidence-based regularization significantly outperforms in its ability to train deep networks.

Fracture analysis of reinforced concrete deep beam strengthened with carbon fiber-reinforced polymer (CFRP) plates was carried out. The present research aims to find out whether the crack propagation in a strengthened deep beam follows linear elastic fracture mechanics (LEFM) theory or nonlinear fracture mechanics theory. To do so, a new energy release rate based on nonlinear fracture mechanics theory was formulated on the finite element method and the discrete cohesive zone model (DCZM) was developed in deep beams. To validate and compare with numerical models, three deep beams with rectangular cross-sections were tested. The code results based on nonlinear fracture mechanics models were compared with experimental results and ABAQUS results carried out based on LEFM. The predicted values of initial stiffness, yielding point and failure load, energy absorption, and compressive strain in the concrete obtained by the proposed model were very close to the experimental results. However, the ABAQUS software results have greater differences with the experimental results. For example, the predicted failure load for the shear-strengthened deep beam using the proposed model has only 6.3% differences compared to the experimental result. However, the predicted failure load using ABAQUS software based on LEFM has greater differences (25.1%) compared to the experimental result.

GANs are well known for success in the realistic image gen-eration. However, they can be applied in tabular data generation as well.We will review and examine some recent papers about tabular GANs inaction. We will generate data to make train distribution bring closer tothe test. Then compare model performance trained on the initial traindataset, with trained on the train with GAN generated data, also wetrain the model by sampling train by adversarial training. We show thatusing GAN might be an option in case of uneven data distribution be-tween train and test data

The COVID-19 pandemic situation has created even more difficulties in the quick identification and screening of the COVID-19 patients for the medical specialists. Therefore, a significant study is necessary for detecting COVID-19 cases using an automated diagnosis method, which can aid in controlling the spreading of the virus. In this paper, the study suggests a Deep Convolutional Neural Network-based multi-classification approach (COV-MCNet) using eight different pre-trained architectures such as VGG16, VGG19, ResNet50V2, DenseNet201, InceptionV3, MobileNet, InceptionResNetV2, Xception which are trained and tested on the X-ray images of COVID-19, Normal, Viral Pneumonia, and Bacterial Pneumonia. The results from 3-class (Normal vs. COVID-19 vs. Viral Pneumonia) showed that only the ResNet50V2 model provides the highest classification performance (accuracy: 95.83%, precision: 96.12%, recall: 96.11%, F1-score: 96.11%, specificity: 97.84%) compared to rest of the models. The results from 4-class (Normal vs. COVID-19 vs. Viral Pneumonia vs. Bacterial Pneumonia) demonstrated that the pre-trained model DenseNet201 provides the highest classification performance (accuracy: 92.54%, precision: 93.05%, recall: 92.81%, F1-score: 92.83%, specificity: 97.47%). Notably, the ResNet50V2 (3-class) and DenseNet201 (4-class) models in the proposed COV-MCNet framework showed higher accuracy compared to the rest six models. This indicates that the designed system can produce promising results to detect the COVID-19 cases on the availability of more data. The proposed multi-classification network (COV-MCNet) significantly speeds up the existing radiology-based method, which will be helpful to the medical community and clinical specialists for early diagnosis of the COVID-19 cases during this pandemic.

The aim of this review is to provide a survey of the recent advances and the main remaining challenges related to the ultrananocrystalline diamond (UNCD) nanowires and other nanostructures which exhibit excellent capability as the core components for many diverse novel sensing devices, due to the unique material properties and geometry advantages. The doping introduced in the gas phase during deposition promotes p-type or n-type conductivity. With the establishment of the UNCD nanofabrication techniques, more and more nanostructure based devices are being explored in measuring basic physical and chemical parameters via classic and quantum methods, as exemplified by gas sensors, ultraviolet photodetectors, piezoresistance effect based devices, biological applications, and nitrogen-vacancy color center based magnetic field quantum sensors. Highlighted finally are some of the remaining challenges and future outlook in this area.

