Optimizing lung cancer classification through hyperparameter tuning.

Artificial intelligence is steadily permeating various sectors, including healthcare. This research specifically addresses lung cancer, the world's deadliest disease with the highest mortality rate. Two primary factors contribute to its onset: genetic predisposition and environmental factors, such as smoking and exposure to pollutants. Recognizing the need for more effective diagnosis techniques, our study embarked on devising a machine learning strategy tailored to boost precision in lung cancer detection. Our aim was to devise a diagnostic method that is both less invasive and cost-effective. To this end, we proposed four methods, benchmarking them against prevalent techniques using a universally recognized dataset from Kaggle. Among our methods, one emerged as particularly promising, outperforming the competition in accuracy, precision and sensitivity. This method utilized hyperparameter tuning, focusing on the Gamma and C parameters, which were set at a value of 10. These parameters influence kernel width and regularization strength, respectively. As a result, we achieved an accuracy of 99.16%, a precision of 98% and a sensitivity rate of 100%. In conclusion, our enhanced prediction mechanism has proven to surpass traditional and contemporary strategies in lung cancer detection.

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures.

Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and CSI of 0.7556, 0.8839, 0.8796, and 0.7140) on the IQ-OTHNCCD dataset, exceeding recent benchmarks and aligning with other reported results. Efficiency evaluations were conducted in various scenarios. For instance, training on only 10 % of LC25000 resulted in high accuracy rates of 99.19 % (J, MCC, Kp, and CSI of 0.9840, 0.9898, 0.9898, and 0.9837) (D1) and 99.30 % (J, MCC, Kp, and CSI of 0.9863, 0.9913, 0.9913, and 0.9861) (D2). In NCT-CRC-HE-100K, D2 achieved an impressive 99.53 % accuracy (J, MCC, Kp, and CSI of 0.9906, 0.9946, 0.9946, and 0.9906) with training on only 30 % of the dataset and testing on the remaining 70 %. When tested on CRC-VAL-HE-7K, D1 and D2 achieved 95 % accuracy (J, MCC, Kp, and CSI of 0.8845, 0.9455, 0.9452, and 0.8745) and 96 % accuracy (J, MCC, Kp, and CSI of 0.8926, 0.9504, 0.9503, and 0.8798), respectively, outperforming previously reported results and aligning closely with others. Lastly, training D2 on just 10 % of NCT-CRC-HE-100K and testing on CRC-VAL-HE-7K resulted in significant outperformance of InceptionV3, Xception, and DenseNet201 benchmarks, achieving an accuracy rate of 82.98 % (J, MCC, Kp, and CSI of 0.7227, 0.8095, 0.8081, and 0.6671). Finally, using explainable AI algorithms such as Grad-CAM, Grad-CAM++, Score-CAM, and Faster Score-CAM, along with their emphasized versions, we visualized the features from the last layer of DenseNet201 for histopathological as well as CT-scan image samples. The proposed dense models, with their multi-modality, robustness, and efficiency in cancer image classification, hold the promise of significant advancements in medical diagnostics. They have the potential to revolutionize early cancer detection and improve healthcare accessibility worldwide.

Genetic variations of penicillin-binding protein 1A: insights into the current status of amoxicillin-based regimens for Helicobacter pylori eradication in Malaysia.

