International Journal of Systematic Innovation

Developing favorite distribution mode of fresh food donations with grey relation analysis and TRIZ

2024-04-01T04:28:39+00:00

Taiwan currently grapples with the intricate task of balancing its food supply and demand, resulting in the emergence of critical food surplus and waste issues. To address this pressing challenge, the government has turned to food donation initiatives led by public associations and private corporations to alleviate food waste concerns. Nevertheless, a significant obstacle remains in the form of the efficient and effective distribution of these fresh food donations from the supply side to the demand side. Therefore, this study aims to pioneer an innovative and optimized distribution model for fresh food donations employing TRIZ (Theory of Inventive Problem Solving) and grey relational analysis.

Through an in-depth analysis of questionnaire data gathered from the public, this research uncovers the most favored distribution model, namely, "Government-invited third-party logistics providers (3PLs) to voluntarily manage distribution services, alongside the provision of preferential subsidies or tax incentives." Building upon these findings, this study offers valuable recommendations for governmental agricultural authorities and other stakeholders within the fresh food donation supply chain, serving as a cornerstone for sustainable food management practices.

Enhancing visibility of nighttime images using wavelet de-composition with kekre's LUV color space

2024-01-02T05:42:13+00:00

Contrast enhancement is a crucial preprocessing method for enhancing the efficiency of subsequent image processing and computer vision tasks. In the past, a lot of effort has been put into improving the visual scenes of pictures taken in low light. Images taken in poor illumination environments frequently reveal issues like color distortion, noise, low brightness, etc., that negatively impact the visual influence on human eyes. Therefore, an approach for improving poorly illuminated images based on wavelet transform is suggested to get around this problem. The input image is first transformed to Kekre's LUV color space, after which discrete wavelet transform (DWT) is applied to part each channel into low and high-frequency components. As the illumination is concentrated on the low-frequency image component, the Exposure-based Sub Image Histogram Equalization (ESIHE) technique is applied to enhance the image's lighting. Besides, limited adaptive histogram equalization (CLAHE) is imposed to control the over-enhancement of specific region's contrast. Modified L, U, and V components are recovered via the inverse discrete wavelet transform (IDWT), and the image is again converted into RGB space. This output is fused with a histogram equalized image using weighted fusion followed by a high boost filter to get the final enhanced output. Experimental outcomes are achieved to validate the efficacy and robustness of the suggested strategy using quality evaluators such as Entropy, NIQE, and BRISQUE rankings explored on ExDark, DPED, and LoLi datasets.

Three possible sources of inconsistency in an innovation ecosystem

2024-02-27T03:42:11+00:00

One of the success factors of an innovation ecosystem is the willingness of its actors to cooperate, which depends on number of factors. In the present analysis, the authors approach the topic from an operational management perspective and examine the actors of an ecosystem through the elements of a general service management framework model. The aim of the study is to identify potential points of inconsistency along the four groups of aspects as potential sources of barriers to collaboration. After literature review, the value system, the operational-business philosophy, the methods and the objectives of a research and technology center are analyzed. The presented approach can serve as a general method for identifying inconsistencies in innovation ecosystems. The current methodology is based on one-by-one analysis, further researches can extend the approach to a multi-player inconsistency evaluation tool.

The integration of Ergonomics Ergo-System Framework (EESF) with the product design process

2024-02-15T02:09:51+00:00

Several research in medical science have revealed that individuals who have scoliosis experience discomfort while sitting upright, leading to symptoms like leg pain, back pain, and claudication. These symptoms can limit their ability to perform certain tasks in the office. Thus, this paper utilized Ergonomics Ergo-System Framework (EESF) to design the innovative ergonomic seating support for scoliosis patients. Through the interview study conducted with a rehabilitation specialist, a physiotherapy expert, and three scoliosis patients in Malaysia, the EESF was integrated to identify patients design issues and needs. The result of solution components and design criteria obtained from the interview study highlights the parameter for the development of the ergonomic seating support. The decision of innovative design of the ergonomic seating support incorporated the modular seating concept for office use, visually aesthetic with emotional design elements, and equipped with adjustable spinal support. To develop the semi-working ergonomic seating supporter concept model for future production, a design process was executed. It is hoped that the outcome of this study will contribute to demonstrate how the EESF can be utilized, integrated with the innovative product design process, and benefit the scoliosis patients.

