Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory

Understanding how congestion at one location can cause ripples throughout large-scale transportation network is vital for transportation researchers and practitioners to pinpoint traffic bottlenecks for congestion mitigation. Traditional studies rely on either mathematical equations or simulation techniques to model traffic congestion dynamics. However, most of the approaches have limitations, largely due to unrealistic assumptions and cumbersome parameter calibration process. With the development of Intelligent Transportation Systems (ITS) and Internet of Things (IoT), transportation data become more and more ubiquitous. This triggers a series of data-driven research to investigate transportation phenomena. Among them, deep learning theory is considered one of the most promising techniques to tackle tremendous high-dimensional data. This study attempts to extend deep learning theory into large-scale transportation network analysis. A deep Restricted Boltzmann Machine and Recurrent Neural Network architecture is utilized to model and predict traffic congestion evolution based on Global Positioning System (GPS) data from taxi. A numerical study in Ningbo, China is conducted to validate the effectiveness and efficiency of the proposed method. Results show that the prediction accuracy can achieve as high as 88% within less than 6 minutes when the model is implemented in a Graphic Processing Unit (GPU)-based parallel computing environment. The predicted congestion evolution patterns can be visualized temporally and spatially through a map-based platform to identify the vulnerable links for proactive congestion mitigation.     

Trust management for internet of things using cloud computing and security in smart cities

Many consumers participate in the smart city via smart portable gadgets such as wearables, personal gadgets, mobile devices, or sensor systems. In the edge computation systems of IoT in the smart city, the fundamental difficulty of the sensor is to pick reliable participants. Since not all smart IoT gadgets are dedicated, certain intelligent IoT gadgets might destroy the networks or services deliberately and degrade the customer experience. A trust-based internet of things (TM-IoT) cloud computing method is proposed in this research. The problem is solved by choosing trustworthy partners to enhance the quality services of the IoT edging network in the Smart architectures. A smart device choice recommendation method based on the changing networks was developed. It applied the evolutionary concept of games to examine the reliability and durability of the technique of trust management presented in this article. The reliability and durability of the trustworthiness-managing system, the Lyapunov concept was applied.A real scenario for personal-health-control systems and air-qualitymonitoring and assessment in a smart city setting confirmed the efficiency of the confidence-management mechanism. Experiments have demonstrated that the methodology for trust administration suggested in this research plays a major part in promoting multi-intelligent gadget collaboration in the IoT edge computer system with an efficiency of 97%. It resists harmful threads against service suppliers more consistently and is ideal for the smart world's massive IoT edge computer system.

     

Sister-chromatid exchange in highly purified human CD4 and CD8 lymphocytes

Sister-chromatid exchange (SCE) frequencies were determined in human peripheral blood CD₄⁺ and CD₈⁺ T lymphocyte subpopulations which were rapidly and highly purified from pooled T lymphocytes by immunological methods. The purified lymphocytes were stimulated with phytohemagglutinin (PHA) for 4 days. CD₄⁺ lymphocytes showed significantly higher SCE frequencies than autologous CD₈⁺ lymphocytes when measured simultaneously after identical bromodeoxyuridine (BrdU) incubation times. Differences in SCE frequencies between CD₄⁺ and CD₈⁺ lymphocytes were also detected when mitomycin C (MMC) was added to the cultures. Higher SCE frequencies in CD₄⁺ lymphocytes were associated with lower proliferating rate indices (PRI) as compared to autologous CD₈⁺ lymphocytes. Abnormalities in CD₄⁺ T lymphocyte function and number in peripheral blood have been observed in several diseases characterized by immunological disorders. Thus, our data may suggest a link between some immunological disturbances and abnormal SCE frequencies in T lymphocyte subsets.     