Introduction. Resistance towards amoxicillin in Helicobacter pylori causes significant therapeutic impasse in healthcare settings worldwide. In Malaysia, the standard H. pylori treatment regimen includes a 14-day course of high-dose proton-pump inhibitor (rabeprazole, 20 mg) with amoxicillin (1000 mg) dual therapy.Hypothesis/Gap Statement. The high eradication rate with amoxicillin-based treatment could be attributed to the primary resistance rates of amoxicillin being relatively low at 0%, however, a low rate of secondary resistance has been documented in Malaysia recently.Aim. This study aims to investigate the amino acid mutations and related genetic variants in PBP1A of H. pylori, correlating with amoxicillin resistance in the Malaysian population.Methodology. The full-length pbp1A gene was amplified via PCR from 50 genomic DNA extracted from gastric biopsy samples of H. pylori-positive treatment-naïve Malaysian patients. The sequences were then compared with reference H. pylori strain ATCC 26695 for mutation and variant detection. A phylogenetic analysis of 50 sequences along with 43 additional sequences from the NCBI database was performed. These additional sequences included both amoxicillin-resistant strains (n=20) and amoxicillin-sensitive strains (n=23).Results. There was a total of 21 variants of amino acids, with three of them located in or near the PBP-motif (SKN402-404). The percentages of these three variants are as follows: K403X, 2%; S405I, 2% and E406K, 16%. Based on the genetic markers identified, the resistance rate for amoxicillin in our sample remained at 0%. The phylogenetic examination suggested that H. pylori might exhibit unique conserved pbp1A sequences within the Malaysian context.Conclusions. Overall, the molecular analysis of PBP1A supported the therapeutic superiority of amoxicillin-based regimens. Therefore, it is crucial to continue monitoring the amoxicillin resistance background of H. pylori with a larger sample size to ensure the sustained effectiveness of amoxicillin-based treatments in Malaysia.

Enhancing lung cancer detection through hybrid features and machine learning hyperparameters optimization techniques.

Machine learning offers significant potential for lung cancer detection, enabling early diagnosis and potentially improving patient outcomes. Feature extraction remains a crucial challenge in this domain. Combining the most relevant features can further enhance detection accuracy. This study employed a hybrid feature extraction approach, which integrates both Gray-level co-occurrence matrix (GLCM) with Haralick and autoencoder features with an autoencoder. These features were subsequently fed into supervised machine learning methods. Support Vector Machine (SVM) Radial Base Function (RBF) and SVM Gaussian achieved perfect performance measures, while SVM polynomial produced an accuracy of 99.89% when utilizing GLCM with an autoencoder, Haralick, and autoencoder features. SVM Gaussian achieved an accuracy of 99.56%, while SVM RBF achieved an accuracy of 99.35% when utilizing GLCM with Haralick features. These results demonstrate the potential of the proposed approach for developing improved diagnostic and prognostic lung cancer treatment planning and decision-making systems.

ASMF: Ambient social media forensics chain of custody with an intelligent digital investigation process using federated learning.

Ambient Intelligence is a concept that relates to a new paradigm of pervasive computing and has the objective of automating responses from the system to humans without any human intervention. In social media forensics, gathering, analyzing, storing, and validating relevant evidence for investigation in a heterogeneous environment is still questionable. There is no hierarchy for automation, even though standardization and secure processes from data collection to validation have not yet been discussed. This poses serious issues for the current investigation procedures and future evidence chain of custody management. This paper contributes threefold. First, it proposes a framework using a blockchain network with a dual chain of data transmission for privacy protection, such as on-chain and off-chain. Second, a protocol is designed to detect and separate local and global cyber threats and undermine multiple federated principles to personalize search space broadly. Third, this study manages personalized updates by means of optimizing backtracking parameters and automating replacements, which directly affects the reduction of negative influence on the social networking environment in terms of imbalanced and distributed data issues. This proposed framework enhances stability in digital investigation. In addition, the simulation uses an extensive social media dataset in different cyberspaces with a variety of cyber threats to investigate. The proposed work outperformed as compared to traditional single-level personalized search and other state-of-the-art schemes.

Reseek-Arrhythmia: Empirical Evaluation of ResNet Architecture for Detection of Arrhythmia.

Arrhythmia is a cardiac condition characterized by an irregular heart rhythm that hinders the proper circulation of blood, posing a severe risk to individuals' lives. Globally, arrhythmias are recognized as a significant health concern, accounting for nearly 12 percent of all deaths. As a result, there has been a growing focus on utilizing artificial intelligence for the detection and classification of abnormal heartbeats. In recent years, self-operated heartbeat detection research has gained popularity due to its cost-effectiveness and potential for expediting therapy for individuals at risk of arrhythmias. However, building an efficient automatic heartbeat monitoring approach for arrhythmia identification and classification comes with several significant challenges. These challenges include addressing issues related to data quality, determining the range for heart rate segmentation, managing data imbalance difficulties, handling intra- and inter-patient variations, distinguishing supraventricular irregular heartbeats from regular heartbeats, and ensuring model interpretability. In this study, we propose the Reseek-Arrhythmia model, which leverages deep learning techniques to automatically detect and classify heart arrhythmia diseases. The model combines different convolutional blocks and identity blocks, along with essential components such as convolution layers, batch normalization layers, and activation layers. To train and evaluate the model, we utilized the MIT-BIH and PTB datasets. Remarkably, the proposed model achieves outstanding performance with an accuracy of 99.35% and 93.50% and an acceptable loss of 0.688 and 0.2564, respectively.