Enhancing digital security using Signa-Deep for online signature verification and identity authentication

2024-01-17T02:46:51+00:00

In the contemporary digital realm, the utilization of online services has surged, facilitated by the seamless integration of deep learning technology, which is paramount in applications demanding precision and efficiency. A pivotal use case in this context is online handwritten signature verification, where the need for exceptional accuracy is indisputable. This paper introduces 'Signa-Deep,' an innovative approach designed to address the challenge of online signature verification and the determination of an individual's authorization status. The study explores a range of methodologies, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), GoogleNet, and MobileNet, to discern the authenticity of signatures and affirm the identity of the signatory. The results of our proposed method are promising, showcasing its potential to significantly enhance the security of digital transactions and identity verification processes. In summary, 'Signa-Deep' harnesses deep learning technology to bolster the accuracy and reliability of online signature verification, thereby contributing to the overall robustness of digital interactions and identity validation processes.

Zero waste toilet a sensor-operated urine diverting toilet for sustainable sanitation and fertilizer production

2024-01-29T02:33:08+00:00

This research introduces an innovative zero waste toilet, a sensor-operated urine-diverting system designed to overcome limitations in current sanitation methods. The toilet directly converts human feces into organic fertilizer while segregating urine from solid waste. Its walls are constructed using repurposed plastic PET bottles filled with local soil, enhancing strength and durability through steel wire interconnection and cement plaster reinforcement. Touchless sensors facilitate automatic flushing upon user entry and after a predetermined duration, with a gesture sensor for post-use cleaning. A front-mounted urine basin ensures proper waste separation. Feces are directed to a specialized tank via a trap system, while urine is directed to the sewer line. The tank features two meshes for effective filtration. Solar energy and sensors power the process, enabling atomization for efficient fertilizer production, followed by composting in a blending tank. The zero waste toilet offers a key advantage: fertilizer production without manual waste handling, aligning with scavenger act regulations. It minimizes waste generation, conserves water, and enhances sanitation. Repurposed plastic bottles reduce plastic pollution, and the system is comfortable, durable, and resource-efficient. Challenges include specialized expertise, initial costs, and user adaptation to automated systems. Further research is needed for optimizing fertilizer production from waste compost. Nonetheless, the zero waste toilet holds promise for sustainable sanitation, improved hygiene, and resource conservation.

Prostate cancer prediction using machine learning techniques

2024-04-11T09:21:48+00:00

Prostate cancer (PCa) is currently the most frequently diagnosed cancer in men in industrialized nations and ranks as the second leading cause of male cancer-related deaths globally, early detection is crucial. Originating in the walnut-shaped gland beneath the bladder, PCa poses a significant risk when not identified in its early stages. The diagnostic process, requiring expertise from radiologists, pathologists, and physicians, is time-consuming and introduces variability, potentially leading to delayed or incorrect diagnoses. This underscores the need for efficient and reliable diagnostic tools in addressing the escalating challenge of PCa diagnosis.This study addresses the critical challenge of PCa diagnosis by employing a comprehensive approach involving feature selection methods and model performance evaluation. Utilizing a PCa dataset from Kaggle, consisting of 100 patient observations with eight independent features and a binary diagnosis result, the study explores the nuanced nature of feature relevance in PCa classification. Comparative analyses of Principal Component Analysis (PCA) and ReliefF feature selection methods reveal the limitations of PCA's emphasis on a dominant feature, while ReliefF, incorporating a distributed set of features, demonstrates improved model accuracy and stability. The Random Forest (RF) model, selected through meticulous parameter tuning, achieves an impressive 95% accuracy by leveraging a substantial number of estimators, limited tree depth, and balanced sample splitting. The findings underscore the crucial interplay between feature selection methods and model parameters in optimizing the accuracy and reliability of PCa classification models. Given the anticipated rise in PCa incidence, this research contributes valuable insights for enhancing diagnostic efficiency and addressing the challenges posed by traditional diagnostic procedures.

A novel hybrid deep belief Google network framework for brain tumor classification

2024-04-08T02:35:40+00:00

Within the fields of law enforcement and forensics applications, latent fingerprints have garnered a lot of interest from researchers. The need from the general public for these uses may be what propels biometrics research forward. Although a lot of work has gone into building techniques for latent fingerprint classification, there are still many difficult issues to solve low quality pictures, segmentation, noise, and intra class variations in that field. To overcome the above difficulties, proposed an Automated Latent Fingerprint Recognition framework in this research using strategies for latent fingerprint pre-processing, feature extraction, and matching. A candidate fingerprint's salient minutiae, which give each fingerprint its individuality and distinguish it from others, are first identified and described, followed by their relative placement in the candidate fingerprint and previously saved fingerprint templates. The experimental analyses using publicly accessible low-quality Latent partial fingerprints was taken from MSU PrintsGAN datasets show that the proposed framework achieves an average equal error rate (EER) value of 0.254 and TAR@FAR achieves 91.43 which is contrasted to various existing approaches.