Effect of cell-seeding density on the proliferation and gene expression profile of human umbilical vein endothelial cells within ex vivo culture

Background aimsCharacterization of endothelial cell–biomaterial interaction is crucial for the development of blood-contacting biomedical devices and implants. However, a crucial parameter that has largely been overlooked is the cell-seeding density.MethodsThis study investigated how varying cell-seeding density influences human umbilical vein endothelial cell (HUVEC) proliferation on three different substrata: gelatin, tissue culture polystyrene (TCPS) and poly-l-lactic acid (PLLA).ResultsThe fastest proliferation was seen on gelatin, followed by TCPS and PLLA, regardless of seeding density. On both TCPS and gelatin, maximal proliferation was attained at an initial seeding density of 1000 cells/cm². At seeding densities above and below 1000 cells/cm², the proliferation rate decreased sharply. On PLLA, there was a decrease in cell numbers over 7 days of culture, below a certain threshold seeding density (c. 2500–3000 cells/cm²), which meant that some of the cells were dying off rather than proliferating. Above this threshold seeding density, HUVEC displayed slow proliferation. Subsequently, quantitative real-time polymerase chain reaction (RT-qPCR) analysis of eight gene markers associated with adhesion and endothelial functionality (VEGF-A, integrin-α5, VWF, ICAM1, ICAM2, VE-cadherin, endoglin and PECAM1) was carried out on HUVEC seeded at varying densities on the three substrata. A significant downregulation of gene expression was observed at an ultralow cell-seeding density of 100 cells/cm². This was accompanied by an extremely slow proliferation rate, probably because of an acute lack of intercellular contacts and paracrine signaling.ConclusionHence, this study demonstrates that seeding density has a profound effect on the proliferation and gene expression profile of endothelial cells seeded on different biomaterial surfaces.     

Explicit coordination to prevent congestion in data center networks

Large cluster-based cloud computing platforms increasingly use commodity Ethernet technologies, such as Gigabit Ethernet, 10GigE, and Fibre Channel over Ethernet (FCoE), for intra-cluster communication. Traffic congestion can become a performance concern in the Ethernet due to consolidation of data, storage, and control traffic over a common layer-2 fabric, as well as consolidation of multiple virtual machines (VMs) over less physical hardware. Even as networking vendors race to develop switch-level hardware support for congestion management, we make the case that virtualization has opened up a complementary set of opportunities to reduce or even eliminate network congestion in cloud computing clusters. We present the design, implementation, and evaluation of a system called XCo, that performs explicit coordination of network transmissions over a shared Ethernet fabric to proactively prevent network congestion. XCo is a software-only distributed solution executing only in the end-nodes. A central controller uses explicit permissions to temporally separate (at millisecond granularity) the transmissions from competing senders through congested links. XCo is fully transparent to applications, presently deployable, and independent of any switch-level hardware support. We present a detailed evaluation of our XCo prototype across a number of network congestion scenarios, and demonstrate that XCo significantly improves network performance during periods of congestion. We also evaluate the behavior of XCo for large topologies using NS3 simulations.     

Physiological and biomechanical differences between wheelchair-dependent and able-bodied subjects during wheelchair ergometry

The purpose of this study was to compare the physiological and biomechanical responses of wheelchair-dependent persons (WCD) to able-bodied persons (AB) during manual wheelchair ergometry. Five WCD and five AB performed a discontinuous wheelchair ergometer test starting at 12.8 W at 30 rev.min-1 (57 m.min-1) with increments of 7.0 W at 6-min intervals. Biomechanical data were collected 3.5 min into each stage followed by the collection of physiological data. After the fifth stage, peak oxygen consumption was determined by having the subject work against a resistance of 14.7-19.6 N at 30 rev.min-1. The WCD had significantly higher net mechanical efficiency at 26.7, 33.6 and 40.6 W in comparison to the AB. The WCD had significantly greater shoulder extension at the point of initial wheel contact as measured by the shoulder angle, while the AB had significantly greater shoulder range of motion at all work rates in comparison to the WCD. The results demonstrate that a significant physiological difference exists in the manner by which WCD and AB accomplish wheelchair ergometry. The biomechanical differences between AB and WCD were found to be a prominent factor contributing to the higher mechanical efficiency of WCD over AB. It was concluded that basic physiological and biomechanical differences exist between WCD and AB in manual wheelchair locomotion and that these differences are important considerations to the interpretation of data in wheelchair ergometry studies.     

