Managerial Constructs and Performance of Small and Medium Enterprises in Bauchi State, Nigeria

Ibrahim Aliyu 한국유통과학회 2017 KODISA ICBE (International Conference on Business Vol.2017 No.-

The study is cross-sectional in nature where data were collected from the population of the study using an adapted survey questionnaire and analyzed to report the finding at a point in time. Thus, the study is not subjected to timeframe. The population of the study is the 545 SMEs in Bauchi State. This is the result of a Collaborative Survey by National Bureau of Statistics (NBS) and SMEDAN of 2012. It was obtained from Bauchi state Ministry of Commerce and it is the latest information the ministry has about the number of SMEs in the state. Therefore, the actual informants of study were 545 owner-managers of these SMEs. The finding suggests that achievement motivation, locus of control, need for dominance, passion for work and risk taking/aversion are important contributors to SMEs’ performance in Bauchi state. Therefore, this study concluded that possession of entrepreneurial characteristics by an SME owner-manager leads to higher SMEs’ performance in Bauchi state. Therefore, this study concluded that application of environmental scanning by owner-managers to a little extent leads to improved SMEs’ performance in the state.

Intelligent Bi-modal Timetable-aware Biometric Attendance System for Enhanced Classroom Attendance

Ibrahim Mohammed Abdullahi,Danlami Maliki,Abdulmalik Muhammad Abubakar,Young-Ae Jung,Kwangki Kim,Ibrahim Aliyu 한국디지털콘텐츠학회 2022 The Journal of Contents Computing Vol.4 No.2

BCI에서 EEG 기반 효율적인 감정 분류를 위한 LSTM 하이퍼파라미터 최적화

Ibrahim Aliyu,Raja Majid Mahmood,임창균(Chang-Gyoon Lim) 한국전자통신학회 2019 한국전자통신학회 논문지 Vol.14 No.6

감정은 인간의 상호 작용에서 중요한 역할을 하는 심리 생리학적 과정이다. 감성 컴퓨팅은 감정을 이해하고 조절할 수 있는 인간 인지 인공 지능의 개발하는데 중점을 둔다. 우울증, 자폐증, 주의력 결핍 과잉 행동 장애 및 게임 중독과 같은 정신 질환이 감정과 관련되어 있기 때문에 이러한 분야의 연구가 중요하다. 감정 인식에 대한 노력에도 불구하고, 비정상적인 EEG 신호로부터의 감정 검출은 여전히 높은 수준의 추상화를 요구하기에 정교한 학습 알고리즘이 필요하다. 이 논문에서는 EEG 기반으로 효율적인 감정 분류를 위해 LSTM을 위한 최적의 하이퍼파라미터를 파악하고자 다양한 실험을 수행하여 이를 분석한 결과를 제시하였다. Emotion is a psycho-physiological process that plays an important role in human interactions. Affective computing is centered on the development of human-aware artificial intelligence that can understand and regulate emotions. This field of study is also critical as mental diseases such as depression, autism, attention deficit hyperactivity disorder, and game addiction are associated with emotion. Despite the efforts in emotions recognition and emotion detection from nonstationary, detecting emotions from abnormal EEG signals requires sophisticated learning algorithms because they require a high level of abstraction. In this paper, we investigated LSTM hyperparameters for an optimal emotion EEG classification. Results of several experiments are hereby presented. From the results, optimal LSTM hyperparameter configuration was achieved.