The Potential of ChatGPT in Assisting Children with Down Syndrome.

ChatGPT, an advanced language generation model developed by OpenAI, has the potential to revolutionize healthcare delivery and support for individuals with various conditions, including Down syndrome. This article explores the applications of ChatGPT in assisting children with Down syndrome, highlighting the benefits it can bring to their education, social interaction, and overall well-being. While acknowledging the challenges and limitations, we examine how ChatGPT can be utilized as a valuable tool in enhancing the lives of these children, promoting their cognitive development, and supporting their unique needs.

A Systematic Review of Mobile Phone Data in Crime Applications: A Coherent Taxonomy Based on Data Types and Analysis Perspectives, Challenges, and Future Research Directions.

Digital technologies have recently become more advanced, allowing for the development of social networking sites and applications. Despite these advancements, phone calls and text messages still make up the largest proportion of mobile data usage. It is possible to study human communication behaviors and mobility patterns using the useful information that mobile phone data provide. Specifically, the digital traces left by the large number of mobile devices provide important information that facilitates a deeper understanding of human behavior and mobility configurations for researchers in various fields, such as criminology, urban sensing, transportation planning, and healthcare. Mobile phone data record significant spatiotemporal (i.e., geospatial and time-related data) and communication (i.e., call) information. These can be used to achieve different research objectives and form the basis of various practical applications, including human mobility models based on spatiotemporal interactions, real-time identification of criminal activities, inference of friendship interactions, and density distribution estimation. The present research primarily reviews studies that have employed mobile phone data to investigate, assess, and predict human communication and mobility patterns in the context of crime prevention. These investigations have sought, for example, to detect suspicious activities, identify criminal networks, and predict crime, as well as understand human communication and mobility patterns in urban sensing applications. To achieve this, a systematic literature review was conducted on crime research studies that were published between 2014 and 2022 and listed in eight electronic databases. In this review, we evaluated the most advanced methods and techniques used in recent criminology applications based on mobile phone data and the benefits of using this information to predict crime and detect suspected criminals. The results of this literature review contribute to improving the existing understanding of where and how populations live and socialize and how to classify individuals based on their mobility patterns. The results show extraordinary growth in studies that utilized mobile phone data to study human mobility and movement patterns compared to studies that used the data to infer communication behaviors. This observation can be attributed to privacy concerns related to acquiring call detail records (CDRs). Additionally, most of the studies used census and survey data for data validation. The results show that social network analysis tools and techniques have been widely employed to detect criminal networks and urban communities. In addition, correlation analysis has been used to investigate spatial-temporal patterns of crime, and ambient population measures have a significant impact on crime rates.

Mobile Phone Data: A Survey of Techniques, Features, and Applications.

Due to the rapid growth in the use of smartphones, the digital traces (e.g., mobile phone data, call detail records) left by the use of these devices have been widely employed to assess and predict human communication behaviors and mobility patterns in various disciplines and domains, such as urban sensing, epidemiology, public transportation, data protection, and criminology. These digital traces provide significant spatiotemporal (geospatial and time-related) data, revealing people's mobility patterns as well as communication (incoming and outgoing calls) data, revealing people's social networks and interactions. Thus, service providers collect smartphone data by recording the details of every user activity or interaction (e.g., making a phone call, sending a text message, or accessing the internet) done using a smartphone and storing these details on their databases. This paper surveys different methods and approaches for assessing and predicting human communication behaviors and mobility patterns from mobile phone data and differentiates them in terms of their strengths and weaknesses. It also gives information about spatial, temporal, and call characteristics that have been extracted from mobile phone data and used to model how people communicate and move. We survey mobile phone data research published between 2013 and 2021 from eight main databases, namely, the ACM Digital Library, IEEE Xplore, MDPI, SAGE, Science Direct, Scopus, SpringerLink, and Web of Science. Based on our inclusion and exclusion criteria, 148 studies were selected.