The transportation industry is rapidly transitioning from Internal Combustion Engine (ICE) based vehicles to Electric Vehicles (EVs) to promote clean energy. However, large-scale adoption of EVs can compromise the reliability of the power grids by introducing large uncertainty in the demand. Demand response with a controlled charge scheduling strategy for EVs can mitigate such issues. In this paper, a deep reinforcement learning- based charge scheduling strategy is developed for individual EVs by considering user’s dynamic driving behavior and charging preferences. The temporal dynamics of user’s anxiety about charging the EV battery is rigorously addressed. A dynamic weight allocation technique is applied to continuously tune user’s priority for charging and cost-saving with respect to charging duration. The sequential charging control problem is formulated as a Markov decision process, and an episodic approach to the deep deterministic policy gradient (DDPG) algorithm with target policy smoothing and delayed policy update techniques is applied to develop the optimal charge scheduling strategy. A real-world dataset that captures user’s driving behavior, such as arrival time, departure time, and charging duration, is utilized in this study. The extensive simulation results reveal the effectiveness of the proposed algorithm in minimizing energy cost while satisfying user’s charging requirements.

This paper reviews non-intrusive load monitoring (NILM) approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e. data with sampling rates lower than the AC base frequency. We first review the many degrees of freedom of these approaches, what has already been done in literature, and compile the main characteristics of the reviewed publications in an extensive overview table. The second part of the paper discusses selected aspects of the literature and corresponding research gaps. In particular, we do a performance comparison with respect to reported MAE and F$_1$-scores and observe different recurring elements in the best performing approaches, namely data sampling intervals below 10\,s, a large field of view, the usage of GAN losses, multi-task learning, and post-processing. Subsequently, multiple input features, multi-task learning and related research gaps are discussed, the need for comparative studies is highlighted, and finally, missing elements for a successful deployment of NILM approaches based on deep neural networks are pointed out. We conclude the review with an outlook on possible future scenarios.

In recent years the field of computer science has experienced great changes, due to the incredible advances in the field of artificial intelligence. Deep Learning models are responsible for most of them since the biggest milestones occurred in 2012 when AlexNet won the image classification challenge called ImageNet. These models have demonstrated great performances in different types of complex tasks like image restoration, medical diagnosis or object recognition. Their disadvantages are related to their high data dependency, which forces experts in the field to follow a precise methodology to obtain accurate models. In this paper, we describe a complete workflow that begins with the management of the raw data until the in-depth interpretation of the performance of the models. This should be taken as a high-level consultation document describing good practices that should be applied. Apart from the step-by-step methodology, we present different use cases that correspond to the two main problems of the field: classification and regression.

Technological advances in DBS hardware and software represent a significant growth area in functional neurosurgery. These advancements have the potential to significantly enhance treatment outcomes and expand the scope of neurological disorders that can be effectively addressed through DBS interventions. The introduction of directional DBS marks a new phase in neuromodulation, offering extended benefits for patients with Parkinson's disease, more efficient optimization of clinical outcomes, and targeted treatment of refractory symptoms through data-driven approaches. Implementing a multimodal programming strategy, incorporating novel current fractionation technology and image-guided tools for lead localization and brain sensing, further reduces reliance on traditional trial-and-error programming methods, paving the way for a more predictive application of this therapy. These advancements are expected to drive the development of sophisticated closed-loop stimulation systems capable of integrating continuous data streams for improved patient care.

Neurodegenerative illnesses, such as Parkinson’s disease (PD), have a substantial impact on the overall well-being of those who are affected. This study investigates and contrasts the capabilities of convolutional neural networks (CNN) in detecting Parkinson’s disease (PD) by utilising hand-drawn images alongside wave and spiral images as input data. This study employs pre-trained CNN models, specifically MobileNet, ResNet50, EfficientNet-B1, and InceptionV3, to classify Parkinson’s disease (PD). The findings demonstrate that MobileNet surpasses other architectural designs, as evidenced by the F1-Score of the four classes: Spiral Normal (0.87), Spiral Parkinson (0.86), Wave Normal (0.97), and Wave Parkinson (0.97). MobileNet has also shown a remarkable accuracy of 0.92 in diagnosing Parkinson’s disease. The result demonstrates the efficacy of MobileNet in extracting features from images. The results of this study enhance the application of deep learning methods in the early detection of PD, as well as help indicate the effectiveness of patient therapy and exercise, promising better patient outcomes through timely intervention and treatment.

