Leilei Pan

An Electronic Nose Network System for Online Monitoring of Livestock Farm Odors

An electronic nose (e-nose)-based network system is developed for monitoring odors in and around livestock farms remotely. This network is built from compact e-noses that are tailored to measure odor compounds and environmental conditions such as temperature, wind speed, and humidity. The e-noses are placed at various applicable locations in and around the farm, and the collected odor data are transmitted via wireless network to a computer server, where the data processing algorithms process and analyze the data. The developed e-nose network system enables more effective odor management capabilities for more efficient operation of odor control practice by providing consistent, comprehensive, real-time data about the environment and odor profile in and around the livestock farms. Experimental and simulation results demonstrate the effectiveness of the developed system.

Real-time Monitoring System for Odours around Livestock Farms

A sensor network-based livestock farm odour monitoring system is proposed for monitoring and analyzing livestock farm odour remotely. The system utilizes a wireless sensor network built from electronic nose nodes which can detect odour compounds and environment factors such as temperature and humidity. The architecture of the system and the functionality of each component is introduced. The proposed odour monitoring system can provide farmers and researchers with more precise odour management capabilities for more efficient operation of odour reduction systems such as ventilation fans. It can aid the development of an optimal overall odour management strategy by providing real-time, detailed data about the livestock farm environment and odour dispersion.

A Neural Network-Based Method for Risk Factor Analysis of West Nile Virus

There is a lack of knowledge about which risk factors are more important in West Nile virus (WNV) transmission and risk magnitude. A better understanding of the risk factors is of great help in developing effective new technologies and appropriate prevention strategies for WNV infection. A contribution analysis of all risk factors in WNV infection would identify those major risk factors. Based on the identified major risk factors, measures to control WNV proliferation could be directed toward those significant risk factors, thus improving the effectiveness and efficiency in developing WNV control and prevention strategies. Neural networks have many generally accepted advantages over conventional analytical techniques, for instance, ability to automatically learn the relationship between the inputs and outputs from training data, powerful generalization ability, and capability of handling nonlinear interactions. In this article, a neural network model was developed for analysis of risk factors in WNV infection. To reveal the relative contribution of the input variables, the neural network was trained using an algorithm called structural learning with forgetting. During the learning, weak neural connections are forced to fade away while a skeletal network with strong connections emerges. The significant risk factors can be identified by analyzing this skeletal network. The proposed approach is tested with the dead bird surveillance data in Ontario, Canada. The results demonstrate the effectiveness of the proposed approach.

Intelligent Computation of Moisture Content in Shrinkable Biomaterials

A technique of intelligent computation of moisture content in shrinkable biomaterials from multiple predictors was developed. All measurable predictors were structured in three sets: biomaterial properties (volume, density, porosity, diffusivity); drying conditions (time, air temperature, humidity, velocity, pressure); and drying technologies. Two typical drying models were considered: time-dependent (thermodynamical) and time-independent (relational). The relationship between predictors and moisture content was established on the basis of multi-factorial linear regression (MLR) and neural networks (NN). Accuracy of statistical approximation was strongly dependent on drying model and chosen set of predictors. Time-independent models demonstrated better accuracy (MSE = 0.214) than time-dependent models (MSE = 0.254). Redundant predictors did not affect the accuracy and generalization ability of statistical models. Results of NN training and testing showed superior accuracy with respect to statistical models. NN worked perfectly well for any combination of non-correlated predictors, improving accuracy to MSE = 0.01. Elimination of redundant predictors further improved accuracy and generalization ability of NN models. The performance of both models was tested for drying of ginseng roots in the range of temperatures from 38 to 50°C, sizes from 10 to 32 mm, and relative humidity from 12 to 40%. Due to the high accuracy and computational efficiency, NN can be used as online estimator of moisture content in drying process.

Development of a New Electronic Nose for Odour Measurement Utilizing Wireless Sensor Networks

The development of an electronic nose for data dissemination via a wireless network is presented in this paper. The design is tailored to odour emissions, and meteorology around pork farms and utilizes four ad-hoc gas sensors as well as two extraneous temperature and humidity sensors to aid in the odour monitoring and analysis of pork odour. Empirical data was gathered and analyzed through experiments using a proven chemical recipe that closely mimics that of pork odour. Thus far the electronic nose has yielded highly qualitative results as compared to that expected of pork odour and has also exhibited the ability to transfer data across a network.

An wireless electronic nose network for odours around livestock farms

An electronic nose-based network system is developed for monitoring odours around livestock farms remotely. This network is built from compact electronic noses which are tailored to detect odour compounds and environment conditions such as temperature, wind speed, and humidity. The electronic noses are placed at various locations of interest around the farm, and the collected odour data are dissemination via a wireless network to a computer server, where the sensor fusion algorithms process and analyze the data. The developed electronic nose network system can provide farmers and researchers with more accurate odour management capabilities for more efficient operation of odour control practice by providing consistent, comprehensive, detailed, real-time data about the environment and odour profile around livestock farms.

Analyzing livestock farm odour using a neuro-fuzzy approach

An adaptive neuro-fuzzy based method for analyzing odour generation factors to the perception of livestock farm odour was proposed. In this approach, the parameters associated with a given membership function could be tuned so as to tailor the membership functions to the input/output data in order to account for these types of variations in the data values. A multi-factor livestock farm odour model was developed, and both numeric factors and linguistic factors were considered. The proposed method was tested with a livestock farm odour database. The results demonstrated the effectiveness of the proposed approach in comparison to a typical neural network.

A neurodynamics model for odour dispersion around livestock farms

Detecting and monitoring odour around livestock farms are difficult. In this paper, a dynamic neural network based model is proposed to locate odour dispersion around livestock facilities. The proposed dispersion model can dynamically represent complex or non-steady-state meteorological and topographical features in and around livestock farm areas. The proposed approach can also model odour dispersions from multiple odour sources, and from various types of sources such like point source, line source, and area source. In addition, the proposed model simulates the odour dispersion through the dynamic neural activity landscape, without explicitly additional models of the dynamic environment, odour sources, and farming activities.

A web based collaborative portal for remote monitoring and analysis of livestock farm odor

Monitoring and analysis of livestock farm environment require a lot of data obtained from distributed farms. The whole process needs cooperation and collaboration of multiple partners with different backgrounds. A single person will have difficulty performing the full process and bringing those data records together, as the data measurement sites (farms) are far away from each other. This paper presents a dynamic and cooperative framework for monitoring and analysis of livestock farm odor. The key and novel contribution of this study is that the proposed framework utilizes a web-based portal application as a platform for distributed applications. This collaborative framework provides an efficient, robust, and user-friendly environment for distributed users to manage and process data records, share analysis results, and collaborate on distributed tasks.

Risk Factor Analysis of West Nile Virus Using Structural Learning with Forgetting Method

A novel neural network based approach for risk factor analysis of infection of West Nile virus (WNV) is proposed. A multi-factor risk analysis model is developed and learnt by an algorithm called structural learning with forgetting. Through the learning, unnecessary connections fade away and a skeletal network emerges. By analyzing the resulted skeletal networks, significant risk factors can be identified, and thus a more thorough understanding of WNV transmission mechanism can be obtained. The proposed approach is tested with a dead birds surveillance data. The results demonstrate the effectiveness of the proposed approach.