CECT: computationally efficient congestion-avoidance and traffic engineering in software-defined cloud data centers

The proliferation of cloud data center applications and network function virtualization (NFV) boosts dynamic and QoS dependent traffic into the data centers network. Currently, lots of network routing protocols are requirement agnostic, while other QoS-aware protocols are computationally complex and inefficient for small flows. In this paper, a computationally efficient congestion avoidance scheme, called CECT, for software-defined cloud data centers is proposed. The proposed algorithm, CECT, not only minimizes network congestion but also reallocates the resources based on the flow requirements. To this end, we use a routing architecture to reconfigure the network resources triggered by two events: (1) the elapsing of a predefined time interval, or, (2) the occurrence of congestion. Moreover, a forwarding table entries compression technique is used to reduce the computational complexity of CECT. In this way, we mathematically formulate an optimization problem and define a genetic algorithm to solve the proposed optimization problem. We test the proposed algorithm on real-world network traffic. Our results show that CECT is computationally fast and the solution is feasible in all cases. In order to evaluate our algorithm in term of throughput, CECT is compared with ECMP (where the shortest path algorithm is used as the cost function). Simulation results confirm that the throughput obtained by running CECT is improved up to 3× compared to ECMP while packet loss is decreased up to 2×.     

Effects of Sodium Selenite on Aflatoxin B1-Induced Decrease of Ileac T cell and the mRNA Contents of IL-2, IL-6, and TNF-α in Broilers

The aim of this work was to assess the protective effect of sodium selenite on the ileum mucosal immunologic toxicity induced by aflatoxin B₁ (AFB₁). One hundred and eighty one-day-old healthy male avian broilers were divided into four groups of three replicates and 15 birds per replicate and fed with basal diet (control group), 0.3 mg/kg AFB₁ (AFB₁ group), 0.4 mg/kg Se (+Se group), and 0.3 mg/kg AFB₁?+?0.4 mg/kg Se (AFB₁+Se group), respectively. The ileac T-cell subsets were determined by the methods of flow cytometry (FCM), and the mRNA contents of interleukin-2 (IL-2), interleukin-6(IL-6), and tumor necrosis factor-alpha (TNF-α) by quantitative real-time PCR. Compared with those in control group, the percentages of CD₃ ⁺, CD₃ ⁺CD₄ ⁺, CD₃ ⁺CD₈ ⁺ intraepithelial lymphocytes (IELs) and LPLs, the CD4⁺/CD8⁺ ratio of IELs, and the mRNA contents of IL-2, IL-6, and TNF-α were decreased in AFB₁ group. However, compared with those in AFB₁ group, these parameters of AFB₁+Se group were increased to be close to those in control group. It was concluded that 0.3 mg/kg AFB₁ could reduce the cellular immune function of the ileum mucosa, but 0.4 mg/kg supplemented dietary selenium showed protective effects on AFB₁-induced immunologic injury.     

Protection against the allergic airway inflammation depends on the modulation of spleen dendritic cell function and induction of regulatory T cells in mice

Background

Allergen-induced imbalance of specific T regulatory (Treg) cells and T helper 2 cells plays a decisive role in the development of immune response against allergens.

Objective

To evaluate effects and potential mechanisms of DNA vaccine containing ovalbumin (OVA) and Fc fusion on allergic airway inflammation.

Methods

Bronchoalveolar lavage (BAL) levels of inflammatory mediators and leukocyte infiltration, expression of CD_11c ⁺CD₈₀ ⁺ and CD_11c ⁺CD₈₆ ⁺ co-stimulatory molecules in spleen dendritic cells (DCs), circulating CD₄ ⁺ and CD₈ ⁺ T cells, Foxp3⁺ in spleen CD₄ ⁺ T cells and spleen CD₄ ⁺ T cells were measured in OVA-sensitized and challenged animals pretreated with pcDNA, OVA-pcDNA, Fc-pcDNA, and OVA-Fc-pcDNA.

Results

OVA-Sensitized and challenged mice developed airway inflammation and Th2 responses, and decreased the proliferation of peripheral CD₄ ⁺and CD₈ ⁺ T cells and the number of spleen Foxp₃ ⁺ Treg. Those changes with increased INF-γ production and reduced OVA-specific IgE production were protected by the pretreatment with OVA-Fc-pcDNA.