LSTM/RNN을 사용한 감정인식을 위한 스택 오토 인코더로 EEG 차원 감소

Ibrahim Aliyu,임창균(Chang-Gyoon Lim) 한국전자통신학회 2020 한국전자통신학회 논문지 Vol.15 No.4

감성 컴퓨팅은 인간의 상호 작용에서 중요한 역할을 하기 때문에 인간을 인식하는 인공 지능을 통해 감정을 이해하고 식별한다. 우울증, 자폐증, 주의력 결핍 과잉 행동 장애 및 게임 중독과 같은 정신 질환을 잘 이해함으로써 감정과 관련된 문제들을 잘 관리할 수 있을 것이다. 이러한 문제들을 해결하기 위해 감정 인식을 위한 다양한 연구가 수행되었는데 기계학습을 적용하는데 있어서는 알고리즘의 복잡성을 줄이고 정확도를 향상시키기 위한 노력이 필요하다. 본 논문에서는 이러한 노력중의 하나로 Stack AutoEncoder (SAE)를 이용하여 차원을 감소하는 방법과 Long-Short-Term-Memory/Recurrent Neural Networks (LSTM / RNN) 분류를 이용한 감성 분류에 대해 연구한 결과를 제시한다. 제안 된 방법은 모델의 복잡성을 줄이고 분류기의 성능을 크게 향상시킨 결과를 가져왔다. Due to the important role played by emotion in human interaction, affective computing is dedicated in trying to understand and regulate emotion through human-aware artificial intelligence. By understanding, emotion mental diseases such as depression, autism, attention deficit hyperactivity disorder, and game addiction will be better managed as they are all associated with emotion. Various studies for emotion recognition have been conducted to solve these problems. In applying machine learning for the emotion recognition, the efforts to reduce the complexity of the algorithm and improve the accuracy are required. In this paper, we investigate emotion Electroencephalogram (EEG) feature reduction and classification using Stack AutoEncoder (SAE) and Long-Short-Term-Memory/Recurrent Neural Networks(LSTM/RNN) classification respectively. The proposed method reduced the complexity of the model and significantly enhance the performance of the classifiers.

Incorporating Recognition in Catfish Counting Algorithm Using Artificial Neural Network and Geometry

( Ibrahim Aliyu ),( Kolo Jonathan Gana ),( Aibinu Abiodun Musa ),( Mutiu Adesina Adegboye ),( Chang Gyoon Lim ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.12

One major and time-consuming task in fish production is obtaining an accurate estimate of the number of fish produced. In most Nigerian farms, fish counting is performed manually. Digital image processing (DIP) is an inexpensive solution, but its accuracy is affected by noise, overlapping fish, and interfering objects. This study developed a catfish recognition and counting algorithm that introduces detection before counting and consists of six steps: image acquisition, pre-processing, segmentation, feature extraction, recognition, and counting. Images were acquired and pre-processed. The segmentation was performed by applying three methods: image binarization using Otsu thresholding, morphological operations using fill hole, dilation, and opening operations, and boundary segmentation using edge detection. The boundary features were extracted using a chain code algorithm and Fourier descriptors (CH-FD), which were used to train an artificial neural network (ANN) to perform the recognition. The new counting approach, based on the geometry of the fish, was applied to determine the number of fish and was found to be suitable for counting fish of any size and handling overlap. The accuracies of the segmentation algorithm, boundary pixel and Fourier descriptors (BD-FD), and the proposed CH-FD method were 90.34%, 96.6%, and 100% respectively. The proposed counting algorithm demonstrated 100% accuracy.

Intelligent Offline Multi Object Recognition Walking Stick for The Blind

Ibrahim Mohammed Abdullahi,Olayemi Mikail Olaniyi,Jacob Omokhafe Irefu,Sangwon Oh,Ibrahim Aliyu 한국디지털콘텐츠학회 2021 The Journal of Contents Computing Vol.3 No.2

Vision is one of the most important characteristics of a human that aid their day to day activities. Loss of vision however affects the ability of humans to freely navigate their environment and recognized objects along their path. Existing object recognition systems for the blind are mostly cloud based and its performance depends on reliable internet access. This makes them unsuitable in places with unreliable internet. Therefore, in this paper, a multi-object recognition intelligent walking stick for the blind that is completely independent of the internet was developed. The system is divided into three units, detection, recognition and communication units. The detection unit make use of an ultrasonic sensor and a buzzer, for informing the user of an impending obstacle. The recognition system makes use of a camera for capturing images with Convolutionary Neural Network architecture and Mobile Network Single Shot Multi-Box Detector (MobileNet SSD) for detecting objects in images. The communication unit transmits the recognised objects through voice to the user in English Language. The entire system was deployed in a Raspberry Pi microcontroller due to its processing power. The result obtained from testing of the device on the field showed that the recognition unit achieved an average sensitivity, specificity, precision and accuracy of 87.26%, 67.45%, 89.07%, 82.50% respectively. This shows that the system is reliable and can be used in recognizing objects for the blind.