Investigating the Effect of COVID-19 on Driver Behavior and Road Safety: A Naturalistic Driving Study in Malaysia.

The spread of the novel coronavirus COVID-19 resulted in unprecedented worldwide countermeasures such as lockdowns and suspensions of all retail, recreational, and religious activities for the majority of 2020. Nonetheless, no adequate scientific data have been provided thus far about the impact of COVID-19 on driving behavior and road safety, especially in Malaysia. This study examined the effect of COVID-19 on driving behavior using naturalistic driving data. This was accomplished by comparing the driving behaviors of the same drivers in three periods: before COVID-19 lockdown, during COVID-19 lockdown, and after COVID-19 lockdown. Thirty people were previously recruited in 2019 to drive an instrumental vehicle on a 25 km route while recording their driving data such as speed, acceleration, deceleration, distance to vehicle ahead, and steering. The data acquisition system incorporated various sensors such as an OBDII reader, a lidar, two ultrasonic sensors, an IMU, and a GPS. The same individuals were contacted again in 2020 to drive the same vehicle on the same route in order to capture their driving behavior during the COVID-19 lockdown. Participants were approached once again in 2022 to repeat the procedure in order to capture their driving behavior after the COVID-19 lockdown. Such valuable and trustworthy data enable the assessment of changes in driving behavior throughout the three time periods. Results showed that drivers committed more violations during the COVID-19 lockdown, with young drivers in particular being most affected by the traffic restrictions, driving significantly faster and performing more aggressive steering behaviors during the COVID-19 lockdown than any other time. Furthermore, the locations where the most speeding offenses were committed are highlighted in order to provide lawmakers with guidance on how to improve traffic safety in those areas, in addition to various recommendations on how to manage traffic during future lockdowns.

Driver Behavior Profiling and Recognition Using Deep-Learning Methods: In Accordance with Traffic Regulations and Experts Guidelines.

The process of collecting driving data and using a computational model to generate a safety score for the driver is known as driver behavior profiling. Existing driver profiles attempt to categorize drivers as either safe or aggressive, which some experts say is not practical. This is due to the "safe/aggressive" categorization being a state that describes a driver's conduct at a specific point in time rather than a continuous state or a human trait. Furthermore, due to the disparity in traffic laws and regulations between countries, what is considered aggressive behavior in one place may differ from what is considered aggressive behavior in another. As a result, adopting existing profiles is not ideal. The authors provide a unique approach to driver behavior profiling based on timeframe data segmentation. The profiling procedure consists of two main parts: row labeling and segment labeling. Row labeling assigns a safety score to each second of driving data based on criteria developed with the help of Malaysian traffic safety experts. Then, rows are accumulated to form timeframe segments. In segment labeling, generated timeframe segments are assigned a safety score using a set of criteria. The score assigned to the generated timeframe segment reflects the driver's behavior during that time period. Following that, the study adopts three deep-learning-based algorithms, namely, Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN), to classify recorded driving data according to the established profiling procedure, and selects the most suitable one for a proposed recognition system. Various techniques were used to prevent the classification algorithms from overfitting. Using gathered naturalistic data, the validity of the modulated algorithms was assessed on various timeframe segments ranging from 1 to 10 s. Results showed that the CNN, which achieved an accuracy of 96.1%, outperformed the other two classification algorithms and was therefore recommended for the recognition system. In addition, recommendations were outlined on how the recognition system would assist in improving traffic safety.

Investigating the Effect of Social and Cultural Factors on Drivers in Malaysia: A Naturalistic Driving Study.