A remarkable strengths of deep neural networks lies in their ability to discover patterns and representations from complex data. Deep learning models can learn and refine features at different levels of abstraction, enabling them to handle complex tasks in computer vision recognition, natural language processing, and speech recognition. The ability to generalize from examples, coupled with the capacity to process vast amounts of data, empowers deep learning to achieve state-of-the-art results across a wide spectrum of applications. An argument for this ability is based on similarities between deep neural networks and the nervous system. In this report, we argue that despite the remarkable performance of deep learning, there are still gaps between deep learning and the nervous system that needs to be closed to enable deep learning doing tasks that currently only the nervous system can perform

Voice spoofing attempts to break into a specific automatic speaker verification (ASV) system by forging the user’s voice, and can be used through methods, such as text-to-speech (TTS), voice conversion (VC), and replay attacks. Recently, deep learning-based voice spoofing countermeasures have been developed. however, the problem with replay is that it is difficult to construct a large number of datasets because it requires a physical recording process. To overcome these problems, this study proposes a pre-training framework based on multi-order acoustic simulation for replay voice spoofing detection. Multi-order acoustic simulation utilizes existing clean signal and room impulse response (RIR) datasets to generate audios, which simulate the various acoustic configurations of the original and replayed audios. The acoustic configuration refers to factors, such as the microphone type, reverberation, time delay, and noise that may occur between a speaker and microphone during the recording process. We assume that a deep learning model trained on an audio that simulates the various acoustic configurations of the original and replayed audios can classify the acoustic configurations of the original and replay audios well. To validate this, we performed pre-training to classify the audio generated by the multi-order acoustic simulation into 3 classes: clean signal, audio simulating the acoustic configuration of the original audio, and audio simulating the acoustic configuration of the replay audio. We also set the weights of the pre-training model to the initial weights of the replay voice spoofing detection model using the existing replay voice spoofing dataset and then performed fine-tuning. To validate the effectiveness of the proposed method, we evaluated the performance of the conventional method without pre-training and proposed method using an objective metric, i.e., the accuracy. As a result, the conventional method achieved 92.94% accuracy and proposed method achieved 98.16% accuracy.

Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods these observations offer the opportunity to address the challenge of estimating precicpation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global aplications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 minutes.

Fruit quality is a critical factor in the produce industry, affecting producers, distributors, consumers, and the economy. High-quality fruits are more appealing, nutritious, and safe, boosting consumer satisfaction and revenue for producers. Artificial Intelligence can aid in assessing the quality of the fruit using images. This paper presents a general machine-learning model for assessing fruit quality using deep image features. The model leverages the learning capabilities of the recent successful networks for image classification called Vision Transformers (ViT). The ViT model is built and trained with a combination of various fruit datasets and learned to distinguish between good and rotten fruit images. The general model demonstrated impressive results in accurately identifying the quality of various fruits such as Apples (with a 99.50% accuracy), Cucumbers (99%), Grapes (100%), Kakis (99.50%), Oranges (99.50%), Papayas (98%), Peaches (98%), Tomatoes (99.50%), and Watermelons (98%). However, it showed slightly lower performance in identifying Guavas (97%), Lemons (97%), Limes (97.50%), mangoes (97.50%), Pears (97%), and Pomegranates (97%).

In Taiwan, peanuts are classified by hand. The kernel quality is judged based on the appearance of peanuts. The identification takes considerable time and labor. Fatigue can induce misrecogni-tion or grade cognition instability due. Peanut defects are generally divided into health, underde-velopment, insect bite, and rupture. This study employed two imaging methods push-boom FX10 and Snapshot. Deep learning was used to detect peanut defects. A push-broom instrument was used for testing. There were 1,560 peanuts, including 240 good and 240 bad ones. There were a total of 1,080 good peanuts and bad peanuts in the test set data, the band selection was used, and a CNN model was built. Based on the results from three methods, 3DCNN could classify with 97%accuracy. The Snapshot was used to achieve the real-time design of a lightweight CNN model. Finally, five bands were selected using PCA, and the screening could be accurate and efficient. The maximum overall accuracy was about 98.5%. Kappa was 97.3% with real-time recognition. This will be a major advantage in the future practical application and commercialization processes. This technique can reduce labor costs, achieve intelligent detection and intelligent grading, and bring breakthroughs to smart agriculture for other crops as well.

The paper is based on the research project P2Endure funded within the H2020-EE-2016-2017 call. The main aim of the research is to propose innovative solutions for deep renovation that are applicable and replicable for the widest range of building typologies, from public to residential and historic buildings. In this paper, the methodology adopted to perform the energy analyses and to verify the achievement of the expected targets in terms of savings is defined, based on a range of real case studies. The main aim is to promote a guideline for designers showing specific instruments to perform towards the attainment of the 60% threshold of the energy savings giving advice on how to further improve the energy performance of the buildings, basing on the overview of the energy analyses run for similar cases.

