Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. Existing traffic flow prediction methods mainly use shallow traffic prediction models and are still unsatisfying for many real-world applications. This situation inspires us to rethink the traffic flow prediction problem based on deep architecture models with big traffic data. In this paper, a novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently. A stacked autoencoder model is used to learn generic traffic flow features, and it is trained in a greedy layerwise fashion. To the best of our knowledge, this is the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Moreover, experiments demonstrate that the proposed method for traffic flow prediction has superior performance.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

Traffic flow prediction is a fundamental problem in transportation modeling and management. Many existing approaches fail to provide favorable results due to being: 1) shallow in architecture; 2) hand engineered in features; and 3) separate in learning. In this paper we propose a deep architecture that consists of two parts, i.e., a deep belief network (DBN) at the bottom and a multitask regression layer at the top. A DBN is employed here for unsupervised feature learning. It can learn effective features for traffic flow prediction in an unsupervised fashion, which has been examined and found to be effective for many areas such as image and audio classification. To the best of our knowledge, this is the first paper that applies the deep learning approach to transportation research. To incorporate multitask learning (MTL) in our deep architecture, a multitask regression layer is used above the DBN for supervised prediction. We further investigate homogeneous MTL and heterogeneous MTL for traffic flow prediction. To take full advantage of weight sharing in our deep architecture, we propose a grouping method based on the weights in the top layer to make MTL more effective. Experiments on transportation data sets show good performance of our deep architecture. Abundant experiments show that our approach achieved close to 5% improvements over the state of the art. It is also presented that MTL can improve the generalization performance of shared tasks. These positive results demonstrate that deep learning and MTL are promising in transportation research.

Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning

Since the early 1980s, short-term traffic forecasting has been an integral part of most Intelligent Transportation Systems (ITS) research and applications; most effort has gone into developing methodologies that can be used to model traffic characteristics and produce anticipated traffic conditions. Existing literature is voluminous, and has largely used single point data from motorways and has employed univariate mathematical models to predict traffic volumes or travel times. Recent developments in technology and the widespread use of powerful computers and mathematical models allow researchers an unprecedented opportunity to expand horizons and direct work in 10 challenging, yet relatively under researched, directions. It is these existing challenges that we review in this paper and offer suggestions for future work.

Short-term traffic forecasting: Where we are and where we’re going

Ayurveda, the traditional Indian medicine (TIM) and traditional Chinese medicine (TCM) remain the most ancient yet living traditions. There has been increased global interest in traditional medicine. Efforts to monitor and regulate herbal drugs and traditional medicine are underway. China has been successful in promoting its therapies with more research and science-based approach, while Ayurveda still needs more extensive scientific research and evidence base. This review gives an overview of basic principles and commonalities of TIM and TCM and discusses key determinants of success, which these great traditions need to address to compete in global markets.

/pdf/ayurveda-and-traditional-chinese-medicine-a-comparative-1pay4y7h32.pdf

Ayurveda and traditional Chinese medicine: a comparative overview.

Black pepper (Piper nigrum) is one of the most widely used among spices. It is valued for its distinct biting quality attributed to the alkaloid, piperine. Black pepper is used not only in human dietaries but also for a variety of other purposes such as medicinal, as a preservative, and in perfumery. Many physiological effects of black pepper, its extracts, or its major active principle, piperine, have been reported in recent decades. Dietary piperine, by favorably stimulating the digestive enzymes of pancreas, enhances the digestive capacity and significantly reduces the gastrointestinal food transit time. Piperine has been demonstrated in in vitro studies to protect against oxidative damage by inhibiting or quenching free radicals and reactive oxygen species. Black pepper or piperine treatment has also been evidenced to lower lipid peroxidation in vivo and beneficially influence cellular thiol status, antioxidant molecules and antioxidant enzymes in a number of experimental situations of oxidative stress. The most far-reaching attribute of piperine has been its inhibitory influence on enzymatic drug biotransforming reactions in the liver. It strongly inhibits hepatic and intestinal aryl hydrocarbon hydroxylase and UDP-glucuronyl transferase. Piperine has been documented to enhance the bioavailability of a number of therapeutic drugs as well as phytochemicals by this very property. Piperine's bioavailability enhancing property is also partly attributed to increased absorption as a result of its effect on the ultrastructure of intestinal brush border. Although initially there were a few controversial reports regarding its safety as a food additive, such evidence has been questionable, and later studies have established the safety of black pepper or its active principle, piperine, in several animal studies. Piperine, while it is non-genotoxic, has in fact been found to possess anti-mutagenic and anti-tumor influences.