Road accidents are increasing every year in Malaysia, and it is always challenging to collect reliable pre-crash data in the transportation community. Existing studies relied on simulators, police crash reports, questionnaires, and surveys to study Malaysia's drivers' behavior. Researchers previously criticized such methods for being biased and unreliable. To fill in the literature gap, this study presents the first naturalistic driving study in Malaysia. Thirty drivers were recruited to drive an instrumented vehicle for 750 km while collecting continuous driving data. The data acquisition system consists of various sensors such as OBDII, lidar, ultrasonic sensors, IMU, and GPS. Irrelevant data were filtered, and experts helped identify safety criteria regarding multiple driving metrics such as maximum acceptable speed limits, safe accelerations, safe decelerations, acceptable distances to vehicles ahead, and safe steering behavior. These thresholds were used to investigate the influence of social and cultural factors on driving in Malaysia. The findings show statistically significant differences between drivers based on gender, age, and cultural background. There are also significant differences in the results for those who drove on weekends rather than weekdays. The study presents several recommendations to various public and governmental sectors to help prevent future accidents and improve traffic safety.

Sequencing-based detection of 23S rRNA domain V mutations in treatment-naïve Helicobacter pylori patients from Malaysia.

OBJECTIVES: In Malaysia, the prevalence of Helicobacter pylori resistance to clarithromycin is increasing. This study aimed to determine mutations in the 23S rRNA domain V directly using bacterial DNA extracted from gastric biopsy specimens with a urease-positive result. METHODS: A 1085-bp fragment of 23S rRNA domain V from samples of 62 treatment-naïve patients with H. pylori infection was amplified by PCR with newly designed primers, followed by sequencing. RESULTS: Of the 62 cases, 42 patients were treated with clarithromycin-based triple therapy and 20 patients were treated with amoxicillin and proton pump inhibitor only; both therapies showed successful eradication rates of 70-73.8%. Sequencing analysis detected 37 point mutations (6 known and 31 novel) with prevalences ranging from 1.6% (1/62) to 72.6% (45/62). A2147G (aka A2143G) appears to be associated with a low eradication rate [40% (2/5) failure rate and 13.3% (6/45) treatment success rate], supporting its role as a clinically significant point mutation. T2186C (aka T2182C) was found in 71.1% (32/45) and 80% (4/5) of treatment success and failure cases, respectively, suggesting that the mutation is clinically insignificant. The eradication success rate in patients with the novel T2929C mutation was decreased three-fold (6.7%; 3/45) compared with the failure rate (20%; 1/5), suggesting that it may play an important role in clarithromycin resistance, thus warranting further study. CONCLUSION: This study identified multiple known and novel mutations in 23S rRNA domain V through direct sequencing. Molecular detection of clarithromycin resistance directly on biopsies offers an alternative to conventional susceptibility testing.

An Adaptive Wake-Up-Interval to Enhance Receiver-Based Ps-Mac Protocol for Wireless Sensor Networks.

Many receiver-based Preamble Sampling Medium Access Control (PS-MAC) protocols have been proposed to provide better performance for variable traffic in a wireless sensor network (WSN). However, most of these protocols cannot prevent the occurrence of incorrect traffic convergence that causes the receiver node to wake-up more frequently than the transmitter node. In this research, a new protocol is proposed to prevent the problem mentioned above. The proposed mechanism has four components, and they are Initial control frame message, traffic estimation function, control frame message, and adaptive function. The initial control frame message is used to initiate the message transmission by the receiver node. The traffic estimation function is proposed to reduce the wake-up frequency of the receiver node by using the proposed traffic status register (TSR), idle listening times (ILTn, ILTk), and "number of wake-up without receiving beacon message" (NWwbm). The control frame message aims to supply the essential information to the receiver node to get the next wake-up-interval (WUI) time for the transmitter node using the proposed adaptive function. The proposed adaptive function is used by the receiver node to calculate the next WUI time of each of the transmitter nodes. Several simulations are conducted based on the benchmark protocols. The outcome of the simulation indicates that the proposed mechanism can prevent the incorrect traffic convergence problem that causes frequent wake-up of the receiver node compared to the transmitter node. Moreover, the simulation results also indicate that the proposed mechanism could reduce energy consumption, produce minor latency, improve the throughput, and produce higher packet delivery ratio compared to other related works.

Microencapsulation Curcuminoids for Effective Delivery in Pharmaceutical Application.