Modelling both long and short-term user interests from historical data is crucial for accurate recommendations. However, unifying these metrics across multiple application domains can be challenging, and existing approaches often rely on complex, intertwined models which can be difficult to interpret. To address this issue, we propose a lightweight, plug-and-play interest enhancement module that fuses interest vectors from two independent models. After analyzing the dataset, we identify deviations in the recommendation performance of long and short-term interest models. To compensate for these differences, we use feature enhancement and loss correction during training. In the fusion process, we explicitly split long-term interest features with longer duration into multiple local features. We then use a shared attention mechanism to fuse multiple local features with short-term interest features to obtain interaction features. To correct for bias between models, we introduce a comparison learning task that monitors the similarity between local features, short-term features, and interaction features. This adaptively reduces the distance between similar features. Our proposed module combines and compares multiple independent long-term and short-term interest models on multiple domain datasets. As a result, it not only accelerates the convergence of the models but also achieves outstanding performance in challenging recommendation scenarios.

Plant-based protein sources derived from microalgae offer promise as low-carbon emission and nutrient-dense sources for human consumption. The current management of microalgae cultivation relies heavily on manual microscopic examination in order to identify desired and competing species, as well as predators. In this study, we trained and tested a transfer learning model modified from EfficientNetV2 B3 on 434 and 161 prospectively acquired images of the preferred Nannochloropsis sp microalgae and competitor Spirulina, respectively, and achieved &gt;98% classification for both species on tenfold cross-validation. The model was further enhanced with gradient-weighted class activation mapping, which allowed visualization of regions of the input images that were relevant to the classification, thereby improving its explainability. In this paper, we demonstrate that a simple deep transfer learning model can be used to identify microalgae species. The application addresses the practical need for robust automated monitoring of microalgae populations on industrial microalgae farms.

In this work we introduce an end-to-end multi-modal neural network to segment the Gross Tumor Volume (GTV) from 3D-CBCT’s during radiotherapy. We improve the tumor segmentation by using a U-net which takes additional information such as the tumor mask generated at the planning phase along with the CBCT volume. The mask contains relevant information about the tumor’s location and can guide the model to use this knowledge appropriately to give a better prediction. This technique could become an alternative to produce segmentation masks of GTV in CBCT automatically during radiotherapy as in the traditional RT-pipeline, they are not segmented. We have evaluated our model on a dataset of 82 patients who have undergone radiotherapy. We compare the results of registered target volumes from planning CT as mask seed with 2 different types of multi-modal architectures. Our model shows a DSC of 0.706±0.002 with Late Fusion and 0.702±0.015 with Early Fusion using the GTV Mask. The performance of the two models on this mask is similar, so we perform further experiments with different types of masks which suggest that Late Fusion model produces a better segmentation of the tumor than the Early Fusion model. We also provide an ablation study consisting of a single modality U-net and a metric based on the Planning CT mask registration. It indicates a clear advantage of using our model to produce segmentation for this type of imaging.

The emergence of unmanned aerial vehicles (UAVs) raised multiple concerns, given their potential for malicious misuse in unlawful acts Vision-based counter-UAV applications offer a reliable solution compared to acoustic and radio frequency-based solutions because of their high detection accuracy in diverse weather conditions. The existing solutions work well on trained datasets, but their accuracy is relatively low for real-time detection. In this paper, we model deep learning-empowered solutions to improve the multi-class UAV's classification performance using single-shot object detection algorithms YOLOv5 and YOLOv7. The transfer learning is employed for performance improvement and rapid training with improved results. We customized a multi-class dataset containing multi-rotor, fixed-wing, and single-rotor UAVs in challenging weather conditions. Experiments show that the integration of transfer learning has achieved good results, with an overall best average-classification precision of 94\%, an average recall of 93.1\%, a mAP$@$0.5 average of 95.3\%, and an average F1 score of 92.33\%. The dataset and code are available as an open source: https://github.com/ZeeshanKaleem/YOLOV5-Large-vs-YOLOV7.git

Hand gesture recognition has many valuable applications in engineering and health care. This study proposes a novel model which can accurately distinguish hand gestures using forearm muscles' surface electromyogram (sEMG) signals. A deep learning algorithm with hyper parameters impacting the final model’s accuracy and a convolutional neural network (CNN) were employed in the recognition stage. The number of convolutional layers, kernels per layer, and neurons in the dense layer were selected for optimization, while the remaining parameters, such as the learning rate, batch size, and number of epochs, were chosen based on trial and error and prior knowledge. The optimal values for the selected hyperparameters were obtained using a genetic algorithm to achieve maximum recognition accuracy. The UC2018 Dual-Myo database was used for training and testing the model based on EMG signals characterizing the activity of eight different hand gestures. The final structure of the model consisted of two convolutional layers with 131 and 28 kernels, a dense layer with 111 neurons, and a softmax layer with eight neurons. Upon optimizing the hyperparameters using the genetic algorithm, the accuracy of the proposed model increased from 91.86% to 96.4% at best and 95.3% on average in real-time applications and 99.6% in an offline mode. Future work is warranted towards improving the architecture and the computational cost.

