Modelling Intelligent Driving Behaviour Using Machine Learning

In vehicular systems, driving is considered to be the most complex task, involving many aspects of external sensory skills as well as cognitive intelligence. External skills include the estimation of distance and speed, time perception, visual and auditory perception, attention, the capability to drive safely and action-reaction time. Cognitive intelligence works as an internal mechanism that manages and holds the overall driver’s intelligent system.These cognitive capacities constitute the frontiers for generating adaptive behaviour for dynamic environments. The parameters for understanding intelligent behaviour are knowledge, reasoning, decision making, habit and cognitive skill. Modelling intelligent behaviour reveals that many of these parameters operate simultaneously to enable drivers to react to current situations. Environmental changes prompt the parameter values to change, a process which continues unless and until all processes are completed. This paper model intelligent behaviour by using a ‘driver behaviour model’ to obtain accurate intelligent driving behaviour patterns. This model works on layering patterns in which hierarchy and coherence are maintained to transfer the data with accuracy from one module to another. These patterns constitute the outcome of different modules that collaborate to generate appropriate values. In this case, accurate patterns were acquired using ANN static and dynamic non-linear autoregressive approach was used and for further accuracy validation, time-series dynamic backpropagation artificial neural network, multilayer perceptron and random sub-space on real-world data were also applied.     

Performance of the MEWMA-CoDa control chart in the presence of measurement errors

This paper can be considered as an extension of the work of Tran et al (for monitoring compositional data using a multivariate exponentially weighted moving average MEWMA-compositional data [CoDa] chart) by taking into account potential measurement errors that are known to highly affect production processes. A linearly covariate error model with a constant error variance is used to study the impact of measurement errors on the MEWMA-CoDa control chart. In particular, the influence of the device parameters (σ_M,b), the number of independent observations m, and the the number of variables p are investigated in terms of the MEWMA optimal couples (r,H) as well as in terms of their corresponding ARLs. A comparison between the Hotelling-CoDa T² and the proposed chart is made in order to show that the MEWMA-CoDa chart is more efficient in detecting shifts in the presence of measurement errors. A real-life example of muesli production, using multiple measurements for each composition, is used to estimate the parameters and also to demonstrate how the MEWMA-CoDa can handle measurement errors to detect shifts in the process.     

Changes in biochemical,hemodynamic, and dialysis adherence parameters in hemodialysis patients during Ramadan

This paper aimed to study the effect of Ramadan fasting on biochemical and clinical parameters and compliance for dialysis. A prospective multicenter observational cross‐sectional study comparing fasting with a non‐fasting stable adult hemodialysis patients for demographic and biochemical parameters, compliance with dialysis, inter‐dialytic weight gain, pre‐ and post‐blood pressure, and frequency of intradialytic hypotensive episodes was carried out. Six hundred thirty‐five patients, of whom 64.1% fasted, were studied. The fasters were younger (53.3 ± 16.2 vs. 58.4 ± 16.1 years; P = 0.001) but had similar duration on dialysis (P = 0.35). More fasters worked (22.0% vs. 14.6%; P = 0.001) and missed dialysis sessions during Ramadan. No differences were noted between groups in sex, diabetic status, or dialysis shift or day. There were no differences in the pre‐ and post‐dialysis blood pressure; serum potassium, albumin or weight gain; diabetic status; sex; and dialysis shift time or days. However, serum phosphorous was significantly higher in the fasting group (2.78 ± 1.8 vs. 2.45 ± 1.6 mmol/L; P = 0.045). There were no intragroup differences in any of the parameters studied when comparing the findings during Ramadan with those in the month before Ramadan. Fasters were significantly younger and more likely to be working, to miss dialysis sessions, and to have higher serum phosphorous levels. No other differences were observed.     

Evaluation of magnetic nanoparticles performance as photocatalyst for the catalytic treatment of direct red 28 dye in synthetic and real water effluents

Integrated water resources management practice is gaining popularity as an alternative water source due to the limited supply of freshwater. The present study was carried out on the photocatalytic degradation of Direct red 28 (DR-28) dye using magnetic nanoparticles (MNPs; Fe₃O₄) as a photocatalyst. The study was conducted on the photocatalytic degradation of DR-28 dye in synthetic dye effluent water, to understand the effects of different photoreaction parameters on the degradation kinetics. The influence of different parameters such as time, amount of photocatalyst, concentration of H₂O₂ and pH was investigated. At the optimum dosage of MNPs (0.6?g/L) with 4?mmol/L of H₂O₂, significant photocatalytic degradation of DR-28 dye (93.2%) was observed. The kinetic study revealed that the photocatalytic degradation followed pseudo-first-order kinetics. The degradation performance of Fe₃O₄ nanoparticles as a photocatalyst for DR-28 dye was compared with titanium dioxide (TiO₂) and it was found that the performance of Fe₃O₄ as a photocatalyst is superior to TiO₂ photocatalyst. The real dye effluent was also degraded at optimum conditions and promising results were achieved.     