Conclusion

DNA vaccine encoding both Fc and OVA showed more effective than DNA vaccine encoding Fc or OVA alone, through the balance of DCs and Treg.     

Immunomodulatory effects of <Emphasis Type="Italic">Caulerpa racemosa</Emphasis> var peltata polysaccharide and its selenizing product on T lymphocytes and NK cells in mice

A polysaccharide, CrvpPS, was isolated from Caulerpa racemosa var peltata. It was reacted with nano-selenium in distilled water containing ascorbic acid (Vit C) to form a stable CrvpPS-nano-Se complex. The immunomodulatory effects of CrvpPS and CrvpPS-nano-Se on T lymphocytes subgroups and NK cells in mice were investigated. After intragastric administration for 10 days separately, both CrvpPS and CrvpPS-nano-Se showed significant stimulatory functions to thymus gland of mice. Moreover, the CrvpPS-nano-Se induced the percentage of CD₃ ⁺, CD₃ ⁺CD₄ ⁺, NK cells and the CD₄ ⁺/CD₈ ⁺ value to increase significantly (P<0.05) when analyzed by flow cytometry, which is better than the CrvpPS, sucrose-nano-Se, and even the positive drug levamisole.     

A dynamic programming heuristic for vehicle routing with time-dependent travel times and required breaks

For the intensively studied vehicle routing problem (VRP), two real-life restrictions have received only minor attention in the VRP-literature: traffic congestion and driving hours regulations. Traffic congestion causes late arrivals at customers and long travel times resulting in large transport costs. To account for traffic congestion, time-dependent travel times should be considered when constructing vehicle routes. Next, driving hours regulations, which restrict the available driving and working times for truck drivers, must be respected. Since violations are severely fined, also driving hours regulations should be considered when constructing vehicle routes, even more in combination with congestion problems. The objective of this paper is to develop a solution method for the VRP with time windows (VRPTW), time-dependent travel times, and driving hours regulations. The major difficulty of this VRPTW extension is to optimize each vehicle’s departure times to minimize the duty time of each driver. Having compact duty times leads to cost savings. However, obtaining compact duty times is much harder when time-dependent travel times and driving hours regulations are considered. We propose a restricted dynamic programming (DP) heuristic for constructing the vehicle routes, and an efficient heuristic for optimizing the vehicle’s departure times for each (partial) vehicle route, such that the complete solution algorithm runs in polynomial time. Computational experiments demonstrate the trade-off between travel distance minimization and duty time minimization, and illustrate the cost savings of extending the depot opening hours such that traveling before the morning peak and after the evening peak becomes possible.     

Human innate immunity under the conditions of five-day dry immersion

The system of congenital immunity was studied in 12 apparently healthy men 18 to 26 years of age subjected to five-day dry immersion without the use of countermeasures. Peripheral blood was analyzed for monocytes, granulocytes, and lymphocytes expressing the TLR²⁺, TLR⁴⁺, TLR⁶⁺, CD11b⁺, CD¹⁴⁺, CD¹⁶⁺, CD¹⁸⁺, CD²⁴⁺, CD³⁶⁺, CD⁵⁴⁺, CD⁵⁶⁺, and CD²⁰⁶⁺ receptors. Expression of the early activation marker CD69 on natural killer cells was studied in unstimulated and interleukin-2-activated mononuclear cell cultures. The negative shifts in the congenital immunity system in some volunteers at the end of immersion and during recovery can be regarded as warnings about the depletion of the system’s reserves and the increase of the risk of infectious diseases, such as those caused by normal microflora, which typically does not provoke pathological reactions in the host.     