Over the past decade, research in the field of Deep Learning has brought about novel improvements in image generation and feature learning; one such example being a Generative Adversarial Network. However, these improvements have been coupled with an increasing demand on mathematical literacy and previous knowledge in the field. Therefore, in this literature review, I seek to introduce Generative Adversarial Networks (GANs) to a broader audience by explaining their background and intuition at a more foundational level. I begin by discussing the mathematical background of this architecture, specifically topics in linear algebra and probability theory. I then proceed to introduce GANs in a more theoretical framework, along with some of the literature on GANs, including their architectural improvements and image-generation capabilities. Finally, I cover state-of-the-art image generation through style-based methods, as well as their implications on society.

This study evaluated the using of machine vision in combination with deep learning to identify weeds in real-time for wheat production system. PMAS-Arid Agriculture university research farm were selected for collection of images (6000 total images) of weeds and wheat crops under different weather condition. During growing season, the database was constructed to identify the weeds. For this study two framework were used TensorFlow and PyTorch under CNNs and Deep learning. Deep learning perfromed better with in PyTourch value as compared to another model in Tensorflow. comparing with other networks such as YOLOv4, we concluded that our network reaches a better result between speed and accuracy. Specifically, the maximum precision of weed and wheat plants were 0.89 and 0.91 respectively with 9.43 ms and 12.38 ms inference time per image (640 × 640) NVIDIA RTX2070 GPU.

To solve two key problems in the identification of people who are infected with COVID-19: the first problem is that the identification accuracy is not high enough. The second problem is that present identification method such as nucleic acid testing is expensive in many countries. Methods: So, I decided to design a fast identification method for COVID-19 patients which is based on deep learning. After the model (CoughNet) learns more than 6,000 cough spectrograms of both COVID-19 patients and normal people, the accuracy rate of identification of COVID-19 patients and normal people is higher than 99% in the test set. Structure: This paper is mainly divided into three parts: the first part introduces the main background and research status of the research; The second part introduces the research methods; The third part introduces the specific process of the experiment.

A hybrid smart process and material design system for nanoimprinting is proposed, which combines with a learning system based on experimental and numerical simulation results. Instead of carrying out extensive learning experiments for various condition, the simulation learning results are partially complimented where the results can be theoretically predicted by numerical simulation. In other word, the lacking data in experimental learning are complimented by simulation-based learning results. Therefore, the prediction of nanoimprint results under various conditions without experimental learning could be realized even for unknown materials. In this study, material and process design for a low-temperature nanoimprint process using glycerol-containing polyvinyl alcohol are demonstrated. Experimental results under limited conditions are learned to investigate optimum Glycerol concentrations and process temperatures. On the other hand, simulation-based learning is used to predict the dependence on press pressure and shape parameters. The prediction results for unknown Glycerol concentrations agreed well with the follow-up experiments.

The Covid-19 also known as the Coronavirus is a viral disease from the SARS-CoV-2 family of virus, as at December 2019 the first case of this virus infection was identified at Wuhan, China, this seemingly isolated case soon became a global pandemic, whose effect was felt globally which also had colossal effects on both health, economic and politics . As at the time of this research about 4.5 million people have died of the Coronavirus and over 215 million people already infected by it. This pandemic stood out not just for its scale but for how social media was a major contribution to its spread as well as to curbing it. The power of social media was used to spread misinformation as well as to spread awareness on the subject, with both having massive impact on the people. In this paper we will be running a sentimental analysis on twitter under the keyword “Covid-19 and Coronavirus”, twitter is a powerful social media tool that is known for its ability to keep trends in the form of tweets, we will be drawing correlations between the peaks of tweet with the peak of infection. We will also be analyzing to know what the impact of these tweets are having on the rate of the infection and vice versa. We will also be analyzing what people are tweeting most about, what are the talking points, comparing both real time and past tweets with real time infection and death rates using deep different learning methods to access what information can be derived from it.

