Combining CT Images and Clinical Features of Four Periods to Predict Whether Patients Have Rectal Cancer

In this paper, we mainly use random forest and broad learning system (BLS) to predict rectal cancer. A total of 246 participants with computed tomography (CT) image records were enrolled. The total model in the training set (combined with imaging and clinical indicators) has the best prediction result, with the area under the curve (AUC) of 0.999 (95% confidence internal (CI): 0.996–1.000) and the accuracy of 0.990 (95%CI: 0.976–1.000). Model 3, the general model in the test set, has the best prediction result, with the AUC of 0.962 (95%CI: 0.915–1.000) and the accuracy of 0.920 (95%CI: 0.845–0.995). The results of the model using random forest prediction are compared with those using BLS prediction. It can be found that there is no statistical difference between the two results. Our prediction model combined with image features has a good prediction result, and this image feature is the most important among all features. Consequently, we can successfully predict rectal cancer through a combination of the clinical indicators and the comprehensive indicators of CT image characteristics in four different periods (plain scan, vein, artery, and excretion).

(Epidemiological Analysis of Varicella in Dalian from 2009 to 2019 and Application of Three Kinds of Model in Prediction Prevalence of Varicella）Study Design: Cross Sectional Study

Objective：This study described the epidemic characteristics of varicella in Dalian from 2009 to 2019, explored the fitting effect of Grey model first-order one variable( GM(1,1)), Markov model, and GM(1,1)-Markov model on varicella data, and found the best fitting method for this type of data, to better predict the incidence trend.Methods: In this study, the epidemiological characteristics of varicella from 2009 to 2019 were analyzed by epidemiological descriptive methods. Using the varicella incidence data from 2009 to 2018, predicted 2019 and compared with actual value. First made GM (1,1) prediction and Markov prediction. Then according to the relative error of the GM(1,1), made GM(1,1)-Markov prediction. Results: This study collected 37223 cases from 2009 to 2019. The average annual incidence was 50.56/100000. Varicella occurred all year round, it had a bimodal distribution. The number of cases had two peaks from April to June and November to January of the following year. The ratio of males to females was 1.167:1. The 4 to 25 accounted for 60.36% of the total population. The age of varicella appeared to shift backward. Students, kindergarten children, scattered children accounted for about 64% of all cases. The GM(1,1) model prediction result of 2019 would be 53.6425, the relative error would be 14.42%, the Markov prediction result would be 56.2075, the relative error would be 10.33%, and the Gray(1,1)-Markov prediction result would be 59.508. The relative error would be 5.06%.Conclusions: Varicella data had its unique development characteristics. The accuracy of GM (1,1) - Markov model is higher than GM(1.1) model and Markov model. The model can be used for prediction and decision guidance.

Water and nitrogen in-situ imaging detection in live corn leaves using near-infrared camera and interference filter

Background Realizing imaging detection of water and nitrogen content in different regions of plant leaves in-site and real-time can provide an efficient new technology for determining crop drought resistance and nutrient regulation mechanisms, or for use in precision agriculture. Near-infrared imaging is the preferred technology for in-situ real-time detection owing to its non-destructive nature; moreover, it provides rich information. However, the use of hyperspectral imaging technology is limited as it is difficult to use it in field because of its high weight and power. Results We developed a smart imaging device using a near-infrared camera and an interference filter; it has a low weight, requires low power, and has a multi-wavelength resolution. The characteristic wavelengths of the filter that realize leaf moisture measurement are 1150 and 1400 nm, respectively, the characteristic wavelength of the filter that realizes nitrogen measurement is 1500 nm, and all filter bandwidths are 25 nm. The prediction result of the average leaf water content model obtained with the device was R2 = 0.930, RMSE = 1.030%; the prediction result of the average nitrogen content model was R2 = 0.750, RMSE = 0.263 g. Conclusions Using the average water and nitrogen content model, an image of distribution of water and nitrogen in different areas of corn leaf was obtained, and its distribution characteristics were consistent with the actual leaf conditions. The experimental materials used in this research were fresh leaves in the field, and the test was completed indoors. Further verification of applying the device and model to the field is underway.

