Modeling broken characters recognition as a set-partitioning problem

This paper presents a novel technique for recognizing broken characters found in degraded text documents by modeling it as a set-partitioning problem (SPP). The proposed technique searches for the optimal set-partition of the connected components by which each subset yields a reconstructed character. Given the non-linear nature of the objective function needed for optimal set-partitioning, we design an algorithm that we call Heuristic Incremental Integer Programming (HIIP). The algorithm employs integer programming (IP) with an incremental approach using heuristics to hasten the convergence. The objective function is formulated as probability functions that reflect common OCR measurements – pattern resemblance, sizing conformity and distance between connected components. We applied the HIIP technique to Thai and English degraded text documents and achieved accuracy rates over 90%. We also compared HIIP against three competing algorithms and achieved higher comparative accuracy in each case.     

Application of cognitive robotics in disassembly of products

Disassembly is a critical step to increase the value of end-of-life (EOL) products and to reduce the environmental footprint. Despite worldwide efforts, disassembly is still performed manually due to the uncertainty associated with the quality and the quantity of the returned EOL products. In this paper, a cognitive robotics based system is proposed to address this problem. The system is equipped with four cognitive functions: reasoning, execution monitoring, learning and revision. The proposed system is tested using LCD screens. The results show that the system is flexible enough to deal with any product models without prior information.     

Doubled layered ITO/SnO2 conducting glass for substrate of dye-sensitized solar cells

The effects of indium tin oxide (ITO) and ITO/SnO₂ conducting substrates on photovoltaic properties of dye-sensitized solar cells (DSCs) using nanocrystalline TiO₂ were studied. The decrease in fill factor of the DSCs was correlated to the increase in resistance of conducting substrate. The heat stability of ITO conducting glass was improved by depositing SnO₂ on ITO layer. The efficiency of the cells using double layered ITO/SnO₂ substrate remarkably increased comparing with that of the cells using ITO substrates. It is worth mentioning that increasing in sintering time, which enhanced the electronic contact between substrate and TiO₂, also modified the cell performance of MP-TiO₂ cells. Our experimental finding suggests that 3000 Å ITO substrate, which was covered by 1000 Å SnO₂ layer, exhibited the best properties for the DSCs.     

Dye-sensitized solar cell made of mesoporous titania by surfactant-assisted templating method

Nanocrystalline mesoporous titania was obtained by surfactant-assisted templating method using tetraisopropyl orthotitanate modified with acethylacetone and laurylamine hydrochloride as template. This material was applied for the electrode of dye-sensitized solar cell. The mesoporous TiO₂ (MP-TiO₂) cells exhibited higher short-circuit photocurrent density and solar energy conversion efficiency compared to P25 (a typical commercial titania powder) cells. The incident photon to current conversion efficiency spectrum of MP-TiO₂ can be improved by using the cell made with 5% P25 additive. Double-layer titania cells were fabricated to further improve cell performance by increasing the film thickness and light scattering. The solar conversion efficiency up to 8.06% was obtained by using the double-layer titania cell sintered at 450 °C for 2 h.     

HS-SPME-GC-MS analysis of volatile aromatic compounds in alcohol related beverages made with mulberry fruits

Wine aroma is one of the most important parameters responsible for its quality, and hence for consumer acceptance. In order to obtain an appropriate technique to study volatile aroma compounds in mulberry wines, headspace-solid phase microextraction (HS-SPME) comb 40°C for 30 min with a 50/30 μm divinylbenzenecarboxen-polydimethylsiloxane (DVB-CAR-PDMS) fiber. Approximately 80 volatile compounds have been quantified in the mulberry wine, pertaining at several chemical groups, mainly higher alcohols, fatty acids, esters, and some volatile phenols whose concentration range from few to 138.36 mg/L. This work describes a novel methodology for the analysis of mulberry wines by HS-SPME coupled to GC-MS. HS-SPME using a 50/30 μm DVB-CAR-PDMS fiber is provided the higher extraction efficiency (p<0.05) for the volatiles including the most esters, higher alcohols, and fatty acids than by the other fibers.     