Sentiment analysis is a process of extracting opinions into the positive, negative, or neutral categories from a pool of text using Natural Language Processing (NLP). In the recent era, our society is swiftly moving towards virtual platforms by joining virtual communities. Social media such as Facebook, Twitter, WhatsApp, etc are playing a very vital role in developing virtual communities. A pandemic situation like COVID-19 accelerated people's involvement in social sites to express their concerns or views regarding crucial issues. Mining public sentiment from these social sites especially from Twitter will help various organizations to understand the people's thoughts about the COVID-19 pandemic and to take necessary steps as well. To analyze the public sentiment from COVID-19 tweets is the main objective of our study. We proposed a deep learning architecture based on Bidirectional Gated Recurrent Unit (BiGRU) to accomplish our objective. We developed two different corpora from unlabelled and labeled COVID-19 tweets and use the unlabelled corpus to build an improved labeled corpus. Our proposed architecture draws a better accuracy of 87% on the improved labeled corpus for mining public sentiment from COVID-19 tweets.

Introduction: Dental segmentation in panoramic radiograph has become very relevant in dentistry, since it allows health professionals to carry out their assessments more clearly and helps them to define the best possible treatment plan for their patients. Objectives: In this work, a comparative study is carried out with four segmentation algorithms (U-Net, DCU-Net, DoubleU-Net and Nano-Net) that are prominent in the medical literature on segmentation and we evaluate their results with the current state of the art of dental segmentation in panoramic radiograph. Methods: These algorithms were tested with a dataset consisting of 1,500 images, considering experiment scenarios with and without augmentation data. Results: DoubleU-Net was the model that presented the best results among the analyzed models, reaching 96.591% accuracy and 92.886% Dice using the dataset with data augmentation. Another model that stood out was Nano-Net using the dataset without data augmentation; this model achieved results close to that of the literature with only 235 thousand trainable parameters, while the literature model (TSASNet) contains 78 million. Conclusions: The results obtained in this work are satisfactory and present paths for a better and more effective dental segmentation process.

Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

The usage and amount of information available on the internet increase over the past decade. This digitization leads to the need for automated answering system to extract fruitful information from redundant and transitional knowledge sources. Such systems are designed to cater the most prominent answer from this giant knowledge source to the user’s query using natural language understanding (NLU) and thus eminently depends on the Question-answering(QA) field. Question answering involves but not limited to the steps like mapping of user’s question to pertinent query, retrieval of relevant information, finding the best suitable answer from the retrieved information etc. The current improvement of deep learning models evince compelling performance improvement in all these tasks. In this review work, the research directions of QA field are analyzed based on the type of question, answer type, source of evidence-answer, and modeling approach. This detailing followed by open challenges of the field like automatic question generation, similarity detection and, low resource availability for a language. In the end, a survey of available datasets and evaluation measures is presented.

Beyond semantic segmentation,3D instance segmentation(a process to delineate objects of interest and also classifying the objects into a set of categories) is gaining more and more interest among researchers since numerous computer vision applications need accurate segmentation processes(autonomous driving, indoor navigation, and even virtual or augmented reality systems…) This paper gives an overview and a technical comparison of the existing deep learning architectures in handling unstructured Euclidean data for the rapidly developing 3D instance segmentation. First, the authors divide the 3D point clouds based instance segmentation techniques into two major categories which are proposal based methods and proposal free methods. Then, they also introduce and compare the most used datasets with regard to 3D instance segmentation. Furthermore, they compare and analyze these techniques performance (speed, accuracy, response to noise…). Finally, this paper provides a review of the possible future directions of deep learning for 3D sensor-based information and provides insight into the most promising areas for prospective research.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

Semantic segmentation is a very popular topic in modern computer vision and it has applications to many fields. Researchers proposed a variety of architectures over time, but the most common ones exploit an encoder-decoder structure that aims to capture the semantics of the image and it low level features. The encoder uses convolutional layers, in general with a stride larger than one, to extract the features, while the decoder recreates the image by upsampling an using skip connections with the first layers. In this work, we use DeepLab as architecture to test the effectiveness of creating an ensemble of networks by randomly changing the activation functions inside the network multiple times. We also use different backbone networks in our DeepLab to validate our findings. We manage to reach a dice coefficient of 0.888, and a mean Intersection over Union (mIoU) of 0.825, in the competitive Kvasir-SEG dataset. Results in skin detection also confirm the performance of the proposed ensemble, which is ranked first with respect to other state-of-the-art approaches (including HardNet) in a large set of testing datasets. The developed code will be available at https://github.com/LorisNanni.

