Deep Learning for Stock Market Prediction.

The prediction of stock groups values has always been attractive and challenging for shareholders due to its inherent dynamics, non-linearity, and complex nature. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals, and basic metals from Tehran stock exchange were chosen for experimental evaluations. Data were collected for the groups based on 10 years of historical records. The value predictions are created for 1, 2, 5, 10, 15, 20, and 30 days in advance. Various machine learning algorithms were utilized for prediction of future values of stock market groups. We employed decision tree, bagging, random forest, adaptive boosting (Adaboost), gradient boosting, and eXtreme gradient boosting (XGBoost), and artificial neural networks (ANN), recurrent neural network (RNN) and long short-term memory (LSTM). Ten technical indicators were selected as the inputs into each of the prediction models. Finally, the results of the predictions were presented for each technique based on four metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. In addition, for tree-based models, there is often an intense competition between Adaboost, Gradient Boosting, and XGBoost.

The effect of water deficit on yield and yield components of safflower (Carthamus tinctorius L.).

The aim of this study carried out in Shahid Chamran Ahwaz, University, in 2001-2002 to determine the effect of different forms of irrigation on the safflower (Carthamus tinctorius L.) yield and yield components. Information was needed on application time of irrigation water on cultivars of safflower (Carthamus tinctorius L.). Increasing competition for water supplies and rising costs of applying water make efficient irrigation important. Yield and water use of safflower were evaluated on silt loam soil. Deficit irrigation treatments; I1: normal irrigation, I2: cutoff irrigation in budding period, I3: cutoff irrigation in flowering period (blooming), I4: cutoff irrigation in maturity period, were examined in Randomized Complete Block Design (RCB) with three replications. In this field experiment irrigation regimes were the main plots and cvs (ARAK 28, ESFAHAN LOCALITY and FO2 cvs) were as sub plots. The plant height, the plant head number, the 1000 seed weight, and the seed yield were measured in this experiment. The different irrigation regimes had a significant effects (p < 0.05) on the seed, the crude oil yields (kg ha(-1)), seed number per boll, harvest index, total dry weight. The highest seed yield (2679 kg seed ha(-1) in cv. ESFAHAN Lo.) and the crude oil yield (855 kg oil ha(-1) in cv. ARAK) were obtained from the I1 irrigation regime. I3 gave the lowest seed yield (1499 kg seed ha(-1) in cv. FO2) and the crude oil yield (449 kg oil ha(-1) in cv. FO2). I1 gave the highest oil percentage (35% in ARAK cv.) and the lowest (27.4% in FO2 cv.) obtained in I4. The different between cvs were significant in number of boll per plant, number of seed per boll, the 1000 seed, high, number of branch per plant, seed yield (kg ha(-1)), crude oil yield and total dry weight.

Diagnostic laparoscopy and ultrasonography for colorectal liver metastases.

BACKGROUND AND AIMS: To evaluate diagnostic laparoscopy (DL) and laparoscopic ultrasonography (LUS) in the diagnostic workout of patients with colorectal liver metastases, who were considered to have resectable disease after multi detector computed tomography (MDCT). MATERIAL AND METHODS: The medical records of 45 patients, 22M/23F, mean age 62.0 (+/-10.6), who were considered to have resectable liver metastases after CT-scan, were analysed. RESULTS: DL and LUS could not be performed in 7 patients (16%) because of adhesions. Unresectable disease was detected by DL in 3 patients (7%), in all cases due to carcinosis. Additional lesions in the liver were detected by DL in 2 cases (4%), none of these making the patient unresectable. LUS showed additional lesions in 3 patients (7%), which in one case (2%) made the patient unresectable. None of the patients in the present study experienced adverse effects to DL or LUS. CONCLUSION: DL and LUS, due to the low efficacy with regard to avoid unnecessary laparotomies and the relative high failure rate because of adhesions, should not be a routine part of the diagnostic work out in patients with colo-rectal liver metastases.

Diverse effects of inhibition of 3-hydroxy-3-methylglutaryl-CoA reductase on the expression of VCAM-1 and E-selectin in endothelial cells.

The expression of monocyte adhesion molecules, such as VCAM-1 (vascular cell adhesion molecule-1) and E-selectin, on the surface of the endothelium is an important step in the initiation and progression of atherosclerotic lesions. We hypothesized that the inhibition of 3-hydroxy-3-methylglutaryl-CoA (HMG-CoA) reductase in endothelial cells could influence the expression of VCAM-1 and E-selectin. Using cultured human umbilical vein endothelial cells, we found that mevastatin (0.1-1 microM) significantly reduced the expression of VCAM-1 protein in cells activated by tumour necrosis factor-alpha (TNF-alpha) for 7 h. In contrast, TNF-alpha-induced E-selectin protein expression was augmented after mevastatin treatment. Mevastatin inhibited the mRNA expression of both VCAM-1 and E-selectin in TNF-alpha-stimulated endothelial cells. The activity of the transcription factor nuclear factor-kappa B, which is known to regulate the transcription of VCAM-1 and E-selectin, was significantly reduced after incubation with mevastatin. Analysis of the time-dependent variation in the TNF-alpha-induced expression of E-selectin, and estimation of the rate of surface disappearance of E-selectin together with measurement of the amounts of E-selectin molecules secreted, indicated that mevastatin inhibited the surface removal of E-selectin. This is compatible with the observed increase in E-selectin expression after statin treatment. All observed effects of mevastatin were reversed by mevalonate, the product of the HMG-CoA reductase reaction. In conclusion, inhibition of HMG-CoA reductase in endothelial cells attenuates VCAM-1 expression, but increases E-selectin expression, after cytokine induction. These diverse effects are associated with changes in the transcriptional regulation of the two adhesion molecule genes and modulation of the surface removal of E-selectin.