An artificial intelligence model to estimate the fat addition ratio for the mixing process in the animal feed industry

In animal feed pellets, the fat content is obtained either from the feed ingredients or is directly added during processing. Additional fat is required when the fat level in the feed ingredients is less than the desired level. This fat can be added either during the mixing process or after the pelleting process. However, adding fat at different time leads to different results. The addition of an increasing amount of fat during the mixing process decreases the pellet durability but enhances the pellet production rate. To avoid a reduction in the pellet durability, limiting the inclusion of fats in the mixer is suggested. The use of suitable fat addition ratios during mixing and after pelleting can improve the pellet quality and the production capability. Many factors significantly affect the decision of how much fat to add, such as the fiber inclusion content in the feed formulation, pellet die size, required feed durability, total required fat, and required additional fat. Due to frequent changes in the feed mix, anticipating the suitable amount of fat addition during the mixing process becomes a cumbersome task for a mill. In this paper, a model for estimating the amount of fat required in the mixer for each feed formulation is proposed. The model is based on the local linear map (LLM) and the back-propagation neural network (BPNN) methods. The LLM is used to identify which feed formulations require the addition of fat both during mixing and after pelleting, whereas the BPNN is employed for estimating the proper total fat required in the mixer, and the ratio of fat to add during the mixing process is subsequently estimated by subtracting the fat in the raw material from the total fat required in the mixer. The model is developed using data from one the largest feed mills in Thailand. The proposed model provides an accurate prediction and is practical for implementation in the mill that was studied.     

IoT Based Root Stress Detection for Lettuce Culture Using Infrared Leaf Temperature Sensor and Light Intensity Sensor

Root stress is a big problem for lettuce farming in tropical climates, especially temperature root stress. Black root rot, a final stage of the temperature root stress, leads to huge production loss. This paper presents the IoTs based root stress detection system for lettuce cultures. The proposed detection algorithm is based on the leaf energy balance and transpiration patterns. Unlike image sensors based detection methods, leaf energy balance principle and transpiration patterns measured from a lettuce leaf are considered as the key features to address the lettuce root stress conditions. The challenge of detecting lettuce stress by using a leaf sensor is to estimate the non-linear function of stomatal conductance. This paper has clarified the concept of detecting lettuce root stress using the transpiration patterns as well. Graphically, the combination of infrared temperature and light intensity sensors is appropriate to deal with the lettuce root stress detection. The proposed detection algorithm has been designed to detect three conditions of root stress problems: normal, root stress, and black root rot conditions. The infrared sensors are very suitable for the sensitive leaf like lettuce. To evaluate the proposed leaf sensor, the experiments are set up to show that the proposed detection algorithm can accurately detect the temperature root stress in different conditions. Moreover, the detection algorithm based leaf area index (LAI) has been discussed to the proposed detection algorithm. In addition, the performance of the proposed detection algorithm has been compared to the LAI based algorithm. The detection accuracy of the proposed detection method is 95% with different root stress conditions.

     

New upper and lower bounds line of sight path loss model for mobile propagation in buildings

This paper proposes a method to predict line-of-sight (LOS) path loss in buildings. We performed measurements in two different types of buildings at a frequency of 1.8 GHz and propose a new path loss model with its upper and lower bounds. The upper and lower bounds depend on max and min values of sampled path loss data. This makes our model limit path loss within the boundary lines. The model includes time-variant effects from the object movement from people in the building and cars in parking areas. These influence reasonably on wave propagation. The results have shown that the proposed model will be useful for the design of the indoor wireless communication systems.     

An application of learning to robotic planning

Conventional approaches to robotic planning have focused on the resolution theorem prover, using general-purpose search heuristics, with the desired goal expressed in terms of logical calculus. These approaches suffer from several drawbacks; one major problem encountered in these approaches is the speed of planning. In this paper we describe an approach of applying supervised learning to robotic planning. The learning system is an intermediate one between rote learning and generalization learning, and is based on the concept of analogy. Simulation examples of various robot tasks are presented to demonstrate the significant increase in the systems's planning speed and to compare it with some existing systems.This work was supported by the National Science Foundation grant ENG-74-17586.     

Phenolic composition and antioxidant activity of Thai and Eri silk sericins

The present study investigates the phenolic contents and antioxidant activities of silk sericin extracted (SSE) from Thai mulberry silkworms (Bombyx mori) and non-mulberry silkworm (Samia ricini). The SSE from all strains revealed the mainly presence of flavonoid compounds including (+)-catechin (20.63–145.64 mg/100 g), quercetin (7.89–35.95 mg/100 g), and (−)-epicatechin (3.36–44.19 mg/100 g). The antioxidant activity of the SSE with water from Chokumnoui 1 was found to have low EC50 values (0.96 mg/mL), the concentrations of the SSE that exhibit 50% reduction in DPPH, and highest scavenging of ABTS^{· +} radicals (1.73 mg TEAC/g) and highest reduce TPRZ-Fe (III) complex to TPTZ-Fe (II) (8.03 mg Fe(II)/g), thus indicating high antioxidant activities. Total phenolic content and total flavonoid content of the SSE showed positive correlated to the scavenging activity of DPPH and ABTS^{· +} radicals and the ferric reducing ability (FRAP assay).