Curcuminoids have been long proven to possess antioxidant, anti-inflammatory and antibacterial properties which are crucial in their role as a pharmacological active agent. However, its poor solubility, high oxidative degradation, light sensitivity and poor bioavailability have been huge hurdles that need to be overcome for it to be administered as an oral or even a topical medication. In this present study, a complex coacervation microencapsulation approach was used to encapsulate the curcuminoids using both gelatin B and chitosan (at the optimum ratio of 30:1% w/w) for a more efficient drug delivery system. Curcuminoids microcapsules (CPM) were developed to be spherical in shape, discrete and free flowing with a reduced color staining effect. The thick wall of the CPM contributes directly to its integrity and stability. Cross-linking increases the density of polymers' wall network, hence, further increasing the decomposition temperature of curcuminoids microcapsules. Microencapsulation demonstrated an increment in curcuminoids solubility, while chemical cross-linking allowed for sustained release of the drug from the microcapsules by lowering the swelling rate of the available polymer networks. Thus, the microcapsules complied with the zero order release kinetics with super case-II transport mechanism. On the basis of all that was discussed above, it can be safely concluded that CPM should be incorporated in delivery system of curcuminoid, especially in its topical delivery for controlled drug release purposes, for not only a more efficient drug delivery system design but also a more efficacious optimization of the pharmacological benefits of curcuminoids.

Wound Healing Property of Curcuminoids as a Microcapsule-Incorporated Cream.

Curcuminoids have been used for the management of burns and wound healing in traditional Chinese medicine practices but the wide application of curcuminoids as a healing agent for wounds has always been a known problem due to their poor solubility, bioavailability, colour staining properties, as well as due to their intense photosensitivity and the need for further formulation approaches to maximise their various properties in order for them to considerably contribute towards the wound healing process. In the present study, a complex coacervation microencapsulation was used to encapsulate curcuminoids using gelatin B and chitosan. This study also focused on studying and confirming the potential of curcuminoids in a microencapsulated form as a wound healing agent. The potential of curcuminoids for wound management was evaluated using an in vitro human keratinocyte cell (HaCaT) model and the in vivo heater-inflicted burn wound model, providing evidence that the antioxidant activities of both forms of curcuminoids, encapsulated or not, are higher than those of butylated hydroxyanisole and butylated hydroxytoluene in trolox equivalent antioxidant capacity (TEAC) and (2,2-diphenyl-1-picryl-hydrazyl-hydrate) (DPPH) studies. However, curcuminoids did not have much impact towards cell migration and proliferation in comparison with the negative control in the in vitro HaCaT study. The micoencapsulation formulation was shown to significantly influence wound healing in terms of increasing the wound contraction rate, hydroxyproline synthesis, and greater epithelialisation, which in turn provides strong justification for the incorporation of the microencapsulated formulation of curcuminoids as a topical treatment for burns and wound healing management as it has the potential to act as a crucial wound healing agent in healthcare settings.

Vision-Based Apple Classification for Smart Manufacturing.

Smart manufacturing enables an efficient manufacturing process by optimizing production and product transaction. The optimization is performed through data analytics that requires reliable and informative data as input. Therefore, in this paper, an accurate data capture approach based on a vision sensor is proposed. Three image recognition methods are studied to determine the best vision-based classification technique, namely Bag of Words (BOW), Spatial Pyramid Matching (SPM) and Convolutional Neural Network (CNN). The vision-based classifiers categorize the apple as defective and non-defective that can be used for automatic inspection, sorting and further analytics. A total of 550 apple images are collected to test the classifiers. The images consist of 275 non-defective and 275 defective apples. The defective category includes various types of defect and severity. The vision-based classifiers are trained and evaluated according to the K-fold cross-validation. The performances of the classifiers from 2-fold, 3-fold, 4-fold, 5-fold and 10-fold are compared. From the evaluation, SPM with SVM classifier attained 98.15% classification accuracy for 10-fold and outperformed the others. In terms of computational time, CNN with SVM classifier is the fastest. However, minimal time difference is observed between the computational time of CNN and SPM, which were separated by only 0.05 s.

Development of an amperometric-based glucose biosensor to measure the glucose content of fruit.