The betatron tune in the Large Hadron Collider (LHC) is measured using a Base-Band Tune (BBQ) system. The processing of these BBQ signals is often perturbed by 50 Hz noise harmonics present in the beam. This causes the tune measurement algorithm, currently based on peak detection, to provide incorrect tune estimates during the acceleration cycle with values that oscillate between neighbouring harmonics. The LHC tune feedback (QFB) cannot be used to its full extent in these conditions as it relies on stable and reliable tune estimates. In this work we propose new tune estimation algorithms, designed to mitigate this problem through different techniques. As ground-truth of the real tune measurement does not exist, we developed a surrogate model, which allowed us to perform a comparative analysis of a simple weighted moving average, Gaussian Processes and different deep learning techniques. The simulated dataset used to train the deep models was also improved using a variant of Generative Adversarial Networks (GANs) called SimGAN. In addition we demonstrate how these methods perform with respect to the present tune estimation algorithm.

Tremendous progress has been witnessed in artificial intelligence within the domain of neural network backed deep learning systems and its applications. As we approach the post Moore’s Law era, the limit of semiconductor fabrication technology along with a rapid increase in data generation rates have lead to an impending growing challenge of tackling newer and more modern machine learning problems. In parallel, quantum computing has exhibited rapid development in recent years. Due to the potential of a quantum speedup, quantum based learning applications have become an area of significant interest, in hopes that we can leverage quantum systems to solve classical problems. In this work, we propose a quantum deep learning architecture; we demonstrate our quantum neural network architecture on tasks ranging from binary and multi-class classification to generative modelling. Powered by a modified quantum differentiation function along with a hybrid quantum-classic design, our architecture encodes the data with a reduced number of qubits and generates a quantum circuit, loading it onto a quantum platform where the model learns the optimal states iteratively. We conduct intensive experiments on both the local computing environment and IBM-Q quantum platform. The evaluation results demonstrate that our architecture is able to outperform Tensorflow-Quantum by up to 12.51% and 11.71% for a comparable classic deep neural network on the task of classification trained with the same network settings. Furthermore, our GAN architecture runs the discriminator and the generator purely on quantum hardware and utilizes the swap test on qubits to calculate the values of loss functions. In comparing our quantum GAN, we note our architecture is able to achieve similar performance with 98.5% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms other quantum based GANs in the literature for up to 125.0% in terms of similarity between generated distributions and original data sets.

Background: Albumin has a pivotal role in the homeostasis of osmotic pressure and is associated with cardiovascular, nephrotic, hepatic, and nutritional diseases. The detection of hypoalbuminemia is a cornerstone for diagnosis of hidden diseases and patient deterioration. We developed and validated a deep-learning-based model (DLM) for detection of hypoalbuminemia using electrocardiography (ECG). Methods: This historical cohort study included data from consecutive patients from two hospitals. The patient data in one hospital were divided into development (82,499 ECGs from 54,248 patients) and internal validation (20,664 ECGs from 20,664 patients) datasets, whereas the patient data in the other hospital were included in only an external validation (37,421 ECGs from 37,421 patients) dataset. An DLM was developed using a 12-lead ECG signal, age, and sex from the development dataset. The endpoint was hypoalbuminemia, defined by serum albumin concentration below 3.5 g/dL. Results: During the internal and external validations, the areas under the receiver operating characteristic curve of the DLM for the detection of hypoalbuminemia were 0.887 (0.877–0.897) and 0.888 (0.880–0.896), respectively. Among the 27,400 individuals without hypoalbuminemia at the initial laboratory exam, those identified by the DLM as higher-risk patients had a significantly larger change in developing hypoalbuminemia than those in the low-risk group (7.09% vs. 1.01%, p < 0.001) during 24 months. The sensitivity map showed that the DLM focused on the T wave and QRS complex for the detection of hypoalbuminemia. Conclusions: The DLM exhibited a high accuracy for hypoalbuminemia detection and prediction using 12-, 6-, and single-lead ECGs.

Classification of human actions from uni-modal and multi-modal datasets is an ongoing research problem in computer vision. This review is aimed to scope current literature on data-fusion and action-recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The rise in number of action recognition datasets intersects with advances in deep-learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality - such as RGB, depth, skeleton, and infrared - has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this article we will focus solely on areas such as data fusion and recognition techniques in the context of vision with a uni-modal and multi-modal perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions.