An Improved Attention-Based Integrated Deep Neural Network for PM2.5 Concentration Prediction

The air quality prediction is a very important and challenging task, especially PM2.5 (particles with diameter less than 2.5 μm) concentration prediction. To improve the accuracy of the PM2.5 concentration prediction, an improved integrated deep neural network method based on attention mechanism is proposed in this paper. Firstly, the influence of exogenous series of other sites on the central site is considered to determine the best relevant site. Secondly, the data of all relevant sites are input into the improved dual-stage two-phase (DSTP) model, then the PM2.5 prediction result of each site is obtained. Finally, with the PM2.5 prediction result of each site, the attention-based layer predicts the PM2.5 concentration at the central site. The experimental results show that the proposed model is superior to most of the latest models.

Metode Exponential Smoothing Pada Peramalan Tingkat Kriminalitas Pencurian Sepeda Motor

: This study aims to determine thecrime rate in motorbike theft cases using the programmeing langiage PHP and MySQL as a database and the application of the Exponential Smoothing method to determine the crime rate of motorcycle theft that occurs in the city of Tanjung Balai for the next period. The data used in this study is motorcycle theft report data from 2018 to 2019 wich was obtained from the Tanjung Balai Police. The benefits of this research can be used by the Tanjung Balai police to determine the extent of the motorcycle theft crime that will occur in a shorter, easier and more accurate manner so that it can take optimal prevention. With the Exponential Smoothing method the alpha value will be searched randomly to find an alpha value that was a minimum error value calculated using Means Absolute Percetage Error (MAPE). Then the prediction results that have an alphan with a minimum error are the best of recommended as a prediction result for the next period. Based on this research, the prediction results obtained from the prediction of the number of motorcycle theft cases the occurred in the city of Tanjung Balai in 2020 were 12 units with an MAPE error value of 0,153%. Keyword : Exponential Smoothing, Theft, Motorcycle, Forecasting Abstrak : Penelitian ini bertujuan untuk menentukan tingkat kriminalitas kasus pencurian sepeda motor dengan menggunakan bahasa pemrograman PHP dan MySQL sebagai basis data serta penerapan metode Exponential Smoothing untuk menentukan tingkat kriminalitas pencurian sepeda motor yang terjadi di kota Tanjung Balai untuk periode berikutnya. Data yang digunakan dalam penelitian ini adalah data laporan pencurian sepeda motor dari tahun 2018 sampai dengan tahun 2019 yang diperoleh dari POLRES Tanjung Balai. Manfaat dari penelitian ini dapat digunakan oleh kepolisian Tanjung Balai untuk menentukan seberapa besar tindak kriminalitas pencurian sepeda motor yang akan terjadi secara lebih singkat, mudah dan akurat sehingga dapat melakukan pencegahan yang optimal. Dengan metode Exponential Smoothing akan dicari nilai alpha secara acak sampai menemukan nilai alpha yang memiliki nilai error yang minimum yang dihitung menggunakan Means Absolute Percetage Error (MAPE). Maka hasil prediksi yang memiliki alpha dengan error minimumlah yang paling baik atau direkomendasikan sebagai hasil prediksi untuk periode selanjutnya. Berdasarkan penelitian ini diperoleh hasil prediksi peramalan jumlah kasus pencurian sepeda motor yang terjadi di kota Tanjung Balai tahun 2020 adalah 12 unit dengan nilai error MAPE sebesar 0,153%. Kata Kunci : Exponential Smoothing, Pencurian, Sepeda Motor, Forecasting

IMPLEMENTASI DATA MINING MENGGUNAKAN MULTI REGRESI UNTUK MEMPREDIKSI RERATA KEDATANGAN MASYARAKAT

This research uses multiple linear regression methods. research is useful to predicate the average number of people's arrival. this research uses Microsoft Excel 2010 and Rapid miner applications. The variables used are independent variables, free: stock blangko, operator, and working time. predicted to use sample x1 = 795,x2= 3 people, x3= 7 hours , and y= 296 people. Prediction result is -92.2484452, error value data 0.548 and 0.548 for public arrivals.