An amperometric enzyme-electrode was introduced where glucose oxidase (GOD) was immobilized on chitosan membrane via crosslinking, and then fastened on a platinum working electrode. The immobilized enzyme showed relatively high retention activity. The activity of the immobilized enzyme was influenced by its loading, being suppressed when more than 0.6 mg enzyme was used in the immobilization. The biosensor showing the highest response to glucose utilized 0.21 ml/cm2 thick chitosan membrane. The optimum experimental conditions for the biosensors in analysing glucose dissolved in 0.1 M phosphate buffer (pH 6.0) were found to be 35°C and 0.6 V applied potential. The introduced biosensor reached a steady-state current at 60 s. The apparent Michaelis-Menten constant ([Formula: see text]) of the biosensor was 14.2350 mM, and its detection limit was 0.05 mM at s/n > 3, determined experimentally. The RSD of repeatability and reproducibility of the biosensor were 2.30% and 3.70%, respectively. The biosensor was showed good stability; it retained ~36% of initial activity after two months of investigation. The performance of the biosensors was evaluated by determining the glucose content in fruit homogenates. Their accuracy was compared to that of a commercial glucose assay kit. There was no significance different between two methods, indicating the introduced biosensor is reliable.

Preventing shoulder-surfing attack with the concept of concealing the password objects' information.

Traditionally, picture-based password systems employ password objects (pictures/icons/symbols) as input during an authentication session, thus making them vulnerable to "shoulder-surfing" attack because the visual interface by function is easily observed by others. Recent software-based approaches attempt to minimize this threat by requiring users to enter their passwords indirectly by performing certain mental tasks to derive the indirect password, thus concealing the user's actual password. However, weaknesses in the positioning of distracter and password objects introduce usability and security issues. In this paper, a new method, which conceals information about the password objects as much as possible, is proposed. Besides concealing the password objects and the number of password objects, the proposed method allows both password and distracter objects to be used as the challenge set's input. The correctly entered password appears to be random and can only be derived with the knowledge of the full set of password objects. Therefore, it would be difficult for a shoulder-surfing adversary to identify the user's actual password. Simulation results indicate that the correct input object and its location are random for each challenge set, thus preventing frequency of occurrence analysis attack. User study results show that the proposed method is able to prevent shoulder-surfing attack.

Study on different molecular weights of chitosan as an immobilization matrix for a glucose biosensor.

Two chitosan samples (medium molecular weight (MMCHI) and low molecular weight (LMCHI)) were investigated as an enzyme immobilization matrix for the fabrication of a glucose biosensor. Chitosan membranes prepared from acetic acid were flexible, transparent, smooth and quick-drying. The FTIR spectra showed the existence of intermolecular interactions between chitosan and glucose oxidase (GOD). Higher catalytic activities were observed on for GOD-MMCHI than GOD-LMCHI and for those crosslinked with glutaraldehyde than using the adsorption technique. Enzyme loading greater than 0.6 mg decreased the activity. Under optimum conditions (pH 6.0, 35°C and applied potential of 0.6 V) response times of 85 s and 65 s were observed for medium molecular weight chitosan glucose biosensor (GOD-MMCHI/PT) and low molecular weight chitosan glucose biosensor (GOD-LMCHI/PT), respectively. The apparent Michaelis-Menten constant ([Formula: see text]) was found to be 12.737 mM for GOD-MMCHI/PT and 17.692 mM for GOD-LMCHI/PT. This indicated that GOD-MMCHI/PT had greater affinity for the enzyme. Moreover, GOD-MMCHI/PT showed higher sensitivity (52.3666 nA/mM glucose) when compared with GOD-LMCHI/PT (9.8579 nA/mM glucose) at S/N>3. Better repeatability and reproducibility were achieved with GOD-MMCHI/PT than GOD-LMCHI/PT regarding glucose measurement. GOD-MMCHI/PT was found to give the highest enzymatic activity among the electrodes under investigation. The extent of interference encountered by GOD-MMCHI/PT and GOD-LMCHI/PT was not significantly different. Although the Nafion coated biosensor significantly reduced the signal due to the interferents under study, it also significantly reduced the response to glucose. The performance of the biosensors in the determination of glucose in rat serum was evaluated. Comparatively better accuracy and recovery results were obtained for GOD-MMCHI/PT. Hence, GOD-MMCHI/PT showed a better performance when compared with GOD-LMCHI/PT. In conclusion, chitosan membranes shave the potential to be a suitable matrix for the development of glucose biosensors.