Wearable cardioverter-defibrillator (life-vest): A feasible bridging treatment in adult congenital heart disease

BackgroundWearable cardioverter-defibrillators (WCDs) are currently used in patients at temporarily heightened risk for sudden cardiac death (SCD) who are temporarily unable to receive an implantable cardioverter-defibrillator (ICD). WCD can safely record and terminate life-threatening arrhythmias through a non-invasive electrode-based system. The current clinical indications for WCD use are varied and keep evolving as experience with this technology increases.MethodsWe reviewed and explored the data behind indications for WCD use and discuss its usefulness in congenital heart disease (CHD) patients.ResultsWe considered 8 consecutive patients (mean age 35.25 years, range 18–51 years, average duration of WCD use 4 months, range 3–6 months) with complex CHD, in which a WCD was used between June 2018 and January 2022. No sustained ventricular arrhythmias requiring shocks were recorded in the observation period. No inappropriate shocks were recorded. All the patients showed a good compliance and a very high mean wear time per day (21.2 ± 1 h a day). Four patients implanted a permanent device (3 CRT-D, 1 ICD), three underwent cardiac surgery at the end of the WCD period and one is still on the waiting list for the operation.ConclusionsLarger trial could confirm the possible conceivable benefit from an extended use of the WCD in certain populations with complex CHD as in our case series, especially in patients with life-treating ventricular arrhythmias waiting for surgery for residual cardiac defects or in the early phases following the surgical/hemodynamic interventions, patients with tachycardiomyopathy expected to improve after the arrhythmias are removed and patients awaiting implantation of an ICD at high risk due to active infection.     

青藏高原植被生态系统垂直分布变化的情景模拟

如何模拟和揭示青藏高原植被生态系统垂直分布在全球气候变化驱动下的时空变化情景,对定量解析青藏高原陆地生态系统对气候变化响应效应具有重要意义。该论文基于Holdridge life zone （HLZ）模型,结合数字高程模型（DEM）数据,改变模型输入参数模式,发展了改进型HLZ生态系统模型。结合1981-2010（T0）时段的气候观测数据和IPCC CMIP5 RCP2.6、RCP4.5、RCP8.5三种情景2011-2040（T1）、2041-2070（T2）、2071-2100（T3）三个时段气候情景数据,实现了青藏高原植被生态系统垂直分布的时空变化情景模拟。引入生态系统平均中心时空偏移趋势模型和生态多样性指数模型,定量揭示了青藏高原植被生态系统在不同垂直带上的时空变化情景。结果显示：青藏高原共有16种植被生态系统类型;冰雪/冰原、高山潮湿苔原和亚高山湿润森林为青藏高原主要的植被生态系统类型,其面积之和占到了青藏高原总面积的56.26%;高山干苔原、亚高山潮湿森林、山地灌丛、山地湿润森林和荒漠等对气候变化的敏感性总体上高于其它类型;在T0-T3期间,青藏高原的高山湿润苔原、高山干苔原、荒漠呈持续减少趋势,平均每10年将分别减少1.96×10⁴km²、0.15×10⁴km²和1.58×10⁴km²;亚高山潮湿森林、山地湿润森林和山地灌丛呈持续增加趋势,平均每10年将分别增加3.42×10⁴km²、2.98×10⁴km²和1.19×10⁴km²;RCP8.5情景下青藏高原的植被生态系统平均中心的偏移幅度最大,RCP4.5情景下的偏移幅度次之,而RCP2.6情景下的偏移幅度最小。另外,在三种气候变化情景驱动下,青藏高原植被生态系统的生态多样性呈减少趋势。总之,未来不同情景的气候变化将直接影响青藏高原植被生态系统的时空分布格局及其生态多样性,气候变化强度越高,影响就越大,而且气候变化对青藏高原植被生态系统的影响呈现出从低海拔到高海拔递增的影响效应。     

The role of S100A4 protein in anticancer cytotoxicity: its presence is required on the surface of CD4+CD25+PGRPs+S100A4+ lymphocyte and undesirable on the surface of target cells