Blockchain-based Poultry Information Management System Design and Implementation using Hyperledger Fabric

Ibrahim, Aliyu,Kamoliddin, Usmonov,Yoo, J.H.,Lim, Chang Gyoon,Jeong, Jung-Chae The Basic Science Institute Chosun University 2021 조선자연과학논문집 Vol.14 No.3

The demand for traceability of meat and livestock supply chains is growing due to the high-profile incidents of hormonal contamination. E. coli, dioxin, BSE, and antibiotics have been recorded. In this paper, we present blockchain-based poultry information management system design and implementation using Hyperledger Fabric. The proposed system offers accurate, decentralized, immutable and consensus process that promote trust and transparency between stakeholders. The main tasks of the system include the recording of the information associated with poultry rearing (from a hatchery to a farm), status report of the farm activities on a monthly basis. The system can track movement of docks through the supply chain until delivery to the final consumer through the retail outlet. The ability to trace the source of livestock product through all the stages of rearing/production, processing and distribution is essential for ensuring food safety as recall of contaminated product can easily be done thereby increasing consumer confidence.

Development of blockchain-based duck history and distribution management system

Ibrahim Aliyu,Usmonov Kamoliddin,Seung Je Seong,Senfeng Cen,Yongjiang Zhao,Chang Gyoon Lim 한국콘텐츠학회 2021 한국콘텐츠학회 ICCC 논문집 Vol.2021 No.12

This paper aims to design a blockchain-based duck supply chain management system that captures assets and data flow from the poultry farm until the final customer. The system is proposed to improve efficiency and transparency of the duck supply chain and address the public health concern of the source of duck product through the use of blockchain technology to provide a verifiable and traceability history of the duck production process. Thus, the main functions of the system design include the recording of the information associated with poultry rearing (from a hatchery to a grow outhouse), status report of the farm activities monthly, tracking the movement of product through the supply chain until delivery to the final consumer through a retail outlet.

CNN-LSTM for Smart Grid Energy Consumption Prediction

Ibrahim Aliyu,Usmonov Kamoliddin,Seung Je Seong,Senfeng Cen,Yongjiang Zhao,Chang Gyoon Lim 한국콘텐츠학회 2021 한국콘텐츠학회 ICCC 논문집 Vol.2021 No.12

This paper aims to forecast monthly electricity across different kinds of consumers such as Residential, Industrial, Official and Commercial sectors. To achieve this, a CNN-LSTM prediction framework for energy demand in smart grid is proposed. Efficient consumption prediction is essential for effective Demand Response (DR) which can enable consumers to minimize their energy usage through proper load curtailment, consumption shift over time, or energy generation and storage at certain times to offer flexibility in the grid.

A Novel Interactive IoT-Based Smart Electricity Power Consumption Management System

Ibrahim Mohammed Abdullahi,Peter Nanpon Gambo,Martins Ake,Ibrahim Aliyu,Seungmin Oh,Jinsul Kim 한국디지털콘텐츠학회 2021 The Journal of Contents Computing Vol.3 No.2

Effective and efficient management of electric power is of significant benefit to the end users and a nation’s economy at large. The unnecessary huge bills and feuds that occur very often in developing countries like Nigeria after every billing period are often because of energy wastage and improper use of energy. This challenge hereby presents us with the need to not only create awareness but to also develop systems that allow for efficient and economic use of electric power. The existing meters that attempt to handle this challenge are in some cases analog, or not interactive, expensive and imposing. These systems are said to be imposing because they do not afford the user the right of deciding what he/she wants to spend in a billing period. Even with the emergence of prepaid meters, users are still unable to interact with individual connection points and decide what is consumed there so as to enhance conservation. These problems have already brought to table the need to develop systems that are automated, yet interactive and smart. The solution is an interactive smart electric consumption management system. Thus, this research work is formed around interaction and smartness. A linPrec Scheduling Algorithm is used to predict what each connection point requires in a billing period by interpolating between previous data points on the system. With the Android App, the User is allowed to communicate with every connection point in the apartment and comfortably determine how much they are willing to spend on electricity in a billing period. The http client guarantees data arrival with a worst-case average response time of 2.095s and a best-case average response time of 0.894s. Also, the power measurement had a Mean Absolute Error of 8.89% which implies high accuracy of 91.1%.