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

To recognize stress and emotion, most of the existing methods only observe and analyze speech patterns from present-time features. However, an emotion (especially for stress) can change because it was triggered by an event while speaking. To address this issue, we propose a novel method for predicting stress and emotions by analyzing prior emotional states. We named this method the deep time-delay Markov network (DTMN). Structurally, the proposed DTMN contains a hidden Markov model (HMM) and a time-delay neural network (TDNN). We evaluated the effectiveness of the proposed DTMN by comparing it with several state transition methods in predicting an emotional state from time-series (sequences) speech data of the SUSAS dataset. The experimental results show that the proposed DTMN can accurately predict present emotional states by outperforming the baseline systems in terms of the prediction error rate (PER). We then modeled the emotional state transition using a finite Markov chain based on the prediction result. We also conducted an ablation experiment to observe the effect of different HMM values and TDNN parameters on the prediction result and the computational training time of the proposed DTMN.

Prediction of Limb Joint Angles Based on Multi-Source Signals by GS-GRNN for Exoskeleton Wearer

To enable exoskeleton wearers to walk on level ground, estimation of lower limb movement is particularly indispensable. In fact, it allows the exoskeleton to follow the human movement in real time. In this paper, the general regression neural network optimized by golden section algorithm (GS-GRNN) is used to realize prediction of the human lower limb joint angle. The human body hip joint angle and the surface electromyographic (sEMG) signals of the thigh muscles are taken as the inputs of a neural network to predict joint angles of lower limbs. To improve the prediction accuracy in different gait phases, the plantar pressure signals are also added into the input. After that, the error between the prediction result and the actual data decreases significantly. Finally, compared with the prediction result of the BP neural network, GRNN shows splendid prediction performance for its less processing time and higher prediction accuracy.

THE USE OF DIGITAL SIGNAL PROCESSING AND A NEURAL NETWORK WHEN GENERATING A FORECAST OF TIME SERIES OF DATA FOR THE PURPOSE OF DETECTING ANOMALIES IN THE IN THE AUTOMATED CONTROL OF TECHNOLOGICAL PROCESSES

n order to detect anomalies and improve the quality of forecasting dynamic data flows observed from sensors in Industrial Control System (ACS)., it is proposed to use a predictive mod-ule consisting of a series-connected digital signal processing unit (DSP) and a predictive unit using a neural network (predictive autoencoder ( Auto Encoder), predictive Autoencoder (PAE)). The study showed that the preliminary DSP block of the predicted input signal, consisting of a parallel set (comb) of digital low-pass filters with finite impulse responses (FIR-LPF), leads to a non-equilibrium account of the correlation relationships of the time samples of the input signal and to increase the accuracy of the final prediction result. The predicted autoencoder (PAE) pro-posed and considered in the work, in addition to restoring the input signal or part of the input signal at the PAE output, also generates the predicted samples of the input signal for the speci-fied number of «forward» time steps at the output, which increases the accuracy of the predic-tion result. The reduction of the forecast error occurs due to the imposition of restrictions in the formation of the forecast, that is, an additional requirement to restore the input samples of the samples – «stabilizers» at the NS output. The introduction of «stabilizers» increases the accuracy of the prediction result.

Prediction of tsunami inundation impact in Padang city

Sumatera Barat has predicted by experts will be hit by earthquake due to subduction of Indo-Australian and Eurasian tectonic plates, this earthquake would result tsunami that will hit Padang city. The tsunami will cause inundation in the several areas of city near the coast. The area of tsunami inundation in Padang city has predicted by expert, this prediction result is displayed on a tsunami inundation map. This paper discusses the impact of tsunami inundation on housing and public facilities in those areas, this result could be used to prepare evacuation planning. The method of study, is by identification of impact tsunami inundation on housing and public facilities. This is carried out with superimpose of tsunami inundation map to Padang city map, submerged housing and public facilities are identified manually. The data then were verified in the field. From result of identification, the depth of inundation in subdistrict are classified, then the public facilities that affected by tsunami inundation are classified in each of subdistrict. Total 27.228 unit house and public facilities that affected by tsunami inundation, 86.3% is housing and 13.4% public facilities. The most affected subdistrict by tsunami inundation is Bungo Pasang, it is 2.899 house and public facilities submerged.