An eruption of volcano is related to the past volcanic and tectonic seismicity. Recently, on November 29, 2020, a 1423 m Mount Ile Lewotolok in Lembata Island has erupted. In here, this paper aimed to assess the volcanic and tectonic seismicity as determinant factor and precursor of recent Mt Ile Lewotolok eruption. The assessment shows that Mt Ile Lewotolok volcanic activities were characterized by both tectonic and deep volcanic seismicity. Since 2010, mean tectonic quake magnitudes of M 4.133 (95%CI:M 3.205-5.062) have occurred at mean depth of 13.500 km (95%CI:8.201-18.799 km) within a distance of 3-4 km from the summit. Tectonic quake has occurred frequently in southwest of Ile Lewotolok and this has contributed to the past eruptions in 2012 and 2017. Recent eruption has been influenced by deep volcanic seismicity rather than local tectonic. Based on November 2020 record, mean of deep volcanic seismicity frequency was 2.190 events/day (95%CI:1.136-3.243 events/day km) that has outnumbered (t_test=2.665, P=0.013) the events of local tectonic quakes (mean 0.621 events/day; 95%CI:0.142-1.099events/day). Prior to the eruption there was significant increase of deep volcanic seismicity (P=0.023) while local tectonic quake was not showing an increasing trend (P=0.764). This result confirms that the deep volcanic seismicity frequency is a precursor that may trigger the eruption and deep volcanic seismicity data can be used as indicator of volcanic activities.

Mouthbrooding or oral incubation, the retention of early developmental stages inside of the mouth for an extended period of time, has evolved multiple times in bony fishes1,2. Though uncommon, this form of parental care has been documented and well-studied in several groups of freshwater fishes but is also known to occur in a small number of marine fishes, all inhabiting coastal waters1,2. A recent paper3, reported for the first time mouthbrooding in a deep-water fish species, the zeiform Parazen pacificus, which according to the authors “fills in a gap in the larval literature for this family of fishes and prompts further investigation into other novel reproductive modes of deep-sea fauna.”

The conventional machine learning (ML) algorithms are continuously advancing and evolving at a fast-paced by introducing the novel learning algorithms. ML models are continually improving using hybridization and ensemble techniques to empower computation, functionality, robustness, and accuracy aspects of modeling. Currently, numerous hybrid and ensemble ML models have been introduced. However, they have not been surveyed in a comprehensive manner. This paper presents the state of the art of novel ML models and their performance and application domains through a novel taxonomy.

This paper proposes a method for recognizing audio events in urban environments that combines handcrafted audio features with a deep learning architectural scheme (Convolutional Neural Networks, CNNs), which has been trained to distinguish between different audio context classes. The core idea is to use the CNNs as a method to extract context-aware deep audio features that can offer supplementary feature representations to any soundscape analysis classification task. Towards this end, the CNN is trained on a database of audio samples which are annotated in terms of their respective "scene" (e.g. train, street, park), and then it is combined with handcrafted audio features in an early fusion approach, in order to recognize the audio event of an unknown audio recording. Detailed experimentation proves that the proposed context-aware deep learning scheme, when combined with the typical handcrafted features, leads to a significant performance boosting in terms of classification accuracy. The main contribution of this work is the demonstration that transferring audio contextual knowledge using CNNs as feature extractors can significantly improve the performance of the audio classifier, without need for CNN training (a rather demanding process that requires huge datasets and complex data augmentation procedures).

An effective on-board cloud detection method in small satellites would greatly improve the downlink data transmission efficiency and reduce the memory cost. In this paper, an ensemble method combining a lightweight U-Net with wavelet image compression is proposed and evaluated. The red, green, blue and infrared waveband images from Landsat-8 dataset are trained and tested to estimate the performance of proposed method. The LeGall-5/3 wavelet transform is applied on the dataset to accelerate the neural network and improve the feasibility of on-board implement. The experiment results illustrate that the overall accuracy of the proposed model achieves 97.45% by utilizing only four bands. Tests on low coefficients of compressed dataset have shown that the overall accuracy of the proposed method is still higher than 95%, while its inference speed is accelerated to 0.055 second per million pixels and maximum memory cost reduces to 2Mb. By taking advantage of mature image compression system in small satellites, the proposed method provides a good possibility of on-board cloud detection based on deep learning.

This paper presents a new method : HIVEC to learn latent vector representations of graphs in a manner that captures the semantic dependencies of sub-structures. The representations can then be used in machine learning algorithms for tasks such as graph classification, clustering etcetera. The method proposed is unsupervised and uses the information of co-occurrence of sub-structures. It introduces a notion of hierarchical embeddings that allows us to avoid repetitive learning of sub-structures for every new graph. As an alternative to deep learning methods, the edit distance similarity between sub-structures is also used to learn vector representations. We compare the performance of these methods against previous work.