Black Pepper and its Pungent Principle-Piperine: A Review of Diverse Physiological Effects

This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg-Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting. The approach uses exponential smoothing to preprocess traffic flow data by removing the lumpiness from collected traffic flow data, before employing a variant of the LM algorithm to train the NN weights of an NN model. This approach aids NN training, as the preprocessed traffic flow data are more smooth and continuous than the original unprocessed traffic flow data. The proposed method was evaluated by forecasting short-term traffic flow conditions on the Mitchell freeway in Western Australia. With regard to the generalization capabilities for short-term traffic flow forecasting, the NN models developed using the proposed approach outperform those that are developed based on the alternative tested algorithms, which are particularly designed either for short-term traffic flow forecasting or for enhancing generalization capabilities of NNs.

/pdf/neural-network-based-models-for-short-term-traffic-flow-3y6phvfejv.pdf

Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm

Piperine, a major active component of black and long peppers, has been reported to enhance drug bioavailability. The present studies were aimed at understanding the interaction of piperine with enzymatic drug biotransforming reactions in hepatic tissue in vitro and in vivo. Piperine inhibited arylhydrocarbon hydroxylation, ethylmorphine-N-demethylation, 7-ethoxycoumarin-O-deethylation and 3-hydroxy-benzo(a)pyrene glucuronidation in rat postmitochondrial supernatant in vitro in a dose-dependent manner. Piperine inhibition of these reactions in postmitochondrial supernatant from 3-methylcholanthrene- and phenobarbital-treated rats was similar to the controls. Inhibition by piperine of arylhydrocarbon hydroxylase (AHH) from 3-methylcholanthrene-treated rats was comparable to that observed with 7,8-benzoflavone. Piperine caused noncompetitive inhibition of hepatic microsomal AHH from the untreated and 3-methylcholanthrene-treated rats with a Ki of 30 microM which was close to the apparent Km of AHH observed in the controls. Similarly, the kinetics of inhibition of ethylmorphine-N-demethylase from control rat liver microsomes exhibited noncompetitive inhibition with an apparent Km of 0.8 mM and Ki of 35 microM. These studies demonstrated that piperine is a nonspecific inhibitor of drug metabolism which shows little discrimination between different cytochrome P-450 forms. Oral administration of piperine in rats strongly inhibited the hepatic AHH and UDP-glucuronyltransferase activities. The maximal inhibition of AHH observed within 1 hr restored to normal value in 6 hr. Pretreatment with piperine prolonged hexobarbital sleeping time and zoxazolamine paralysis time in mice at half the dose of SKF-525A. These results demonstrate that piperine is a potent inhibitor of drug metabolism.

Biochemical basis of enhanced drug bioavailability by piperine: evidence that piperine is a potent inhibitor of drug metabolism.

The gastric ulcer protective effect of boswellic acids, a leukotriene inhibitor from Boswellia serrata, in rats.

Tinospora cordifolia (Guduchi or Amrita) is an important drug of Ayurvedic System of Medicine and found mention in various classical texts for the treatment of diseases such as jaundice, fever, diabetes and skin disease etc. In present times, this drug has been subjected for numerous chemicals, pharmacological, pre-clinical and clinical investigations and many new therapeutic applications have been indicated. This paper presents a critical review in areas of chemical constituents, proved pre-clinical and clinical trials along with its medicinal uses in different streams of medical sciences.

/pdf/tinospora-cordifolia-guduchi-a-reservoir-plant-for-3zwojt5tgy.pdf

Tinospora cordifolia (Guduchi), a reservoir plant for therapeutic applications: A Review

The post-partum period in cattle is characterised by an increased risk of infection of the uterus, as the anatomical barriers are broached during parturition and remain open for several days. Infection of the uterus is largely influenced by the balance between bacterial contamination and the local and systemic immune status during pregnancy and around parturition. Infectious diseases are more prevalent during this period, because of an impaired immune status before and immediately after parturition. Neutrophils play a primary role in the defence of the uterus against infection. Influx of neutrophils into the uterus is thought to be mediated by chemoattractants, chemokines and adhesion molecules, such as β2-integrin (complement receptor 3) and l-selectin (CD62L). Other cellular components activated in the uterus during this period include lymphocytes, eosinophils, mast cells and macrophages. The major classes of immunoglobulins (IgM, IgA and IgG), either by passive diffusion or local production, play an important protective role in the uterus by acting as opsonins to enhance phagocytosis, stimulating the complement pathways or blocking pathogens from adhering to mucosal surfaces. Endometrial cells express toll-like receptor 4 (TLR4), which recognises lipopolysaccharides of Escherichia coli and other Gram negative bacteria, the most common causes of bovine endometritis. Activation of TLR4 triggers the production of tumour necrosis factor α and other pro-inflammatory cytokines. The periparturient period is also characterised by an increased secretion of prostaglandin F2α, which enhances uterine immune defences.

J. Singh

Papers

Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm

Biochemical basis of enhanced drug bioavailability by piperine: evidence that piperine is a potent inhibitor of drug metabolism.

The gastric ulcer protective effect of boswellic acids, a leukotriene inhibitor from Boswellia serrata, in rats.

Tinospora cordifolia (Guduchi), a reservoir plant for therapeutic applications: A Review

The immune status of the bovine uterus during the peripartum period.