A linear approximation method for the Shapley value

The Shapley value is a key solution concept for coalitional games in general and voting games in particular. Its main advantage is that it provides a unique and fair solution, but its main drawback is the complexity of computing it (e.g., for voting games this complexity is #p-complete). However, given the importance of the Shapley value and voting games, a number of approximation methods have been developed to overcome this complexity. Among these, Owen's multi-linear extension method is the most time efficient, being linear in the number of players. Now, in addition to speed, the other key criterion for an approximation algorithm is its approximation error. On this dimension, the multi-linear extension method is less impressive. Against this background, this paper presents a new approximation algorithm, based on randomization, for computing the Shapley value of voting games. This method has time complexity linear in the number of players, but has an approximation error that is, on average, lower than Owen's. In addition to this comparative study, we empirically evaluate the error for our method and show how the different parameters of the voting game affect it. Specifically, we show the following effects. First, as the number of players in a voting game increases, the average percentage error decreases. Second, as the quota increases, the average percentage error decreases. Third, the error is different for players with different weights; players with weight closer to the mean weight have a lower error than those with weight further away. We then extend our approximation to the more general k-majority voting games and show that, for n players, the method has time complexity O(k²n) and the upper bound on its approximation error is .     

Tied factor analysis for face recognition across large pose differences

Face recognition algorithms perform very unreliably when the pose of the probe face is different from the gallery face: typical feature vectors vary more with pose than with identity. We propose a generative model that creates a one-to-many mapping from an idealized "identity" space to the observed data space. In identity space, the representation for each individual does not vary with pose. We model the measured feature vector as being generated by a pose-contingent linear transformation of the identity variable in the presence of Gaussian noise. We term this model "tied" factor analysis. The choice of linear transformation (factors) depends on the pose, but the loadings are constant (tied) for a given individual. We use the EM algorithm to estimate the linear transformations and the noise parameters from training data. We propose a probabilistic distance metric which allows a full posterior over possible matches to be established. We introduce a novel feature extraction process and investigate recognition performance using the FERET, XM2VTS and PIE databases. Recognition performance compares favourably to contemporary approaches.     

Engineered Lactobacillus paracasei Producing Palmitoylethanolamide (PEA) Prevents Colitis in Mice

Palmitoylethanolamide (PEA) is an N-acylethanolamide produced on-demand by the enzyme N-acylphosphatidylethanolamine-preferring phospholipase D (NAPE-PLD). Being a key member of the larger family of bioactive autacoid local injury antagonist amides (ALIAmides), PEA significantly improves the clinical and histopathological stigmata in models of ulcerative colitis (UC). Despite its safety profile, high PEA doses are required in vivo to exert its therapeutic activity; therefore, PEA has been tested only in animals or human biopsy samples, to date. To overcome these limitations, we developed an NAPE-PLD-expressing Lactobacillus paracasei F19 (pNAPE-LP), able to produce PEA under the boost of ultra-low palmitate supply, and investigated its therapeutic potential in a murine model of UC. The coadministration of pNAPE-LP and palmitate led to a time-dependent release of PEA, resulting in a significant amelioration of the clinical and histological damage score, with a significantly reduced neutrophil infiltration, lower expression and release of pro-inflammatory cytokines and oxidative stress markers, and a markedly improved epithelial barrier integrity. We concluded that pNAPE-LP with ultra-low palmitate supply stands as a new method to increase the in situ intestinal delivery of PEA and as a new therapeutic able of controlling intestinal inflammation in inflammatory bowel disease.     

Acid Sphingomyelinase Deficiency: A Clinical and Immunological Perspective

Acid sphingomyelinase deficiency (ASMD) is a lysosomal storage disease caused by deficient activity of acid sphingomyelinase (ASM) enzyme, leading to the accumulation of varying degrees of sphingomyelin. Lipid storage leads to foam cell infiltration in tissues, and clinical features including hepatosplenomegaly, pulmonary insufficiency and in some cases central nervous system involvement. ASM enzyme replacement therapy is currently in clinical trial being the first treatment addressing the underlying pathology of the disease. Therefore, presently, it is critical to better comprehend ASMD to improve its diagnose and monitoring. Lung disease, including recurrent pulmonary infections, are common in ASMD patients. Along with lung disease, several immune system alterations have been described both in patients and in ASMD animal models, thus highlighting the role of ASM enzyme in the immune system. In this review, we summarized the pivotal roles of ASM in several immune system cells namely on macrophages, Natural Killer (NK) cells, NKT cells, B cells and T cells. In addition, an overview of diagnose, monitoring and treatment of ASMD is provided highlighting the new enzyme replacement therapy available.     

Crosstalk between Sodium–Glucose Cotransporter Inhibitors and Sodium–Hydrogen Exchanger 1 and 3 in Cardiometabolic Diseases

Abnormality in glucose homeostasis due to hyperglycemia or insulin resistance is the hallmark of type 2 diabetes mellitus (T2DM). These metabolic abnormalities in T2DM lead to cellular dysfunction and the development of diabetic cardiomyopathy leading to heart failure. New antihyperglycemic agents including glucagon-like peptide-1 receptor agonists and the sodium–glucose cotransporter-2 inhibitors (SGLT2i) have been shown to attenuate endothelial dysfunction at the cellular level. In addition, they improved cardiovascular safety by exhibiting cardioprotective effects. The mechanism by which these drugs exert their cardioprotective effects is unknown, although recent studies have shown that cardiovascular homeostasis occurs through the interplay of the sodium–hydrogen exchangers (NHE), specifically NHE1 and NHE3, with SGLT2i. Another theoretical explanation for the cardioprotective effects of SGLT2i is through natriuresis by the kidney. This theory highlights the possible involvement of renal NHE transporters in the management of heart failure. This review outlines the possible mechanisms responsible for causing diabetic cardiomyopathy and discusses the interaction between NHE and SGLT2i in cardiovascular diseases.