S100A4 is a Ca²⁺-binding protein that performs an important role in metastasis. It is also known for its antitumor functions. S100A4 is expressed by a specialized subset of CD⁴⁺CD²⁵⁺ lymphocytes and is present on those cell's membranes along with peptidoglycan recognition proteins (PGRPs). There, by interacting with major heat shock protein Hsp70, S100A4 plays an important cytotoxic role. The resulting stably formed complex of PGRPs, S100A4 and Hsp70 is required for the identification and binding between a lymphocyte and a target cell. Here, we investigated the S100A4 functions in CD⁴⁺CD²⁵⁺PGRPs⁺S100A4⁺ lymphocyte cytotoxicity against target cells. We demonstrated that those lymphocytes do not form a stable complex with the tumor target cells that themselves have S1004A on their surface. That observation can be explained by our finding that S100A4 precludes the formation of a stable complex between PGRPs, S100A4 (on the lymphocytes’ surface), and Hsp70 (on the target cells’ surface). The decrease in S100A4 level in CD⁴⁺CD²⁵⁺PGRPs⁺S100A4⁺ lymphocytes inhibits their cytotoxic activity, while the addition of S100A4 in the medium restores it. Thus, the resistance of target cells to CD⁴⁺CD²⁵⁺PGRPs⁺ S100A4⁺ lymphocyte cytotoxicity depends on their S100A4 expression level and can be countered by S100A4 antibodies.     

IL-17作为分子佐剂增强蛋白疫苗细胞免疫应答的研究

目的:为了进一步增强重组蛋白质疫苗的细胞免疫应答,利用重组的IL-17作为分子佐剂,与卵清蛋白(ovalbumin,OVA)一起免疫小鼠,研究IL-17作为分子佐剂对适应性免疫的影响,探索IL-17对蛋白疫苗诱导的免疫反应,特别是细胞免疫应答的影响.方法:用OVA作为特异性蛋白疫苗,与不同剂量的IL-17联合免疫C57...     

Tradeoffs between Maize Silage Yield and Nitrate Leaching in a Mediterranean Nitrate-Vulnerable Zone under Current and Projected Climate Scenarios

Future climatic changes may have profound impacts on cropping systems and affect the agronomic and environmental sustainability of current N management practices. The objectives of this work were to i) evaluate the ability of the SALUS crop model to reproduce experimental crop yield and soil nitrate dynamics results under different N fertilizer treatments in a farmer’s field, ii) use the SALUS model to estimate the impacts of different N fertilizer treatments on NO₃^- leaching under future climate scenarios generated by twenty nine different global circulation models, and iii) identify the management system that best minimizes NO₃^- leaching and maximizes yield under projected future climate conditions. A field experiment (maize-triticale rotation) was conducted in a nitrate vulnerable zone on the west coast of Sardinia, Italy to evaluate N management strategies that include urea fertilization (NMIN), conventional fertilization with dairy slurry and urea (CONV), and no fertilization (N0). An ensemble of 29 global circulation models (GCM) was used to simulate different climate scenarios for two Representative Circulation Pathways (RCP6.0 and RCP8.5) and evaluate potential nitrate leaching and biomass production in this region over the next 50 years. Data collected from two growing seasons showed that the SALUS model adequately simulated both nitrate leaching and crop yield, with a relative error that ranged between 0.4% and 13%. Nitrate losses under RCP8.5 were lower than under RCP6.0 only for NMIN. Accordingly, levels of plant N uptake, N use efficiency and biomass production were higher under RCP8.5 than RCP6.0. Simulations under both RCP scenarios indicated that the NMIN treatment demonstrated both the highest biomass production and NO₃^- losses. The newly proposed best management practice (BMP), developed from crop N uptake data, was identified as the optimal N fertilizer management practice since it minimized NO₃^- leaching and maximized biomass production over the long term.     

Dynamic QoS/QoE-aware reliable service composition framework for edge intelligence

Edge intelligence has become popular recently since it brings smartness and copes with some shortcomings of conventional technologies such as cloud computing, Internet of Things (IoT), and centralized AI adoptions. However, although utilizing edge intelligence contributes to providing smart systems such as automated driving systems, smart cities, and connected healthcare systems, it is not free from limitations. There exist various challenges in integrating AI and edge computing, one of which is addressed in this paper. Our main focus is to handle the adoption of AI methods on resource-constrained edge devices. In this regard, we introduce the concept of Edge devices as a Service (EdaaS) and propose a quality of service (QoS) and quality of experience (QoE)-aware dynamic and reliable framework for AI subtasks composition. The proposed framework is evaluated utilizing three well-known meta-heuristics in terms of various metrics for a connected healthcare application scenario. The experimental results confirm the applicability of the proposed framework. Moreover, the results reveal that black widow optimization (BWO) can handle the issue more efficiently compared to particle swarm optimization (PSO) and simulated annealing (SA). The overall efficiency of BWO over PSO is 95%, and BWO outperforms SA with 100% efficiency. It means that BWO prevails SA and PSO in all and 95% of the experiments, respectively.

     

Prediction of daily global solar radiation and air temperature using six machine learning algorithms; a case of 27 European countries

The prediction of global solar radiation in a region is of great importance as it provides investors and politicians with more detailed knowledge about the solar resource of that region, which can be very beneficial for large-scale solar energy development. In this sense, the main objective of this study is to predict the daily global solar radiation data of 27 cities (Brussels, Paris, Lisbon, Madrid…), located in 27 countries, which have mostly different solar radiation distributions in Europe. In this research, six different machine-learning algorithms (Linear model (LM), Decision Tree (DT), Support Vector Machine (SVM), Deep Learning (DL), Random Forest (RF) and Gradient Boosted Trees (GBT)) are used. In the training of these algorithms, daily air temperature(Ta), wind speed(Va), relative humidity(RH) and solar radiation of these cities are used. The data is supplied from the Meteonorm tool and cover the last years grouped in two periods (1960–1990; 2000–2019). To decide on the success of these algorithms, four different statistical metrics (Average Relative Error (ARE), Average absolute Error (AAE), Root Mean Squared Error (RMSE), and R² (R-Squared)) are discussed in the study. In addition, the forecasting of air temperature and global solar radiation of these cities in 2050 and 2100 were made using three of the most recent Intergovernmental Panel on Climate Change (IPCC) scenarios (RCP2.6; RCP 4.5, and RCP 8.5). The results show that ARE, R,² and RMSE values of all algorithms are ranging from 0.114 to 6.321, from 0.382 to 0.985, from 0.145 to 2.126 MJ/m², respectively. By analysing all the algorithms, it is noticed that the Decision tree exhibited the worst result in terms of R,² and RMSE metrics. Among the six prediction algorithms, the DL was recognized as the only algorithm that exceeded the t-critical value (The t-critical value is the cutoff between retaining or rejecting the null hypothesis). Globally, all the six machine learning algorithms used in this research can be applied to predict the daily global solar radiation data with good accuracy. Despite this, the SVM model is the best model among all the six models used. It is followed by the DL, LM, GB, RF and DT, respectively.     

Immunopathological effect of the mycotoxins cyclopiazonic acid and T-2 toxin on broiler chicken

Forty, newly hatched, unsexed broiler chicks were fed diets containing 10 ppm cyclopiazonic acid (CPA) and 1 ppm T-2 toxin (T₂) either individually or in combination for 28 days to study the immunopathological effects. Lymphoid organs revealed lymphocytolysis and lymphoid depletion in all toxin fed birds. Thymic and splenic CD⁺₄ and CD⁺₈ lymphocytes decreased significantly (p < 0.01) in toxin fed birds when compared to the control. Thymic CD⁺₈ lymphocytes of T₂ and CPA-T₂ showed significant (p < 0.01) decrease from that of CPA and control groups. Splenic CD⁺₄ and CD⁺₈ lymphocytes showed significant (p < 0.01) decrease in CPA and CPA-T₂ fed groups when compared to the control. The T₂ group did not differ significantly from that of control. The stimulation index (SI) of splenocytes to concavalin A revealed significant (p < 0.01) decrease in all toxin fed birds. Significant (p < 0.01) decrease were observed for the haemagglutination inhibition (HI) titres to Newcastle disease virus vaccine F strain (NDV) of birds fed CPA, T₂ and in combination. Significant (p < 0.01) interaction was found for lymphocyte subsets, SI and HI titres to NDV. The study indicated the immunosuppressive effect of these toxins either alone or in combination in broiler chicks.Forms part of M.V.Sc. thesis of the first author approved by the Tamil Nadu Veterinary and Animal Sciences University, Chennai 600 051, India.